fix(frontend): minor copilot UI fixes

Bumps the production-dependencies group in /autogpt_platform/backend
with 2 updates: [fastapi](https://github.com/fastapi/fastapi) and
[langfuse](https://github.com/langfuse/langfuse).

Updates `fastapi` from 0.128.5 to 0.128.6
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/fastapi/fastapi/releases">fastapi's
releases</a>.</em></p>
<blockquote>
<h2>0.128.6</h2>
<h3>Fixes</h3>
<ul>
<li>🐛 Fix <code>on_startup</code> and <code>on_shutdown</code>
parameters of <code>APIRouter</code>. PR <a
href="https://redirect.github.com/fastapi/fastapi/pull/14873">#14873</a>
by <a
href="https://github.com/YuriiMotov"><code>@​YuriiMotov</code></a>.</li>
</ul>
<h3>Translations</h3>
<ul>
<li>🌐 Update translations for zh (update-outdated). PR <a
href="https://redirect.github.com/fastapi/fastapi/pull/14843">#14843</a>
by <a
href="https://github.com/tiangolo"><code>@​tiangolo</code></a>.</li>
</ul>
<h3>Internal</h3>
<ul>
<li>✅ Fix parameterized tests with snapshots. PR <a
href="https://redirect.github.com/fastapi/fastapi/pull/14875">#14875</a>
by <a
href="https://github.com/YuriiMotov"><code>@​YuriiMotov</code></a>.</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="fbca586c1d"><code>fbca586</code></a>
📝 Update release notes</li>
<li><a
href="4e879799dd"><code>4e87979</code></a>
📝 Update release notes</li>
<li><a
href="0a4033aeee"><code>0a4033a</code></a>
🔖 Release version 0.128.6</li>
<li><a
href="ed2512a5ec"><code>ed2512a</code></a>
🐛 Fix <code>on_startup</code> and <code>on_shutdown</code> parameters of
<code>APIRouter</code> (<a
href="https://redirect.github.com/fastapi/fastapi/issues/14873">#14873</a>)</li>
<li><a
href="0c0f6332e2"><code>0c0f633</code></a>
📝 Update release notes</li>
<li><a
href="227cb85a03"><code>227cb85</code></a>
✅ Fix parameterized tests with snapshots (<a
href="https://redirect.github.com/fastapi/fastapi/issues/14875">#14875</a>)</li>
<li><a
href="cd31576d57"><code>cd31576</code></a>
📝 Update release notes</li>
<li><a
href="376e108580"><code>376e108</code></a>
🌐 Update translations for zh (update-outdated) (<a
href="https://redirect.github.com/fastapi/fastapi/issues/14843">#14843</a>)</li>
<li>See full diff in <a
href="https://github.com/fastapi/fastapi/compare/0.128.5...0.128.6">compare
view</a></li>
</ul>
</details>
<br />

Updates `langfuse` from 3.13.0 to 3.14.1
<details>
<summary>Commits</summary>
<ul>
<li>See full diff in <a
href="https://github.com/langfuse/langfuse/commits">compare
view</a></li>
</ul>
</details>
<br />


Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore <dependency name> major version` will close this
group update PR and stop Dependabot creating any more for the specific
dependency's major version (unless you unignore this specific
dependency's major version or upgrade to it yourself)
- `@dependabot ignore <dependency name> minor version` will close this
group update PR and stop Dependabot creating any more for the specific
dependency's minor version (unless you unignore this specific
dependency's minor version or upgrade to it yourself)
- `@dependabot ignore <dependency name>` will close this group update PR
and stop Dependabot creating any more for the specific dependency
(unless you unignore this specific dependency or upgrade to it yourself)
- `@dependabot unignore <dependency name>` will remove all of the ignore
conditions of the specified dependency
- `@dependabot unignore <dependency name> <ignore condition>` will
remove the ignore condition of the specified dependency and ignore
conditions


</details>

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Zamil Majdy <zamil.majdy@agpt.co>
Co-authored-by: Otto <otto@agpt.co>

.github/workflows/platform-fullstack-ci.yml

@@ -56,7 +56,7 @@ jobs:
         run: pnpm install --frozen-lockfile
 
   types:
-    runs-on: ubuntu-latest
+    runs-on: big-boi
     needs: setup
     strategy:
       fail-fast: false
@@ -85,7 +85,7 @@ jobs:
 
       - name: Run docker compose
         run: |
-          docker compose -f ../docker-compose.yml --profile local --profile deps_backend up -d
+          docker compose -f ../docker-compose.yml --profile local up -d deps_backend
 
       - name: Restore dependencies cache
         uses: actions/cache@v5

autogpt_platform/autogpt_libs/poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.2.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.1.1 and should not be changed by hand.
 
 [[package]]
 name = "annotated-doc"
@@ -67,7 +67,7 @@ description = "Backport of asyncio.Runner, a context manager that controls event
 optional = false
 python-versions = "<3.11,>=3.8"
 groups = ["dev"]
-markers = "python_version == \"3.10\""
+markers = "python_version < \"3.11\""
 files = [
     {file = "backports_asyncio_runner-1.2.0-py3-none-any.whl", hash = "sha256:0da0a936a8aeb554eccb426dc55af3ba63bcdc69fa1a600b5bb305413a4477b5"},
     {file = "backports_asyncio_runner-1.2.0.tar.gz", hash = "sha256:a5aa7b2b7d8f8bfcaa2b57313f70792df84e32a2a746f585213373f900b42162"},
@@ -326,100 +326,118 @@ files = [
 
 [[package]]
 name = "coverage"
-version = "7.10.5"
+version = "7.13.4"
 description = "Code coverage measurement for Python"
 optional = false
-python-versions = ">=3.9"
+python-versions = ">=3.10"
 groups = ["dev"]
 files = [
-    {file = "coverage-7.10.5-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c6a5c3414bfc7451b879141ce772c546985163cf553f08e0f135f0699a911801"},
-    {file = "coverage-7.10.5-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:bc8e4d99ce82f1710cc3c125adc30fd1487d3cf6c2cd4994d78d68a47b16989a"},
-    {file = "coverage-7.10.5-cp310-cp310-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:02252dc1216e512a9311f596b3169fad54abcb13827a8d76d5630c798a50a754"},
-    {file = "coverage-7.10.5-cp310-cp310-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:73269df37883e02d460bee0cc16be90509faea1e3bd105d77360b512d5bb9c33"},
-    {file = "coverage-7.10.5-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1f8a81b0614642f91c9effd53eec284f965577591f51f547a1cbeb32035b4c2f"},
-    {file = "coverage-7.10.5-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:6a29f8e0adb7f8c2b95fa2d4566a1d6e6722e0a637634c6563cb1ab844427dd9"},
-    {file = "coverage-7.10.5-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:fcf6ab569436b4a647d4e91accba12509ad9f2554bc93d3aee23cc596e7f99c3"},
-    {file = "coverage-7.10.5-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:90dc3d6fb222b194a5de60af8d190bedeeddcbc7add317e4a3cd333ee6b7c879"},
-    {file = "coverage-7.10.5-cp310-cp310-win32.whl", hash = "sha256:414a568cd545f9dc75f0686a0049393de8098414b58ea071e03395505b73d7a8"},
-    {file = "coverage-7.10.5-cp310-cp310-win_amd64.whl", hash = "sha256:e551f9d03347196271935fd3c0c165f0e8c049220280c1120de0084d65e9c7ff"},
-    {file = "coverage-7.10.5-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:c177e6ffe2ebc7c410785307758ee21258aa8e8092b44d09a2da767834f075f2"},
-    {file = "coverage-7.10.5-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:14d6071c51ad0f703d6440827eaa46386169b5fdced42631d5a5ac419616046f"},
-    {file = "coverage-7.10.5-cp311-cp311-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:61f78c7c3bc272a410c5ae3fde7792b4ffb4acc03d35a7df73ca8978826bb7ab"},
-    {file = "coverage-7.10.5-cp311-cp311-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:f39071caa126f69d63f99b324fb08c7b1da2ec28cbb1fe7b5b1799926492f65c"},
-    {file = "coverage-7.10.5-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:343a023193f04d46edc46b2616cdbee68c94dd10208ecd3adc56fcc54ef2baa1"},
-    {file = "coverage-7.10.5-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:585ffe93ae5894d1ebdee69fc0b0d4b7c75d8007983692fb300ac98eed146f78"},
-    {file = "coverage-7.10.5-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:b0ef4e66f006ed181df29b59921bd8fc7ed7cd6a9289295cd8b2824b49b570df"},
-    {file = "coverage-7.10.5-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:eb7b0bbf7cc1d0453b843eca7b5fa017874735bef9bfdfa4121373d2cc885ed6"},
-    {file = "coverage-7.10.5-cp311-cp311-win32.whl", hash = "sha256:1d043a8a06987cc0c98516e57c4d3fc2c1591364831e9deb59c9e1b4937e8caf"},
-    {file = "coverage-7.10.5-cp311-cp311-win_amd64.whl", hash = "sha256:fefafcca09c3ac56372ef64a40f5fe17c5592fab906e0fdffd09543f3012ba50"},
-    {file = "coverage-7.10.5-cp311-cp311-win_arm64.whl", hash = "sha256:7e78b767da8b5fc5b2faa69bb001edafcd6f3995b42a331c53ef9572c55ceb82"},
-    {file = "coverage-7.10.5-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:c2d05c7e73c60a4cecc7d9b60dbfd603b4ebc0adafaef371445b47d0f805c8a9"},
-    {file = "coverage-7.10.5-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:32ddaa3b2c509778ed5373b177eb2bf5662405493baeff52278a0b4f9415188b"},
-    {file = "coverage-7.10.5-cp312-cp312-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:dd382410039fe062097aa0292ab6335a3f1e7af7bba2ef8d27dcda484918f20c"},
-    {file = "coverage-7.10.5-cp312-cp312-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:7fa22800f3908df31cea6fb230f20ac49e343515d968cc3a42b30d5c3ebf9b5a"},
-    {file = "coverage-7.10.5-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f366a57ac81f5e12797136552f5b7502fa053c861a009b91b80ed51f2ce651c6"},
-    {file = "coverage-7.10.5-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:5f1dc8f1980a272ad4a6c84cba7981792344dad33bf5869361576b7aef42733a"},
-    {file = "coverage-7.10.5-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:2285c04ee8676f7938b02b4936d9b9b672064daab3187c20f73a55f3d70e6b4a"},
-    {file = "coverage-7.10.5-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:c2492e4dd9daab63f5f56286f8a04c51323d237631eb98505d87e4c4ff19ec34"},
-    {file = "coverage-7.10.5-cp312-cp312-win32.whl", hash = "sha256:38a9109c4ee8135d5df5505384fc2f20287a47ccbe0b3f04c53c9a1989c2bbaf"},
-    {file = "coverage-7.10.5-cp312-cp312-win_amd64.whl", hash = "sha256:6b87f1ad60b30bc3c43c66afa7db6b22a3109902e28c5094957626a0143a001f"},
-    {file = "coverage-7.10.5-cp312-cp312-win_arm64.whl", hash = "sha256:672a6c1da5aea6c629819a0e1461e89d244f78d7b60c424ecf4f1f2556c041d8"},
-    {file = "coverage-7.10.5-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:ef3b83594d933020f54cf65ea1f4405d1f4e41a009c46df629dd964fcb6e907c"},
-    {file = "coverage-7.10.5-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:2b96bfdf7c0ea9faebce088a3ecb2382819da4fbc05c7b80040dbc428df6af44"},
-    {file = "coverage-7.10.5-cp313-cp313-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:63df1fdaffa42d914d5c4d293e838937638bf75c794cf20bee12978fc8c4e3bc"},
-    {file = "coverage-7.10.5-cp313-cp313-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:8002dc6a049aac0e81ecec97abfb08c01ef0c1fbf962d0c98da3950ace89b869"},
-    {file = "coverage-7.10.5-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:63d4bb2966d6f5f705a6b0c6784c8969c468dbc4bcf9d9ded8bff1c7e092451f"},
-    {file = "coverage-7.10.5-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:1f672efc0731a6846b157389b6e6d5d5e9e59d1d1a23a5c66a99fd58339914d5"},
-    {file = "coverage-7.10.5-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:3f39cef43d08049e8afc1fde4a5da8510fc6be843f8dea350ee46e2a26b2f54c"},
-    {file = "coverage-7.10.5-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:2968647e3ed5a6c019a419264386b013979ff1fb67dd11f5c9886c43d6a31fc2"},
-    {file = "coverage-7.10.5-cp313-cp313-win32.whl", hash = "sha256:0d511dda38595b2b6934c2b730a1fd57a3635c6aa2a04cb74714cdfdd53846f4"},
-    {file = "coverage-7.10.5-cp313-cp313-win_amd64.whl", hash = "sha256:9a86281794a393513cf117177fd39c796b3f8e3759bb2764259a2abba5cce54b"},
-    {file = "coverage-7.10.5-cp313-cp313-win_arm64.whl", hash = "sha256:cebd8e906eb98bb09c10d1feed16096700b1198d482267f8bf0474e63a7b8d84"},
-    {file = "coverage-7.10.5-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:0520dff502da5e09d0d20781df74d8189ab334a1e40d5bafe2efaa4158e2d9e7"},
-    {file = "coverage-7.10.5-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:d9cd64aca68f503ed3f1f18c7c9174cbb797baba02ca8ab5112f9d1c0328cd4b"},
-    {file = "coverage-7.10.5-cp313-cp313t-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:0913dd1613a33b13c4f84aa6e3f4198c1a21ee28ccb4f674985c1f22109f0aae"},
-    {file = "coverage-7.10.5-cp313-cp313t-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:1b7181c0feeb06ed8a02da02792f42f829a7b29990fef52eff257fef0885d760"},
-    {file = "coverage-7.10.5-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:36d42b7396b605f774d4372dd9c49bed71cbabce4ae1ccd074d155709dd8f235"},
-    {file = "coverage-7.10.5-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:b4fdc777e05c4940b297bf47bf7eedd56a39a61dc23ba798e4b830d585486ca5"},
-    {file = "coverage-7.10.5-cp313-cp313t-musllinux_1_2_i686.whl", hash = "sha256:42144e8e346de44a6f1dbd0a56575dd8ab8dfa7e9007da02ea5b1c30ab33a7db"},
-    {file = "coverage-7.10.5-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:66c644cbd7aed8fe266d5917e2c9f65458a51cfe5eeff9c05f15b335f697066e"},
-    {file = "coverage-7.10.5-cp313-cp313t-win32.whl", hash = "sha256:2d1b73023854068c44b0c554578a4e1ef1b050ed07cf8b431549e624a29a66ee"},
-    {file = "coverage-7.10.5-cp313-cp313t-win_amd64.whl", hash = "sha256:54a1532c8a642d8cc0bd5a9a51f5a9dcc440294fd06e9dda55e743c5ec1a8f14"},
-    {file = "coverage-7.10.5-cp313-cp313t-win_arm64.whl", hash = "sha256:74d5b63fe3f5f5d372253a4ef92492c11a4305f3550631beaa432fc9df16fcff"},
-    {file = "coverage-7.10.5-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:68c5e0bc5f44f68053369fa0d94459c84548a77660a5f2561c5e5f1e3bed7031"},
-    {file = "coverage-7.10.5-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:cf33134ffae93865e32e1e37df043bef15a5e857d8caebc0099d225c579b0fa3"},
-    {file = "coverage-7.10.5-cp314-cp314-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:ad8fa9d5193bafcf668231294241302b5e683a0518bf1e33a9a0dfb142ec3031"},
-    {file = "coverage-7.10.5-cp314-cp314-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:146fa1531973d38ab4b689bc764592fe6c2f913e7e80a39e7eeafd11f0ef6db2"},
-    {file = "coverage-7.10.5-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6013a37b8a4854c478d3219ee8bc2392dea51602dd0803a12d6f6182a0061762"},
-    {file = "coverage-7.10.5-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:eb90fe20db9c3d930fa2ad7a308207ab5b86bf6a76f54ab6a40be4012d88fcae"},
-    {file = "coverage-7.10.5-cp314-cp314-musllinux_1_2_i686.whl", hash = "sha256:384b34482272e960c438703cafe63316dfbea124ac62006a455c8410bf2a2262"},
-    {file = "coverage-7.10.5-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:467dc74bd0a1a7de2bedf8deaf6811f43602cb532bd34d81ffd6038d6d8abe99"},
-    {file = "coverage-7.10.5-cp314-cp314-win32.whl", hash = "sha256:556d23d4e6393ca898b2e63a5bca91e9ac2d5fb13299ec286cd69a09a7187fde"},
-    {file = "coverage-7.10.5-cp314-cp314-win_amd64.whl", hash = "sha256:f4446a9547681533c8fa3e3c6cf62121eeee616e6a92bd9201c6edd91beffe13"},
-    {file = "coverage-7.10.5-cp314-cp314-win_arm64.whl", hash = "sha256:5e78bd9cf65da4c303bf663de0d73bf69f81e878bf72a94e9af67137c69b9fe9"},
-    {file = "coverage-7.10.5-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:5661bf987d91ec756a47c7e5df4fbcb949f39e32f9334ccd3f43233bbb65e508"},
-    {file = "coverage-7.10.5-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:a46473129244db42a720439a26984f8c6f834762fc4573616c1f37f13994b357"},
-    {file = "coverage-7.10.5-cp314-cp314t-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:1f64b8d3415d60f24b058b58d859e9512624bdfa57a2d1f8aff93c1ec45c429b"},
-    {file = "coverage-7.10.5-cp314-cp314t-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:44d43de99a9d90b20e0163f9770542357f58860a26e24dc1d924643bd6aa7cb4"},
-    {file = "coverage-7.10.5-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a931a87e5ddb6b6404e65443b742cb1c14959622777f2a4efd81fba84f5d91ba"},
-    {file = "coverage-7.10.5-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:f9559b906a100029274448f4c8b8b0a127daa4dade5661dfd821b8c188058842"},
-    {file = "coverage-7.10.5-cp314-cp314t-musllinux_1_2_i686.whl", hash = "sha256:b08801e25e3b4526ef9ced1aa29344131a8f5213c60c03c18fe4c6170ffa2874"},
-    {file = "coverage-7.10.5-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:ed9749bb8eda35f8b636fb7632f1c62f735a236a5d4edadd8bbcc5ea0542e732"},
-    {file = "coverage-7.10.5-cp314-cp314t-win32.whl", hash = "sha256:609b60d123fc2cc63ccee6d17e4676699075db72d14ac3c107cc4976d516f2df"},
-    {file = "coverage-7.10.5-cp314-cp314t-win_amd64.whl", hash = "sha256:0666cf3d2c1626b5a3463fd5b05f5e21f99e6aec40a3192eee4d07a15970b07f"},
-    {file = "coverage-7.10.5-cp314-cp314t-win_arm64.whl", hash = "sha256:bc85eb2d35e760120540afddd3044a5bf69118a91a296a8b3940dfc4fdcfe1e2"},
-    {file = "coverage-7.10.5-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:62835c1b00c4a4ace24c1a88561a5a59b612fbb83a525d1c70ff5720c97c0610"},
-    {file = "coverage-7.10.5-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:5255b3bbcc1d32a4069d6403820ac8e6dbcc1d68cb28a60a1ebf17e47028e898"},
-    {file = "coverage-7.10.5-cp39-cp39-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:3876385722e335d6e991c430302c24251ef9c2a9701b2b390f5473199b1b8ebf"},
-    {file = "coverage-7.10.5-cp39-cp39-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:8048ce4b149c93447a55d279078c8ae98b08a6951a3c4d2d7e87f4efc7bfe100"},
-    {file = "coverage-7.10.5-cp39-cp39-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4028e7558e268dd8bcf4d9484aad393cafa654c24b4885f6f9474bf53183a82a"},
-    {file = "coverage-7.10.5-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:03f47dc870eec0367fcdd603ca6a01517d2504e83dc18dbfafae37faec66129a"},
-    {file = "coverage-7.10.5-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:2d488d7d42b6ded7ea0704884f89dcabd2619505457de8fc9a6011c62106f6e5"},
-    {file = "coverage-7.10.5-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:b3dcf2ead47fa8be14224ee817dfc1df98043af568fe120a22f81c0eb3c34ad2"},
-    {file = "coverage-7.10.5-cp39-cp39-win32.whl", hash = "sha256:02650a11324b80057b8c9c29487020073d5e98a498f1857f37e3f9b6ea1b2426"},
-    {file = "coverage-7.10.5-cp39-cp39-win_amd64.whl", hash = "sha256:b45264dd450a10f9e03237b41a9a24e85cbb1e278e5a32adb1a303f58f0017f3"},
-    {file = "coverage-7.10.5-py3-none-any.whl", hash = "sha256:0be24d35e4db1d23d0db5c0f6a74a962e2ec83c426b5cac09f4234aadef38e4a"},
-    {file = "coverage-7.10.5.tar.gz", hash = "sha256:f2e57716a78bc3ae80b2207be0709a3b2b63b9f2dcf9740ee6ac03588a2015b6"},
+    {file = "coverage-7.13.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:0fc31c787a84f8cd6027eba44010517020e0d18487064cd3d8968941856d1415"},
+    {file = "coverage-7.13.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a32ebc02a1805adf637fc8dec324b5cdacd2e493515424f70ee33799573d661b"},
+    {file = "coverage-7.13.4-cp310-cp310-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:e24f9156097ff9dc286f2f913df3a7f63c0e333dcafa3c196f2c18b4175ca09a"},
+    {file = "coverage-7.13.4-cp310-cp310-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:8041b6c5bfdc03257666e9881d33b1abc88daccaf73f7b6340fb7946655cd10f"},
+    {file = "coverage-7.13.4-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:2a09cfa6a5862bc2fc6ca7c3def5b2926194a56b8ab78ffcf617d28911123012"},
+    {file = "coverage-7.13.4-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:296f8b0af861d3970c2a4d8c91d48eb4dd4771bcef9baedec6a9b515d7de3def"},
+    {file = "coverage-7.13.4-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:e101609bcbbfb04605ea1027b10dc3735c094d12d40826a60f897b98b1c30256"},
+    {file = "coverage-7.13.4-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:aa3feb8db2e87ff5e6d00d7e1480ae241876286691265657b500886c98f38bda"},
+    {file = "coverage-7.13.4-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:4fc7fa81bbaf5a02801b65346c8b3e657f1d93763e58c0abdf7c992addd81a92"},
+    {file = "coverage-7.13.4-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:33901f604424145c6e9c2398684b92e176c0b12df77d52db81c20abd48c3794c"},
+    {file = "coverage-7.13.4-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:bb28c0f2cf2782508a40cec377935829d5fcc3ad9a3681375af4e84eb34b6b58"},
+    {file = "coverage-7.13.4-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:9d107aff57a83222ddbd8d9ee705ede2af2cc926608b57abed8ef96b50b7e8f9"},
+    {file = "coverage-7.13.4-cp310-cp310-win32.whl", hash = "sha256:a6f94a7d00eb18f1b6d403c91a88fd58cfc92d4b16080dfdb774afc8294469bf"},
+    {file = "coverage-7.13.4-cp310-cp310-win_amd64.whl", hash = "sha256:2cb0f1e000ebc419632bbe04366a8990b6e32c4e0b51543a6484ffe15eaeda95"},
+    {file = "coverage-7.13.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d490ba50c3f35dd7c17953c68f3270e7ccd1c6642e2d2afe2d8e720b98f5a053"},
+    {file = "coverage-7.13.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:19bc3c88078789f8ef36acb014d7241961dbf883fd2533d18cb1e7a5b4e28b11"},
+    {file = "coverage-7.13.4-cp311-cp311-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:3998e5a32e62fdf410c0dbd3115df86297995d6e3429af80b8798aad894ca7aa"},
+    {file = "coverage-7.13.4-cp311-cp311-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:8e264226ec98e01a8e1054314af91ee6cde0eacac4f465cc93b03dbe0bce2fd7"},
+    {file = "coverage-7.13.4-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a3aa4e7b9e416774b21797365b358a6e827ffadaaca81b69ee02946852449f00"},
+    {file = "coverage-7.13.4-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:71ca20079dd8f27fcf808817e281e90220475cd75115162218d0e27549f95fef"},
+    {file = "coverage-7.13.4-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:e2f25215f1a359ab17320b47bcdaca3e6e6356652e8256f2441e4ef972052903"},
+    {file = "coverage-7.13.4-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:d65b2d373032411e86960604dc4edac91fdfb5dca539461cf2cbe78327d1e64f"},
+    {file = "coverage-7.13.4-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:94eb63f9b363180aff17de3e7c8760c3ba94664ea2695c52f10111244d16a299"},
+    {file = "coverage-7.13.4-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:e856bf6616714c3a9fbc270ab54103f4e685ba236fa98c054e8f87f266c93505"},
+    {file = "coverage-7.13.4-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:65dfcbe305c3dfe658492df2d85259e0d79ead4177f9ae724b6fb245198f55d6"},
+    {file = "coverage-7.13.4-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:b507778ae8a4c915436ed5c2e05b4a6cecfa70f734e19c22a005152a11c7b6a9"},
+    {file = "coverage-7.13.4-cp311-cp311-win32.whl", hash = "sha256:784fc3cf8be001197b652d51d3fd259b1e2262888693a4636e18879f613a62a9"},
+    {file = "coverage-7.13.4-cp311-cp311-win_amd64.whl", hash = "sha256:2421d591f8ca05b308cf0092807308b2facbefe54af7c02ac22548b88b95c98f"},
+    {file = "coverage-7.13.4-cp311-cp311-win_arm64.whl", hash = "sha256:79e73a76b854d9c6088fe5d8b2ebe745f8681c55f7397c3c0a016192d681045f"},
+    {file = "coverage-7.13.4-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:02231499b08dabbe2b96612993e5fc34217cdae907a51b906ac7fca8027a4459"},
+    {file = "coverage-7.13.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40aa8808140e55dc022b15d8aa7f651b6b3d68b365ea0398f1441e0b04d859c3"},
+    {file = "coverage-7.13.4-cp312-cp312-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:5b856a8ccf749480024ff3bd7310adaef57bf31fd17e1bfc404b7940b6986634"},
+    {file = "coverage-7.13.4-cp312-cp312-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:2c048ea43875fbf8b45d476ad79f179809c590ec7b79e2035c662e7afa3192e3"},
+    {file = "coverage-7.13.4-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b7b38448866e83176e28086674fe7368ab8590e4610fb662b44e345b86d63ffa"},
+    {file = "coverage-7.13.4-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:de6defc1c9badbf8b9e67ae90fd00519186d6ab64e5cc5f3d21359c2a9b2c1d3"},
+    {file = "coverage-7.13.4-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:7eda778067ad7ffccd23ecffce537dface96212576a07924cbf0d8799d2ded5a"},
+    {file = "coverage-7.13.4-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:e87f6c587c3f34356c3759f0420693e35e7eb0e2e41e4c011cb6ec6ecbbf1db7"},
+    {file = "coverage-7.13.4-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:8248977c2e33aecb2ced42fef99f2d319e9904a36e55a8a68b69207fb7e43edc"},
+    {file = "coverage-7.13.4-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:25381386e80ae727608e662474db537d4df1ecd42379b5ba33c84633a2b36d47"},
+    {file = "coverage-7.13.4-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:ee756f00726693e5ba94d6df2bdfd64d4852d23b09bb0bc700e3b30e6f333985"},
+    {file = "coverage-7.13.4-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:fdfc1e28e7c7cdce44985b3043bc13bbd9c747520f94a4d7164af8260b3d91f0"},
+    {file = "coverage-7.13.4-cp312-cp312-win32.whl", hash = "sha256:01d4cbc3c283a17fc1e42d614a119f7f438eabb593391283adca8dc86eff1246"},
+    {file = "coverage-7.13.4-cp312-cp312-win_amd64.whl", hash = "sha256:9401ebc7ef522f01d01d45532c68c5ac40fb27113019b6b7d8b208f6e9baa126"},
+    {file = "coverage-7.13.4-cp312-cp312-win_arm64.whl", hash = "sha256:b1ec7b6b6e93255f952e27ab58fbc68dcc468844b16ecbee881aeb29b6ab4d8d"},
+    {file = "coverage-7.13.4-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:b66a2da594b6068b48b2692f043f35d4d3693fb639d5ea8b39533c2ad9ac3ab9"},
+    {file = "coverage-7.13.4-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:3599eb3992d814d23b35c536c28df1a882caa950f8f507cef23d1cbf334995ac"},
+    {file = "coverage-7.13.4-cp313-cp313-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:93550784d9281e374fb5a12bf1324cc8a963fd63b2d2f223503ef0fd4aa339ea"},
+    {file = "coverage-7.13.4-cp313-cp313-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:b720ce6a88a2755f7c697c23268ddc47a571b88052e6b155224347389fdf6a3b"},
+    {file = "coverage-7.13.4-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:7b322db1284a2ed3aa28ffd8ebe3db91c929b7a333c0820abec3d838ef5b3525"},
+    {file = "coverage-7.13.4-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:f4594c67d8a7c89cf922d9df0438c7c7bb022ad506eddb0fdb2863359ff78242"},
+    {file = "coverage-7.13.4-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:53d133df809c743eb8bce33b24bcababb371f4441340578cd406e084d94a6148"},
+    {file = "coverage-7.13.4-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:76451d1978b95ba6507a039090ba076105c87cc76fc3efd5d35d72093964d49a"},
+    {file = "coverage-7.13.4-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:7f57b33491e281e962021de110b451ab8a24182589be17e12a22c79047935e23"},
+    {file = "coverage-7.13.4-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:1731dc33dc276dafc410a885cbf5992f1ff171393e48a21453b78727d090de80"},
+    {file = "coverage-7.13.4-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:bd60d4fe2f6fa7dff9223ca1bbc9f05d2b6697bc5961072e5d3b952d46e1b1ea"},
+    {file = "coverage-7.13.4-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:9181a3ccead280b828fae232df12b16652702b49d41e99d657f46cc7b1f6ec7a"},
+    {file = "coverage-7.13.4-cp313-cp313-win32.whl", hash = "sha256:f53d492307962561ac7de4cd1de3e363589b000ab69617c6156a16ba7237998d"},
+    {file = "coverage-7.13.4-cp313-cp313-win_amd64.whl", hash = "sha256:e6f70dec1cc557e52df5306d051ef56003f74d56e9c4dd7ddb07e07ef32a84dd"},
+    {file = "coverage-7.13.4-cp313-cp313-win_arm64.whl", hash = "sha256:fb07dc5da7e849e2ad31a5d74e9bece81f30ecf5a42909d0a695f8bd1874d6af"},
+    {file = "coverage-7.13.4-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:40d74da8e6c4b9ac18b15331c4b5ebc35a17069410cad462ad4f40dcd2d50c0d"},
+    {file = "coverage-7.13.4-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:4223b4230a376138939a9173f1bdd6521994f2aff8047fae100d6d94d50c5a12"},
+    {file = "coverage-7.13.4-cp313-cp313t-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:1d4be36a5114c499f9f1f9195e95ebf979460dbe2d88e6816ea202010ba1c34b"},
+    {file = "coverage-7.13.4-cp313-cp313t-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:200dea7d1e8095cc6e98cdabe3fd1d21ab17d3cee6dab00cadbb2fe35d9c15b9"},
+    {file = "coverage-7.13.4-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b8eb931ee8e6d8243e253e5ed7336deea6904369d2fd8ae6e43f68abbf167092"},
+    {file = "coverage-7.13.4-cp313-cp313t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:75eab1ebe4f2f64d9509b984f9314d4aa788540368218b858dad56dc8f3e5eb9"},
+    {file = "coverage-7.13.4-cp313-cp313t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:c35eb28c1d085eb7d8c9b3296567a1bebe03ce72962e932431b9a61f28facf26"},
+    {file = "coverage-7.13.4-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:eb88b316ec33760714a4720feb2816a3a59180fd58c1985012054fa7aebee4c2"},
+    {file = "coverage-7.13.4-cp313-cp313t-musllinux_1_2_i686.whl", hash = "sha256:7d41eead3cc673cbd38a4417deb7fd0b4ca26954ff7dc6078e33f6ff97bed940"},
+    {file = "coverage-7.13.4-cp313-cp313t-musllinux_1_2_ppc64le.whl", hash = "sha256:fb26a934946a6afe0e326aebe0730cdff393a8bc0bbb65a2f41e30feddca399c"},
+    {file = "coverage-7.13.4-cp313-cp313t-musllinux_1_2_riscv64.whl", hash = "sha256:dae88bc0fc77edaa65c14be099bd57ee140cf507e6bfdeea7938457ab387efb0"},
+    {file = "coverage-7.13.4-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:845f352911777a8e722bfce168958214951e07e47e5d5d9744109fa5fe77f79b"},
+    {file = "coverage-7.13.4-cp313-cp313t-win32.whl", hash = "sha256:2fa8d5f8de70688a28240de9e139fa16b153cc3cbb01c5f16d88d6505ebdadf9"},
+    {file = "coverage-7.13.4-cp313-cp313t-win_amd64.whl", hash = "sha256:9351229c8c8407645840edcc277f4a2d44814d1bc34a2128c11c2a031d45a5dd"},
+    {file = "coverage-7.13.4-cp313-cp313t-win_arm64.whl", hash = "sha256:30b8d0512f2dc8c8747557e8fb459d6176a2c9e5731e2b74d311c03b78451997"},
+    {file = "coverage-7.13.4-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:300deaee342f90696ed186e3a00c71b5b3d27bffe9e827677954f4ee56969601"},
+    {file = "coverage-7.13.4-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:29e3220258d682b6226a9b0925bc563ed9a1ebcff3cad30f043eceea7eaf2689"},
+    {file = "coverage-7.13.4-cp314-cp314-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:391ee8f19bef69210978363ca930f7328081c6a0152f1166c91f0b5fdd2a773c"},
+    {file = "coverage-7.13.4-cp314-cp314-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:0dd7ab8278f0d58a0128ba2fca25824321f05d059c1441800e934ff2efa52129"},
+    {file = "coverage-7.13.4-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:78cdf0d578b15148b009ccf18c686aa4f719d887e76e6b40c38ffb61d264a552"},
+    {file = "coverage-7.13.4-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:48685fee12c2eb3b27c62f2658e7ea21e9c3239cba5a8a242801a0a3f6a8c62a"},
+    {file = "coverage-7.13.4-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:4e83efc079eb39480e6346a15a1bcb3e9b04759c5202d157e1dd4303cd619356"},
+    {file = "coverage-7.13.4-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:ecae9737b72408d6a950f7e525f30aca12d4bd8dd95e37342e5beb3a2a8c4f71"},
+    {file = "coverage-7.13.4-cp314-cp314-musllinux_1_2_i686.whl", hash = "sha256:ae4578f8528569d3cf303fef2ea569c7f4c4059a38c8667ccef15c6e1f118aa5"},
+    {file = "coverage-7.13.4-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:6fdef321fdfbb30a197efa02d48fcd9981f0d8ad2ae8903ac318adc653f5df98"},
+    {file = "coverage-7.13.4-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:2b0f6ccf3dbe577170bebfce1318707d0e8c3650003cb4b3a9dd744575daa8b5"},
+    {file = "coverage-7.13.4-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:75fcd519f2a5765db3f0e391eb3b7d150cce1a771bf4c9f861aeab86c767a3c0"},
+    {file = "coverage-7.13.4-cp314-cp314-win32.whl", hash = "sha256:8e798c266c378da2bd819b0677df41ab46d78065fb2a399558f3f6cae78b2fbb"},
+    {file = "coverage-7.13.4-cp314-cp314-win_amd64.whl", hash = "sha256:245e37f664d89861cf2329c9afa2c1fe9e6d4e1a09d872c947e70718aeeac505"},
+    {file = "coverage-7.13.4-cp314-cp314-win_arm64.whl", hash = "sha256:ad27098a189e5838900ce4c2a99f2fe42a0bf0c2093c17c69b45a71579e8d4a2"},
+    {file = "coverage-7.13.4-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:85480adfb35ffc32d40918aad81b89c69c9cc5661a9b8a81476d3e645321a056"},
+    {file = "coverage-7.13.4-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:79be69cf7f3bf9b0deeeb062eab7ac7f36cd4cc4c4dd694bd28921ba4d8596cc"},
+    {file = "coverage-7.13.4-cp314-cp314t-manylinux1_i686.manylinux_2_28_i686.manylinux_2_5_i686.whl", hash = "sha256:caa421e2684e382c5d8973ac55e4f36bed6821a9bad5c953494de960c74595c9"},
+    {file = "coverage-7.13.4-cp314-cp314t-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:14375934243ee05f56c45393fe2ce81fe5cc503c07cee2bdf1725fb8bef3ffaf"},
+    {file = "coverage-7.13.4-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:25a41c3104d08edb094d9db0d905ca54d0cd41c928bb6be3c4c799a54753af55"},
+    {file = "coverage-7.13.4-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:6f01afcff62bf9a08fb32b2c1d6e924236c0383c02c790732b6537269e466a72"},
+    {file = "coverage-7.13.4-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:eb9078108fbf0bcdde37c3f4779303673c2fa1fe8f7956e68d447d0dd426d38a"},
+    {file = "coverage-7.13.4-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:0e086334e8537ddd17e5f16a344777c1ab8194986ec533711cbe6c41cde841b6"},
+    {file = "coverage-7.13.4-cp314-cp314t-musllinux_1_2_i686.whl", hash = "sha256:725d985c5ab621268b2edb8e50dfe57633dc69bda071abc470fed55a14935fd3"},
+    {file = "coverage-7.13.4-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:3c06f0f1337c667b971ca2f975523347e63ec5e500b9aa5882d91931cd3ef750"},
+    {file = "coverage-7.13.4-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:590c0ed4bf8e85f745e6b805b2e1c457b2e33d5255dd9729743165253bc9ad39"},
+    {file = "coverage-7.13.4-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:eb30bf180de3f632cd043322dad5751390e5385108b2807368997d1a92a509d0"},
+    {file = "coverage-7.13.4-cp314-cp314t-win32.whl", hash = "sha256:c4240e7eded42d131a2d2c4dec70374b781b043ddc79a9de4d55ca71f8e98aea"},
+    {file = "coverage-7.13.4-cp314-cp314t-win_amd64.whl", hash = "sha256:4c7d3cc01e7350f2f0f6f7036caaf5673fb56b6998889ccfe9e1c1fe75a9c932"},
+    {file = "coverage-7.13.4-cp314-cp314t-win_arm64.whl", hash = "sha256:23e3f687cf945070d1c90f85db66d11e3025665d8dafa831301a0e0038f3db9b"},
+    {file = "coverage-7.13.4-py3-none-any.whl", hash = "sha256:1af1641e57cf7ba1bd67d677c9abdbcd6cc2ab7da3bca7fa1e2b7e50e65f2ad0"},
+    {file = "coverage-7.13.4.tar.gz", hash = "sha256:e5c8f6ed1e61a8b2dcdf31eb0b9bbf0130750ca79c1c49eb898e2ad86f5ccc91"},
 ]
 
 [package.dependencies]
@@ -523,7 +541,7 @@ description = "Backport of PEP 654 (exception groups)"
 optional = false
 python-versions = ">=3.7"
 groups = ["main", "dev"]
-markers = "python_version == \"3.10\""
+markers = "python_version < \"3.11\""
 files = [
     {file = "exceptiongroup-1.3.0-py3-none-any.whl", hash = "sha256:4d111e6e0c13d0644cad6ddaa7ed0261a0b36971f6d23e7ec9b4b9097da78a10"},
     {file = "exceptiongroup-1.3.0.tar.gz", hash = "sha256:b241f5885f560bc56a59ee63ca4c6a8bfa46ae4ad651af316d4e81817bb9fd88"},
@@ -2162,23 +2180,23 @@ testing = ["coverage (>=6.2)", "hypothesis (>=5.7.1)"]
 
 [[package]]
 name = "pytest-cov"
-version = "6.2.1"
+version = "7.0.0"
 description = "Pytest plugin for measuring coverage."
 optional = false
 python-versions = ">=3.9"
 groups = ["dev"]
 files = [
-    {file = "pytest_cov-6.2.1-py3-none-any.whl", hash = "sha256:f5bc4c23f42f1cdd23c70b1dab1bbaef4fc505ba950d53e0081d0730dd7e86d5"},
-    {file = "pytest_cov-6.2.1.tar.gz", hash = "sha256:25cc6cc0a5358204b8108ecedc51a9b57b34cc6b8c967cc2c01a4e00d8a67da2"},
+    {file = "pytest_cov-7.0.0-py3-none-any.whl", hash = "sha256:3b8e9558b16cc1479da72058bdecf8073661c7f57f7d3c5f22a1c23507f2d861"},
+    {file = "pytest_cov-7.0.0.tar.gz", hash = "sha256:33c97eda2e049a0c5298e91f519302a1334c26ac65c1a483d6206fd458361af1"},
 ]
 
 [package.dependencies]
-coverage = {version = ">=7.5", extras = ["toml"]}
+coverage = {version = ">=7.10.6", extras = ["toml"]}
 pluggy = ">=1.2"
-pytest = ">=6.2.5"
+pytest = ">=7"
 
 [package.extras]
-testing = ["fields", "hunter", "process-tests", "pytest-xdist", "virtualenv"]
+testing = ["process-tests", "pytest-xdist", "virtualenv"]
 
 [[package]]
 name = "pytest-mock"
@@ -2545,7 +2563,7 @@ description = "A lil' TOML parser"
 optional = false
 python-versions = ">=3.8"
 groups = ["dev"]
-markers = "python_version == \"3.10\""
+markers = "python_version < \"3.11\""
 files = [
     {file = "tomli-2.2.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:678e4fa69e4575eb77d103de3df8a895e1591b48e740211bd1067378c69e8249"},
     {file = "tomli-2.2.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:023aa114dd824ade0100497eb2318602af309e5a55595f76b626d6d9f3b7b0a6"},
@@ -2893,4 +2911,4 @@ type = ["pytest-mypy"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.10,<4.0"
-content-hash = "b7ac335a86aa44c3d7d2802298818b389a6f1286e3e9b7b0edb2ff06377cecaf"
+content-hash = "40eae94995dc0a388fa832ed4af9b6137f28d5b5ced3aaea70d5f91d4d9a179d"

autogpt_platform/autogpt_libs/pyproject.toml

@@ -26,7 +26,7 @@ pyright = "^1.1.408"
 pytest = "^8.4.1"
 pytest-asyncio = "^1.3.0"
 pytest-mock = "^3.15.1"
-pytest-cov = "^6.2.1"
+pytest-cov = "^7.0.0"
 ruff = "^0.15.0"
 
 [build-system]

autogpt_platform/backend/backend/api/features/chat/db.py

@@ -45,10 +45,7 @@ async def create_chat_session(
         successfulAgentRuns=SafeJson({}),
         successfulAgentSchedules=SafeJson({}),
     )
-    return await PrismaChatSession.prisma().create(
-        data=data,
-        include={"Messages": True},
-    )
+    return await PrismaChatSession.prisma().create(data=data)
 
 
 async def update_chat_session(

autogpt_platform/backend/backend/api/features/chat/response_model.py

@@ -18,6 +18,10 @@ class ResponseType(str, Enum):
     START = "start"
     FINISH = "finish"
 
+    # Step lifecycle (one LLM API call within a message)
+    START_STEP = "start-step"
+    FINISH_STEP = "finish-step"
+
     # Text streaming
     TEXT_START = "text-start"
     TEXT_DELTA = "text-delta"
@@ -57,6 +61,16 @@ class StreamStart(StreamBaseResponse):
         description="Task ID for SSE reconnection. Clients can reconnect using GET /tasks/{taskId}/stream",
     )
 
+    def to_sse(self) -> str:
+        """Convert to SSE format, excluding non-protocol fields like taskId."""
+        import json
+
+        data: dict[str, Any] = {
+            "type": self.type.value,
+            "messageId": self.messageId,
+        }
+        return f"data: {json.dumps(data)}\n\n"
+
 
 class StreamFinish(StreamBaseResponse):
     """End of message/stream."""
@@ -64,6 +78,26 @@ class StreamFinish(StreamBaseResponse):
     type: ResponseType = ResponseType.FINISH
 
 
+class StreamStartStep(StreamBaseResponse):
+    """Start of a step (one LLM API call within a message).
+
+    The AI SDK uses this to add a step-start boundary to message.parts,
+    enabling visual separation between multiple LLM calls in a single message.
+    """
+
+    type: ResponseType = ResponseType.START_STEP
+
+
+class StreamFinishStep(StreamBaseResponse):
+    """End of a step (one LLM API call within a message).
+
+    The AI SDK uses this to reset activeTextParts and activeReasoningParts,
+    so the next LLM call in a tool-call continuation starts with clean state.
+    """
+
+    type: ResponseType = ResponseType.FINISH_STEP
+
+
 # ========== Text Streaming ==========
 
 
@@ -117,7 +151,7 @@ class StreamToolOutputAvailable(StreamBaseResponse):
     type: ResponseType = ResponseType.TOOL_OUTPUT_AVAILABLE
     toolCallId: str = Field(..., description="Tool call ID this responds to")
     output: str | dict[str, Any] = Field(..., description="Tool execution output")
-    # Additional fields for internal use (not part of AI SDK spec but useful)
+    # Keep these for internal backend use
     toolName: str | None = Field(
         default=None, description="Name of the tool that was executed"
     )
@@ -125,6 +159,17 @@ class StreamToolOutputAvailable(StreamBaseResponse):
         default=True, description="Whether the tool execution succeeded"
     )
 
+    def to_sse(self) -> str:
+        """Convert to SSE format, excluding non-spec fields."""
+        import json
+
+        data = {
+            "type": self.type.value,
+            "toolCallId": self.toolCallId,
+            "output": self.output,
+        }
+        return f"data: {json.dumps(data)}\n\n"
+
 
 # ========== Other ==========
 

autogpt_platform/backend/backend/api/features/chat/routes.py

@@ -6,7 +6,7 @@ from collections.abc import AsyncGenerator
 from typing import Annotated
 
 from autogpt_libs import auth
-from fastapi import APIRouter, Depends, Header, HTTPException, Query, Security
+from fastapi import APIRouter, Depends, Header, HTTPException, Query, Response, Security
 from fastapi.responses import StreamingResponse
 from pydantic import BaseModel
 
@@ -17,7 +17,29 @@ from . import stream_registry
 from .completion_handler import process_operation_failure, process_operation_success
 from .config import ChatConfig
 from .model import ChatSession, create_chat_session, get_chat_session, get_user_sessions
-from .response_model import StreamFinish, StreamHeartbeat, StreamStart
+from .response_model import StreamFinish, StreamHeartbeat
+from .tools.models import (
+    AgentDetailsResponse,
+    AgentOutputResponse,
+    AgentPreviewResponse,
+    AgentSavedResponse,
+    AgentsFoundResponse,
+    BlockListResponse,
+    BlockOutputResponse,
+    ClarificationNeededResponse,
+    DocPageResponse,
+    DocSearchResultsResponse,
+    ErrorResponse,
+    ExecutionStartedResponse,
+    InputValidationErrorResponse,
+    NeedLoginResponse,
+    NoResultsResponse,
+    OperationInProgressResponse,
+    OperationPendingResponse,
+    OperationStartedResponse,
+    SetupRequirementsResponse,
+    UnderstandingUpdatedResponse,
+)
 
 config = ChatConfig()
 
@@ -266,12 +288,36 @@ async def stream_chat_post(
 
     """
     import asyncio
+    import time
+
+    stream_start_time = time.perf_counter()
+    log_meta = {"component": "ChatStream", "session_id": session_id}
+    if user_id:
+        log_meta["user_id"] = user_id
+
+    logger.info(
+        f"[TIMING] stream_chat_post STARTED, session={session_id}, "
+        f"user={user_id}, message_len={len(request.message)}",
+        extra={"json_fields": log_meta},
+    )
 
     session = await _validate_and_get_session(session_id, user_id)
+    logger.info(
+        f"[TIMING] session validated in {(time.perf_counter() - stream_start_time)*1000:.1f}ms",
+        extra={
+            "json_fields": {
+                **log_meta,
+                "duration_ms": (time.perf_counter() - stream_start_time) * 1000,
+            }
+        },
+    )
 
     # Create a task in the stream registry for reconnection support
     task_id = str(uuid_module.uuid4())
     operation_id = str(uuid_module.uuid4())
+    log_meta["task_id"] = task_id
+
+    task_create_start = time.perf_counter()
     await stream_registry.create_task(
         task_id=task_id,
         session_id=session_id,
@@ -280,14 +326,28 @@ async def stream_chat_post(
         tool_name="chat",
         operation_id=operation_id,
     )
+    logger.info(
+        f"[TIMING] create_task completed in {(time.perf_counter() - task_create_start)*1000:.1f}ms",
+        extra={
+            "json_fields": {
+                **log_meta,
+                "duration_ms": (time.perf_counter() - task_create_start) * 1000,
+            }
+        },
+    )
 
     # Background task that runs the AI generation independently of SSE connection
     async def run_ai_generation():
-        try:
-            # Emit a start event with task_id for reconnection
-            start_chunk = StreamStart(messageId=task_id, taskId=task_id)
-            await stream_registry.publish_chunk(task_id, start_chunk)
+        import time as time_module
 
+        gen_start_time = time_module.perf_counter()
+        logger.info(
+            f"[TIMING] run_ai_generation STARTED, task={task_id}, session={session_id}, user={user_id}",
+            extra={"json_fields": log_meta},
+        )
+        first_chunk_time, ttfc = None, None
+        chunk_count = 0
+        try:
             async for chunk in chat_service.stream_chat_completion(
                 session_id,
                 request.message,
@@ -295,25 +355,79 @@ async def stream_chat_post(
                 user_id=user_id,
                 session=session,  # Pass pre-fetched session to avoid double-fetch
                 context=request.context,
+                _task_id=task_id,  # Pass task_id so service emits start with taskId for reconnection
             ):
+                chunk_count += 1
+                if first_chunk_time is None:
+                    first_chunk_time = time_module.perf_counter()
+                    ttfc = first_chunk_time - gen_start_time
+                    logger.info(
+                        f"[TIMING] FIRST AI CHUNK at {ttfc:.2f}s, type={type(chunk).__name__}",
+                        extra={
+                            "json_fields": {
+                                **log_meta,
+                                "chunk_type": type(chunk).__name__,
+                                "time_to_first_chunk_ms": ttfc * 1000,
+                            }
+                        },
+                    )
                 # Write to Redis (subscribers will receive via XREAD)
                 await stream_registry.publish_chunk(task_id, chunk)
 
-            # Mark task as completed
+            gen_end_time = time_module.perf_counter()
+            total_time = (gen_end_time - gen_start_time) * 1000
+            logger.info(
+                f"[TIMING] run_ai_generation FINISHED in {total_time/1000:.1f}s; "
+                f"task={task_id}, session={session_id}, "
+                f"ttfc={ttfc or -1:.2f}s, n_chunks={chunk_count}",
+                extra={
+                    "json_fields": {
+                        **log_meta,
+                        "total_time_ms": total_time,
+                        "time_to_first_chunk_ms": (
+                            ttfc * 1000 if ttfc is not None else None
+                        ),
+                        "n_chunks": chunk_count,
+                    }
+                },
+            )
             await stream_registry.mark_task_completed(task_id, "completed")
         except Exception as e:
+            elapsed = time_module.perf_counter() - gen_start_time
             logger.error(
-                f"Error in background AI generation for session {session_id}: {e}"
+                f"[TIMING] run_ai_generation ERROR after {elapsed:.2f}s: {e}",
+                extra={
+                    "json_fields": {
+                        **log_meta,
+                        "elapsed_ms": elapsed * 1000,
+                        "error": str(e),
+                    }
+                },
             )
             await stream_registry.mark_task_completed(task_id, "failed")
 
     # Start the AI generation in a background task
     bg_task = asyncio.create_task(run_ai_generation())
     await stream_registry.set_task_asyncio_task(task_id, bg_task)
+    setup_time = (time.perf_counter() - stream_start_time) * 1000
+    logger.info(
+        f"[TIMING] Background task started, setup={setup_time:.1f}ms",
+        extra={"json_fields": {**log_meta, "setup_time_ms": setup_time}},
+    )
 
     # SSE endpoint that subscribes to the task's stream
     async def event_generator() -> AsyncGenerator[str, None]:
+        import time as time_module
+
+        event_gen_start = time_module.perf_counter()
+        logger.info(
+            f"[TIMING] event_generator STARTED, task={task_id}, session={session_id}, "
+            f"user={user_id}",
+            extra={"json_fields": log_meta},
+        )
         subscriber_queue = None
+        first_chunk_yielded = False
+        chunks_yielded = 0
         try:
             # Subscribe to the task stream (this replays existing messages + live updates)
             subscriber_queue = await stream_registry.subscribe_to_task(
@@ -328,22 +442,70 @@ async def stream_chat_post(
                 return
 
             # Read from the subscriber queue and yield to SSE
+            logger.info(
+                "[TIMING] Starting to read from subscriber_queue",
+                extra={"json_fields": log_meta},
+            )
             while True:
                 try:
                     chunk = await asyncio.wait_for(subscriber_queue.get(), timeout=30.0)
+                    chunks_yielded += 1
+
+                    if not first_chunk_yielded:
+                        first_chunk_yielded = True
+                        elapsed = time_module.perf_counter() - event_gen_start
+                        logger.info(
+                            f"[TIMING] FIRST CHUNK from queue at {elapsed:.2f}s, "
+                            f"type={type(chunk).__name__}",
+                            extra={
+                                "json_fields": {
+                                    **log_meta,
+                                    "chunk_type": type(chunk).__name__,
+                                    "elapsed_ms": elapsed * 1000,
+                                }
+                            },
+                        )
+
                     yield chunk.to_sse()
 
                     # Check for finish signal
                     if isinstance(chunk, StreamFinish):
+                        total_time = time_module.perf_counter() - event_gen_start
+                        logger.info(
+                            f"[TIMING] StreamFinish received in {total_time:.2f}s; "
+                            f"n_chunks={chunks_yielded}",
+                            extra={
+                                "json_fields": {
+                                    **log_meta,
+                                    "chunks_yielded": chunks_yielded,
+                                    "total_time_ms": total_time * 1000,
+                                }
+                            },
+                        )
                         break
                 except asyncio.TimeoutError:
-                    # Send heartbeat to keep connection alive
                     yield StreamHeartbeat().to_sse()
 
         except GeneratorExit:
+            logger.info(
+                f"[TIMING] GeneratorExit (client disconnected), chunks={chunks_yielded}",
+                extra={
+                    "json_fields": {
+                        **log_meta,
+                        "chunks_yielded": chunks_yielded,
+                        "reason": "client_disconnect",
+                    }
+                },
+            )
             pass  # Client disconnected - background task continues
         except Exception as e:
-            logger.error(f"Error in SSE stream for task {task_id}: {e}")
+            elapsed = (time_module.perf_counter() - event_gen_start) * 1000
+            logger.error(
+                f"[TIMING] event_generator ERROR after {elapsed:.1f}ms: {e}",
+                extra={
+                    "json_fields": {**log_meta, "elapsed_ms": elapsed, "error": str(e)}
+                },
+            )
         finally:
             # Unsubscribe when client disconnects or stream ends to prevent resource leak
             if subscriber_queue is not None:
@@ -357,6 +519,18 @@ async def stream_chat_post(
                         exc_info=True,
                     )
             # AI SDK protocol termination - always yield even if unsubscribe fails
+            total_time = time_module.perf_counter() - event_gen_start
+            logger.info(
+                f"[TIMING] event_generator FINISHED in {total_time:.2f}s; "
+                f"task={task_id}, session={session_id}, n_chunks={chunks_yielded}",
+                extra={
+                    "json_fields": {
+                        **log_meta,
+                        "total_time_ms": total_time * 1000,
+                        "chunks_yielded": chunks_yielded,
+                    }
+                },
+            )
             yield "data: [DONE]\n\n"
 
     return StreamingResponse(
@@ -374,63 +548,90 @@ async def stream_chat_post(
 @router.get(
     "/sessions/{session_id}/stream",
 )
-async def stream_chat_get(
+async def resume_session_stream(
     session_id: str,
-    message: Annotated[str, Query(min_length=1, max_length=10000)],
     user_id: str | None = Depends(auth.get_user_id),
-    is_user_message: bool = Query(default=True),
 ):
     """
-    Stream chat responses for a session (GET - legacy endpoint).
+    Resume an active stream for a session.
 
-    Streams the AI/completion responses in real time over Server-Sent Events (SSE), including:
-      - Text fragments as they are generated
-      - Tool call UI elements (if invoked)
-      - Tool execution results
+    Called by the AI SDK's ``useChat(resume: true)`` on page load.
+    Checks for an active (in-progress) task on the session and either replays
+    the full SSE stream or returns 204 No Content if nothing is running.
 
     Args:
-        session_id: The chat session identifier to associate with the streamed messages.
-        message: The user's new message to process.
+        session_id: The chat session identifier.
         user_id: Optional authenticated user ID.
-        is_user_message: Whether the message is a user message.
-    Returns:
-        StreamingResponse: SSE-formatted response chunks.
 
+    Returns:
+        StreamingResponse (SSE) when an active stream exists,
+        or 204 No Content when there is nothing to resume.
     """
-    session = await _validate_and_get_session(session_id, user_id)
+    import asyncio
+
+    active_task, _last_id = await stream_registry.get_active_task_for_session(
+        session_id, user_id
+    )
+
+    if not active_task:
+        return Response(status_code=204)
+
+    subscriber_queue = await stream_registry.subscribe_to_task(
+        task_id=active_task.task_id,
+        user_id=user_id,
+        last_message_id="0-0",  # Full replay so useChat rebuilds the message
+    )
+
+    if subscriber_queue is None:
+        return Response(status_code=204)
 
     async def event_generator() -> AsyncGenerator[str, None]:
         chunk_count = 0
         first_chunk_type: str | None = None
-        async for chunk in chat_service.stream_chat_completion(
-            session_id,
-            message,
-            is_user_message=is_user_message,
-            user_id=user_id,
-            session=session,  # Pass pre-fetched session to avoid double-fetch
-        ):
-            if chunk_count < 3:
-                logger.info(
-                    "Chat stream chunk",
-                    extra={
-                        "session_id": session_id,
-                        "chunk_type": str(chunk.type),
-                    },
+        try:
+            while True:
+                try:
+                    chunk = await asyncio.wait_for(subscriber_queue.get(), timeout=30.0)
+                    if chunk_count < 3:
+                        logger.info(
+                            "Resume stream chunk",
+                            extra={
+                                "session_id": session_id,
+                                "chunk_type": str(chunk.type),
+                            },
+                        )
+                    if not first_chunk_type:
+                        first_chunk_type = str(chunk.type)
+                    chunk_count += 1
+                    yield chunk.to_sse()
+
+                    if isinstance(chunk, StreamFinish):
+                        break
+                except asyncio.TimeoutError:
+                    yield StreamHeartbeat().to_sse()
+        except GeneratorExit:
+            pass
+        except Exception as e:
+            logger.error(f"Error in resume stream for session {session_id}: {e}")
+        finally:
+            try:
+                await stream_registry.unsubscribe_from_task(
+                    active_task.task_id, subscriber_queue
                 )
-            if not first_chunk_type:
-                first_chunk_type = str(chunk.type)
-            chunk_count += 1
-            yield chunk.to_sse()
-        logger.info(
-            "Chat stream completed",
-            extra={
-                "session_id": session_id,
-                "chunk_count": chunk_count,
-                "first_chunk_type": first_chunk_type,
-            },
-        )
-        # AI SDK protocol termination
-        yield "data: [DONE]\n\n"
+            except Exception as unsub_err:
+                logger.error(
+                    f"Error unsubscribing from task {active_task.task_id}: {unsub_err}",
+                    exc_info=True,
+                )
+            logger.info(
+                "Resume stream completed",
+                extra={
+                    "session_id": session_id,
+                    "n_chunks": chunk_count,
+                    "first_chunk_type": first_chunk_type,
+                },
+            )
+            yield "data: [DONE]\n\n"
 
     return StreamingResponse(
         event_generator(),
@@ -438,8 +639,8 @@ async def stream_chat_get(
         headers={
             "Cache-Control": "no-cache",
             "Connection": "keep-alive",
-            "X-Accel-Buffering": "no",  # Disable nginx buffering
-            "x-vercel-ai-ui-message-stream": "v1",  # AI SDK protocol header
+            "X-Accel-Buffering": "no",
+            "x-vercel-ai-ui-message-stream": "v1",
         },
     )
 
@@ -751,3 +952,42 @@ async def health_check() -> dict:
         "service": "chat",
         "version": "0.1.0",
     }
+
+
+# ========== Schema Export (for OpenAPI / Orval codegen) ==========
+
+ToolResponseUnion = (
+    AgentsFoundResponse
+    | NoResultsResponse
+    | AgentDetailsResponse
+    | SetupRequirementsResponse
+    | ExecutionStartedResponse
+    | NeedLoginResponse
+    | ErrorResponse
+    | InputValidationErrorResponse
+    | AgentOutputResponse
+    | UnderstandingUpdatedResponse
+    | AgentPreviewResponse
+    | AgentSavedResponse
+    | ClarificationNeededResponse
+    | BlockListResponse
+    | BlockOutputResponse
+    | DocSearchResultsResponse
+    | DocPageResponse
+    | OperationStartedResponse
+    | OperationPendingResponse
+    | OperationInProgressResponse
+)
+
+
+@router.get(
+    "/schema/tool-responses",
+    response_model=ToolResponseUnion,
+    include_in_schema=True,
+    summary="[Dummy] Tool response type export for codegen",
+    description="This endpoint is not meant to be called. It exists solely to "
+    "expose tool response models in the OpenAPI schema for frontend codegen.",
+)
+async def _tool_response_schema() -> ToolResponseUnion:  # type: ignore[return]
+    """Never called at runtime. Exists only so Orval generates TS types."""
+    raise HTTPException(status_code=501, detail="Schema-only endpoint")

autogpt_platform/backend/backend/api/features/chat/service.py

@@ -1,15 +1,12 @@
 import asyncio
 import logging
 import time
-import uuid as uuid_module
 from asyncio import CancelledError
 from collections.abc import AsyncGenerator
 from typing import TYPE_CHECKING, Any, cast
 
 import openai
 
-from backend.util.prompt import compress_context
-
 if TYPE_CHECKING:
     from backend.util.prompt import CompressResult
 
@@ -55,8 +52,10 @@ from .response_model import (
     StreamBaseResponse,
     StreamError,
     StreamFinish,
+    StreamFinishStep,
     StreamHeartbeat,
     StreamStart,
+    StreamStartStep,
     StreamTextDelta,
     StreamTextEnd,
     StreamTextStart,
@@ -354,6 +353,10 @@ async def stream_chat_completion(
     retry_count: int = 0,
     session: ChatSession | None = None,
     context: dict[str, str] | None = None,  # {url: str, content: str}
+    _continuation_message_id: (
+        str | None
+    ) = None,  # Internal: reuse message ID for tool call continuations
+    _task_id: str | None = None,  # Internal: task ID for SSE reconnection support
 ) -> AsyncGenerator[StreamBaseResponse, None]:
     """Main entry point for streaming chat completions with database handling.
 
@@ -374,21 +377,45 @@ async def stream_chat_completion(
         ValueError: If max_context_messages is exceeded
 
     """
+    completion_start = time.monotonic()
+
+    # Build log metadata for structured logging
+    log_meta = {"component": "ChatService", "session_id": session_id}
+    if user_id:
+        log_meta["user_id"] = user_id
+
     logger.info(
-        f"Streaming chat completion for session {session_id} for message {message} and user id {user_id}. Message is user message: {is_user_message}"
+        f"[TIMING] stream_chat_completion STARTED, session={session_id}, user={user_id}, "
+        f"message_len={len(message) if message else 0}, is_user={is_user_message}",
+        extra={
+            "json_fields": {
+                **log_meta,
+                "message_len": len(message) if message else 0,
+                "is_user_message": is_user_message,
+            }
+        },
     )
 
     # Only fetch from Redis if session not provided (initial call)
     if session is None:
+        fetch_start = time.monotonic()
         session = await get_chat_session(session_id, user_id)
+        fetch_time = (time.monotonic() - fetch_start) * 1000
         logger.info(
-            f"Fetched session from Redis: {session.session_id if session else 'None'}, "
-            f"message_count={len(session.messages) if session else 0}"
+            f"[TIMING] get_chat_session took {fetch_time:.1f}ms, "
+            f"n_messages={len(session.messages) if session else 0}",
+            extra={
+                "json_fields": {
+                    **log_meta,
+                    "duration_ms": fetch_time,
+                    "n_messages": len(session.messages) if session else 0,
+                }
+            },
         )
     else:
         logger.info(
-            f"Using provided session object: {session.session_id}, "
-            f"message_count={len(session.messages)}"
+            f"[TIMING] Using provided session, messages={len(session.messages)}",
+            extra={"json_fields": {**log_meta, "n_messages": len(session.messages)}},
         )
 
     if not session:
@@ -409,17 +436,25 @@ async def stream_chat_completion(
 
         # Track user message in PostHog
         if is_user_message:
+            posthog_start = time.monotonic()
             track_user_message(
                 user_id=user_id,
                 session_id=session_id,
                 message_length=len(message),
             )
+            posthog_time = (time.monotonic() - posthog_start) * 1000
+            logger.info(
+                f"[TIMING] track_user_message took {posthog_time:.1f}ms",
+                extra={"json_fields": {**log_meta, "duration_ms": posthog_time}},
+            )
 
-    logger.info(
-        f"Upserting session: {session.session_id} with user id {session.user_id}, "
-        f"message_count={len(session.messages)}"
-    )
+    upsert_start = time.monotonic()
     session = await upsert_chat_session(session)
+    upsert_time = (time.monotonic() - upsert_start) * 1000
+    logger.info(
+        f"[TIMING] upsert_chat_session took {upsert_time:.1f}ms",
+        extra={"json_fields": {**log_meta, "duration_ms": upsert_time}},
+    )
     assert session, "Session not found"
 
     # Generate title for new sessions on first user message (non-blocking)
@@ -457,7 +492,13 @@ async def stream_chat_completion(
             asyncio.create_task(_update_title())
 
     # Build system prompt with business understanding
+    prompt_start = time.monotonic()
     system_prompt, understanding = await _build_system_prompt(user_id)
+    prompt_time = (time.monotonic() - prompt_start) * 1000
+    logger.info(
+        f"[TIMING] _build_system_prompt took {prompt_time:.1f}ms",
+        extra={"json_fields": {**log_meta, "duration_ms": prompt_time}},
+    )
 
     # Initialize variables for streaming
     assistant_response = ChatMessage(
@@ -480,13 +521,29 @@ async def stream_chat_completion(
     should_retry = False
 
     # Generate unique IDs for AI SDK protocol
-    message_id = str(uuid_module.uuid4())
+    import uuid as uuid_module
+
+    is_continuation = _continuation_message_id is not None
+    message_id = _continuation_message_id or str(uuid_module.uuid4())
     text_block_id = str(uuid_module.uuid4())
 
-    # Yield message start
-    yield StreamStart(messageId=message_id)
+    # Only yield message start for the initial call, not for continuations.
+    setup_time = (time.monotonic() - completion_start) * 1000
+    logger.info(
+        f"[TIMING] Setup complete, yielding StreamStart at {setup_time:.1f}ms",
+        extra={"json_fields": {**log_meta, "setup_time_ms": setup_time}},
+    )
+    if not is_continuation:
+        yield StreamStart(messageId=message_id, taskId=_task_id)
+
+    # Emit start-step before each LLM call (AI SDK uses this to add step boundaries)
+    yield StreamStartStep()
 
     try:
+        logger.info(
+            "[TIMING] Calling _stream_chat_chunks",
+            extra={"json_fields": log_meta},
+        )
         async for chunk in _stream_chat_chunks(
             session=session,
             tools=tools,
@@ -586,6 +643,10 @@ async def stream_chat_completion(
                     )
                 yield chunk
             elif isinstance(chunk, StreamFinish):
+                if has_done_tool_call:
+                    # Tool calls happened — close the step but don't send message-level finish.
+                    # The continuation will open a new step, and finish will come at the end.
+                    yield StreamFinishStep()
                 if not has_done_tool_call:
                     # Emit text-end before finish if we received text but haven't closed it
                     if has_received_text and not text_streaming_ended:
@@ -617,6 +678,8 @@ async def stream_chat_completion(
                             has_saved_assistant_message = True
 
                     has_yielded_end = True
+                    # Emit finish-step before finish (resets AI SDK text/reasoning state)
+                    yield StreamFinishStep()
                     yield chunk
             elif isinstance(chunk, StreamError):
                 has_yielded_error = True
@@ -666,6 +729,10 @@ async def stream_chat_completion(
             logger.info(
                 f"Retryable error encountered. Attempt {retry_count + 1}/{config.max_retries}"
             )
+            # Close the current step before retrying so the recursive call's
+            # StreamStartStep doesn't produce unbalanced step events.
+            if not has_yielded_end:
+                yield StreamFinishStep()
             should_retry = True
         else:
             # Non-retryable error or max retries exceeded
@@ -701,6 +768,7 @@ async def stream_chat_completion(
                 error_response = StreamError(errorText=error_message)
                 yield error_response
             if not has_yielded_end:
+                yield StreamFinishStep()
                 yield StreamFinish()
             return
 
@@ -715,6 +783,8 @@ async def stream_chat_completion(
             retry_count=retry_count + 1,
             session=session,
             context=context,
+            _continuation_message_id=message_id,  # Reuse message ID since start was already sent
+            _task_id=_task_id,
         ):
             yield chunk
         return  # Exit after retry to avoid double-saving in finally block
@@ -784,6 +854,8 @@ async def stream_chat_completion(
             session=session,  # Pass session object to avoid Redis refetch
             context=context,
             tool_call_response=str(tool_response_messages),
+            _continuation_message_id=message_id,  # Reuse message ID to avoid duplicates
+            _task_id=_task_id,
         ):
             yield chunk
 
@@ -840,6 +912,10 @@ async def _manage_context_window(
     Returns:
         CompressResult with compacted messages and metadata
     """
+    import openai
+
+    from backend.util.prompt import compress_context
+
     # Convert messages to dict format
     messages_dict = []
     for msg in messages:
@@ -890,9 +966,21 @@ async def _stream_chat_chunks(
         SSE formatted JSON response objects
 
     """
+    import time as time_module
+
+    stream_chunks_start = time_module.perf_counter()
     model = config.model
 
-    logger.info("Starting pure chat stream")
+    # Build log metadata for structured logging
+    log_meta = {"component": "ChatService", "session_id": session.session_id}
+    if session.user_id:
+        log_meta["user_id"] = session.user_id
+
+    logger.info(
+        f"[TIMING] _stream_chat_chunks STARTED, session={session.session_id}, "
+        f"user={session.user_id}, n_messages={len(session.messages)}",
+        extra={"json_fields": {**log_meta, "n_messages": len(session.messages)}},
+    )
 
     messages = session.to_openai_messages()
     if system_prompt:
@@ -903,12 +991,18 @@ async def _stream_chat_chunks(
         messages = [system_message] + messages
 
     # Apply context window management
+    context_start = time_module.perf_counter()
     context_result = await _manage_context_window(
         messages=messages,
         model=model,
         api_key=config.api_key,
         base_url=config.base_url,
     )
+    context_time = (time_module.perf_counter() - context_start) * 1000
+    logger.info(
+        f"[TIMING] _manage_context_window took {context_time:.1f}ms",
+        extra={"json_fields": {**log_meta, "duration_ms": context_time}},
+    )
 
     if context_result.error:
         if "System prompt dropped" in context_result.error:
@@ -943,9 +1037,19 @@ async def _stream_chat_chunks(
 
         while retry_count <= MAX_RETRIES:
             try:
+                elapsed = (time_module.perf_counter() - stream_chunks_start) * 1000
+                retry_info = (
+                    f" (retry {retry_count}/{MAX_RETRIES})" if retry_count > 0 else ""
+                )
                 logger.info(
-                    f"Creating OpenAI chat completion stream..."
-                    f"{f' (retry {retry_count}/{MAX_RETRIES})' if retry_count > 0 else ''}"
+                    f"[TIMING] Creating OpenAI stream at {elapsed:.1f}ms{retry_info}",
+                    extra={
+                        "json_fields": {
+                            **log_meta,
+                            "elapsed_ms": elapsed,
+                            "retry_count": retry_count,
+                        }
+                    },
                 )
 
                 # Build extra_body for OpenRouter tracing and PostHog analytics
@@ -962,6 +1066,7 @@ async def _stream_chat_chunks(
                         :128
                     ]  # OpenRouter limit
 
+                api_call_start = time_module.perf_counter()
                 stream = await client.chat.completions.create(
                     model=model,
                     messages=cast(list[ChatCompletionMessageParam], messages),
@@ -971,6 +1076,11 @@ async def _stream_chat_chunks(
                     stream_options=ChatCompletionStreamOptionsParam(include_usage=True),
                     extra_body=extra_body,
                 )
+                api_init_time = (time_module.perf_counter() - api_call_start) * 1000
+                logger.info(
+                    f"[TIMING] OpenAI stream object returned in {api_init_time:.1f}ms",
+                    extra={"json_fields": {**log_meta, "duration_ms": api_init_time}},
+                )
 
                 # Variables to accumulate tool calls
                 tool_calls: list[dict[str, Any]] = []
@@ -981,10 +1091,13 @@ async def _stream_chat_chunks(
 
                 # Track if we've started the text block
                 text_started = False
+                first_content_chunk = True
+                chunk_count = 0
 
                 # Process the stream
                 chunk: ChatCompletionChunk
                 async for chunk in stream:
+                    chunk_count += 1
                     if chunk.usage:
                         yield StreamUsage(
                             promptTokens=chunk.usage.prompt_tokens,
@@ -1007,6 +1120,23 @@ async def _stream_chat_chunks(
                             if not text_started and text_block_id:
                                 yield StreamTextStart(id=text_block_id)
                                 text_started = True
+                            # Log timing for first content chunk
+                            if first_content_chunk:
+                                first_content_chunk = False
+                                ttfc = (
+                                    time_module.perf_counter() - api_call_start
+                                ) * 1000
+                                logger.info(
+                                    f"[TIMING] FIRST CONTENT CHUNK at {ttfc:.1f}ms "
+                                    f"(since API call), n_chunks={chunk_count}",
+                                    extra={
+                                        "json_fields": {
+                                            **log_meta,
+                                            "time_to_first_chunk_ms": ttfc,
+                                            "n_chunks": chunk_count,
+                                        }
+                                    },
+                                )
                             # Stream the text delta
                             text_response = StreamTextDelta(
                                 id=text_block_id or "",
@@ -1063,7 +1193,21 @@ async def _stream_chat_chunks(
                                         toolName=tool_calls[idx]["function"]["name"],
                                     )
                                     emitted_start_for_idx.add(idx)
-                logger.info(f"Stream complete. Finish reason: {finish_reason}")
+                stream_duration = time_module.perf_counter() - api_call_start
+                logger.info(
+                    f"[TIMING] OpenAI stream COMPLETE, finish_reason={finish_reason}, "
+                    f"duration={stream_duration:.2f}s, "
+                    f"n_chunks={chunk_count}, n_tool_calls={len(tool_calls)}",
+                    extra={
+                        "json_fields": {
+                            **log_meta,
+                            "stream_duration_ms": stream_duration * 1000,
+                            "finish_reason": finish_reason,
+                            "n_chunks": chunk_count,
+                            "n_tool_calls": len(tool_calls),
+                        }
+                    },
+                )
 
                 # Yield all accumulated tool calls after the stream is complete
                 # This ensures all tool call arguments have been fully received
@@ -1083,6 +1227,12 @@ async def _stream_chat_chunks(
                         # Re-raise to trigger retry logic in the parent function
                         raise
 
+                total_time = (time_module.perf_counter() - stream_chunks_start) * 1000
+                logger.info(
+                    f"[TIMING] _stream_chat_chunks COMPLETED in {total_time/1000:.1f}s; "
+                    f"session={session.session_id}, user={session.user_id}",
+                    extra={"json_fields": {**log_meta, "total_time_ms": total_time}},
+                )
                 yield StreamFinish()
                 return
             except Exception as e:
@@ -1150,6 +1300,8 @@ async def _yield_tool_call(
         KeyError: If expected tool call fields are missing
         TypeError: If tool call structure is invalid
     """
+    import uuid as uuid_module
+
     tool_name = tool_calls[yield_idx]["function"]["name"]
     tool_call_id = tool_calls[yield_idx]["id"]
 
@@ -1560,6 +1712,7 @@ async def _execute_long_running_tool_with_streaming(
             task_id,
             StreamError(errorText=str(e)),
         )
+        await stream_registry.publish_chunk(task_id, StreamFinishStep())
         await stream_registry.publish_chunk(task_id, StreamFinish())
 
         await _update_pending_operation(
@@ -1770,6 +1923,8 @@ async def _generate_llm_continuation_with_streaming(
     after a tool result is saved. Chunks are published to the stream registry
     so reconnecting clients can receive them.
     """
+    import uuid as uuid_module
+
     try:
         # Load fresh session from DB (bypass cache to get the updated tool result)
         await invalidate_session_cache(session_id)
@@ -1805,12 +1960,17 @@ async def _generate_llm_continuation_with_streaming(
             extra_body["session_id"] = session_id[:128]
 
         # Make streaming LLM call (no tools - just text response)
+        from typing import cast
+
+        from openai.types.chat import ChatCompletionMessageParam
+
         # Generate unique IDs for AI SDK protocol
         message_id = str(uuid_module.uuid4())
         text_block_id = str(uuid_module.uuid4())
 
         # Publish start event
         await stream_registry.publish_chunk(task_id, StreamStart(messageId=message_id))
+        await stream_registry.publish_chunk(task_id, StreamStartStep())
         await stream_registry.publish_chunk(task_id, StreamTextStart(id=text_block_id))
 
         # Stream the response
@@ -1834,6 +1994,7 @@ async def _generate_llm_continuation_with_streaming(
 
         # Publish end events
         await stream_registry.publish_chunk(task_id, StreamTextEnd(id=text_block_id))
+        await stream_registry.publish_chunk(task_id, StreamFinishStep())
 
         if assistant_content:
             # Reload session from DB to avoid race condition with user messages
@@ -1875,4 +2036,5 @@ async def _generate_llm_continuation_with_streaming(
             task_id,
             StreamError(errorText=f"Failed to generate response: {e}"),
         )
+        await stream_registry.publish_chunk(task_id, StreamFinishStep())
         await stream_registry.publish_chunk(task_id, StreamFinish())

autogpt_platform/backend/backend/api/features/chat/stream_registry.py

@@ -104,6 +104,24 @@ async def create_task(
     Returns:
         The created ActiveTask instance (metadata only)
     """
+    import time
+
+    start_time = time.perf_counter()
+
+    # Build log metadata for structured logging
+    log_meta = {
+        "component": "StreamRegistry",
+        "task_id": task_id,
+        "session_id": session_id,
+    }
+    if user_id:
+        log_meta["user_id"] = user_id
+
+    logger.info(
+        f"[TIMING] create_task STARTED, task={task_id}, session={session_id}, user={user_id}",
+        extra={"json_fields": log_meta},
+    )
+
     task = ActiveTask(
         task_id=task_id,
         session_id=session_id,
@@ -114,10 +132,18 @@ async def create_task(
     )
 
     # Store metadata in Redis
+    redis_start = time.perf_counter()
     redis = await get_redis_async()
+    redis_time = (time.perf_counter() - redis_start) * 1000
+    logger.info(
+        f"[TIMING] get_redis_async took {redis_time:.1f}ms",
+        extra={"json_fields": {**log_meta, "duration_ms": redis_time}},
+    )
+
     meta_key = _get_task_meta_key(task_id)
     op_key = _get_operation_mapping_key(operation_id)
 
+    hset_start = time.perf_counter()
     await redis.hset(  # type: ignore[misc]
         meta_key,
         mapping={
@@ -131,12 +157,22 @@ async def create_task(
             "created_at": task.created_at.isoformat(),
         },
     )
+    hset_time = (time.perf_counter() - hset_start) * 1000
+    logger.info(
+        f"[TIMING] redis.hset took {hset_time:.1f}ms",
+        extra={"json_fields": {**log_meta, "duration_ms": hset_time}},
+    )
+
     await redis.expire(meta_key, config.stream_ttl)
 
     # Create operation_id -> task_id mapping for webhook lookups
     await redis.set(op_key, task_id, ex=config.stream_ttl)
 
-    logger.debug(f"Created task {task_id} for session {session_id}")
+    total_time = (time.perf_counter() - start_time) * 1000
+    logger.info(
+        f"[TIMING] create_task COMPLETED in {total_time:.1f}ms; task={task_id}, session={session_id}",
+        extra={"json_fields": {**log_meta, "total_time_ms": total_time}},
+    )
 
     return task
 
@@ -156,26 +192,60 @@ async def publish_chunk(
     Returns:
         The Redis Stream message ID
     """
+    import time
+
+    start_time = time.perf_counter()
+    chunk_type = type(chunk).__name__
     chunk_json = chunk.model_dump_json()
     message_id = "0-0"
 
+    # Build log metadata
+    log_meta = {
+        "component": "StreamRegistry",
+        "task_id": task_id,
+        "chunk_type": chunk_type,
+    }
+
     try:
         redis = await get_redis_async()
         stream_key = _get_task_stream_key(task_id)
 
         # Write to Redis Stream for persistence and real-time delivery
+        xadd_start = time.perf_counter()
         raw_id = await redis.xadd(
             stream_key,
             {"data": chunk_json},
             maxlen=config.stream_max_length,
         )
+        xadd_time = (time.perf_counter() - xadd_start) * 1000
         message_id = raw_id if isinstance(raw_id, str) else raw_id.decode()
 
         # Set TTL on stream to match task metadata TTL
         await redis.expire(stream_key, config.stream_ttl)
+
+        total_time = (time.perf_counter() - start_time) * 1000
+        # Only log timing for significant chunks or slow operations
+        if (
+            chunk_type
+            in ("StreamStart", "StreamFinish", "StreamTextStart", "StreamTextEnd")
+            or total_time > 50
+        ):
+            logger.info(
+                f"[TIMING] publish_chunk {chunk_type} in {total_time:.1f}ms (xadd={xadd_time:.1f}ms)",
+                extra={
+                    "json_fields": {
+                        **log_meta,
+                        "total_time_ms": total_time,
+                        "xadd_time_ms": xadd_time,
+                        "message_id": message_id,
+                    }
+                },
+            )
     except Exception as e:
+        elapsed = (time.perf_counter() - start_time) * 1000
         logger.error(
-            f"Failed to publish chunk for task {task_id}: {e}",
+            f"[TIMING] Failed to publish chunk {chunk_type} after {elapsed:.1f}ms: {e}",
+            extra={"json_fields": {**log_meta, "elapsed_ms": elapsed, "error": str(e)}},
             exc_info=True,
         )
 
@@ -200,24 +270,61 @@ async def subscribe_to_task(
         An asyncio Queue that will receive stream chunks, or None if task not found
         or user doesn't have access
     """
+    import time
+
+    start_time = time.perf_counter()
+
+    # Build log metadata
+    log_meta = {"component": "StreamRegistry", "task_id": task_id}
+    if user_id:
+        log_meta["user_id"] = user_id
+
+    logger.info(
+        f"[TIMING] subscribe_to_task STARTED, task={task_id}, user={user_id}, last_msg={last_message_id}",
+        extra={"json_fields": {**log_meta, "last_message_id": last_message_id}},
+    )
+
+    redis_start = time.perf_counter()
     redis = await get_redis_async()
     meta_key = _get_task_meta_key(task_id)
     meta: dict[Any, Any] = await redis.hgetall(meta_key)  # type: ignore[misc]
+    hgetall_time = (time.perf_counter() - redis_start) * 1000
+    logger.info(
+        f"[TIMING] Redis hgetall took {hgetall_time:.1f}ms",
+        extra={"json_fields": {**log_meta, "duration_ms": hgetall_time}},
+    )
 
     if not meta:
-        logger.debug(f"Task {task_id} not found in Redis")
+        elapsed = (time.perf_counter() - start_time) * 1000
+        logger.info(
+            f"[TIMING] Task not found in Redis after {elapsed:.1f}ms",
+            extra={
+                "json_fields": {
+                    **log_meta,
+                    "elapsed_ms": elapsed,
+                    "reason": "task_not_found",
+                }
+            },
+        )
         return None
 
     # Note: Redis client uses decode_responses=True, so keys are strings
     task_status = meta.get("status", "")
     task_user_id = meta.get("user_id", "") or None
+    log_meta["session_id"] = meta.get("session_id", "")
 
     # Validate ownership - if task has an owner, requester must match
     if task_user_id:
         if user_id != task_user_id:
             logger.warning(
-                f"User {user_id} denied access to task {task_id} "
-                f"owned by {task_user_id}"
+                f"[TIMING] Access denied: user {user_id} tried to access task owned by {task_user_id}",
+                extra={
+                    "json_fields": {
+                        **log_meta,
+                        "task_owner": task_user_id,
+                        "reason": "access_denied",
+                    }
+                },
             )
             return None
 
@@ -225,7 +332,19 @@ async def subscribe_to_task(
     stream_key = _get_task_stream_key(task_id)
 
     # Step 1: Replay messages from Redis Stream
+    xread_start = time.perf_counter()
     messages = await redis.xread({stream_key: last_message_id}, block=0, count=1000)
+    xread_time = (time.perf_counter() - xread_start) * 1000
+    logger.info(
+        f"[TIMING] Redis xread (replay) took {xread_time:.1f}ms, status={task_status}",
+        extra={
+            "json_fields": {
+                **log_meta,
+                "duration_ms": xread_time,
+                "task_status": task_status,
+            }
+        },
+    )
 
     replayed_count = 0
     replay_last_id = last_message_id
@@ -244,19 +363,48 @@ async def subscribe_to_task(
                     except Exception as e:
                         logger.warning(f"Failed to replay message: {e}")
 
-    logger.debug(f"Task {task_id}: replayed {replayed_count} messages")
+    logger.info(
+        f"[TIMING] Replayed {replayed_count} messages, last_id={replay_last_id}",
+        extra={
+            "json_fields": {
+                **log_meta,
+                "n_messages_replayed": replayed_count,
+                "replay_last_id": replay_last_id,
+            }
+        },
+    )
 
     # Step 2: If task is still running, start stream listener for live updates
     if task_status == "running":
+        logger.info(
+            "[TIMING] Task still running, starting _stream_listener",
+            extra={"json_fields": {**log_meta, "task_status": task_status}},
+        )
         listener_task = asyncio.create_task(
-            _stream_listener(task_id, subscriber_queue, replay_last_id)
+            _stream_listener(task_id, subscriber_queue, replay_last_id, log_meta)
         )
         # Track listener task for cleanup on unsubscribe
         _listener_tasks[id(subscriber_queue)] = (task_id, listener_task)
     else:
         # Task is completed/failed - add finish marker
+        logger.info(
+            f"[TIMING] Task already {task_status}, adding StreamFinish",
+            extra={"json_fields": {**log_meta, "task_status": task_status}},
+        )
         await subscriber_queue.put(StreamFinish())
 
+    total_time = (time.perf_counter() - start_time) * 1000
+    logger.info(
+        f"[TIMING] subscribe_to_task COMPLETED in {total_time:.1f}ms; task={task_id}, "
+        f"n_messages_replayed={replayed_count}",
+        extra={
+            "json_fields": {
+                **log_meta,
+                "total_time_ms": total_time,
+                "n_messages_replayed": replayed_count,
+            }
+        },
+    )
     return subscriber_queue
 
 
@@ -264,6 +412,7 @@ async def _stream_listener(
     task_id: str,
     subscriber_queue: asyncio.Queue[StreamBaseResponse],
     last_replayed_id: str,
+    log_meta: dict | None = None,
 ) -> None:
     """Listen to Redis Stream for new messages using blocking XREAD.
 
@@ -274,10 +423,27 @@ async def _stream_listener(
         task_id: Task ID to listen for
         subscriber_queue: Queue to deliver messages to
         last_replayed_id: Last message ID from replay (continue from here)
+        log_meta: Structured logging metadata
     """
+    import time
+
+    start_time = time.perf_counter()
+
+    # Use provided log_meta or build minimal one
+    if log_meta is None:
+        log_meta = {"component": "StreamRegistry", "task_id": task_id}
+
+    logger.info(
+        f"[TIMING] _stream_listener STARTED, task={task_id}, last_id={last_replayed_id}",
+        extra={"json_fields": {**log_meta, "last_replayed_id": last_replayed_id}},
+    )
+
     queue_id = id(subscriber_queue)
     # Track the last successfully delivered message ID for recovery hints
     last_delivered_id = last_replayed_id
+    messages_delivered = 0
+    first_message_time = None
+    xread_count = 0
 
     try:
         redis = await get_redis_async()
@@ -287,9 +453,39 @@ async def _stream_listener(
         while True:
             # Block for up to 30 seconds waiting for new messages
             # This allows periodic checking if task is still running
+            xread_start = time.perf_counter()
+            xread_count += 1
             messages = await redis.xread(
                 {stream_key: current_id}, block=30000, count=100
             )
+            xread_time = (time.perf_counter() - xread_start) * 1000
+
+            if messages:
+                msg_count = sum(len(msgs) for _, msgs in messages)
+                logger.info(
+                    f"[TIMING] xread #{xread_count} returned {msg_count} messages in {xread_time:.1f}ms",
+                    extra={
+                        "json_fields": {
+                            **log_meta,
+                            "xread_count": xread_count,
+                            "n_messages": msg_count,
+                            "duration_ms": xread_time,
+                        }
+                    },
+                )
+            elif xread_time > 1000:
+                # Only log timeouts (30s blocking)
+                logger.info(
+                    f"[TIMING] xread #{xread_count} timeout after {xread_time:.1f}ms",
+                    extra={
+                        "json_fields": {
+                            **log_meta,
+                            "xread_count": xread_count,
+                            "duration_ms": xread_time,
+                            "reason": "timeout",
+                        }
+                    },
+                )
 
             if not messages:
                 # Timeout - check if task is still running
@@ -326,10 +522,30 @@ async def _stream_listener(
                                 )
                                 # Update last delivered ID on successful delivery
                                 last_delivered_id = current_id
+                                messages_delivered += 1
+                                if first_message_time is None:
+                                    first_message_time = time.perf_counter()
+                                    elapsed = (first_message_time - start_time) * 1000
+                                    logger.info(
+                                        f"[TIMING] FIRST live message at {elapsed:.1f}ms, type={type(chunk).__name__}",
+                                        extra={
+                                            "json_fields": {
+                                                **log_meta,
+                                                "elapsed_ms": elapsed,
+                                                "chunk_type": type(chunk).__name__,
+                                            }
+                                        },
+                                    )
                             except asyncio.TimeoutError:
                                 logger.warning(
-                                    f"Subscriber queue full for task {task_id}, "
-                                    f"message delivery timed out after {QUEUE_PUT_TIMEOUT}s"
+                                    f"[TIMING] Subscriber queue full, delivery timed out after {QUEUE_PUT_TIMEOUT}s",
+                                    extra={
+                                        "json_fields": {
+                                            **log_meta,
+                                            "timeout_s": QUEUE_PUT_TIMEOUT,
+                                            "reason": "queue_full",
+                                        }
+                                    },
                                 )
                                 # Send overflow error with recovery info
                                 try:
@@ -351,15 +567,44 @@ async def _stream_listener(
 
                             # Stop listening on finish
                             if isinstance(chunk, StreamFinish):
+                                total_time = (time.perf_counter() - start_time) * 1000
+                                logger.info(
+                                    f"[TIMING] StreamFinish received in {total_time/1000:.1f}s; delivered={messages_delivered}",
+                                    extra={
+                                        "json_fields": {
+                                            **log_meta,
+                                            "total_time_ms": total_time,
+                                            "messages_delivered": messages_delivered,
+                                        }
+                                    },
+                                )
                                 return
                     except Exception as e:
-                        logger.warning(f"Error processing stream message: {e}")
+                        logger.warning(
+                            f"Error processing stream message: {e}",
+                            extra={"json_fields": {**log_meta, "error": str(e)}},
+                        )
 
     except asyncio.CancelledError:
-        logger.debug(f"Stream listener cancelled for task {task_id}")
+        elapsed = (time.perf_counter() - start_time) * 1000
+        logger.info(
+            f"[TIMING] _stream_listener CANCELLED after {elapsed:.1f}ms, delivered={messages_delivered}",
+            extra={
+                "json_fields": {
+                    **log_meta,
+                    "elapsed_ms": elapsed,
+                    "messages_delivered": messages_delivered,
+                    "reason": "cancelled",
+                }
+            },
+        )
         raise  # Re-raise to propagate cancellation
     except Exception as e:
-        logger.error(f"Stream listener error for task {task_id}: {e}")
+        elapsed = (time.perf_counter() - start_time) * 1000
+        logger.error(
+            f"[TIMING] _stream_listener ERROR after {elapsed:.1f}ms: {e}",
+            extra={"json_fields": {**log_meta, "elapsed_ms": elapsed, "error": str(e)}},
+        )
         # On error, send finish to unblock subscriber
         try:
             await asyncio.wait_for(
@@ -368,10 +613,24 @@ async def _stream_listener(
             )
         except (asyncio.TimeoutError, asyncio.QueueFull):
             logger.warning(
-                f"Could not deliver finish event for task {task_id} after error"
+                "Could not deliver finish event after error",
+                extra={"json_fields": log_meta},
             )
     finally:
         # Clean up listener task mapping on exit
+        total_time = (time.perf_counter() - start_time) * 1000
+        logger.info(
+            f"[TIMING] _stream_listener FINISHED in {total_time/1000:.1f}s; task={task_id}, "
+            f"delivered={messages_delivered}, xread_count={xread_count}",
+            extra={
+                "json_fields": {
+                    **log_meta,
+                    "total_time_ms": total_time,
+                    "messages_delivered": messages_delivered,
+                    "xread_count": xread_count,
+                }
+            },
+        )
         _listener_tasks.pop(queue_id, None)
 
 
@@ -598,8 +857,10 @@ def _reconstruct_chunk(chunk_data: dict) -> StreamBaseResponse | None:
         ResponseType,
         StreamError,
         StreamFinish,
+        StreamFinishStep,
         StreamHeartbeat,
         StreamStart,
+        StreamStartStep,
         StreamTextDelta,
         StreamTextEnd,
         StreamTextStart,
@@ -613,6 +874,8 @@ def _reconstruct_chunk(chunk_data: dict) -> StreamBaseResponse | None:
     type_to_class: dict[str, type[StreamBaseResponse]] = {
         ResponseType.START.value: StreamStart,
         ResponseType.FINISH.value: StreamFinish,
+        ResponseType.START_STEP.value: StreamStartStep,
+        ResponseType.FINISH_STEP.value: StreamFinishStep,
         ResponseType.TEXT_START.value: StreamTextStart,
         ResponseType.TEXT_DELTA.value: StreamTextDelta,
         ResponseType.TEXT_END.value: StreamTextEnd,

autogpt_platform/backend/backend/api/features/chat/tools/create_agent.py

@@ -3,8 +3,6 @@
 import logging
 from typing import Any
 
-from pydantic import BaseModel, field_validator
-
 from backend.api.features.chat.model import ChatSession
 
 from .agent_generator import (
@@ -30,26 +28,6 @@ from .models import (
 logger = logging.getLogger(__name__)
 
 
-class CreateAgentInput(BaseModel):
-    """Input parameters for the create_agent tool."""
-
-    description: str = ""
-    context: str = ""
-    save: bool = True
-    # Internal async processing params (passed by long-running tool handler)
-    _operation_id: str | None = None
-    _task_id: str | None = None
-
-    @field_validator("description", "context", mode="before")
-    @classmethod
-    def strip_strings(cls, v: Any) -> str:
-        """Strip whitespace from string fields."""
-        return v.strip() if isinstance(v, str) else (v if v is not None else "")
-
-    class Config:
-        extra = "allow"  # Allow _operation_id, _task_id from kwargs
-
-
 class CreateAgentTool(BaseTool):
     """Tool for creating agents from natural language descriptions."""
 
@@ -107,7 +85,7 @@ class CreateAgentTool(BaseTool):
         self,
         user_id: str | None,
         session: ChatSession,
-        **kwargs: Any,
+        **kwargs,
     ) -> ToolResponseBase:
         """Execute the create_agent tool.
 
@@ -116,14 +94,16 @@ class CreateAgentTool(BaseTool):
         2. Generate agent JSON (external service handles fixing and validation)
         3. Preview or save based on the save parameter
         """
-        params = CreateAgentInput(**kwargs)
+        description = kwargs.get("description", "").strip()
+        context = kwargs.get("context", "")
+        save = kwargs.get("save", True)
         session_id = session.session_id if session else None
 
-        # Extract async processing params
+        # Extract async processing params (passed by long-running tool handler)
         operation_id = kwargs.get("_operation_id")
         task_id = kwargs.get("_task_id")
 
-        if not params.description:
+        if not description:
             return ErrorResponse(
                 message="Please provide a description of what the agent should do.",
                 error="Missing description parameter",
@@ -135,7 +115,7 @@ class CreateAgentTool(BaseTool):
             try:
                 library_agents = await get_all_relevant_agents_for_generation(
                     user_id=user_id,
-                    search_query=params.description,
+                    search_query=description,
                     include_marketplace=True,
                 )
                 logger.debug(
@@ -146,7 +126,7 @@ class CreateAgentTool(BaseTool):
 
         try:
             decomposition_result = await decompose_goal(
-                params.description, params.context, library_agents
+                description, context, library_agents
             )
         except AgentGeneratorNotConfiguredError:
             return ErrorResponse(
@@ -162,7 +142,7 @@ class CreateAgentTool(BaseTool):
             return ErrorResponse(
                 message="Failed to analyze the goal. The agent generation service may be unavailable. Please try again.",
                 error="decomposition_failed",
-                details={"description": params.description[:100]},
+                details={"description": description[:100]},
                 session_id=session_id,
             )
 
@@ -178,7 +158,7 @@ class CreateAgentTool(BaseTool):
                 message=user_message,
                 error=f"decomposition_failed:{error_type}",
                 details={
-                    "description": params.description[:100],
+                    "description": description[:100],
                     "service_error": error_msg,
                     "error_type": error_type,
                 },
@@ -264,7 +244,7 @@ class CreateAgentTool(BaseTool):
             return ErrorResponse(
                 message="Failed to generate the agent. The agent generation service may be unavailable. Please try again.",
                 error="generation_failed",
-                details={"description": params.description[:100]},
+                details={"description": description[:100]},
                 session_id=session_id,
             )
 
@@ -286,7 +266,7 @@ class CreateAgentTool(BaseTool):
                 message=user_message,
                 error=f"generation_failed:{error_type}",
                 details={
-                    "description": params.description[:100],
+                    "description": description[:100],
                     "service_error": error_msg,
                     "error_type": error_type,
                 },
@@ -311,7 +291,7 @@ class CreateAgentTool(BaseTool):
         node_count = len(agent_json.get("nodes", []))
         link_count = len(agent_json.get("links", []))
 
-        if not params.save:
+        if not save:
             return AgentPreviewResponse(
                 message=(
                     f"I've generated an agent called '{agent_name}' with {node_count} blocks. "

autogpt_platform/backend/backend/api/features/chat/tools/customize_agent.py

@@ -3,8 +3,6 @@
 import logging
 from typing import Any
 
-from pydantic import BaseModel, field_validator
-
 from backend.api.features.chat.model import ChatSession
 from backend.api.features.store import db as store_db
 from backend.api.features.store.exceptions import AgentNotFoundError
@@ -29,23 +27,6 @@ from .models import (
 logger = logging.getLogger(__name__)
 
 
-class CustomizeAgentInput(BaseModel):
-    """Input parameters for the customize_agent tool."""
-
-    agent_id: str = ""
-    modifications: str = ""
-    context: str = ""
-    save: bool = True
-
-    @field_validator("agent_id", "modifications", "context", mode="before")
-    @classmethod
-    def strip_strings(cls, v: Any) -> str:
-        """Strip whitespace from string fields."""
-        if isinstance(v, str):
-            return v.strip()
-        return v if v is not None else ""
-
-
 class CustomizeAgentTool(BaseTool):
     """Tool for customizing marketplace/template agents using natural language."""
 
@@ -111,7 +92,7 @@ class CustomizeAgentTool(BaseTool):
         self,
         user_id: str | None,
         session: ChatSession,
-        **kwargs: Any,
+        **kwargs,
     ) -> ToolResponseBase:
         """Execute the customize_agent tool.
 
@@ -121,17 +102,20 @@ class CustomizeAgentTool(BaseTool):
         3. Call customize_template with the modification request
         4. Preview or save based on the save parameter
         """
-        params = CustomizeAgentInput(**kwargs)
+        agent_id = kwargs.get("agent_id", "").strip()
+        modifications = kwargs.get("modifications", "").strip()
+        context = kwargs.get("context", "")
+        save = kwargs.get("save", True)
         session_id = session.session_id if session else None
 
-        if not params.agent_id:
+        if not agent_id:
             return ErrorResponse(
                 message="Please provide the marketplace agent ID (e.g., 'creator/agent-name').",
                 error="missing_agent_id",
                 session_id=session_id,
             )
 
-        if not params.modifications:
+        if not modifications:
             return ErrorResponse(
                 message="Please describe how you want to customize this agent.",
                 error="missing_modifications",
@@ -139,11 +123,11 @@ class CustomizeAgentTool(BaseTool):
             )
 
         # Parse agent_id in format "creator/slug"
-        parts = [p.strip() for p in params.agent_id.split("/")]
+        parts = [p.strip() for p in agent_id.split("/")]
         if len(parts) != 2 or not parts[0] or not parts[1]:
             return ErrorResponse(
                 message=(
-                    f"Invalid agent ID format: '{params.agent_id}'. "
+                    f"Invalid agent ID format: '{agent_id}'. "
                     "Expected format is 'creator/agent-name' "
                     "(e.g., 'autogpt/newsletter-writer')."
                 ),
@@ -161,14 +145,14 @@ class CustomizeAgentTool(BaseTool):
         except AgentNotFoundError:
             return ErrorResponse(
                 message=(
-                    f"Could not find marketplace agent '{params.agent_id}'. "
+                    f"Could not find marketplace agent '{agent_id}'. "
                     "Please check the agent ID and try again."
                 ),
                 error="agent_not_found",
                 session_id=session_id,
             )
         except Exception as e:
-            logger.error(f"Error fetching marketplace agent {params.agent_id}: {e}")
+            logger.error(f"Error fetching marketplace agent {agent_id}: {e}")
             return ErrorResponse(
                 message="Failed to fetch the marketplace agent. Please try again.",
                 error="fetch_error",
@@ -178,7 +162,7 @@ class CustomizeAgentTool(BaseTool):
         if not agent_details.store_listing_version_id:
             return ErrorResponse(
                 message=(
-                    f"The agent '{params.agent_id}' does not have an available version. "
+                    f"The agent '{agent_id}' does not have an available version. "
                     "Please try a different agent."
                 ),
                 error="no_version_available",
@@ -190,7 +174,7 @@ class CustomizeAgentTool(BaseTool):
             graph = await store_db.get_agent(agent_details.store_listing_version_id)
             template_agent = graph_to_json(graph)
         except Exception as e:
-            logger.error(f"Error fetching agent graph for {params.agent_id}: {e}")
+            logger.error(f"Error fetching agent graph for {agent_id}: {e}")
             return ErrorResponse(
                 message="Failed to fetch the agent configuration. Please try again.",
                 error="graph_fetch_error",
@@ -201,8 +185,8 @@ class CustomizeAgentTool(BaseTool):
         try:
             result = await customize_template(
                 template_agent=template_agent,
-                modification_request=params.modifications,
-                context=params.context,
+                modification_request=modifications,
+                context=context,
             )
         except AgentGeneratorNotConfiguredError:
             return ErrorResponse(
@@ -214,7 +198,7 @@ class CustomizeAgentTool(BaseTool):
                 session_id=session_id,
             )
         except Exception as e:
-            logger.error(f"Error calling customize_template for {params.agent_id}: {e}")
+            logger.error(f"Error calling customize_template for {agent_id}: {e}")
             return ErrorResponse(
                 message=(
                     "Failed to customize the agent due to a service error. "
@@ -235,25 +219,55 @@ class CustomizeAgentTool(BaseTool):
                 session_id=session_id,
             )
 
-        # Handle response using match/case for cleaner pattern matching
-        return await self._handle_customization_result(
-            result=result,
-            params=params,
-            agent_details=agent_details,
-            user_id=user_id,
-            session_id=session_id,
-        )
+        # Handle error response
+        if isinstance(result, dict) and result.get("type") == "error":
+            error_msg = result.get("error", "Unknown error")
+            error_type = result.get("error_type", "unknown")
+            user_message = get_user_message_for_error(
+                error_type,
+                operation="customize the agent",
+                llm_parse_message=(
+                    "The AI had trouble customizing the agent. "
+                    "Please try again or simplify your request."
+                ),
+                validation_message=(
+                    "The customized agent failed validation. "
+                    "Please try rephrasing your request."
+                ),
+                error_details=error_msg,
+            )
+            return ErrorResponse(
+                message=user_message,
+                error=f"customization_failed:{error_type}",
+                session_id=session_id,
+            )
 
-    async def _handle_customization_result(
-        self,
-        result: dict[str, Any],
-        params: CustomizeAgentInput,
-        agent_details: Any,
-        user_id: str | None,
-        session_id: str | None,
-    ) -> ToolResponseBase:
-        """Handle the result from customize_template using pattern matching."""
-        # Ensure result is a dict
+        # Handle clarifying questions
+        if isinstance(result, dict) and result.get("type") == "clarifying_questions":
+            questions = result.get("questions") or []
+            if not isinstance(questions, list):
+                logger.error(
+                    f"Unexpected clarifying questions format: {type(questions)}"
+                )
+                questions = []
+            return ClarificationNeededResponse(
+                message=(
+                    "I need some more information to customize this agent. "
+                    "Please answer the following questions:"
+                ),
+                questions=[
+                    ClarifyingQuestion(
+                        question=q.get("question", ""),
+                        keyword=q.get("keyword", ""),
+                        example=q.get("example"),
+                    )
+                    for q in questions
+                    if isinstance(q, dict)
+                ],
+                session_id=session_id,
+            )
+
+        # Result should be the customized agent JSON
         if not isinstance(result, dict):
             logger.error(f"Unexpected customize_template response type: {type(result)}")
             return ErrorResponse(
@@ -262,77 +276,8 @@ class CustomizeAgentTool(BaseTool):
                 session_id=session_id,
             )
 
-        result_type = result.get("type")
+        customized_agent = result
 
-        match result_type:
-            case "error":
-                error_msg = result.get("error", "Unknown error")
-                error_type = result.get("error_type", "unknown")
-                user_message = get_user_message_for_error(
-                    error_type,
-                    operation="customize the agent",
-                    llm_parse_message=(
-                        "The AI had trouble customizing the agent. "
-                        "Please try again or simplify your request."
-                    ),
-                    validation_message=(
-                        "The customized agent failed validation. "
-                        "Please try rephrasing your request."
-                    ),
-                    error_details=error_msg,
-                )
-                return ErrorResponse(
-                    message=user_message,
-                    error=f"customization_failed:{error_type}",
-                    session_id=session_id,
-                )
-
-            case "clarifying_questions":
-                questions_data = result.get("questions") or []
-                if not isinstance(questions_data, list):
-                    logger.error(
-                        f"Unexpected clarifying questions format: {type(questions_data)}"
-                    )
-                    questions_data = []
-
-                questions = [
-                    ClarifyingQuestion(
-                        question=q.get("question", "") if isinstance(q, dict) else "",
-                        keyword=q.get("keyword", "") if isinstance(q, dict) else "",
-                        example=q.get("example") if isinstance(q, dict) else None,
-                    )
-                    for q in questions_data
-                    if isinstance(q, dict)
-                ]
-
-                return ClarificationNeededResponse(
-                    message=(
-                        "I need some more information to customize this agent. "
-                        "Please answer the following questions:"
-                    ),
-                    questions=questions,
-                    session_id=session_id,
-                )
-
-            case _:
-                # Default case: result is the customized agent JSON
-                return await self._save_or_preview_agent(
-                    customized_agent=result,
-                    params=params,
-                    agent_details=agent_details,
-                    user_id=user_id,
-                    session_id=session_id,
-                )
-
-    async def _save_or_preview_agent(
-        self,
-        customized_agent: dict[str, Any],
-        params: CustomizeAgentInput,
-        agent_details: Any,
-        user_id: str | None,
-        session_id: str | None,
-    ) -> ToolResponseBase:
-        """Save or preview the customized agent based on params.save."""
         agent_name = customized_agent.get(
             "name", f"Customized {agent_details.agent_name}"
         )
@@ -342,7 +287,7 @@ class CustomizeAgentTool(BaseTool):
         node_count = len(nodes) if isinstance(nodes, list) else 0
         link_count = len(links) if isinstance(links, list) else 0
 
-        if not params.save:
+        if not save:
             return AgentPreviewResponse(
                 message=(
                     f"I've customized the agent '{agent_details.agent_name}'. "

autogpt_platform/backend/backend/api/features/chat/tools/edit_agent.py

@@ -3,8 +3,6 @@
 import logging
 from typing import Any
 
-from pydantic import BaseModel, ConfigDict, field_validator
-
 from backend.api.features.chat.model import ChatSession
 
 from .agent_generator import (
@@ -29,20 +27,6 @@ from .models import (
 logger = logging.getLogger(__name__)
 
 
-class EditAgentInput(BaseModel):
-    model_config = ConfigDict(extra="allow")
-
-    agent_id: str = ""
-    changes: str = ""
-    context: str = ""
-    save: bool = True
-
-    @field_validator("agent_id", "changes", "context", mode="before")
-    @classmethod
-    def strip_strings(cls, v: Any) -> str:
-        return v.strip() if isinstance(v, str) else (v if v is not None else "")
-
-
 class EditAgentTool(BaseTool):
     """Tool for editing existing agents using natural language."""
 
@@ -106,7 +90,7 @@ class EditAgentTool(BaseTool):
         self,
         user_id: str | None,
         session: ChatSession,
-        **kwargs: Any,
+        **kwargs,
     ) -> ToolResponseBase:
         """Execute the edit_agent tool.
 
@@ -115,32 +99,35 @@ class EditAgentTool(BaseTool):
         2. Generate updated agent (external service handles fixing and validation)
         3. Preview or save based on the save parameter
         """
-        params = EditAgentInput(**kwargs)
+        agent_id = kwargs.get("agent_id", "").strip()
+        changes = kwargs.get("changes", "").strip()
+        context = kwargs.get("context", "")
+        save = kwargs.get("save", True)
         session_id = session.session_id if session else None
 
         # Extract async processing params (passed by long-running tool handler)
         operation_id = kwargs.get("_operation_id")
         task_id = kwargs.get("_task_id")
 
-        if not params.agent_id:
+        if not agent_id:
             return ErrorResponse(
                 message="Please provide the agent ID to edit.",
                 error="Missing agent_id parameter",
                 session_id=session_id,
             )
 
-        if not params.changes:
+        if not changes:
             return ErrorResponse(
                 message="Please describe what changes you want to make.",
                 error="Missing changes parameter",
                 session_id=session_id,
             )
 
-        current_agent = await get_agent_as_json(params.agent_id, user_id)
+        current_agent = await get_agent_as_json(agent_id, user_id)
 
         if current_agent is None:
             return ErrorResponse(
-                message=f"Could not find agent '{params.agent_id}' in your library.",
+                message=f"Could not find agent with ID '{agent_id}' in your library.",
                 error="agent_not_found",
                 session_id=session_id,
             )
@@ -151,7 +138,7 @@ class EditAgentTool(BaseTool):
                 graph_id = current_agent.get("id")
                 library_agents = await get_all_relevant_agents_for_generation(
                     user_id=user_id,
-                    search_query=params.changes,
+                    search_query=changes,
                     exclude_graph_id=graph_id,
                     include_marketplace=True,
                 )
@@ -161,11 +148,9 @@ class EditAgentTool(BaseTool):
             except Exception as e:
                 logger.warning(f"Failed to fetch library agents: {e}")
 
-        update_request = params.changes
-        if params.context:
-            update_request = (
-                f"{params.changes}\n\nAdditional context:\n{params.context}"
-            )
+        update_request = changes
+        if context:
+            update_request = f"{changes}\n\nAdditional context:\n{context}"
 
         try:
             result = await generate_agent_patch(
@@ -189,7 +174,7 @@ class EditAgentTool(BaseTool):
             return ErrorResponse(
                 message="Failed to generate changes. The agent generation service may be unavailable or timed out. Please try again.",
                 error="update_generation_failed",
-                details={"agent_id": params.agent_id, "changes": params.changes[:100]},
+                details={"agent_id": agent_id, "changes": changes[:100]},
                 session_id=session_id,
             )
 
@@ -221,8 +206,8 @@ class EditAgentTool(BaseTool):
                 message=user_message,
                 error=f"update_generation_failed:{error_type}",
                 details={
-                    "agent_id": params.agent_id,
-                    "changes": params.changes[:100],
+                    "agent_id": agent_id,
+                    "changes": changes[:100],
                     "service_error": error_msg,
                     "error_type": error_type,
                 },
@@ -254,7 +239,7 @@ class EditAgentTool(BaseTool):
         node_count = len(updated_agent.get("nodes", []))
         link_count = len(updated_agent.get("links", []))
 
-        if not params.save:
+        if not save:
             return AgentPreviewResponse(
                 message=(
                     f"I've updated the agent. "

autogpt_platform/backend/backend/api/features/chat/tools/find_agent.py

@@ -2,8 +2,6 @@
 
 from typing import Any
 
-from pydantic import BaseModel, field_validator
-
 from backend.api.features.chat.model import ChatSession
 
 from .agent_search import search_agents
@@ -11,18 +9,6 @@ from .base import BaseTool
 from .models import ToolResponseBase
 
 
-class FindAgentInput(BaseModel):
-    """Input parameters for the find_agent tool."""
-
-    query: str = ""
-
-    @field_validator("query", mode="before")
-    @classmethod
-    def strip_string(cls, v: Any) -> str:
-        """Strip whitespace from query."""
-        return v.strip() if isinstance(v, str) else (v if v is not None else "")
-
-
 class FindAgentTool(BaseTool):
     """Tool for discovering agents from the marketplace."""
 
@@ -50,11 +36,10 @@ class FindAgentTool(BaseTool):
         }
 
     async def _execute(
-        self, user_id: str | None, session: ChatSession, **kwargs: Any
+        self, user_id: str | None, session: ChatSession, **kwargs
     ) -> ToolResponseBase:
-        params = FindAgentInput(**kwargs)
         return await search_agents(
-            query=params.query,
+            query=kwargs.get("query", "").strip(),
             source="marketplace",
             session_id=session.session_id,
             user_id=user_id,

autogpt_platform/backend/backend/api/features/chat/tools/find_block.py

@@ -2,7 +2,6 @@ import logging
 from typing import Any
 
 from prisma.enums import ContentType
-from pydantic import BaseModel, field_validator
 
 from backend.api.features.chat.model import ChatSession
 from backend.api.features.chat.tools.base import BaseTool, ToolResponseBase
@@ -41,18 +40,6 @@ COPILOT_EXCLUDED_BLOCK_IDS = {
 }
 
 
-class FindBlockInput(BaseModel):
-    """Input parameters for the find_block tool."""
-
-    query: str = ""
-
-    @field_validator("query", mode="before")
-    @classmethod
-    def strip_string(cls, v: Any) -> str:
-        """Strip whitespace from query."""
-        return v.strip() if isinstance(v, str) else (v if v is not None else "")
-
-
 class FindBlockTool(BaseTool):
     """Tool for searching available blocks."""
 
@@ -94,24 +81,24 @@ class FindBlockTool(BaseTool):
         self,
         user_id: str | None,
         session: ChatSession,
-        **kwargs: Any,
+        **kwargs,
     ) -> ToolResponseBase:
         """Search for blocks matching the query.
 
         Args:
             user_id: User ID (required)
             session: Chat session
-            **kwargs: Tool parameters
+            query: Search query
 
         Returns:
             BlockListResponse: List of matching blocks
             NoResultsResponse: No blocks found
             ErrorResponse: Error message
         """
-        params = FindBlockInput(**kwargs)
+        query = kwargs.get("query", "").strip()
         session_id = session.session_id
 
-        if not params.query:
+        if not query:
             return ErrorResponse(
                 message="Please provide a search query",
                 session_id=session_id,
@@ -120,7 +107,7 @@ class FindBlockTool(BaseTool):
         try:
             # Search for blocks using hybrid search
             results, total = await unified_hybrid_search(
-                query=params.query,
+                query=query,
                 content_types=[ContentType.BLOCK],
                 page=1,
                 page_size=_OVERFETCH_PAGE_SIZE,
@@ -128,7 +115,7 @@ class FindBlockTool(BaseTool):
 
             if not results:
                 return NoResultsResponse(
-                    message=f"No blocks found for '{params.query}'",
+                    message=f"No blocks found for '{query}'",
                     suggestions=[
                         "Try broader keywords like 'email', 'http', 'text', 'ai'",
                         "Check spelling of technical terms",
@@ -230,7 +217,7 @@ class FindBlockTool(BaseTool):
 
             if not blocks:
                 return NoResultsResponse(
-                    message=f"No blocks found for '{params.query}'",
+                    message=f"No blocks found for '{query}'",
                     suggestions=[
                         "Try broader keywords like 'email', 'http', 'text', 'ai'",
                     ],
@@ -239,13 +226,13 @@ class FindBlockTool(BaseTool):
 
             return BlockListResponse(
                 message=(
-                    f"Found {len(blocks)} block(s) matching '{params.query}'. "
+                    f"Found {len(blocks)} block(s) matching '{query}'. "
                     "To execute a block, use run_block with the block's 'id' field "
                     "and provide 'input_data' matching the block's input_schema."
                 ),
                 blocks=blocks,
                 count=len(blocks),
-                query=params.query,
+                query=query,
                 session_id=session_id,
             )
 

autogpt_platform/backend/backend/api/features/chat/tools/find_library_agent.py

@@ -2,8 +2,6 @@
 
 from typing import Any
 
-from pydantic import BaseModel, field_validator
-
 from backend.api.features.chat.model import ChatSession
 
 from .agent_search import search_agents
@@ -11,15 +9,6 @@ from .base import BaseTool
 from .models import ToolResponseBase
 
 
-class FindLibraryAgentInput(BaseModel):
-    query: str = ""
-
-    @field_validator("query", mode="before")
-    @classmethod
-    def strip_string(cls, v: Any) -> str:
-        return v.strip() if isinstance(v, str) else (v if v is not None else "")
-
-
 class FindLibraryAgentTool(BaseTool):
     """Tool for searching agents in the user's library."""
 
@@ -53,11 +42,10 @@ class FindLibraryAgentTool(BaseTool):
         return True
 
     async def _execute(
-        self, user_id: str | None, session: ChatSession, **kwargs: Any
+        self, user_id: str | None, session: ChatSession, **kwargs
     ) -> ToolResponseBase:
-        params = FindLibraryAgentInput(**kwargs)
         return await search_agents(
-            query=params.query,
+            query=kwargs.get("query", "").strip(),
             source="library",
             session_id=session.session_id,
             user_id=user_id,

autogpt_platform/backend/backend/api/features/chat/tools/get_doc_page.py

@@ -4,8 +4,6 @@ import logging
 from pathlib import Path
 from typing import Any
 
-from pydantic import BaseModel, field_validator
-
 from backend.api.features.chat.model import ChatSession
 from backend.api.features.chat.tools.base import BaseTool
 from backend.api.features.chat.tools.models import (
@@ -20,18 +18,6 @@ logger = logging.getLogger(__name__)
 DOCS_BASE_URL = "https://docs.agpt.co"
 
 
-class GetDocPageInput(BaseModel):
-    """Input parameters for the get_doc_page tool."""
-
-    path: str = ""
-
-    @field_validator("path", mode="before")
-    @classmethod
-    def strip_string(cls, v: Any) -> str:
-        """Strip whitespace from path."""
-        return v.strip() if isinstance(v, str) else (v if v is not None else "")
-
-
 class GetDocPageTool(BaseTool):
     """Tool for fetching full content of a documentation page."""
 
@@ -89,23 +75,23 @@ class GetDocPageTool(BaseTool):
         self,
         user_id: str | None,
         session: ChatSession,
-        **kwargs: Any,
+        **kwargs,
     ) -> ToolResponseBase:
         """Fetch full content of a documentation page.
 
         Args:
             user_id: User ID (not required for docs)
             session: Chat session
-            **kwargs: Tool parameters
+            path: Path to the documentation file
 
         Returns:
             DocPageResponse: Full document content
             ErrorResponse: Error message
         """
-        params = GetDocPageInput(**kwargs)
+        path = kwargs.get("path", "").strip()
         session_id = session.session_id if session else None
 
-        if not params.path:
+        if not path:
             return ErrorResponse(
                 message="Please provide a documentation path.",
                 error="Missing path parameter",
@@ -113,7 +99,7 @@ class GetDocPageTool(BaseTool):
             )
 
         # Sanitize path to prevent directory traversal
-        if ".." in params.path or params.path.startswith("/"):
+        if ".." in path or path.startswith("/"):
             return ErrorResponse(
                 message="Invalid documentation path.",
                 error="invalid_path",
@@ -121,11 +107,11 @@ class GetDocPageTool(BaseTool):
             )
 
         docs_root = self._get_docs_root()
-        full_path = docs_root / params.path
+        full_path = docs_root / path
 
         if not full_path.exists():
             return ErrorResponse(
-                message=f"Documentation page not found: {params.path}",
+                message=f"Documentation page not found: {path}",
                 error="not_found",
                 session_id=session_id,
             )
@@ -142,19 +128,19 @@ class GetDocPageTool(BaseTool):
 
         try:
             content = full_path.read_text(encoding="utf-8")
-            title = self._extract_title(content, params.path)
+            title = self._extract_title(content, path)
 
             return DocPageResponse(
                 message=f"Retrieved documentation page: {title}",
                 title=title,
-                path=params.path,
+                path=path,
                 content=content,
-                doc_url=self._make_doc_url(params.path),
+                doc_url=self._make_doc_url(path),
                 session_id=session_id,
             )
 
         except Exception as e:
-            logger.error(f"Failed to read documentation page {params.path}: {e}")
+            logger.error(f"Failed to read documentation page {path}: {e}")
             return ErrorResponse(
                 message=f"Failed to read documentation page: {str(e)}",
                 error="read_failed",

autogpt_platform/backend/backend/api/features/chat/tools/helpers.py

@@ -0,0 +1,29 @@
+"""Shared helpers for chat tools."""
+
+from typing import Any
+
+
+def get_inputs_from_schema(
+    input_schema: dict[str, Any],
+    exclude_fields: set[str] | None = None,
+) -> list[dict[str, Any]]:
+    """Extract input field info from JSON schema."""
+    if not isinstance(input_schema, dict):
+        return []
+
+    exclude = exclude_fields or set()
+    properties = input_schema.get("properties", {})
+    required = set(input_schema.get("required", []))
+
+    return [
+        {
+            "name": name,
+            "title": schema.get("title", name),
+            "type": schema.get("type", "string"),
+            "description": schema.get("description", ""),
+            "required": name in required,
+            "default": schema.get("default"),
+        }
+        for name, schema in properties.items()
+        if name not in exclude
+    ]

autogpt_platform/backend/backend/api/features/chat/tools/run_agent.py

@@ -24,6 +24,7 @@ from backend.util.timezone_utils import (
 )
 
 from .base import BaseTool
+from .helpers import get_inputs_from_schema
 from .models import (
     AgentDetails,
     AgentDetailsResponse,
@@ -261,7 +262,7 @@ class RunAgentTool(BaseTool):
                         ),
                         requirements={
                             "credentials": requirements_creds_list,
-                            "inputs": self._get_inputs_list(graph.input_schema),
+                            "inputs": get_inputs_from_schema(graph.input_schema),
                             "execution_modes": self._get_execution_modes(graph),
                         },
                     ),
@@ -369,22 +370,6 @@ class RunAgentTool(BaseTool):
                 session_id=session_id,
             )
 
-    def _get_inputs_list(self, input_schema: dict[str, Any]) -> list[dict[str, Any]]:
-        """Extract inputs list from schema."""
-        inputs_list = []
-        if isinstance(input_schema, dict) and "properties" in input_schema:
-            for field_name, field_schema in input_schema["properties"].items():
-                inputs_list.append(
-                    {
-                        "name": field_name,
-                        "title": field_schema.get("title", field_name),
-                        "type": field_schema.get("type", "string"),
-                        "description": field_schema.get("description", ""),
-                        "required": field_name in input_schema.get("required", []),
-                    }
-                )
-        return inputs_list
-
     def _get_execution_modes(self, graph: GraphModel) -> list[str]:
         """Get available execution modes for the graph."""
         trigger_info = graph.trigger_setup_info
@@ -398,7 +383,7 @@ class RunAgentTool(BaseTool):
         suffix: str,
     ) -> str:
         """Build a message describing available inputs for an agent."""
-        inputs_list = self._get_inputs_list(graph.input_schema)
+        inputs_list = get_inputs_from_schema(graph.input_schema)
         required_names = [i["name"] for i in inputs_list if i["required"]]
         optional_names = [i["name"] for i in inputs_list if not i["required"]]
 

autogpt_platform/backend/backend/api/features/chat/tools/run_block.py

@@ -5,7 +5,6 @@ import uuid
 from collections import defaultdict
 from typing import Any
 
-from pydantic import BaseModel, field_validator
 from pydantic_core import PydanticUndefined
 
 from backend.api.features.chat.model import ChatSession
@@ -13,14 +12,15 @@ from backend.api.features.chat.tools.find_block import (
     COPILOT_EXCLUDED_BLOCK_IDS,
     COPILOT_EXCLUDED_BLOCK_TYPES,
 )
-from backend.data.block import get_block
+from backend.data.block import AnyBlockSchema, get_block
 from backend.data.execution import ExecutionContext
-from backend.data.model import CredentialsMetaInput
+from backend.data.model import CredentialsFieldInfo, CredentialsMetaInput
 from backend.data.workspace import get_or_create_workspace
 from backend.integrations.creds_manager import IntegrationCredentialsManager
 from backend.util.exceptions import BlockError
 
 from .base import BaseTool
+from .helpers import get_inputs_from_schema
 from .models import (
     BlockOutputResponse,
     ErrorResponse,
@@ -29,30 +29,14 @@ from .models import (
     ToolResponseBase,
     UserReadiness,
 )
-from .utils import build_missing_credentials_from_field_info
+from .utils import (
+    build_missing_credentials_from_field_info,
+    match_credentials_to_requirements,
+)
 
 logger = logging.getLogger(__name__)
 
 
-class RunBlockInput(BaseModel):
-    """Input parameters for the run_block tool."""
-
-    block_id: str = ""
-    input_data: dict[str, Any] = {}
-
-    @field_validator("block_id", mode="before")
-    @classmethod
-    def strip_block_id(cls, v: Any) -> str:
-        """Strip whitespace from block_id."""
-        return v.strip() if isinstance(v, str) else (v if v is not None else "")
-
-    @field_validator("input_data", mode="before")
-    @classmethod
-    def ensure_dict(cls, v: Any) -> dict[str, Any]:
-        """Ensure input_data is a dict."""
-        return v if isinstance(v, dict) else {}
-
-
 class RunBlockTool(BaseTool):
     """Tool for executing a block and returning its outputs."""
 
@@ -97,118 +81,41 @@ class RunBlockTool(BaseTool):
     def requires_auth(self) -> bool:
         return True
 
-    async def _check_block_credentials(
-        self,
-        user_id: str,
-        block: Any,
-        input_data: dict[str, Any] | None = None,
-    ) -> tuple[dict[str, CredentialsMetaInput], list[CredentialsMetaInput]]:
-        """
-        Check if user has required credentials for a block.
-
-        Args:
-            user_id: User ID
-            block: Block to check credentials for
-            input_data: Input data for the block (used to determine provider via discriminator)
-
-        Returns:
-            tuple[matched_credentials, missing_credentials]
-        """
-        matched_credentials: dict[str, CredentialsMetaInput] = {}
-        missing_credentials: list[CredentialsMetaInput] = []
-        input_data = input_data or {}
-
-        # Get credential field info from block's input schema
-        credentials_fields_info = block.input_schema.get_credentials_fields_info()
-
-        if not credentials_fields_info:
-            return matched_credentials, missing_credentials
-
-        # Get user's available credentials
-        creds_manager = IntegrationCredentialsManager()
-        available_creds = await creds_manager.store.get_all_creds(user_id)
-
-        for field_name, field_info in credentials_fields_info.items():
-            effective_field_info = field_info
-            if field_info.discriminator and field_info.discriminator_mapping:
-                # Get discriminator from input, falling back to schema default
-                discriminator_value = input_data.get(field_info.discriminator)
-                if discriminator_value is None:
-                    field = block.input_schema.model_fields.get(
-                        field_info.discriminator
-                    )
-                    if field and field.default is not PydanticUndefined:
-                        discriminator_value = field.default
-
-                if (
-                    discriminator_value
-                    and discriminator_value in field_info.discriminator_mapping
-                ):
-                    effective_field_info = field_info.discriminate(discriminator_value)
-                    logger.debug(
-                        f"Discriminated provider for {field_name}: "
-                        f"{discriminator_value} -> {effective_field_info.provider}"
-                    )
-
-            matching_cred = next(
-                (
-                    cred
-                    for cred in available_creds
-                    if cred.provider in effective_field_info.provider
-                    and cred.type in effective_field_info.supported_types
-                ),
-                None,
-            )
-
-            if matching_cred:
-                matched_credentials[field_name] = CredentialsMetaInput(
-                    id=matching_cred.id,
-                    provider=matching_cred.provider,  # type: ignore
-                    type=matching_cred.type,
-                    title=matching_cred.title,
-                )
-            else:
-                # Create a placeholder for the missing credential
-                provider = next(iter(effective_field_info.provider), "unknown")
-                cred_type = next(iter(effective_field_info.supported_types), "api_key")
-                missing_credentials.append(
-                    CredentialsMetaInput(
-                        id=field_name,
-                        provider=provider,  # type: ignore
-                        type=cred_type,  # type: ignore
-                        title=field_name.replace("_", " ").title(),
-                    )
-                )
-
-        return matched_credentials, missing_credentials
-
     async def _execute(
         self,
         user_id: str | None,
         session: ChatSession,
-        **kwargs: Any,
+        **kwargs,
     ) -> ToolResponseBase:
         """Execute a block with the given input data.
 
         Args:
             user_id: User ID (required)
             session: Chat session
-            **kwargs: Tool parameters
+            block_id: Block UUID to execute
+            input_data: Input values for the block
 
         Returns:
             BlockOutputResponse: Block execution outputs
             SetupRequirementsResponse: Missing credentials
             ErrorResponse: Error message
         """
-        params = RunBlockInput(**kwargs)
+        block_id = kwargs.get("block_id", "").strip()
+        input_data = kwargs.get("input_data", {})
         session_id = session.session_id
 
-        if not params.block_id:
+        if not block_id:
             return ErrorResponse(
                 message="Please provide a block_id",
                 session_id=session_id,
             )
 
+        if not isinstance(input_data, dict):
+            return ErrorResponse(
+                message="input_data must be an object",
+                session_id=session_id,
+            )
+
         if not user_id:
             return ErrorResponse(
                 message="Authentication required",
@@ -216,15 +123,15 @@ class RunBlockTool(BaseTool):
             )
 
         # Get the block
-        block = get_block(params.block_id)
+        block = get_block(block_id)
         if not block:
             return ErrorResponse(
-                message=f"Block '{params.block_id}' not found",
+                message=f"Block '{block_id}' not found",
                 session_id=session_id,
             )
         if block.disabled:
             return ErrorResponse(
-                message=f"Block '{params.block_id}' is disabled",
+                message=f"Block '{block_id}' is disabled",
                 session_id=session_id,
             )
 
@@ -244,8 +151,8 @@ class RunBlockTool(BaseTool):
         logger.info(f"Executing block {block.name} ({block_id}) for user {user_id}")
 
         creds_manager = IntegrationCredentialsManager()
-        matched_credentials, missing_credentials = await self._check_block_credentials(
-            user_id, block, params.input_data
+        matched_credentials, missing_credentials = (
+            await self._resolve_block_credentials(user_id, block, input_data)
         )
 
         if missing_credentials:
@@ -263,7 +170,7 @@ class RunBlockTool(BaseTool):
                 ),
                 session_id=session_id,
                 setup_info=SetupInfo(
-                    agent_id=params.block_id,
+                    agent_id=block_id,
                     agent_name=block.name,
                     user_readiness=UserReadiness(
                         has_all_credentials=False,
@@ -292,7 +199,7 @@ class RunBlockTool(BaseTool):
             # - node_exec_id = unique per block execution
             synthetic_graph_id = f"copilot-session-{session.session_id}"
             synthetic_graph_exec_id = f"copilot-session-{session.session_id}"
-            synthetic_node_id = f"copilot-node-{params.block_id}"
+            synthetic_node_id = f"copilot-node-{block_id}"
             synthetic_node_exec_id = (
                 f"copilot-{session.session_id}-{uuid.uuid4().hex[:8]}"
             )
@@ -327,8 +234,8 @@ class RunBlockTool(BaseTool):
 
             for field_name, cred_meta in matched_credentials.items():
                 # Inject metadata into input_data (for validation)
-                if field_name not in params.input_data:
-                    params.input_data[field_name] = cred_meta.model_dump()
+                if field_name not in input_data:
+                    input_data[field_name] = cred_meta.model_dump()
 
                 # Fetch actual credentials and pass as kwargs (for execution)
                 actual_credentials = await creds_manager.get(
@@ -345,14 +252,14 @@ class RunBlockTool(BaseTool):
             # Execute the block and collect outputs
             outputs: dict[str, list[Any]] = defaultdict(list)
             async for output_name, output_data in block.execute(
-                params.input_data,
+                input_data,
                 **exec_kwargs,
             ):
                 outputs[output_name].append(output_data)
 
             return BlockOutputResponse(
                 message=f"Block '{block.name}' executed successfully",
-                block_id=params.block_id,
+                block_id=block_id,
                 block_name=block.name,
                 outputs=dict(outputs),
                 success=True,
@@ -374,29 +281,75 @@ class RunBlockTool(BaseTool):
                 session_id=session_id,
             )
 
-    def _get_inputs_list(self, block: Any) -> list[dict[str, Any]]:
+    async def _resolve_block_credentials(
+        self,
+        user_id: str,
+        block: AnyBlockSchema,
+        input_data: dict[str, Any] | None = None,
+    ) -> tuple[dict[str, CredentialsMetaInput], list[CredentialsMetaInput]]:
+        """
+        Resolve credentials for a block by matching user's available credentials.
+
+        Args:
+            user_id: User ID
+            block: Block to resolve credentials for
+            input_data: Input data for the block (used to determine provider via discriminator)
+
+        Returns:
+            tuple of (matched_credentials, missing_credentials) - matched credentials
+            are used for block execution, missing ones indicate setup requirements.
+        """
+        input_data = input_data or {}
+        requirements = self._resolve_discriminated_credentials(block, input_data)
+
+        if not requirements:
+            return {}, []
+
+        return await match_credentials_to_requirements(user_id, requirements)
+
+    def _get_inputs_list(self, block: AnyBlockSchema) -> list[dict[str, Any]]:
         """Extract non-credential inputs from block schema."""
-        inputs_list = []
         schema = block.input_schema.jsonschema()
-        properties = schema.get("properties", {})
-        required_fields = set(schema.get("required", []))
-
-        # Get credential field names to exclude
         credentials_fields = set(block.input_schema.get_credentials_fields().keys())
+        return get_inputs_from_schema(schema, exclude_fields=credentials_fields)
 
-        for field_name, field_schema in properties.items():
-            # Skip credential fields
-            if field_name in credentials_fields:
-                continue
+    def _resolve_discriminated_credentials(
+        self,
+        block: AnyBlockSchema,
+        input_data: dict[str, Any],
+    ) -> dict[str, CredentialsFieldInfo]:
+        """Resolve credential requirements, applying discriminator logic where needed."""
+        credentials_fields_info = block.input_schema.get_credentials_fields_info()
+        if not credentials_fields_info:
+            return {}
 
-            inputs_list.append(
-                {
-                    "name": field_name,
-                    "title": field_schema.get("title", field_name),
-                    "type": field_schema.get("type", "string"),
-                    "description": field_schema.get("description", ""),
-                    "required": field_name in required_fields,
-                }
-            )
+        resolved: dict[str, CredentialsFieldInfo] = {}
 
-        return inputs_list
+        for field_name, field_info in credentials_fields_info.items():
+            effective_field_info = field_info
+
+            if field_info.discriminator and field_info.discriminator_mapping:
+                discriminator_value = input_data.get(field_info.discriminator)
+                if discriminator_value is None:
+                    field = block.input_schema.model_fields.get(
+                        field_info.discriminator
+                    )
+                    if field and field.default is not PydanticUndefined:
+                        discriminator_value = field.default
+
+                if (
+                    discriminator_value
+                    and discriminator_value in field_info.discriminator_mapping
+                ):
+                    effective_field_info = field_info.discriminate(discriminator_value)
+                    # For host-scoped credentials, add the discriminator value
+                    # (e.g., URL) so _credential_is_for_host can match it
+                    effective_field_info.discriminator_values.add(discriminator_value)
+                    logger.debug(
+                        f"Discriminated provider for {field_name}: "
+                        f"{discriminator_value} -> {effective_field_info.provider}"
+                    )
+
+            resolved[field_name] = effective_field_info
+
+        return resolved

autogpt_platform/backend/backend/api/features/chat/tools/search_docs.py

@@ -4,7 +4,6 @@ import logging
 from typing import Any
 
 from prisma.enums import ContentType
-from pydantic import BaseModel, field_validator
 
 from backend.api.features.chat.model import ChatSession
 from backend.api.features.chat.tools.base import BaseTool
@@ -29,18 +28,6 @@ MAX_RESULTS = 5
 SNIPPET_LENGTH = 200
 
 
-class SearchDocsInput(BaseModel):
-    """Input parameters for the search_docs tool."""
-
-    query: str = ""
-
-    @field_validator("query", mode="before")
-    @classmethod
-    def strip_string(cls, v: Any) -> str:
-        """Strip whitespace from query."""
-        return v.strip() if isinstance(v, str) else (v if v is not None else "")
-
-
 class SearchDocsTool(BaseTool):
     """Tool for searching AutoGPT platform documentation."""
 
@@ -104,24 +91,24 @@ class SearchDocsTool(BaseTool):
         self,
         user_id: str | None,
         session: ChatSession,
-        **kwargs: Any,
+        **kwargs,
     ) -> ToolResponseBase:
         """Search documentation and return relevant sections.
 
         Args:
             user_id: User ID (not required for docs)
             session: Chat session
-            **kwargs: Tool parameters
+            query: Search query
 
         Returns:
             DocSearchResultsResponse: List of matching documentation sections
             NoResultsResponse: No results found
             ErrorResponse: Error message
         """
-        params = SearchDocsInput(**kwargs)
+        query = kwargs.get("query", "").strip()
         session_id = session.session_id if session else None
 
-        if not params.query:
+        if not query:
             return ErrorResponse(
                 message="Please provide a search query.",
                 error="Missing query parameter",
@@ -131,7 +118,7 @@ class SearchDocsTool(BaseTool):
         try:
             # Search using hybrid search for DOCUMENTATION content type only
             results, total = await unified_hybrid_search(
-                query=params.query,
+                query=query,
                 content_types=[ContentType.DOCUMENTATION],
                 page=1,
                 page_size=MAX_RESULTS * 2,  # Fetch extra for deduplication
@@ -140,7 +127,7 @@ class SearchDocsTool(BaseTool):
 
             if not results:
                 return NoResultsResponse(
-                    message=f"No documentation found for '{params.query}'.",
+                    message=f"No documentation found for '{query}'.",
                     suggestions=[
                         "Try different keywords",
                         "Use more general terms",
@@ -175,7 +162,7 @@ class SearchDocsTool(BaseTool):
 
             if not deduplicated:
                 return NoResultsResponse(
-                    message=f"No documentation found for '{params.query}'.",
+                    message=f"No documentation found for '{query}'.",
                     suggestions=[
                         "Try different keywords",
                         "Use more general terms",
@@ -208,7 +195,7 @@ class SearchDocsTool(BaseTool):
                 message=f"Found {len(doc_results)} relevant documentation sections.",
                 results=doc_results,
                 count=len(doc_results),
-                query=params.query,
+                query=query,
                 session_id=session_id,
             )
 

autogpt_platform/backend/backend/api/features/chat/tools/utils.py

@@ -8,6 +8,7 @@ from backend.api.features.library import model as library_model
 from backend.api.features.store import db as store_db
 from backend.data.graph import GraphModel
 from backend.data.model import (
+    Credentials,
     CredentialsFieldInfo,
     CredentialsMetaInput,
     HostScopedCredentials,
@@ -223,6 +224,99 @@ async def get_or_create_library_agent(
     return library_agents[0]
 
 
+async def match_credentials_to_requirements(
+    user_id: str,
+    requirements: dict[str, CredentialsFieldInfo],
+) -> tuple[dict[str, CredentialsMetaInput], list[CredentialsMetaInput]]:
+    """
+    Match user's credentials against a dictionary of credential requirements.
+
+    This is the core matching logic shared by both graph and block credential matching.
+    """
+    matched: dict[str, CredentialsMetaInput] = {}
+    missing: list[CredentialsMetaInput] = []
+
+    if not requirements:
+        return matched, missing
+
+    available_creds = await get_user_credentials(user_id)
+
+    for field_name, field_info in requirements.items():
+        matching_cred = find_matching_credential(available_creds, field_info)
+
+        if matching_cred:
+            try:
+                matched[field_name] = create_credential_meta_from_match(matching_cred)
+            except Exception as e:
+                logger.error(
+                    f"Failed to create CredentialsMetaInput for field '{field_name}': "
+                    f"provider={matching_cred.provider}, type={matching_cred.type}, "
+                    f"credential_id={matching_cred.id}",
+                    exc_info=True,
+                )
+                provider = next(iter(field_info.provider), "unknown")
+                cred_type = next(iter(field_info.supported_types), "api_key")
+                missing.append(
+                    CredentialsMetaInput(
+                        id=field_name,
+                        provider=provider,  # type: ignore
+                        type=cred_type,  # type: ignore
+                        title=f"{field_name} (validation failed: {e})",
+                    )
+                )
+        else:
+            provider = next(iter(field_info.provider), "unknown")
+            cred_type = next(iter(field_info.supported_types), "api_key")
+            missing.append(
+                CredentialsMetaInput(
+                    id=field_name,
+                    provider=provider,  # type: ignore
+                    type=cred_type,  # type: ignore
+                    title=field_name.replace("_", " ").title(),
+                )
+            )
+
+    return matched, missing
+
+
+async def get_user_credentials(user_id: str) -> list[Credentials]:
+    """Get all available credentials for a user."""
+    creds_manager = IntegrationCredentialsManager()
+    return await creds_manager.store.get_all_creds(user_id)
+
+
+def find_matching_credential(
+    available_creds: list[Credentials],
+    field_info: CredentialsFieldInfo,
+) -> Credentials | None:
+    """Find a credential that matches the required provider, type, scopes, and host."""
+    for cred in available_creds:
+        if cred.provider not in field_info.provider:
+            continue
+        if cred.type not in field_info.supported_types:
+            continue
+        if cred.type == "oauth2" and not _credential_has_required_scopes(
+            cred, field_info
+        ):
+            continue
+        if cred.type == "host_scoped" and not _credential_is_for_host(cred, field_info):
+            continue
+        return cred
+    return None
+
+
+def create_credential_meta_from_match(
+    matching_cred: Credentials,
+) -> CredentialsMetaInput:
+    """Create a CredentialsMetaInput from a matched credential."""
+    return CredentialsMetaInput(
+        id=matching_cred.id,
+        provider=matching_cred.provider,  # type: ignore
+        type=matching_cred.type,
+        title=matching_cred.title,
+    )
+
+
 async def match_user_credentials_to_graph(
     user_id: str,
     graph: GraphModel,
@@ -331,8 +425,6 @@ def _credential_has_required_scopes(
     # If no scopes are required, any credential matches
     if not requirements.required_scopes:
         return True
-
-    # Check that credential scopes are a superset of required scopes
     return set(credential.scopes).issuperset(requirements.required_scopes)
 
 

autogpt_platform/backend/backend/api/features/chat/tools/workspace_files.py

@@ -2,9 +2,9 @@
 
 import base64
 import logging
-from typing import Any
+from typing import Any, Optional
 
-from pydantic import BaseModel, field_validator
+from pydantic import BaseModel
 
 from backend.api.features.chat.model import ChatSession
 from backend.data.workspace import get_or_create_workspace
@@ -78,65 +78,6 @@ class WorkspaceDeleteResponse(ToolResponseBase):
     success: bool
 
 
-# Input models for workspace tools
-class ListWorkspaceFilesInput(BaseModel):
-    """Input parameters for list_workspace_files tool."""
-
-    path_prefix: str | None = None
-    limit: int = 50
-    include_all_sessions: bool = False
-
-    @field_validator("path_prefix", mode="before")
-    @classmethod
-    def strip_path(cls, v: Any) -> str | None:
-        return v.strip() if isinstance(v, str) else None
-
-
-class ReadWorkspaceFileInput(BaseModel):
-    """Input parameters for read_workspace_file tool."""
-
-    file_id: str | None = None
-    path: str | None = None
-    force_download_url: bool = False
-
-    @field_validator("file_id", "path", mode="before")
-    @classmethod
-    def strip_strings(cls, v: Any) -> str | None:
-        return v.strip() if isinstance(v, str) else None
-
-
-class WriteWorkspaceFileInput(BaseModel):
-    """Input parameters for write_workspace_file tool."""
-
-    filename: str = ""
-    content_base64: str = ""
-    path: str | None = None
-    mime_type: str | None = None
-    overwrite: bool = False
-
-    @field_validator("filename", "content_base64", mode="before")
-    @classmethod
-    def strip_required(cls, v: Any) -> str:
-        return v.strip() if isinstance(v, str) else (v if v is not None else "")
-
-    @field_validator("path", "mime_type", mode="before")
-    @classmethod
-    def strip_optional(cls, v: Any) -> str | None:
-        return v.strip() if isinstance(v, str) else None
-
-
-class DeleteWorkspaceFileInput(BaseModel):
-    """Input parameters for delete_workspace_file tool."""
-
-    file_id: str | None = None
-    path: str | None = None
-
-    @field_validator("file_id", "path", mode="before")
-    @classmethod
-    def strip_strings(cls, v: Any) -> str | None:
-        return v.strip() if isinstance(v, str) else None
-
-
 class ListWorkspaceFilesTool(BaseTool):
     """Tool for listing files in user's workspace."""
 
@@ -190,9 +131,8 @@ class ListWorkspaceFilesTool(BaseTool):
         self,
         user_id: str | None,
         session: ChatSession,
-        **kwargs: Any,
+        **kwargs,
     ) -> ToolResponseBase:
-        params = ListWorkspaceFilesInput(**kwargs)
         session_id = session.session_id
 
         if not user_id:
@@ -201,7 +141,9 @@ class ListWorkspaceFilesTool(BaseTool):
                 session_id=session_id,
             )
 
-        limit = min(params.limit, 100)
+        path_prefix: Optional[str] = kwargs.get("path_prefix")
+        limit = min(kwargs.get("limit", 50), 100)
+        include_all_sessions: bool = kwargs.get("include_all_sessions", False)
 
         try:
             workspace = await get_or_create_workspace(user_id)
@@ -209,13 +151,13 @@ class ListWorkspaceFilesTool(BaseTool):
             manager = WorkspaceManager(user_id, workspace.id, session_id)
 
             files = await manager.list_files(
-                path=params.path_prefix,
+                path=path_prefix,
                 limit=limit,
-                include_all_sessions=params.include_all_sessions,
+                include_all_sessions=include_all_sessions,
             )
             total = await manager.get_file_count(
-                path=params.path_prefix,
-                include_all_sessions=params.include_all_sessions,
+                path=path_prefix,
+                include_all_sessions=include_all_sessions,
             )
 
             file_infos = [
@@ -229,9 +171,7 @@ class ListWorkspaceFilesTool(BaseTool):
                 for f in files
             ]
 
-            scope_msg = (
-                "all sessions" if params.include_all_sessions else "current session"
-            )
+            scope_msg = "all sessions" if include_all_sessions else "current session"
             return WorkspaceFileListResponse(
                 files=file_infos,
                 total_count=total,
@@ -319,9 +259,8 @@ class ReadWorkspaceFileTool(BaseTool):
         self,
         user_id: str | None,
         session: ChatSession,
-        **kwargs: Any,
+        **kwargs,
     ) -> ToolResponseBase:
-        params = ReadWorkspaceFileInput(**kwargs)
         session_id = session.session_id
 
         if not user_id:
@@ -330,7 +269,11 @@ class ReadWorkspaceFileTool(BaseTool):
                 session_id=session_id,
             )
 
-        if not params.file_id and not params.path:
+        file_id: Optional[str] = kwargs.get("file_id")
+        path: Optional[str] = kwargs.get("path")
+        force_download_url: bool = kwargs.get("force_download_url", False)
+
+        if not file_id and not path:
             return ErrorResponse(
                 message="Please provide either file_id or path",
                 session_id=session_id,
@@ -342,21 +285,21 @@ class ReadWorkspaceFileTool(BaseTool):
             manager = WorkspaceManager(user_id, workspace.id, session_id)
 
             # Get file info
-            if params.file_id:
-                file_info = await manager.get_file_info(params.file_id)
+            if file_id:
+                file_info = await manager.get_file_info(file_id)
                 if file_info is None:
                     return ErrorResponse(
-                        message=f"File not found: {params.file_id}",
+                        message=f"File not found: {file_id}",
                         session_id=session_id,
                     )
-                target_file_id = params.file_id
+                target_file_id = file_id
             else:
                 # path is guaranteed to be non-None here due to the check above
-                assert params.path is not None
-                file_info = await manager.get_file_info_by_path(params.path)
+                assert path is not None
+                file_info = await manager.get_file_info_by_path(path)
                 if file_info is None:
                     return ErrorResponse(
-                        message=f"File not found at path: {params.path}",
+                        message=f"File not found at path: {path}",
                         session_id=session_id,
                     )
                 target_file_id = file_info.id
@@ -366,7 +309,7 @@ class ReadWorkspaceFileTool(BaseTool):
             is_text_file = self._is_text_mime_type(file_info.mimeType)
 
             # Return inline content for small text files (unless force_download_url)
-            if is_small_file and is_text_file and not params.force_download_url:
+            if is_small_file and is_text_file and not force_download_url:
                 content = await manager.read_file_by_id(target_file_id)
                 content_b64 = base64.b64encode(content).decode("utf-8")
 
@@ -486,9 +429,8 @@ class WriteWorkspaceFileTool(BaseTool):
         self,
         user_id: str | None,
         session: ChatSession,
-        **kwargs: Any,
+        **kwargs,
     ) -> ToolResponseBase:
-        params = WriteWorkspaceFileInput(**kwargs)
         session_id = session.session_id
 
         if not user_id:
@@ -497,13 +439,19 @@ class WriteWorkspaceFileTool(BaseTool):
                 session_id=session_id,
             )
 
-        if not params.filename:
+        filename: str = kwargs.get("filename", "")
+        content_b64: str = kwargs.get("content_base64", "")
+        path: Optional[str] = kwargs.get("path")
+        mime_type: Optional[str] = kwargs.get("mime_type")
+        overwrite: bool = kwargs.get("overwrite", False)
+
+        if not filename:
             return ErrorResponse(
                 message="Please provide a filename",
                 session_id=session_id,
             )
 
-        if not params.content_base64:
+        if not content_b64:
             return ErrorResponse(
                 message="Please provide content_base64",
                 session_id=session_id,
@@ -511,7 +459,7 @@ class WriteWorkspaceFileTool(BaseTool):
 
         # Decode content
         try:
-            content = base64.b64decode(params.content_base64)
+            content = base64.b64decode(content_b64)
         except Exception:
             return ErrorResponse(
                 message="Invalid base64-encoded content",
@@ -528,7 +476,7 @@ class WriteWorkspaceFileTool(BaseTool):
 
         try:
             # Virus scan
-            await scan_content_safe(content, filename=params.filename)
+            await scan_content_safe(content, filename=filename)
 
             workspace = await get_or_create_workspace(user_id)
             # Pass session_id for session-scoped file access
@@ -536,10 +484,10 @@ class WriteWorkspaceFileTool(BaseTool):
 
             file_record = await manager.write_file(
                 content=content,
-                filename=params.filename,
-                path=params.path,
-                mime_type=params.mime_type,
-                overwrite=params.overwrite,
+                filename=filename,
+                path=path,
+                mime_type=mime_type,
+                overwrite=overwrite,
             )
 
             return WorkspaceWriteResponse(
@@ -609,9 +557,8 @@ class DeleteWorkspaceFileTool(BaseTool):
         self,
         user_id: str | None,
         session: ChatSession,
-        **kwargs: Any,
+        **kwargs,
     ) -> ToolResponseBase:
-        params = DeleteWorkspaceFileInput(**kwargs)
         session_id = session.session_id
 
         if not user_id:
@@ -620,7 +567,10 @@ class DeleteWorkspaceFileTool(BaseTool):
                 session_id=session_id,
             )
 
-        if not params.file_id and not params.path:
+        file_id: Optional[str] = kwargs.get("file_id")
+        path: Optional[str] = kwargs.get("path")
+
+        if not file_id and not path:
             return ErrorResponse(
                 message="Please provide either file_id or path",
                 session_id=session_id,
@@ -633,15 +583,15 @@ class DeleteWorkspaceFileTool(BaseTool):
 
             # Determine the file_id to delete
             target_file_id: str
-            if params.file_id:
-                target_file_id = params.file_id
+            if file_id:
+                target_file_id = file_id
             else:
                 # path is guaranteed to be non-None here due to the check above
-                assert params.path is not None
-                file_info = await manager.get_file_info_by_path(params.path)
+                assert path is not None
+                file_info = await manager.get_file_info_by_path(path)
                 if file_info is None:
                     return ErrorResponse(
-                        message=f"File not found at path: {params.path}",
+                        message=f"File not found at path: {path}",
                         session_id=session_id,
                     )
                 target_file_id = file_info.id

autogpt_platform/backend/backend/api/features/store/hybrid_search.py

@@ -8,6 +8,7 @@ Includes BM25 reranking for improved lexical relevance.
 
 import logging
 import re
+import time
 from dataclasses import dataclass
 from typing import Any, Literal
 
@@ -362,7 +363,11 @@ async def unified_hybrid_search(
         LIMIT {limit_param} OFFSET {offset_param}
     """
 
-    results = await query_raw_with_schema(sql_query, *params)
+    try:
+        results = await query_raw_with_schema(sql_query, *params)
+    except Exception as e:
+        await _log_vector_error_diagnostics(e)
+        raise
 
     total = results[0]["total_count"] if results else 0
     # Apply BM25 reranking
@@ -686,7 +691,11 @@ async def hybrid_search(
         LIMIT {limit_param} OFFSET {offset_param}
     """
 
-    results = await query_raw_with_schema(sql_query, *params)
+    try:
+        results = await query_raw_with_schema(sql_query, *params)
+    except Exception as e:
+        await _log_vector_error_diagnostics(e)
+        raise
 
     total = results[0]["total_count"] if results else 0
 
@@ -718,6 +727,87 @@ async def hybrid_search_simple(
     return await hybrid_search(query=query, page=page, page_size=page_size)
 
 
+# ============================================================================
+# Diagnostics
+# ============================================================================
+
+# Rate limit: only log vector error diagnostics once per this interval
+_VECTOR_DIAG_INTERVAL_SECONDS = 60
+_last_vector_diag_time: float = 0
+
+
+async def _log_vector_error_diagnostics(error: Exception) -> None:
+    """Log diagnostic info when 'type vector does not exist' error occurs.
+
+    Note: Diagnostic queries use query_raw_with_schema which may run on a different
+    pooled connection than the one that failed. Session-level search_path can differ,
+    so these diagnostics show cluster-wide state, not necessarily the failed session.
+
+    Includes rate limiting to avoid log spam - only logs once per minute.
+    Caller should re-raise the error after calling this function.
+    """
+    global _last_vector_diag_time
+
+    # Check if this is the vector type error
+    error_str = str(error).lower()
+    if not (
+        "type" in error_str and "vector" in error_str and "does not exist" in error_str
+    ):
+        return
+
+    # Rate limit: only log once per interval
+    now = time.time()
+    if now - _last_vector_diag_time < _VECTOR_DIAG_INTERVAL_SECONDS:
+        return
+    _last_vector_diag_time = now
+
+    try:
+        diagnostics: dict[str, object] = {}
+
+        try:
+            search_path_result = await query_raw_with_schema("SHOW search_path")
+            diagnostics["search_path"] = search_path_result
+        except Exception as e:
+            diagnostics["search_path"] = f"Error: {e}"
+
+        try:
+            schema_result = await query_raw_with_schema("SELECT current_schema()")
+            diagnostics["current_schema"] = schema_result
+        except Exception as e:
+            diagnostics["current_schema"] = f"Error: {e}"
+
+        try:
+            user_result = await query_raw_with_schema(
+                "SELECT current_user, session_user, current_database()"
+            )
+            diagnostics["user_info"] = user_result
+        except Exception as e:
+            diagnostics["user_info"] = f"Error: {e}"
+
+        try:
+            # Check pgvector extension installation (cluster-wide, stable info)
+            ext_result = await query_raw_with_schema(
+                "SELECT extname, extversion, nspname as schema "
+                "FROM pg_extension e "
+                "JOIN pg_namespace n ON e.extnamespace = n.oid "
+                "WHERE extname = 'vector'"
+            )
+            diagnostics["pgvector_extension"] = ext_result
+        except Exception as e:
+            diagnostics["pgvector_extension"] = f"Error: {e}"
+
+        logger.error(
+            f"Vector type error diagnostics:\n"
+            f"  Error: {error}\n"
+            f"  search_path: {diagnostics.get('search_path')}\n"
+            f"  current_schema: {diagnostics.get('current_schema')}\n"
+            f"  user_info: {diagnostics.get('user_info')}\n"
+            f"  pgvector_extension: {diagnostics.get('pgvector_extension')}"
+        )
+    except Exception as diag_error:
+        logger.error(f"Failed to collect vector error diagnostics: {diag_error}")
+
+
 # Backward compatibility alias - HybridSearchWeights maps to StoreAgentSearchWeights
 # for existing code that expects the popularity parameter
 HybridSearchWeights = StoreAgentSearchWeights

autogpt_platform/backend/backend/data/rabbitmq.py

@@ -1,3 +1,4 @@
+import asyncio
 import logging
 from abc import ABC, abstractmethod
 from enum import Enum
@@ -225,6 +226,10 @@ class SyncRabbitMQ(RabbitMQBase):
 class AsyncRabbitMQ(RabbitMQBase):
     """Asynchronous RabbitMQ client"""
 
+    def __init__(self, config: RabbitMQConfig):
+        super().__init__(config)
+        self._reconnect_lock: asyncio.Lock | None = None
+
     @property
     def is_connected(self) -> bool:
         return bool(self._connection and not self._connection.is_closed)
@@ -235,7 +240,17 @@ class AsyncRabbitMQ(RabbitMQBase):
 
     @conn_retry("AsyncRabbitMQ", "Acquiring async connection")
     async def connect(self):
-        if self.is_connected:
+        if self.is_connected and self._channel and not self._channel.is_closed:
+            return
+
+        if (
+            self.is_connected
+            and self._connection
+            and (self._channel is None or self._channel.is_closed)
+        ):
+            self._channel = await self._connection.channel()
+            await self._channel.set_qos(prefetch_count=1)
+            await self.declare_infrastructure()
             return
 
         self._connection = await aio_pika.connect_robust(
@@ -291,24 +306,46 @@ class AsyncRabbitMQ(RabbitMQBase):
                     exchange, routing_key=queue.routing_key or queue.name
                 )
 
-    @func_retry
-    async def publish_message(
+    @property
+    def _lock(self) -> asyncio.Lock:
+        if self._reconnect_lock is None:
+            self._reconnect_lock = asyncio.Lock()
+        return self._reconnect_lock
+
+    async def _ensure_channel(self) -> aio_pika.abc.AbstractChannel:
+        """Get a valid channel, reconnecting if the current one is stale.
+
+        Uses a lock to prevent concurrent reconnection attempts from racing.
+        """
+        if self.is_ready:
+            return self._channel  # type: ignore  # is_ready guarantees non-None
+
+        async with self._lock:
+            # Double-check after acquiring lock
+            if self.is_ready:
+                return self._channel  # type: ignore
+
+            self._channel = None
+            await self.connect()
+
+            if self._channel is None:
+                raise RuntimeError("Channel should be established after connect")
+
+            return self._channel
+
+    async def _publish_once(
         self,
         routing_key: str,
         message: str,
         exchange: Optional[Exchange] = None,
         persistent: bool = True,
     ) -> None:
-        if not self.is_ready:
-            await self.connect()
-
-        if self._channel is None:
-            raise RuntimeError("Channel should be established after connect")
+        channel = await self._ensure_channel()
 
         if exchange:
-            exchange_obj = await self._channel.get_exchange(exchange.name)
+            exchange_obj = await channel.get_exchange(exchange.name)
         else:
-            exchange_obj = self._channel.default_exchange
+            exchange_obj = channel.default_exchange
 
         await exchange_obj.publish(
             aio_pika.Message(
@@ -322,9 +359,23 @@ class AsyncRabbitMQ(RabbitMQBase):
             routing_key=routing_key,
         )
 
+    @func_retry
+    async def publish_message(
+        self,
+        routing_key: str,
+        message: str,
+        exchange: Optional[Exchange] = None,
+        persistent: bool = True,
+    ) -> None:
+        try:
+            await self._publish_once(routing_key, message, exchange, persistent)
+        except aio_pika.exceptions.ChannelInvalidStateError:
+            logger.warning(
+                "RabbitMQ channel invalid, forcing reconnect and retrying publish"
+            )
+            async with self._lock:
+                self._channel = None
+            await self._publish_once(routing_key, message, exchange, persistent)
+
     async def get_channel(self) -> aio_pika.abc.AbstractChannel:
-        if not self.is_ready:
-            await self.connect()
-        if self._channel is None:
-            raise RuntimeError("Channel should be established after connect")
-        return self._channel
+        return await self._ensure_channel()

autogpt_platform/backend/poetry.lock

@@ -1382,14 +1382,14 @@ tzdata = "*"
 
 [[package]]
 name = "fastapi"
-version = "0.128.5"
+version = "0.128.6"
 description = "FastAPI framework, high performance, easy to learn, fast to code, ready for production"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "fastapi-0.128.5-py3-none-any.whl", hash = "sha256:bceec0de8aa6564599c5bcc0593b0d287703562c848271fca8546fd2c87bf4dd"},
-    {file = "fastapi-0.128.5.tar.gz", hash = "sha256:a7173579fc162d6471e3c6fbd9a4b7610c7a3b367bcacf6c4f90d5d022cab711"},
+    {file = "fastapi-0.128.6-py3-none-any.whl", hash = "sha256:bb1c1ef87d6086a7132d0ab60869d6f1ee67283b20fbf84ec0003bd335099509"},
+    {file = "fastapi-0.128.6.tar.gz", hash = "sha256:0cb3946557e792d731b26a42b04912f16367e3c3135ea8290f620e234f2b604f"},
 ]
 
 [package.dependencies]
@@ -3078,14 +3078,14 @@ type = ["pygobject-stubs", "pytest-mypy (>=1.0.1)", "shtab", "types-pywin32"]
 
 [[package]]
 name = "langfuse"
-version = "3.13.0"
+version = "3.14.1"
 description = "A client library for accessing langfuse"
 optional = false
 python-versions = "<4.0,>=3.10"
 groups = ["main"]
 files = [
-    {file = "langfuse-3.13.0-py3-none-any.whl", hash = "sha256:71912ddac1cc831a65df895eae538a556f564c094ae51473e747426e9ded1a9d"},
-    {file = "langfuse-3.13.0.tar.gz", hash = "sha256:dacea8111ca4442e97dbfec4f8d676cf9709b35357a26e468f8887b95de0012f"},
+    {file = "langfuse-3.14.1-py3-none-any.whl", hash = "sha256:17bed605dbfc9947cbd1738a715f6d27c1b80b6da9f2946586171958fa5820d0"},
+    {file = "langfuse-3.14.1.tar.gz", hash = "sha256:404a6104cd29353d7829aa417ec46565b04917e5599afdda96c5b0865f4bc991"},
 ]
 
 [package.dependencies]
@@ -8440,4 +8440,4 @@ cffi = ["cffi (>=1.17,<2.0) ; platform_python_implementation != \"PyPy\" and pyt
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.10,<3.14"
-content-hash = "14686ee0e2dc446a75d0db145b08dc410dc31c357e25085bb0f9b0174711c4b1"
+content-hash = "fc135114e01de39c8adf70f6132045e7d44a19473c1279aee0978de65aad1655"

autogpt_platform/backend/pyproject.toml

@@ -21,7 +21,7 @@ cryptography = "^46.0"
 discord-py = "^2.5.2"
 e2b-code-interpreter = "^1.5.2"
 elevenlabs = "^1.50.0"
-fastapi = "^0.128.5"
+fastapi = "^0.128.6"
 feedparser = "^6.0.11"
 flake8 = "^7.3.0"
 google-api-python-client = "^2.177.0"
@@ -34,7 +34,7 @@ html2text = "^2024.2.26"
 jinja2 = "^3.1.6"
 jsonref = "^1.1.0"
 jsonschema = "^4.25.0"
-langfuse = "^3.11.0"
+langfuse = "^3.14.1"
 launchdarkly-server-sdk = "^9.14.1"
 mem0ai = "^0.1.115"
 moviepy = "^2.1.2"

autogpt_platform/frontend/Dockerfile

@@ -25,8 +25,12 @@ RUN if [ -f .env.production ]; then \
       cp .env.default .env; \
     fi
 RUN pnpm run generate:api
+# Disable source-map generation in Docker builds to halve webpack memory usage.
+# Source maps are only useful when SENTRY_AUTH_TOKEN is set (Vercel deploys);
+# the Docker image never uploads them, so generating them just wastes RAM.
+ENV NEXT_PUBLIC_SOURCEMAPS="false"
 # In CI, we want NEXT_PUBLIC_PW_TEST=true during build so Next.js inlines it
-RUN if [ "$NEXT_PUBLIC_PW_TEST" = "true" ]; then NEXT_PUBLIC_PW_TEST=true NODE_OPTIONS="--max-old-space-size=4096" pnpm build; else NODE_OPTIONS="--max-old-space-size=4096" pnpm build; fi
+RUN if [ "$NEXT_PUBLIC_PW_TEST" = "true" ]; then NEXT_PUBLIC_PW_TEST=true NODE_OPTIONS="--max-old-space-size=8192" pnpm build; else NODE_OPTIONS="--max-old-space-size=8192" pnpm build; fi
 
 # Prod stage - based on NextJS reference Dockerfile https://github.com/vercel/next.js/blob/64271354533ed16da51be5dce85f0dbd15f17517/examples/with-docker/Dockerfile
 FROM node:21-alpine AS prod

autogpt_platform/frontend/next.config.mjs

@@ -1,8 +1,12 @@
 import { withSentryConfig } from "@sentry/nextjs";
 
+// Allow Docker builds to skip source-map generation (halves memory usage).
+// Defaults to true so Vercel/local builds are unaffected.
+const enableSourceMaps = process.env.NEXT_PUBLIC_SOURCEMAPS !== "false";
+
 /** @type {import('next').NextConfig} */
 const nextConfig = {
-  productionBrowserSourceMaps: true,
+  productionBrowserSourceMaps: enableSourceMaps,
   // Externalize OpenTelemetry packages to fix Turbopack HMR issues
   serverExternalPackages: [
     "@opentelemetry/instrumentation",
@@ -14,9 +18,37 @@ const nextConfig = {
     serverActions: {
       bodySizeLimit: "256mb",
     },
-    // Increase body size limit for API routes (file uploads) - 256MB to match backend limit
-    proxyClientMaxBodySize: "256mb",
     middlewareClientMaxBodySize: "256mb",
+    // Limit parallel webpack workers to reduce peak memory during builds.
+    cpus: 2,
+  },
+  // Work around cssnano "Invalid array length" bug in Next.js's bundled
+  // cssnano-simple comment parser when processing very large CSS chunks.
+  // CSS is still bundled correctly; gzip handles most of the size savings anyway.
+  webpack: (config, { dev }) => {
+    if (!dev) {
+      // Next.js adds CssMinimizerPlugin internally (after user config), so we
+      // can't filter it from config.plugins. Instead, intercept the webpack
+      // compilation hooks and replace the buggy plugin's tap with a no-op.
+      config.plugins.push({
+        apply(compiler) {
+          compiler.hooks.compilation.tap(
+            "DisableCssMinimizer",
+            (compilation) => {
+              compilation.hooks.processAssets.intercept({
+                register: (tap) => {
+                  if (tap.name === "CssMinimizerPlugin") {
+                    return { ...tap, fn: async () => {} };
+                  }
+                  return tap;
+                },
+              });
+            },
+          );
+        },
+      });
+    }
+    return config;
   },
   images: {
     domains: [
@@ -54,9 +86,16 @@ const nextConfig = {
   transpilePackages: ["geist"],
 };
 
-const isDevelopmentBuild = process.env.NODE_ENV !== "production";
+// Only run the Sentry webpack plugin when we can actually upload source maps
+// (i.e. on Vercel with SENTRY_AUTH_TOKEN set). The Sentry *runtime* SDK
+// (imported in app code) still captures errors without the plugin.
+// Skipping the plugin saves ~1 GB of peak memory during `next build`.
+const skipSentryPlugin =
+  process.env.NODE_ENV !== "production" ||
+  !enableSourceMaps ||
+  !process.env.SENTRY_AUTH_TOKEN;
 
-export default isDevelopmentBuild
+export default skipSentryPlugin
   ? nextConfig
   : withSentryConfig(nextConfig, {
       // For all available options, see:
@@ -96,7 +135,7 @@ export default isDevelopmentBuild
 
       // This helps Sentry with sourcemaps... https://docs.sentry.io/platforms/javascript/guides/nextjs/sourcemaps/
       sourcemaps: {
-        disable: false,
+        disable: !enableSourceMaps,
         assets: [".next/**/*.js", ".next/**/*.js.map"],
         ignore: ["**/node_modules/**"],
         deleteSourcemapsAfterUpload: false, // Source is public anyway :)

autogpt_platform/frontend/package.json

@@ -7,7 +7,7 @@
   },
   "scripts": {
     "dev": "pnpm run generate:api:force && next dev --turbo",
-    "build": "next build",
+    "build": "cross-env NODE_OPTIONS=--max-old-space-size=16384 next build",
     "start": "next start",
     "start:standalone": "cd .next/standalone && node server.js",
     "lint": "next lint && prettier --check .",
@@ -30,6 +30,7 @@
     "defaults"
   ],
   "dependencies": {
+    "@ai-sdk/react": "3.0.61",
     "@faker-js/faker": "10.0.0",
     "@hookform/resolvers": "5.2.2",
     "@next/third-parties": "15.4.6",
@@ -60,6 +61,10 @@
     "@rjsf/utils": "6.1.2",
     "@rjsf/validator-ajv8": "6.1.2",
     "@sentry/nextjs": "10.27.0",
+    "@streamdown/cjk": "1.0.1",
+    "@streamdown/code": "1.0.1",
+    "@streamdown/math": "1.0.1",
+    "@streamdown/mermaid": "1.0.1",
     "@supabase/ssr": "0.7.0",
     "@supabase/supabase-js": "2.78.0",
     "@tanstack/react-query": "5.90.6",
@@ -68,6 +73,7 @@
     "@vercel/analytics": "1.5.0",
     "@vercel/speed-insights": "1.2.0",
     "@xyflow/react": "12.9.2",
+    "ai": "6.0.59",
     "boring-avatars": "1.11.2",
     "class-variance-authority": "0.7.1",
     "clsx": "2.1.1",
@@ -87,7 +93,6 @@
     "launchdarkly-react-client-sdk": "3.9.0",
     "lodash": "4.17.21",
     "lucide-react": "0.552.0",
-    "moment": "2.30.1",
     "next": "15.4.10",
     "next-themes": "0.4.6",
     "nuqs": "2.7.2",
@@ -112,9 +117,11 @@
     "remark-math": "6.0.0",
     "shepherd.js": "14.5.1",
     "sonner": "2.0.7",
+    "streamdown": "2.1.0",
     "tailwind-merge": "2.6.0",
     "tailwind-scrollbar": "3.1.0",
     "tailwindcss-animate": "1.0.7",
+    "use-stick-to-bottom": "1.1.2",
     "uuid": "11.1.0",
     "vaul": "1.1.2",
     "zod": "3.25.76",
@@ -172,7 +179,8 @@
   },
   "pnpm": {
     "overrides": {
-      "@opentelemetry/instrumentation": "0.209.0"
+      "@opentelemetry/instrumentation": "0.209.0",
+      "lodash-es": "4.17.23"
     }
   },
   "packageManager": "pnpm@10.20.0+sha512.cf9998222162dd85864d0a8102e7892e7ba4ceadebbf5a31f9c2fce48dfce317a9c53b9f6464d1ef9042cba2e02ae02a9f7c143a2b438cd93c91840f0192b9dd"

autogpt_platform/frontend/src/app/(platform)/build/components/NewControlPanel/NewBlockMenu/BlockMenuSearchBar/useBlockMenuSearchBar.ts

@@ -1,4 +1,4 @@
-import { debounce } from "lodash";
+import debounce from "lodash/debounce";
 import { useCallback, useEffect, useRef, useState } from "react";
 import { useBlockMenuStore } from "../../../../stores/blockMenuStore";
 import { getQueryClient } from "@/lib/react-query/queryClient";

autogpt_platform/frontend/src/app/(platform)/build/components/NewControlPanel/NewBlockMenu/HorizontalScroll.tsx

@@ -70,10 +70,10 @@ export const HorizontalScroll: React.FC<HorizontalScrollAreaProps> = ({
           {children}
         </div>
         {canScrollLeft && (
-          <div className="pointer-events-none absolute inset-y-0 left-0 w-8 bg-gradient-to-r from-white via-white/80 to-white/0" />
+          <div className="pointer-events-none absolute inset-y-0 left-0 w-8 bg-gradient-to-r from-background via-background/80 to-background/0" />
         )}
         {canScrollRight && (
-          <div className="pointer-events-none absolute inset-y-0 right-0 w-8 bg-gradient-to-l from-white via-white/80 to-white/0" />
+          <div className="pointer-events-none absolute inset-y-0 right-0 w-8 bg-gradient-to-l from-background via-background/80 to-background/0" />
         )}
         {canScrollLeft && (
           <button

autogpt_platform/frontend/src/app/(platform)/copilot/CopilotPage.tsx

@@ -0,0 +1,80 @@
+"use client";
+
+import { SidebarProvider } from "@/components/ui/sidebar";
+import { ChatContainer } from "./components/ChatContainer/ChatContainer";
+import { ChatSidebar } from "./components/ChatSidebar/ChatSidebar";
+import { MobileDrawer } from "./components/MobileDrawer/MobileDrawer";
+import { MobileHeader } from "./components/MobileHeader/MobileHeader";
+import { ScaleLoader } from "./components/ScaleLoader/ScaleLoader";
+import { useCopilotPage } from "./useCopilotPage";
+
+export function CopilotPage() {
+  const {
+    sessionId,
+    messages,
+    status,
+    error,
+    stop,
+    createSession,
+    onSend,
+    isLoadingSession,
+    isCreatingSession,
+    isUserLoading,
+    isLoggedIn,
+    // Mobile drawer
+    isMobile,
+    isDrawerOpen,
+    sessions,
+    isLoadingSessions,
+    handleOpenDrawer,
+    handleCloseDrawer,
+    handleDrawerOpenChange,
+    handleSelectSession,
+    handleNewChat,
+  } = useCopilotPage();
+
+  if (isUserLoading || !isLoggedIn) {
+    return (
+      <div className="fixed inset-0 z-50 flex items-center justify-center bg-[#f8f8f9]">
+        <ScaleLoader className="text-neutral-400" />
+      </div>
+    );
+  }
+
+  return (
+    <SidebarProvider
+      defaultOpen={true}
+      className="h-[calc(100vh-72px)] min-h-0"
+    >
+      {!isMobile && <ChatSidebar />}
+      <div className="relative flex h-full w-full flex-col overflow-hidden bg-[#f8f8f9] px-0">
+        {isMobile && <MobileHeader onOpenDrawer={handleOpenDrawer} />}
+        <div className="flex-1 overflow-hidden">
+          <ChatContainer
+            messages={messages}
+            status={status}
+            error={error}
+            sessionId={sessionId}
+            isLoadingSession={isLoadingSession}
+            isCreatingSession={isCreatingSession}
+            onCreateSession={createSession}
+            onSend={onSend}
+            onStop={stop}
+          />
+        </div>
+      </div>
+      {isMobile && (
+        <MobileDrawer
+          isOpen={isDrawerOpen}
+          sessions={sessions}
+          currentSessionId={sessionId}
+          isLoading={isLoadingSessions}
+          onSelectSession={handleSelectSession}
+          onNewChat={handleNewChat}
+          onClose={handleCloseDrawer}
+          onOpenChange={handleDrawerOpenChange}
+        />
+      )}
+    </SidebarProvider>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatContainer/ChatContainer.tsx

@@ -0,0 +1,74 @@
+"use client";
+import { ChatInput } from "@/app/(platform)/copilot/components/ChatInput/ChatInput";
+import { UIDataTypes, UIMessage, UITools } from "ai";
+import { LayoutGroup, motion } from "framer-motion";
+import { ChatMessagesContainer } from "../ChatMessagesContainer/ChatMessagesContainer";
+import { CopilotChatActionsProvider } from "../CopilotChatActionsProvider/CopilotChatActionsProvider";
+import { EmptySession } from "../EmptySession/EmptySession";
+
+export interface ChatContainerProps {
+  messages: UIMessage<unknown, UIDataTypes, UITools>[];
+  status: string;
+  error: Error | undefined;
+  sessionId: string | null;
+  isLoadingSession: boolean;
+  isCreatingSession: boolean;
+  onCreateSession: () => void | Promise<string>;
+  onSend: (message: string) => void | Promise<void>;
+  onStop: () => void;
+}
+export const ChatContainer = ({
+  messages,
+  status,
+  error,
+  sessionId,
+  isLoadingSession,
+  isCreatingSession,
+  onCreateSession,
+  onSend,
+  onStop,
+}: ChatContainerProps) => {
+  const inputLayoutId = "copilot-2-chat-input";
+
+  return (
+    <CopilotChatActionsProvider onSend={onSend}>
+      <LayoutGroup id="copilot-2-chat-layout">
+        <div className="flex h-full min-h-0 w-full flex-col bg-[#f8f8f9] px-2 lg:px-0">
+          {sessionId ? (
+            <div className="mx-auto flex h-full min-h-0 w-full max-w-3xl flex-col">
+              <ChatMessagesContainer
+                messages={messages}
+                status={status}
+                error={error}
+                isLoading={isLoadingSession}
+              />
+              <motion.div
+                initial={{ opacity: 0 }}
+                animate={{ opacity: 1 }}
+                transition={{ duration: 0.3 }}
+                className="relative px-3 pb-2 pt-2"
+              >
+                <div className="pointer-events-none absolute left-0 right-0 top-[-18px] z-10 h-6 bg-gradient-to-b from-transparent to-[#f8f8f9]" />
+                <ChatInput
+                  inputId="chat-input-session"
+                  onSend={onSend}
+                  disabled={status === "streaming"}
+                  isStreaming={status === "streaming"}
+                  onStop={onStop}
+                  placeholder="What else can I help with?"
+                />
+              </motion.div>
+            </div>
+          ) : (
+            <EmptySession
+              inputLayoutId={inputLayoutId}
+              isCreatingSession={isCreatingSession}
+              onCreateSession={onCreateSession}
+              onSend={onSend}
+            />
+          )}
+        </div>
+      </LayoutGroup>
+    </CopilotChatActionsProvider>
+  );
+};

autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatInput/ChatInput.tsx

@@ -6,17 +6,19 @@ import {
   MicrophoneIcon,
   StopIcon,
 } from "@phosphor-icons/react";
+import { ChangeEvent, useCallback } from "react";
 import { RecordingIndicator } from "./components/RecordingIndicator";
 import { useChatInput } from "./useChatInput";
 import { useVoiceRecording } from "./useVoiceRecording";
 
 export interface Props {
-  onSend: (message: string) => void;
+  onSend: (message: string) => void | Promise<void>;
   disabled?: boolean;
   isStreaming?: boolean;
   onStop?: () => void;
   placeholder?: string;
   className?: string;
+  inputId?: string;
 }
 
 export function ChatInput({
@@ -26,14 +28,14 @@ export function ChatInput({
   onStop,
   placeholder = "Type your message...",
   className,
+  inputId = "chat-input",
 }: Props) {
-  const inputId = "chat-input";
   const {
     value,
     setValue,
     handleKeyDown: baseHandleKeyDown,
     handleSubmit,
-    handleChange,
+    handleChange: baseHandleChange,
     hasMultipleLines,
   } = useChatInput({
     onSend,
@@ -60,6 +62,15 @@ export function ChatInput({
     inputId,
   });
 
+  // Block text changes when recording
+  const handleChange = useCallback(
+    (e: ChangeEvent<HTMLTextAreaElement>) => {
+      if (isRecording) return;
+      baseHandleChange(e);
+    },
+    [isRecording, baseHandleChange],
+  );
+
   return (
     <form onSubmit={handleSubmit} className={cn("relative flex-1", className)}>
       <div className="relative">

autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatInput/useChatInput.ts

@@ -21,6 +21,7 @@ export function useChatInput({
 }: Args) {
   const [value, setValue] = useState("");
   const [hasMultipleLines, setHasMultipleLines] = useState(false);
+  const [isSending, setIsSending] = useState(false);
 
   useEffect(
     function focusOnMount() {
@@ -100,34 +101,40 @@ export function useChatInput({
     }
   }, [value, maxRows, inputId]);
 
-  const handleSend = () => {
-    if (disabled || !value.trim()) return;
-    onSend(value.trim());
-    setValue("");
-    setHasMultipleLines(false);
-    const textarea = document.getElementById(inputId) as HTMLTextAreaElement;
-    const wrapper = document.getElementById(
-      `${inputId}-wrapper`,
-    ) as HTMLDivElement;
-    if (textarea) {
-      textarea.style.height = "auto";
+  async function handleSend() {
+    if (disabled || isSending || !value.trim()) return;
+
+    setIsSending(true);
+    try {
+      await onSend(value.trim());
+      setValue("");
+      setHasMultipleLines(false);
+      const textarea = document.getElementById(inputId) as HTMLTextAreaElement;
+      const wrapper = document.getElementById(
+        `${inputId}-wrapper`,
+      ) as HTMLDivElement;
+      if (textarea) {
+        textarea.style.height = "auto";
+      }
+      if (wrapper) {
+        wrapper.style.height = "";
+        wrapper.style.maxHeight = "";
+      }
+    } finally {
+      setIsSending(false);
     }
-    if (wrapper) {
-      wrapper.style.height = "";
-      wrapper.style.maxHeight = "";
-    }
-  };
+  }
 
   function handleKeyDown(event: KeyboardEvent<HTMLTextAreaElement>) {
     if (event.key === "Enter" && !event.shiftKey) {
       event.preventDefault();
-      handleSend();
+      void handleSend();
     }
   }
 
   function handleSubmit(e: FormEvent<HTMLFormElement>) {
     e.preventDefault();
-    handleSend();
+    void handleSend();
   }
 
   function handleChange(e: ChangeEvent<HTMLTextAreaElement>) {
@@ -142,5 +149,6 @@ export function useChatInput({
     handleSubmit,
     handleChange,
     hasMultipleLines,
+    isSending,
   };
 }

autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatInput/useVoiceRecording.ts

@@ -38,9 +38,13 @@ export function useVoiceRecording({
   const streamRef = useRef<MediaStream | null>(null);
   const isRecordingRef = useRef(false);
 
-  const isSupported =
-    typeof window !== "undefined" &&
-    !!(navigator.mediaDevices && navigator.mediaDevices.getUserMedia);
+  const [isSupported, setIsSupported] = useState(false);
+
+  useEffect(() => {
+    setIsSupported(
+      !!(navigator.mediaDevices && navigator.mediaDevices.getUserMedia),
+    );
+  }, []);
 
   const clearTimer = useCallback(() => {
     if (timerRef.current) {
@@ -214,17 +218,33 @@ export function useVoiceRecording({
 
   const handleKeyDown = useCallback(
     (event: KeyboardEvent<HTMLTextAreaElement>) => {
-      if (event.key === " " && !value.trim() && !isTranscribing) {
+      // Allow space to toggle recording (start when empty, stop when recording)
+      if (event.key === " " && !isTranscribing) {
+        if (isRecordingRef.current) {
+          // Stop recording on space
+          event.preventDefault();
+          stopRecording();
+          return;
+        } else if (!value.trim()) {
+          // Start recording on space when input is empty
+          event.preventDefault();
+          void startRecording();
+          return;
+        }
+      }
+      // Block all key events when recording (except space handled above)
+      if (isRecordingRef.current) {
         event.preventDefault();
-        toggleRecording();
         return;
       }
       baseHandleKeyDown(event);
     },
-    [value, isTranscribing, toggleRecording, baseHandleKeyDown],
+    [value, isTranscribing, stopRecording, startRecording, baseHandleKeyDown],
   );
 
   const showMicButton = isSupported;
+  // Don't include isRecording in disabled state - we need key events to work
+  // Text input is blocked via handleKeyDown instead
   const isInputDisabled = disabled || isStreaming || isTranscribing;
 
   // Cleanup on unmount

autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/ChatMessagesContainer.tsx

@@ -0,0 +1,274 @@
+import { getGetWorkspaceDownloadFileByIdUrl } from "@/app/api/__generated__/endpoints/workspace/workspace";
+import {
+  Conversation,
+  ConversationContent,
+  ConversationScrollButton,
+} from "@/components/ai-elements/conversation";
+import {
+  Message,
+  MessageContent,
+  MessageResponse,
+} from "@/components/ai-elements/message";
+import { LoadingSpinner } from "@/components/atoms/LoadingSpinner/LoadingSpinner";
+import { ToolUIPart, UIDataTypes, UIMessage, UITools } from "ai";
+import { useEffect, useState } from "react";
+import { CreateAgentTool } from "../../tools/CreateAgent/CreateAgent";
+import { EditAgentTool } from "../../tools/EditAgent/EditAgent";
+import { FindAgentsTool } from "../../tools/FindAgents/FindAgents";
+import { FindBlocksTool } from "../../tools/FindBlocks/FindBlocks";
+import { RunAgentTool } from "../../tools/RunAgent/RunAgent";
+import { RunBlockTool } from "../../tools/RunBlock/RunBlock";
+import { SearchDocsTool } from "../../tools/SearchDocs/SearchDocs";
+import { ViewAgentOutputTool } from "../../tools/ViewAgentOutput/ViewAgentOutput";
+
+// ---------------------------------------------------------------------------
+// Workspace media support
+// ---------------------------------------------------------------------------
+
+/**
+ * Resolve workspace:// URLs in markdown text to proxy download URLs.
+ * Detects MIME type from the hash fragment (e.g. workspace://id#video/mp4)
+ * and prefixes the alt text with "video:" so the custom img component can
+ * render a <video> element instead.
+ */
+function resolveWorkspaceUrls(text: string): string {
+  return text.replace(
+    /!\[([^\]]*)\]\(workspace:\/\/([^)#\s]+)(?:#([^)\s]*))?\)/g,
+    (_match, alt: string, fileId: string, mimeHint?: string) => {
+      const apiPath = getGetWorkspaceDownloadFileByIdUrl(fileId);
+      const url = `/api/proxy${apiPath}`;
+      if (mimeHint?.startsWith("video/")) {
+        return `![video:${alt || "Video"}](${url})`;
+      }
+      return `![${alt || "Image"}](${url})`;
+    },
+  );
+}
+
+/**
+ * Custom img component for Streamdown that renders <video> elements
+ * for workspace video files (detected via "video:" alt-text prefix).
+ * Falls back to <video> when an <img> fails to load for workspace files.
+ */
+function WorkspaceMediaImage(props: React.JSX.IntrinsicElements["img"]) {
+  const { src, alt, ...rest } = props;
+  const [imgFailed, setImgFailed] = useState(false);
+  const isWorkspace = src?.includes("/workspace/files/") ?? false;
+
+  if (!src) return null;
+
+  if (alt?.startsWith("video:") || (imgFailed && isWorkspace)) {
+    return (
+      <span className="my-2 inline-block">
+        <video
+          controls
+          className="h-auto max-w-full rounded-md border border-zinc-200"
+          preload="metadata"
+        >
+          <source src={src} />
+          Your browser does not support the video tag.
+        </video>
+      </span>
+    );
+  }
+
+  return (
+    // eslint-disable-next-line @next/next/no-img-element
+    <img
+      src={src}
+      alt={alt || "Image"}
+      className="h-auto max-w-full rounded-md border border-zinc-200"
+      loading="lazy"
+      onError={() => {
+        if (isWorkspace) setImgFailed(true);
+      }}
+      {...rest}
+    />
+  );
+}
+
+/** Stable components override for Streamdown (avoids re-creating on every render). */
+const STREAMDOWN_COMPONENTS = { img: WorkspaceMediaImage };
+
+const THINKING_PHRASES = [
+  "Thinking...",
+  "Considering this...",
+  "Working through this...",
+  "Analyzing your request...",
+  "Reasoning...",
+  "Looking into it...",
+  "Processing your request...",
+  "Mulling this over...",
+  "Piecing it together...",
+  "On it...",
+];
+
+function getRandomPhrase() {
+  return THINKING_PHRASES[Math.floor(Math.random() * THINKING_PHRASES.length)];
+}
+
+interface ChatMessagesContainerProps {
+  messages: UIMessage<unknown, UIDataTypes, UITools>[];
+  status: string;
+  error: Error | undefined;
+  isLoading: boolean;
+}
+
+export const ChatMessagesContainer = ({
+  messages,
+  status,
+  error,
+  isLoading,
+}: ChatMessagesContainerProps) => {
+  const [thinkingPhrase, setThinkingPhrase] = useState(getRandomPhrase);
+
+  useEffect(() => {
+    if (status === "submitted") {
+      setThinkingPhrase(getRandomPhrase());
+    }
+  }, [status]);
+
+  const lastMessage = messages[messages.length - 1];
+  const lastAssistantHasVisibleContent =
+    lastMessage?.role === "assistant" &&
+    lastMessage.parts.some(
+      (p) =>
+        (p.type === "text" && p.text.trim().length > 0) ||
+        p.type.startsWith("tool-"),
+    );
+
+  const showThinking =
+    status === "submitted" ||
+    (status === "streaming" && !lastAssistantHasVisibleContent);
+
+  return (
+    <Conversation className="min-h-0 flex-1">
+      <ConversationContent className="flex min-h-screen flex-1 flex-col gap-6 px-3 py-6">
+        {isLoading && messages.length === 0 && (
+          <div className="flex min-h-full flex-1 items-center justify-center">
+            <LoadingSpinner className="text-neutral-600" />
+          </div>
+        )}
+        {messages.map((message, messageIndex) => {
+          const isLastAssistant =
+            messageIndex === messages.length - 1 &&
+            message.role === "assistant";
+          const messageHasVisibleContent = message.parts.some(
+            (p) =>
+              (p.type === "text" && p.text.trim().length > 0) ||
+              p.type.startsWith("tool-"),
+          );
+
+          return (
+            <Message from={message.role} key={message.id}>
+              <MessageContent
+                className={
+                  "text-[1rem] leading-relaxed " +
+                  "group-[.is-user]:rounded-xl group-[.is-user]:bg-purple-100 group-[.is-user]:px-3 group-[.is-user]:py-2.5 group-[.is-user]:text-slate-900 group-[.is-user]:[border-bottom-right-radius:0] " +
+                  "group-[.is-assistant]:bg-transparent group-[.is-assistant]:text-slate-900"
+                }
+              >
+                {message.parts.map((part, i) => {
+                  switch (part.type) {
+                    case "text":
+                      return (
+                        <MessageResponse
+                          key={`${message.id}-${i}`}
+                          components={STREAMDOWN_COMPONENTS}
+                        >
+                          {resolveWorkspaceUrls(part.text)}
+                        </MessageResponse>
+                      );
+                    case "tool-find_block":
+                      return (
+                        <FindBlocksTool
+                          key={`${message.id}-${i}`}
+                          part={part as ToolUIPart}
+                        />
+                      );
+                    case "tool-find_agent":
+                    case "tool-find_library_agent":
+                      return (
+                        <FindAgentsTool
+                          key={`${message.id}-${i}`}
+                          part={part as ToolUIPart}
+                        />
+                      );
+                    case "tool-search_docs":
+                    case "tool-get_doc_page":
+                      return (
+                        <SearchDocsTool
+                          key={`${message.id}-${i}`}
+                          part={part as ToolUIPart}
+                        />
+                      );
+                    case "tool-run_block":
+                      return (
+                        <RunBlockTool
+                          key={`${message.id}-${i}`}
+                          part={part as ToolUIPart}
+                        />
+                      );
+                    case "tool-run_agent":
+                    case "tool-schedule_agent":
+                      return (
+                        <RunAgentTool
+                          key={`${message.id}-${i}`}
+                          part={part as ToolUIPart}
+                        />
+                      );
+                    case "tool-create_agent":
+                      return (
+                        <CreateAgentTool
+                          key={`${message.id}-${i}`}
+                          part={part as ToolUIPart}
+                        />
+                      );
+                    case "tool-edit_agent":
+                      return (
+                        <EditAgentTool
+                          key={`${message.id}-${i}`}
+                          part={part as ToolUIPart}
+                        />
+                      );
+                    case "tool-view_agent_output":
+                      return (
+                        <ViewAgentOutputTool
+                          key={`${message.id}-${i}`}
+                          part={part as ToolUIPart}
+                        />
+                      );
+                    default:
+                      return null;
+                  }
+                })}
+                {isLastAssistant &&
+                  !messageHasVisibleContent &&
+                  showThinking && (
+                    <span className="inline-block animate-shimmer bg-gradient-to-r from-neutral-400 via-neutral-600 to-neutral-400 bg-[length:200%_100%] bg-clip-text text-transparent">
+                      {thinkingPhrase}
+                    </span>
+                  )}
+              </MessageContent>
+            </Message>
+          );
+        })}
+        {showThinking && lastMessage?.role !== "assistant" && (
+          <Message from="assistant">
+            <MessageContent className="text-[1rem] leading-relaxed">
+              <span className="inline-block animate-shimmer bg-gradient-to-r from-neutral-400 via-neutral-600 to-neutral-400 bg-[length:200%_100%] bg-clip-text text-transparent">
+                {thinkingPhrase}
+              </span>
+            </MessageContent>
+          </Message>
+        )}
+        {error && (
+          <div className="rounded-lg bg-red-50 p-3 text-red-600">
+            Error: {error.message}
+          </div>
+        )}
+      </ConversationContent>
+      <ConversationScrollButton />
+    </Conversation>
+  );
+};

autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatSidebar/ChatSidebar.tsx

@@ -0,0 +1,188 @@
+"use client";
+import { useGetV2ListSessions } from "@/app/api/__generated__/endpoints/chat/chat";
+import { Button } from "@/components/atoms/Button/Button";
+import { LoadingSpinner } from "@/components/atoms/LoadingSpinner/LoadingSpinner";
+import { Text } from "@/components/atoms/Text/Text";
+import {
+  Sidebar,
+  SidebarContent,
+  SidebarFooter,
+  SidebarHeader,
+  SidebarTrigger,
+  useSidebar,
+} from "@/components/ui/sidebar";
+import { cn } from "@/lib/utils";
+import { PlusCircleIcon, PlusIcon } from "@phosphor-icons/react";
+import { motion } from "framer-motion";
+import { parseAsString, useQueryState } from "nuqs";
+
+export function ChatSidebar() {
+  const { state } = useSidebar();
+  const isCollapsed = state === "collapsed";
+  const [sessionId, setSessionId] = useQueryState("sessionId", parseAsString);
+
+  const { data: sessionsResponse, isLoading: isLoadingSessions } =
+    useGetV2ListSessions({ limit: 50 });
+
+  const sessions =
+    sessionsResponse?.status === 200 ? sessionsResponse.data.sessions : [];
+
+  function handleNewChat() {
+    setSessionId(null);
+  }
+
+  function handleSelectSession(id: string) {
+    setSessionId(id);
+  }
+
+  function formatDate(dateString: string) {
+    const date = new Date(dateString);
+    const now = new Date();
+    const diffMs = now.getTime() - date.getTime();
+    const diffDays = Math.floor(diffMs / (1000 * 60 * 60 * 24));
+
+    if (diffDays === 0) return "Today";
+    if (diffDays === 1) return "Yesterday";
+    if (diffDays < 7) return `${diffDays} days ago`;
+
+    const day = date.getDate();
+    const ordinal =
+      day % 10 === 1 && day !== 11
+        ? "st"
+        : day % 10 === 2 && day !== 12
+          ? "nd"
+          : day % 10 === 3 && day !== 13
+            ? "rd"
+            : "th";
+    const month = date.toLocaleDateString("en-US", { month: "short" });
+    const year = date.getFullYear();
+
+    return `${day}${ordinal} ${month} ${year}`;
+  }
+
+  return (
+    <Sidebar
+      variant="inset"
+      collapsible="icon"
+      className="!top-[50px] !h-[calc(100vh-50px)] border-r border-zinc-100 px-0"
+    >
+      {isCollapsed && (
+        <SidebarHeader
+          className={cn(
+            "flex",
+            isCollapsed
+              ? "flex-row items-center justify-between gap-y-4 md:flex-col md:items-start md:justify-start"
+              : "flex-row items-center justify-between",
+          )}
+        >
+          <motion.div
+            key={isCollapsed ? "header-collapsed" : "header-expanded"}
+            className="flex flex-col items-center gap-3 pt-4"
+            initial={{ opacity: 0, filter: "blur(3px)" }}
+            animate={{ opacity: 1, filter: "blur(0px)" }}
+            transition={{ type: "spring", bounce: 0.2 }}
+          >
+            <div className="flex flex-col items-center gap-2">
+              <SidebarTrigger />
+              <Button
+                variant="ghost"
+                onClick={handleNewChat}
+                style={{ minWidth: "auto", width: "auto" }}
+              >
+                <PlusCircleIcon className="!size-5" />
+                <span className="sr-only">New Chat</span>
+              </Button>
+            </div>
+          </motion.div>
+        </SidebarHeader>
+      )}
+      <SidebarContent className="gap-4 overflow-y-auto px-4 py-4 [-ms-overflow-style:none] [scrollbar-width:none] [&::-webkit-scrollbar]:hidden">
+        {!isCollapsed && (
+          <motion.div
+            initial={{ opacity: 0 }}
+            animate={{ opacity: 1 }}
+            transition={{ duration: 0.2, delay: 0.1 }}
+            className="flex items-center justify-between px-3"
+          >
+            <Text variant="h3" size="body-medium">
+              Your chats
+            </Text>
+            <div className="relative left-6">
+              <SidebarTrigger />
+            </div>
+          </motion.div>
+        )}
+
+        {!isCollapsed && (
+          <motion.div
+            initial={{ opacity: 0 }}
+            animate={{ opacity: 1 }}
+            transition={{ duration: 0.2, delay: 0.15 }}
+            className="mt-4 flex flex-col gap-1"
+          >
+            {isLoadingSessions ? (
+              <div className="flex min-h-[30rem] items-center justify-center py-4">
+                <LoadingSpinner size="small" className="text-neutral-600" />
+              </div>
+            ) : sessions.length === 0 ? (
+              <p className="py-4 text-center text-sm text-neutral-500">
+                No conversations yet
+              </p>
+            ) : (
+              sessions.map((session) => (
+                <button
+                  key={session.id}
+                  onClick={() => handleSelectSession(session.id)}
+                  className={cn(
+                    "w-full rounded-lg px-3 py-2.5 text-left transition-colors",
+                    session.id === sessionId
+                      ? "bg-zinc-100"
+                      : "hover:bg-zinc-50",
+                  )}
+                >
+                  <div className="flex min-w-0 max-w-full flex-col overflow-hidden">
+                    <div className="min-w-0 max-w-full">
+                      <Text
+                        variant="body"
+                        className={cn(
+                          "truncate font-normal",
+                          session.id === sessionId
+                            ? "text-zinc-600"
+                            : "text-zinc-800",
+                        )}
+                      >
+                        {session.title || `Untitled chat`}
+                      </Text>
+                    </div>
+                    <Text variant="small" className="text-neutral-400">
+                      {formatDate(session.updated_at)}
+                    </Text>
+                  </div>
+                </button>
+              ))
+            )}
+          </motion.div>
+        )}
+      </SidebarContent>
+      {!isCollapsed && sessionId && (
+        <SidebarFooter className="shrink-0 bg-zinc-50 p-3 pb-1 shadow-[0_-4px_6px_-1px_rgba(0,0,0,0.05)]">
+          <motion.div
+            initial={{ opacity: 0 }}
+            animate={{ opacity: 1 }}
+            transition={{ duration: 0.2, delay: 0.2 }}
+          >
+            <Button
+              variant="primary"
+              size="small"
+              onClick={handleNewChat}
+              className="w-full"
+              leftIcon={<PlusIcon className="h-4 w-4" weight="bold" />}
+            >
+              New Chat
+            </Button>
+          </motion.div>
+        </SidebarFooter>
+      )}
+    </Sidebar>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotChatActionsProvider/CopilotChatActionsProvider.tsx

@@ -0,0 +1,16 @@
+"use client";
+
+import { CopilotChatActionsContext } from "./useCopilotChatActions";
+
+interface Props {
+  onSend: (message: string) => void | Promise<void>;
+  children: React.ReactNode;
+}
+
+export function CopilotChatActionsProvider({ onSend, children }: Props) {
+  return (
+    <CopilotChatActionsContext.Provider value={{ onSend }}>
+      {children}
+    </CopilotChatActionsContext.Provider>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotChatActionsProvider/useCopilotChatActions.ts

@@ -0,0 +1,23 @@
+"use client";
+
+import { createContext, useContext } from "react";
+
+interface CopilotChatActions {
+  onSend: (message: string) => void | Promise<void>;
+}
+
+const CopilotChatActionsContext = createContext<CopilotChatActions | null>(
+  null,
+);
+
+export function useCopilotChatActions(): CopilotChatActions {
+  const ctx = useContext(CopilotChatActionsContext);
+  if (!ctx) {
+    throw new Error(
+      "useCopilotChatActions must be used within CopilotChatActionsProvider",
+    );
+  }
+  return ctx;
+}
+
+export { CopilotChatActionsContext };

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/CopilotShell.tsx

@@ -1,99 +0,0 @@
-"use client";
-
-import { ChatLoader } from "@/components/contextual/Chat/components/ChatLoader/ChatLoader";
-import { Text } from "@/components/atoms/Text/Text";
-import { NAVBAR_HEIGHT_PX } from "@/lib/constants";
-import type { ReactNode } from "react";
-import { DesktopSidebar } from "./components/DesktopSidebar/DesktopSidebar";
-import { MobileDrawer } from "./components/MobileDrawer/MobileDrawer";
-import { MobileHeader } from "./components/MobileHeader/MobileHeader";
-import { useCopilotShell } from "./useCopilotShell";
-
-interface Props {
-  children: ReactNode;
-}
-
-export function CopilotShell({ children }: Props) {
-  const {
-    isMobile,
-    isDrawerOpen,
-    isLoading,
-    isCreatingSession,
-    isLoggedIn,
-    hasActiveSession,
-    sessions,
-    currentSessionId,
-    handleOpenDrawer,
-    handleCloseDrawer,
-    handleDrawerOpenChange,
-    handleNewChatClick,
-    handleSessionClick,
-    hasNextPage,
-    isFetchingNextPage,
-    fetchNextPage,
-  } = useCopilotShell();
-
-  if (!isLoggedIn) {
-    return (
-      <div className="flex h-full items-center justify-center">
-        <ChatLoader />
-      </div>
-    );
-  }
-
-  return (
-    <div
-      className="flex overflow-hidden bg-[#EFEFF0]"
-      style={{ height: `calc(100vh - ${NAVBAR_HEIGHT_PX}px)` }}
-    >
-      {!isMobile && (
-        <DesktopSidebar
-          sessions={sessions}
-          currentSessionId={currentSessionId}
-          isLoading={isLoading}
-          hasNextPage={hasNextPage}
-          isFetchingNextPage={isFetchingNextPage}
-          onSelectSession={handleSessionClick}
-          onFetchNextPage={fetchNextPage}
-          onNewChat={handleNewChatClick}
-          hasActiveSession={Boolean(hasActiveSession)}
-        />
-      )}
-
-      <div className="relative flex min-h-0 flex-1 flex-col">
-        {isMobile && <MobileHeader onOpenDrawer={handleOpenDrawer} />}
-        <div className="flex min-h-0 flex-1 flex-col">
-          {isCreatingSession ? (
-            <div className="flex h-full flex-1 flex-col items-center justify-center bg-[#f8f8f9]">
-              <div className="flex flex-col items-center gap-4">
-                <ChatLoader />
-                <Text variant="body" className="text-zinc-500">
-                  Creating your chat...
-                </Text>
-              </div>
-            </div>
-          ) : (
-            children
-          )}
-        </div>
-      </div>
-
-      {isMobile && (
-        <MobileDrawer
-          isOpen={isDrawerOpen}
-          sessions={sessions}
-          currentSessionId={currentSessionId}
-          isLoading={isLoading}
-          hasNextPage={hasNextPage}
-          isFetchingNextPage={isFetchingNextPage}
-          onSelectSession={handleSessionClick}
-          onFetchNextPage={fetchNextPage}
-          onNewChat={handleNewChatClick}
-          onClose={handleCloseDrawer}
-          onOpenChange={handleDrawerOpenChange}
-          hasActiveSession={Boolean(hasActiveSession)}
-        />
-      )}
-    </div>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/components/DesktopSidebar/DesktopSidebar.tsx

@@ -1,70 +0,0 @@
-import type { SessionSummaryResponse } from "@/app/api/__generated__/models/sessionSummaryResponse";
-import { Button } from "@/components/atoms/Button/Button";
-import { Text } from "@/components/atoms/Text/Text";
-import { scrollbarStyles } from "@/components/styles/scrollbars";
-import { cn } from "@/lib/utils";
-import { Plus } from "@phosphor-icons/react";
-import { SessionsList } from "../SessionsList/SessionsList";
-
-interface Props {
-  sessions: SessionSummaryResponse[];
-  currentSessionId: string | null;
-  isLoading: boolean;
-  hasNextPage: boolean;
-  isFetchingNextPage: boolean;
-  onSelectSession: (sessionId: string) => void;
-  onFetchNextPage: () => void;
-  onNewChat: () => void;
-  hasActiveSession: boolean;
-}
-
-export function DesktopSidebar({
-  sessions,
-  currentSessionId,
-  isLoading,
-  hasNextPage,
-  isFetchingNextPage,
-  onSelectSession,
-  onFetchNextPage,
-  onNewChat,
-  hasActiveSession,
-}: Props) {
-  return (
-    <aside className="flex h-full w-80 flex-col border-r border-zinc-100 bg-zinc-50">
-      <div className="shrink-0 px-6 py-4">
-        <Text variant="h3" size="body-medium">
-          Your chats
-        </Text>
-      </div>
-      <div
-        className={cn(
-          "flex min-h-0 flex-1 flex-col overflow-y-auto px-3 py-3",
-          scrollbarStyles,
-        )}
-      >
-        <SessionsList
-          sessions={sessions}
-          currentSessionId={currentSessionId}
-          isLoading={isLoading}
-          hasNextPage={hasNextPage}
-          isFetchingNextPage={isFetchingNextPage}
-          onSelectSession={onSelectSession}
-          onFetchNextPage={onFetchNextPage}
-        />
-      </div>
-      {hasActiveSession && (
-        <div className="shrink-0 bg-zinc-50 p-3 shadow-[0_-4px_6px_-1px_rgba(0,0,0,0.05)]">
-          <Button
-            variant="primary"
-            size="small"
-            onClick={onNewChat}
-            className="w-full"
-            leftIcon={<Plus width="1rem" height="1rem" />}
-          >
-            New Chat
-          </Button>
-        </div>
-      )}
-    </aside>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/components/MobileDrawer/MobileDrawer.tsx

@@ -1,91 +0,0 @@
-import type { SessionSummaryResponse } from "@/app/api/__generated__/models/sessionSummaryResponse";
-import { Button } from "@/components/atoms/Button/Button";
-import { scrollbarStyles } from "@/components/styles/scrollbars";
-import { cn } from "@/lib/utils";
-import { PlusIcon, X } from "@phosphor-icons/react";
-import { Drawer } from "vaul";
-import { SessionsList } from "../SessionsList/SessionsList";
-
-interface Props {
-  isOpen: boolean;
-  sessions: SessionSummaryResponse[];
-  currentSessionId: string | null;
-  isLoading: boolean;
-  hasNextPage: boolean;
-  isFetchingNextPage: boolean;
-  onSelectSession: (sessionId: string) => void;
-  onFetchNextPage: () => void;
-  onNewChat: () => void;
-  onClose: () => void;
-  onOpenChange: (open: boolean) => void;
-  hasActiveSession: boolean;
-}
-
-export function MobileDrawer({
-  isOpen,
-  sessions,
-  currentSessionId,
-  isLoading,
-  hasNextPage,
-  isFetchingNextPage,
-  onSelectSession,
-  onFetchNextPage,
-  onNewChat,
-  onClose,
-  onOpenChange,
-  hasActiveSession,
-}: Props) {
-  return (
-    <Drawer.Root open={isOpen} onOpenChange={onOpenChange} direction="left">
-      <Drawer.Portal>
-        <Drawer.Overlay className="fixed inset-0 z-[60] bg-black/10 backdrop-blur-sm" />
-        <Drawer.Content className="fixed left-0 top-0 z-[70] flex h-full w-80 flex-col border-r border-zinc-200 bg-zinc-50">
-          <div className="shrink-0 border-b border-zinc-200 p-4">
-            <div className="flex items-center justify-between">
-              <Drawer.Title className="text-lg font-semibold text-zinc-800">
-                Your chats
-              </Drawer.Title>
-              <Button
-                variant="icon"
-                size="icon"
-                aria-label="Close sessions"
-                onClick={onClose}
-              >
-                <X width="1.25rem" height="1.25rem" />
-              </Button>
-            </div>
-          </div>
-          <div
-            className={cn(
-              "flex min-h-0 flex-1 flex-col overflow-y-auto px-3 py-3",
-              scrollbarStyles,
-            )}
-          >
-            <SessionsList
-              sessions={sessions}
-              currentSessionId={currentSessionId}
-              isLoading={isLoading}
-              hasNextPage={hasNextPage}
-              isFetchingNextPage={isFetchingNextPage}
-              onSelectSession={onSelectSession}
-              onFetchNextPage={onFetchNextPage}
-            />
-          </div>
-          {hasActiveSession && (
-            <div className="shrink-0 bg-white p-3 shadow-[0_-4px_6px_-1px_rgba(0,0,0,0.05)]">
-              <Button
-                variant="primary"
-                size="small"
-                onClick={onNewChat}
-                className="w-full"
-                leftIcon={<PlusIcon width="1rem" height="1rem" />}
-              >
-                New Chat
-              </Button>
-            </div>
-          )}
-        </Drawer.Content>
-      </Drawer.Portal>
-    </Drawer.Root>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/components/MobileDrawer/useMobileDrawer.ts

@@ -1,24 +0,0 @@
-import { useState } from "react";
-
-export function useMobileDrawer() {
-  const [isDrawerOpen, setIsDrawerOpen] = useState(false);
-
-  const handleOpenDrawer = () => {
-    setIsDrawerOpen(true);
-  };
-
-  const handleCloseDrawer = () => {
-    setIsDrawerOpen(false);
-  };
-
-  const handleDrawerOpenChange = (open: boolean) => {
-    setIsDrawerOpen(open);
-  };
-
-  return {
-    isDrawerOpen,
-    handleOpenDrawer,
-    handleCloseDrawer,
-    handleDrawerOpenChange,
-  };
-}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/components/SessionsList/SessionsList.tsx

@@ -1,80 +0,0 @@
-import type { SessionSummaryResponse } from "@/app/api/__generated__/models/sessionSummaryResponse";
-import { Skeleton } from "@/components/__legacy__/ui/skeleton";
-import { Text } from "@/components/atoms/Text/Text";
-import { InfiniteList } from "@/components/molecules/InfiniteList/InfiniteList";
-import { cn } from "@/lib/utils";
-import { getSessionTitle } from "../../helpers";
-
-interface Props {
-  sessions: SessionSummaryResponse[];
-  currentSessionId: string | null;
-  isLoading: boolean;
-  hasNextPage: boolean;
-  isFetchingNextPage: boolean;
-  onSelectSession: (sessionId: string) => void;
-  onFetchNextPage: () => void;
-}
-
-export function SessionsList({
-  sessions,
-  currentSessionId,
-  isLoading,
-  hasNextPage,
-  isFetchingNextPage,
-  onSelectSession,
-  onFetchNextPage,
-}: Props) {
-  if (isLoading) {
-    return (
-      <div className="space-y-1">
-        {Array.from({ length: 5 }).map((_, i) => (
-          <div key={i} className="rounded-lg px-3 py-2.5">
-            <Skeleton className="h-5 w-full" />
-          </div>
-        ))}
-      </div>
-    );
-  }
-
-  if (sessions.length === 0) {
-    return (
-      <div className="flex h-full items-center justify-center">
-        <Text variant="body" className="text-zinc-500">
-          You don&apos;t have previous chats
-        </Text>
-      </div>
-    );
-  }
-
-  return (
-    <InfiniteList
-      items={sessions}
-      hasMore={hasNextPage}
-      isFetchingMore={isFetchingNextPage}
-      onEndReached={onFetchNextPage}
-      className="space-y-1"
-      renderItem={(session) => {
-        const isActive = session.id === currentSessionId;
-        return (
-          <button
-            onClick={() => onSelectSession(session.id)}
-            className={cn(
-              "w-full rounded-lg px-3 py-2.5 text-left transition-colors",
-              isActive ? "bg-zinc-100" : "hover:bg-zinc-50",
-            )}
-          >
-            <Text
-              variant="body"
-              className={cn(
-                "font-normal",
-                isActive ? "text-zinc-600" : "text-zinc-800",
-              )}
-            >
-              {getSessionTitle(session)}
-            </Text>
-          </button>
-        );
-      }}
-    />
-  );
-}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/components/SessionsList/useSessionsPagination.ts

@@ -1,91 +0,0 @@
-import { useGetV2ListSessions } from "@/app/api/__generated__/endpoints/chat/chat";
-import type { SessionSummaryResponse } from "@/app/api/__generated__/models/sessionSummaryResponse";
-import { okData } from "@/app/api/helpers";
-import { useEffect, useState } from "react";
-
-const PAGE_SIZE = 50;
-
-export interface UseSessionsPaginationArgs {
-  enabled: boolean;
-}
-
-export function useSessionsPagination({ enabled }: UseSessionsPaginationArgs) {
-  const [offset, setOffset] = useState(0);
-
-  const [accumulatedSessions, setAccumulatedSessions] = useState<
-    SessionSummaryResponse[]
-  >([]);
-
-  const [totalCount, setTotalCount] = useState<number | null>(null);
-
-  const { data, isLoading, isFetching, isError } = useGetV2ListSessions(
-    { limit: PAGE_SIZE, offset },
-    {
-      query: {
-        enabled: enabled && offset >= 0,
-      },
-    },
-  );
-
-  useEffect(() => {
-    const responseData = okData(data);
-    if (responseData) {
-      const newSessions = responseData.sessions;
-      const total = responseData.total;
-      setTotalCount(total);
-
-      if (offset === 0) {
-        setAccumulatedSessions(newSessions);
-      } else {
-        setAccumulatedSessions((prev) => [...prev, ...newSessions]);
-      }
-    } else if (!enabled) {
-      setAccumulatedSessions([]);
-      setTotalCount(null);
-    }
-  }, [data, offset, enabled]);
-
-  const hasNextPage =
-    totalCount !== null && accumulatedSessions.length < totalCount;
-
-  const areAllSessionsLoaded =
-    totalCount !== null &&
-    accumulatedSessions.length >= totalCount &&
-    !isFetching &&
-    !isLoading;
-
-  useEffect(() => {
-    if (
-      hasNextPage &&
-      !isFetching &&
-      !isLoading &&
-      !isError &&
-      totalCount !== null
-    ) {
-      setOffset((prev) => prev + PAGE_SIZE);
-    }
-  }, [hasNextPage, isFetching, isLoading, isError, totalCount]);
-
-  const fetchNextPage = () => {
-    if (hasNextPage && !isFetching) {
-      setOffset((prev) => prev + PAGE_SIZE);
-    }
-  };
-
-  const reset = () => {
-    // Only reset the offset - keep existing sessions visible during refetch
-    // The effect will replace sessions when new data arrives at offset 0
-    setOffset(0);
-  };
-
-  return {
-    sessions: accumulatedSessions,
-    isLoading,
-    isFetching,
-    hasNextPage,
-    areAllSessionsLoaded,
-    totalCount,
-    fetchNextPage,
-    reset,
-  };
-}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/helpers.ts

@@ -1,106 +0,0 @@
-import type { SessionDetailResponse } from "@/app/api/__generated__/models/sessionDetailResponse";
-import type { SessionSummaryResponse } from "@/app/api/__generated__/models/sessionSummaryResponse";
-import { format, formatDistanceToNow, isToday } from "date-fns";
-
-export function convertSessionDetailToSummary(session: SessionDetailResponse) {
-  return {
-    id: session.id,
-    created_at: session.created_at,
-    updated_at: session.updated_at,
-    title: undefined,
-  };
-}
-
-export function filterVisibleSessions(sessions: SessionSummaryResponse[]) {
-  const fiveMinutesAgo = Date.now() - 5 * 60 * 1000;
-  return sessions.filter((session) => {
-    const hasBeenUpdated = session.updated_at !== session.created_at;
-
-    if (hasBeenUpdated) return true;
-
-    const isRecentlyCreated =
-      new Date(session.created_at).getTime() > fiveMinutesAgo;
-
-    return isRecentlyCreated;
-  });
-}
-
-export function getSessionTitle(session: SessionSummaryResponse) {
-  if (session.title) return session.title;
-
-  const isNewSession = session.updated_at === session.created_at;
-
-  if (isNewSession) {
-    const createdDate = new Date(session.created_at);
-    if (isToday(createdDate)) {
-      return "Today";
-    }
-    return format(createdDate, "MMM d, yyyy");
-  }
-
-  return "Untitled Chat";
-}
-
-export function getSessionUpdatedLabel(session: SessionSummaryResponse) {
-  if (!session.updated_at) return "";
-  return formatDistanceToNow(new Date(session.updated_at), { addSuffix: true });
-}
-
-export function mergeCurrentSessionIntoList(
-  accumulatedSessions: SessionSummaryResponse[],
-  currentSessionId: string | null,
-  currentSessionData: SessionDetailResponse | null | undefined,
-  recentlyCreatedSessions?: Map<string, SessionSummaryResponse>,
-) {
-  const filteredSessions: SessionSummaryResponse[] = [];
-  const addedIds = new Set<string>();
-
-  if (accumulatedSessions.length > 0) {
-    const visibleSessions = filterVisibleSessions(accumulatedSessions);
-
-    if (currentSessionId) {
-      const currentInAll = accumulatedSessions.find(
-        (s) => s.id === currentSessionId,
-      );
-      if (currentInAll) {
-        const isInVisible = visibleSessions.some(
-          (s) => s.id === currentSessionId,
-        );
-        if (!isInVisible) {
-          filteredSessions.push(currentInAll);
-          addedIds.add(currentInAll.id);
-        }
-      }
-    }
-
-    for (const session of visibleSessions) {
-      if (!addedIds.has(session.id)) {
-        filteredSessions.push(session);
-        addedIds.add(session.id);
-      }
-    }
-  }
-
-  if (currentSessionId && currentSessionData) {
-    if (!addedIds.has(currentSessionId)) {
-      const summarySession = convertSessionDetailToSummary(currentSessionData);
-      filteredSessions.unshift(summarySession);
-      addedIds.add(currentSessionId);
-    }
-  }
-
-  if (recentlyCreatedSessions) {
-    for (const [sessionId, sessionData] of recentlyCreatedSessions) {
-      if (!addedIds.has(sessionId)) {
-        filteredSessions.unshift(sessionData);
-        addedIds.add(sessionId);
-      }
-    }
-  }
-
-  return filteredSessions;
-}
-
-export function getCurrentSessionId(searchParams: URLSearchParams) {
-  return searchParams.get("sessionId");
-}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/useCopilotShell.ts

@@ -1,124 +0,0 @@
-"use client";
-
-import {
-  getGetV2GetSessionQueryKey,
-  getGetV2ListSessionsQueryKey,
-  useGetV2GetSession,
-} from "@/app/api/__generated__/endpoints/chat/chat";
-import { okData } from "@/app/api/helpers";
-import { useChatStore } from "@/components/contextual/Chat/chat-store";
-import { useBreakpoint } from "@/lib/hooks/useBreakpoint";
-import { useSupabase } from "@/lib/supabase/hooks/useSupabase";
-import { useQueryClient } from "@tanstack/react-query";
-import { usePathname, useSearchParams } from "next/navigation";
-import { useCopilotStore } from "../../copilot-page-store";
-import { useCopilotSessionId } from "../../useCopilotSessionId";
-import { useMobileDrawer } from "./components/MobileDrawer/useMobileDrawer";
-import { getCurrentSessionId } from "./helpers";
-import { useShellSessionList } from "./useShellSessionList";
-
-export function useCopilotShell() {
-  const pathname = usePathname();
-  const searchParams = useSearchParams();
-  const queryClient = useQueryClient();
-  const breakpoint = useBreakpoint();
-  const { isLoggedIn } = useSupabase();
-  const isMobile =
-    breakpoint === "base" || breakpoint === "sm" || breakpoint === "md";
-
-  const { urlSessionId, setUrlSessionId } = useCopilotSessionId();
-
-  const isOnHomepage = pathname === "/copilot";
-  const paramSessionId = searchParams.get("sessionId");
-
-  const {
-    isDrawerOpen,
-    handleOpenDrawer,
-    handleCloseDrawer,
-    handleDrawerOpenChange,
-  } = useMobileDrawer();
-
-  const paginationEnabled = !isMobile || isDrawerOpen || !!paramSessionId;
-
-  const currentSessionId = getCurrentSessionId(searchParams);
-
-  const { data: currentSessionData } = useGetV2GetSession(
-    currentSessionId || "",
-    {
-      query: {
-        enabled: !!currentSessionId,
-        select: okData,
-      },
-    },
-  );
-
-  const {
-    sessions,
-    isLoading,
-    isSessionsFetching,
-    hasNextPage,
-    fetchNextPage,
-    resetPagination,
-    recentlyCreatedSessionsRef,
-  } = useShellSessionList({
-    paginationEnabled,
-    currentSessionId,
-    currentSessionData,
-    isOnHomepage,
-    paramSessionId,
-  });
-
-  const stopStream = useChatStore((s) => s.stopStream);
-  const isCreatingSession = useCopilotStore((s) => s.isCreatingSession);
-
-  function handleSessionClick(sessionId: string) {
-    if (sessionId === currentSessionId) return;
-
-    // Stop current stream - SSE reconnection allows resuming later
-    if (currentSessionId) {
-      stopStream(currentSessionId);
-    }
-
-    if (recentlyCreatedSessionsRef.current.has(sessionId)) {
-      queryClient.invalidateQueries({
-        queryKey: getGetV2GetSessionQueryKey(sessionId),
-      });
-    }
-    setUrlSessionId(sessionId, { shallow: false });
-    if (isMobile) handleCloseDrawer();
-  }
-
-  function handleNewChatClick() {
-    // Stop current stream - SSE reconnection allows resuming later
-    if (currentSessionId) {
-      stopStream(currentSessionId);
-    }
-
-    resetPagination();
-    queryClient.invalidateQueries({
-      queryKey: getGetV2ListSessionsQueryKey(),
-    });
-    setUrlSessionId(null, { shallow: false });
-    if (isMobile) handleCloseDrawer();
-  }
-
-  return {
-    isMobile,
-    isDrawerOpen,
-    isLoggedIn,
-    hasActiveSession:
-      Boolean(currentSessionId) && (!isOnHomepage || Boolean(paramSessionId)),
-    isLoading: isLoading || isCreatingSession,
-    isCreatingSession,
-    sessions,
-    currentSessionId: urlSessionId,
-    handleOpenDrawer,
-    handleCloseDrawer,
-    handleDrawerOpenChange,
-    handleNewChatClick,
-    handleSessionClick,
-    hasNextPage,
-    isFetchingNextPage: isSessionsFetching,
-    fetchNextPage,
-  };
-}

autogpt_platform/frontend/src/app/(platform)/copilot/components/CopilotShell/useShellSessionList.ts

@@ -1,113 +0,0 @@
-import { getGetV2ListSessionsQueryKey } from "@/app/api/__generated__/endpoints/chat/chat";
-import type { SessionDetailResponse } from "@/app/api/__generated__/models/sessionDetailResponse";
-import type { SessionSummaryResponse } from "@/app/api/__generated__/models/sessionSummaryResponse";
-import { useChatStore } from "@/components/contextual/Chat/chat-store";
-import { useQueryClient } from "@tanstack/react-query";
-import { useEffect, useMemo, useRef } from "react";
-import { useSessionsPagination } from "./components/SessionsList/useSessionsPagination";
-import {
-  convertSessionDetailToSummary,
-  filterVisibleSessions,
-  mergeCurrentSessionIntoList,
-} from "./helpers";
-
-interface UseShellSessionListArgs {
-  paginationEnabled: boolean;
-  currentSessionId: string | null;
-  currentSessionData: SessionDetailResponse | null | undefined;
-  isOnHomepage: boolean;
-  paramSessionId: string | null;
-}
-
-export function useShellSessionList({
-  paginationEnabled,
-  currentSessionId,
-  currentSessionData,
-  isOnHomepage,
-  paramSessionId,
-}: UseShellSessionListArgs) {
-  const queryClient = useQueryClient();
-  const onStreamComplete = useChatStore((s) => s.onStreamComplete);
-
-  const {
-    sessions: accumulatedSessions,
-    isLoading: isSessionsLoading,
-    isFetching: isSessionsFetching,
-    hasNextPage,
-    fetchNextPage,
-    reset: resetPagination,
-  } = useSessionsPagination({
-    enabled: paginationEnabled,
-  });
-
-  const recentlyCreatedSessionsRef = useRef<
-    Map<string, SessionSummaryResponse>
-  >(new Map());
-
-  useEffect(() => {
-    if (isOnHomepage && !paramSessionId) {
-      queryClient.invalidateQueries({
-        queryKey: getGetV2ListSessionsQueryKey(),
-      });
-    }
-  }, [isOnHomepage, paramSessionId, queryClient]);
-
-  useEffect(() => {
-    if (currentSessionId && currentSessionData) {
-      const isNewSession =
-        currentSessionData.updated_at === currentSessionData.created_at;
-      const isNotInAccumulated = !accumulatedSessions.some(
-        (s) => s.id === currentSessionId,
-      );
-      if (isNewSession || isNotInAccumulated) {
-        const summary = convertSessionDetailToSummary(currentSessionData);
-        recentlyCreatedSessionsRef.current.set(currentSessionId, summary);
-      }
-    }
-  }, [currentSessionId, currentSessionData, accumulatedSessions]);
-
-  useEffect(() => {
-    for (const sessionId of recentlyCreatedSessionsRef.current.keys()) {
-      if (accumulatedSessions.some((s) => s.id === sessionId)) {
-        recentlyCreatedSessionsRef.current.delete(sessionId);
-      }
-    }
-  }, [accumulatedSessions]);
-
-  useEffect(() => {
-    const unsubscribe = onStreamComplete(() => {
-      queryClient.invalidateQueries({
-        queryKey: getGetV2ListSessionsQueryKey(),
-      });
-    });
-    return unsubscribe;
-  }, [onStreamComplete, queryClient]);
-
-  const sessions = useMemo(
-    () =>
-      mergeCurrentSessionIntoList(
-        accumulatedSessions,
-        currentSessionId,
-        currentSessionData,
-        recentlyCreatedSessionsRef.current,
-      ),
-    [accumulatedSessions, currentSessionId, currentSessionData],
-  );
-
-  const visibleSessions = useMemo(
-    () => filterVisibleSessions(sessions),
-    [sessions],
-  );
-
-  const isLoading = isSessionsLoading && accumulatedSessions.length === 0;
-
-  return {
-    sessions: visibleSessions,
-    isLoading,
-    isSessionsFetching,
-    hasNextPage,
-    fetchNextPage,
-    resetPagination,
-    recentlyCreatedSessionsRef,
-  };
-}

autogpt_platform/frontend/src/app/(platform)/copilot/components/EmptySession/EmptySession.tsx

@@ -0,0 +1,111 @@
+"use client";
+
+import { ChatInput } from "@/app/(platform)/copilot/components/ChatInput/ChatInput";
+import { Button } from "@/components/atoms/Button/Button";
+import { Text } from "@/components/atoms/Text/Text";
+import { useSupabase } from "@/lib/supabase/hooks/useSupabase";
+import { SpinnerGapIcon } from "@phosphor-icons/react";
+import { motion } from "framer-motion";
+import { useEffect, useState } from "react";
+import {
+  getGreetingName,
+  getInputPlaceholder,
+  getQuickActions,
+} from "./helpers";
+
+interface Props {
+  inputLayoutId: string;
+  isCreatingSession: boolean;
+  onCreateSession: () => void | Promise<string>;
+  onSend: (message: string) => void | Promise<void>;
+}
+
+export function EmptySession({
+  inputLayoutId,
+  isCreatingSession,
+  onSend,
+}: Props) {
+  const { user } = useSupabase();
+  const greetingName = getGreetingName(user);
+  const quickActions = getQuickActions();
+  const [loadingAction, setLoadingAction] = useState<string | null>(null);
+  const [inputPlaceholder, setInputPlaceholder] = useState(
+    getInputPlaceholder(),
+  );
+
+  useEffect(() => {
+    setInputPlaceholder(getInputPlaceholder(window.innerWidth));
+  }, [window.innerWidth]);
+
+  async function handleQuickActionClick(action: string) {
+    if (isCreatingSession || loadingAction) return;
+
+    setLoadingAction(action);
+    try {
+      await onSend(action);
+    } finally {
+      setLoadingAction(null);
+    }
+  }
+
+  return (
+    <div className="flex h-full flex-1 items-center justify-center overflow-y-auto bg-[#f8f8f9] px-0 py-5 md:px-6 md:py-10">
+      <motion.div
+        className="w-full max-w-3xl text-center"
+        initial={{ opacity: 0 }}
+        animate={{ opacity: 1 }}
+        transition={{ duration: 0.3 }}
+      >
+        <div className="mx-auto max-w-3xl">
+          <Text variant="h3" className="mb-1 !text-[1.375rem] text-zinc-700">
+            Hey, <span className="text-violet-600">{greetingName}</span>
+          </Text>
+          <Text variant="h3" className="mb-8 !font-normal">
+            Tell me about your work — I&apos;ll find what to automate.
+          </Text>
+
+          <div className="mb-6">
+            <motion.div
+              layoutId={inputLayoutId}
+              transition={{ type: "spring", bounce: 0.2, duration: 0.65 }}
+              className="w-full px-2"
+            >
+              <ChatInput
+                inputId="chat-input-empty"
+                onSend={onSend}
+                disabled={isCreatingSession}
+                placeholder={inputPlaceholder}
+                className="w-full"
+              />
+            </motion.div>
+          </div>
+        </div>
+
+        <div className="flex flex-wrap items-center justify-center gap-3 overflow-x-auto [-ms-overflow-style:none] [scrollbar-width:none] [&::-webkit-scrollbar]:hidden">
+          {quickActions.map((action) => (
+            <Button
+              key={action}
+              type="button"
+              variant="outline"
+              size="small"
+              onClick={() => void handleQuickActionClick(action)}
+              disabled={isCreatingSession || loadingAction !== null}
+              aria-busy={loadingAction === action}
+              leftIcon={
+                loadingAction === action ? (
+                  <SpinnerGapIcon
+                    className="h-4 w-4 animate-spin"
+                    weight="bold"
+                  />
+                ) : null
+              }
+              className="h-auto shrink-0 border-zinc-300 px-3 py-2 text-[.9rem] text-zinc-600"
+            >
+              {action}
+            </Button>
+          ))}
+        </div>
+      </motion.div>
+    </div>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/EmptySession/helpers.ts

@@ -1,6 +1,26 @@
-import type { User } from "@supabase/supabase-js";
+import { User } from "@supabase/supabase-js";
 
-export function getGreetingName(user?: User | null): string {
+export function getInputPlaceholder(width?: number) {
+  if (!width) return "What's your role and what eats up most of your day?";
+
+  if (width < 500) {
+    return "I'm a chef and I hate...";
+  }
+  if (width <= 1080) {
+    return "What's your role and what eats up most of your day?";
+  }
+  return "What's your role and what eats up most of your day? e.g. 'I'm a recruiter and I hate...'";
+}
+
+export function getQuickActions() {
+  return [
+    "I don't know where to start, just ask me stuff",
+    "I do the same thing every week and it's killing me",
+    "Help me find where I'm wasting my time",
+  ];
+}
+
+export function getGreetingName(user?: User | null) {
   if (!user) return "there";
   const metadata = user.user_metadata as Record<string, unknown> | undefined;
   const fullName = metadata?.full_name;
@@ -16,30 +36,3 @@ export function getGreetingName(user?: User | null): string {
   }
   return "there";
 }
-
-export function buildCopilotChatUrl(prompt: string): string {
-  const trimmed = prompt.trim();
-  if (!trimmed) return "/copilot/chat";
-  const encoded = encodeURIComponent(trimmed);
-  return `/copilot/chat?prompt=${encoded}`;
-}
-
-export function getQuickActions(): string[] {
-  return [
-    "I don't know where to start, just ask me stuff",
-    "I do the same thing every week and it's killing me",
-    "Help me find where I'm wasting my time",
-  ];
-}
-
-export function getInputPlaceholder(width?: number) {
-  if (!width) return "What's your role and what eats up most of your day?";
-
-  if (width < 500) {
-    return "I'm a chef and I hate...";
-  }
-  if (width <= 1080) {
-    return "What's your role and what eats up most of your day?";
-  }
-  return "What's your role and what eats up most of your day? e.g. 'I'm a recruiter and I hate...'";
-}

autogpt_platform/frontend/src/app/(platform)/copilot/components/MobileDrawer/MobileDrawer.tsx

@@ -0,0 +1,140 @@
+import type { SessionSummaryResponse } from "@/app/api/__generated__/models/sessionSummaryResponse";
+import { Button } from "@/components/atoms/Button/Button";
+import { Text } from "@/components/atoms/Text/Text";
+import { scrollbarStyles } from "@/components/styles/scrollbars";
+import { cn } from "@/lib/utils";
+import { PlusIcon, SpinnerGapIcon, X } from "@phosphor-icons/react";
+import { Drawer } from "vaul";
+
+interface Props {
+  isOpen: boolean;
+  sessions: SessionSummaryResponse[];
+  currentSessionId: string | null;
+  isLoading: boolean;
+  onSelectSession: (sessionId: string) => void;
+  onNewChat: () => void;
+  onClose: () => void;
+  onOpenChange: (open: boolean) => void;
+}
+
+function formatDate(dateString: string) {
+  const date = new Date(dateString);
+  const now = new Date();
+  const diffMs = now.getTime() - date.getTime();
+  const diffDays = Math.floor(diffMs / (1000 * 60 * 60 * 24));
+
+  if (diffDays === 0) return "Today";
+  if (diffDays === 1) return "Yesterday";
+  if (diffDays < 7) return `${diffDays} days ago`;
+
+  const day = date.getDate();
+  const ordinal =
+    day % 10 === 1 && day !== 11
+      ? "st"
+      : day % 10 === 2 && day !== 12
+        ? "nd"
+        : day % 10 === 3 && day !== 13
+          ? "rd"
+          : "th";
+  const month = date.toLocaleDateString("en-US", { month: "short" });
+  const year = date.getFullYear();
+
+  return `${day}${ordinal} ${month} ${year}`;
+}
+
+export function MobileDrawer({
+  isOpen,
+  sessions,
+  currentSessionId,
+  isLoading,
+  onSelectSession,
+  onNewChat,
+  onClose,
+  onOpenChange,
+}: Props) {
+  return (
+    <Drawer.Root open={isOpen} onOpenChange={onOpenChange} direction="left">
+      <Drawer.Portal>
+        <Drawer.Overlay className="fixed inset-0 z-[60] bg-black/10 backdrop-blur-sm" />
+        <Drawer.Content className="fixed left-0 top-0 z-[70] flex h-full w-80 flex-col border-r border-zinc-200 bg-zinc-50">
+          <div className="shrink-0 border-b border-zinc-200 px-4 py-2">
+            <div className="flex items-center justify-between">
+              <Drawer.Title className="text-lg font-semibold text-zinc-800">
+                Your chats
+              </Drawer.Title>
+              <Button
+                variant="icon"
+                size="icon"
+                aria-label="Close sessions"
+                onClick={onClose}
+              >
+                <X width="1rem" height="1rem" />
+              </Button>
+            </div>
+          </div>
+          <div
+            className={cn(
+              "flex min-h-0 flex-1 flex-col gap-1 overflow-y-auto px-3 py-3",
+              scrollbarStyles,
+            )}
+          >
+            {isLoading ? (
+              <div className="flex items-center justify-center py-4">
+                <SpinnerGapIcon className="h-5 w-5 animate-spin text-neutral-400" />
+              </div>
+            ) : sessions.length === 0 ? (
+              <p className="py-4 text-center text-sm text-neutral-500">
+                No conversations yet
+              </p>
+            ) : (
+              sessions.map((session) => (
+                <button
+                  key={session.id}
+                  onClick={() => onSelectSession(session.id)}
+                  className={cn(
+                    "w-full rounded-lg px-3 py-2.5 text-left transition-colors",
+                    session.id === currentSessionId
+                      ? "bg-zinc-100"
+                      : "hover:bg-zinc-50",
+                  )}
+                >
+                  <div className="flex min-w-0 max-w-full flex-col overflow-hidden">
+                    <div className="min-w-0 max-w-full">
+                      <Text
+                        variant="body"
+                        className={cn(
+                          "truncate font-normal",
+                          session.id === currentSessionId
+                            ? "text-zinc-600"
+                            : "text-zinc-800",
+                        )}
+                      >
+                        {session.title || "Untitled chat"}
+                      </Text>
+                    </div>
+                    <Text variant="small" className="text-neutral-400">
+                      {formatDate(session.updated_at)}
+                    </Text>
+                  </div>
+                </button>
+              ))
+            )}
+          </div>
+          {currentSessionId && (
+            <div className="shrink-0 bg-white p-3 shadow-[0_-4px_6px_-1px_rgba(0,0,0,0.05)]">
+              <Button
+                variant="primary"
+                size="small"
+                onClick={onNewChat}
+                className="w-full"
+                leftIcon={<PlusIcon width="1rem" height="1rem" />}
+              >
+                New Chat
+              </Button>
+            </div>
+          )}
+        </Drawer.Content>
+      </Drawer.Portal>
+    </Drawer.Root>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/MorphingTextAnimation/MorphingTextAnimation.tsx

@@ -0,0 +1,54 @@
+import { cn } from "@/lib/utils";
+import { AnimatePresence, motion } from "framer-motion";
+
+interface Props {
+  text: string;
+  className?: string;
+}
+
+export function MorphingTextAnimation({ text, className }: Props) {
+  const letters = text.split("");
+
+  return (
+    <div className={cn(className)}>
+      <AnimatePresence mode="popLayout" initial={false}>
+        <motion.div key={text} className="whitespace-nowrap">
+          <motion.span className="inline-flex overflow-hidden">
+            {letters.map((char, index) => (
+              <motion.span
+                key={`${text}-${index}`}
+                initial={{
+                  opacity: 0,
+                  y: 8,
+                  rotateX: "80deg",
+                  filter: "blur(6px)",
+                }}
+                animate={{
+                  opacity: 1,
+                  y: 0,
+                  rotateX: "0deg",
+                  filter: "blur(0px)",
+                }}
+                exit={{
+                  opacity: 0,
+                  y: -8,
+                  rotateX: "-80deg",
+                  filter: "blur(6px)",
+                }}
+                style={{ willChange: "transform" }}
+                transition={{
+                  delay: 0.015 * index,
+                  type: "spring",
+                  bounce: 0.5,
+                }}
+                className="inline-block"
+              >
+                {char === " " ? "\u00A0" : char}
+              </motion.span>
+            ))}
+          </motion.span>
+        </motion.div>
+      </AnimatePresence>
+    </div>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/OrbitLoader/OrbitLoader.module.css

@@ -0,0 +1,69 @@
+.loader {
+  position: relative;
+  animation: rotate 1s infinite;
+}
+
+.loader::before,
+.loader::after {
+  border-radius: 50%;
+  content: "";
+  display: block;
+  /* 40% of container size */
+  height: 40%;
+  width: 40%;
+}
+
+.loader::before {
+  animation: ball1 1s infinite;
+  background-color: #a1a1aa; /* zinc-400 */
+  box-shadow: calc(var(--spacing)) 0 0 #18181b; /* zinc-900 */
+  margin-bottom: calc(var(--gap));
+}
+
+.loader::after {
+  animation: ball2 1s infinite;
+  background-color: #18181b; /* zinc-900 */
+  box-shadow: calc(var(--spacing)) 0 0 #a1a1aa; /* zinc-400 */
+}
+
+@keyframes rotate {
+  0% {
+    transform: rotate(0deg) scale(0.8);
+  }
+  50% {
+    transform: rotate(360deg) scale(1.2);
+  }
+  100% {
+    transform: rotate(720deg) scale(0.8);
+  }
+}
+
+@keyframes ball1 {
+  0% {
+    box-shadow: calc(var(--spacing)) 0 0 #18181b;
+  }
+  50% {
+    box-shadow: 0 0 0 #18181b;
+    margin-bottom: 0;
+    transform: translate(calc(var(--spacing) / 2), calc(var(--spacing) / 2));
+  }
+  100% {
+    box-shadow: calc(var(--spacing)) 0 0 #18181b;
+    margin-bottom: calc(var(--gap));
+  }
+}
+
+@keyframes ball2 {
+  0% {
+    box-shadow: calc(var(--spacing)) 0 0 #a1a1aa;
+  }
+  50% {
+    box-shadow: 0 0 0 #a1a1aa;
+    margin-top: calc(var(--ball-size) * -1);
+    transform: translate(calc(var(--spacing) / 2), calc(var(--spacing) / 2));
+  }
+  100% {
+    box-shadow: calc(var(--spacing)) 0 0 #a1a1aa;
+    margin-top: 0;
+  }
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/OrbitLoader/OrbitLoader.tsx

@@ -0,0 +1,28 @@
+import { cn } from "@/lib/utils";
+import styles from "./OrbitLoader.module.css";
+
+interface Props {
+  size?: number;
+  className?: string;
+}
+
+export function OrbitLoader({ size = 24, className }: Props) {
+  const ballSize = Math.round(size * 0.4);
+  const spacing = Math.round(size * 0.6);
+  const gap = Math.round(size * 0.2);
+
+  return (
+    <div
+      className={cn(styles.loader, className)}
+      style={
+        {
+          width: size,
+          height: size,
+          "--ball-size": `${ballSize}px`,
+          "--spacing": `${spacing}px`,
+          "--gap": `${gap}px`,
+        } as React.CSSProperties
+      }
+    />
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/ProgressBar/ProgressBar.tsx

@@ -0,0 +1,26 @@
+import { cn } from "@/lib/utils";
+
+interface Props {
+  value: number;
+  label?: string;
+  className?: string;
+}
+
+export function ProgressBar({ value, label, className }: Props) {
+  const clamped = Math.min(100, Math.max(0, value));
+
+  return (
+    <div className={cn("flex flex-col gap-1.5", className)}>
+      <div className="flex items-center justify-between text-xs text-neutral-500">
+        <span>{label ?? "Working on it..."}</span>
+        <span>{Math.round(clamped)}%</span>
+      </div>
+      <div className="h-2 w-full overflow-hidden rounded-full bg-neutral-200">
+        <div
+          className="h-full rounded-full bg-neutral-900 transition-[width] duration-300 ease-out"
+          style={{ width: `${clamped}%` }}
+        />
+      </div>
+    </div>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/PulseLoader/PulseLoader.module.css

@@ -0,0 +1,34 @@
+.loader {
+  position: relative;
+  display: inline-block;
+  flex-shrink: 0;
+}
+
+.loader::before,
+.loader::after {
+  content: "";
+  box-sizing: border-box;
+  width: 100%;
+  height: 100%;
+  border-radius: 50%;
+  background: currentColor;
+  position: absolute;
+  left: 0;
+  top: 0;
+  animation: ripple 2s linear infinite;
+}
+
+.loader::after {
+  animation-delay: 1s;
+}
+
+@keyframes ripple {
+  0% {
+    transform: scale(0);
+    opacity: 1;
+  }
+  100% {
+    transform: scale(1);
+    opacity: 0;
+  }
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/PulseLoader/PulseLoader.tsx

@@ -0,0 +1,16 @@
+import { cn } from "@/lib/utils";
+import styles from "./PulseLoader.module.css";
+
+interface Props {
+  size?: number;
+  className?: string;
+}
+
+export function PulseLoader({ size = 24, className }: Props) {
+  return (
+    <div
+      className={cn(styles.loader, className)}
+      style={{ width: size, height: size }}
+    />
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/ScaleLoader/ScaleLoader.module.css

@@ -0,0 +1,35 @@
+.loader {
+  width: 48px;
+  height: 48px;
+  display: inline-block;
+  position: relative;
+}
+
+.loader::after,
+.loader::before {
+  content: "";
+  box-sizing: border-box;
+  width: 100%;
+  height: 100%;
+  border-radius: 50%;
+  background: currentColor;
+  position: absolute;
+  left: 0;
+  top: 0;
+  animation: animloader 2s linear infinite;
+}
+
+.loader::after {
+  animation-delay: 1s;
+}
+
+@keyframes animloader {
+  0% {
+    transform: scale(0);
+    opacity: 1;
+  }
+  100% {
+    transform: scale(1);
+    opacity: 0;
+  }
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/ScaleLoader/ScaleLoader.tsx

@@ -0,0 +1,16 @@
+import { cn } from "@/lib/utils";
+import styles from "./ScaleLoader.module.css";
+
+interface Props {
+  size?: number;
+  className?: string;
+}
+
+export function ScaleLoader({ size = 48, className }: Props) {
+  return (
+    <div
+      className={cn(styles.loader, className)}
+      style={{ width: size, height: size }}
+    />
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/SpinnerLoader/SpinnerLoader.module.css

@@ -0,0 +1,57 @@
+.loader {
+  position: relative;
+  display: inline-block;
+  flex-shrink: 0;
+  transform: rotateZ(45deg);
+  perspective: 1000px;
+  border-radius: 50%;
+  color: currentColor;
+}
+
+.loader::before,
+.loader::after {
+  content: "";
+  display: block;
+  position: absolute;
+  top: 0;
+  left: 0;
+  width: inherit;
+  height: inherit;
+  border-radius: 50%;
+  transform: rotateX(70deg);
+  animation: spin 1s linear infinite;
+}
+
+.loader::after {
+  color: var(--spinner-accent, #a855f7);
+  transform: rotateY(70deg);
+  animation-delay: 0.4s;
+}
+
+@keyframes spin {
+  0%,
+  100% {
+    box-shadow: 0.2em 0 0 0 currentColor;
+  }
+  12% {
+    box-shadow: 0.2em 0.2em 0 0 currentColor;
+  }
+  25% {
+    box-shadow: 0 0.2em 0 0 currentColor;
+  }
+  37% {
+    box-shadow: -0.2em 0.2em 0 0 currentColor;
+  }
+  50% {
+    box-shadow: -0.2em 0 0 0 currentColor;
+  }
+  62% {
+    box-shadow: -0.2em -0.2em 0 0 currentColor;
+  }
+  75% {
+    box-shadow: 0 -0.2em 0 0 currentColor;
+  }
+  87% {
+    box-shadow: 0.2em -0.2em 0 0 currentColor;
+  }
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/SpinnerLoader/SpinnerLoader.tsx

@@ -0,0 +1,16 @@
+import { cn } from "@/lib/utils";
+import styles from "./SpinnerLoader.module.css";
+
+interface Props {
+  size?: number;
+  className?: string;
+}
+
+export function SpinnerLoader({ size = 24, className }: Props) {
+  return (
+    <div
+      className={cn(styles.loader, className)}
+      style={{ width: size, height: size }}
+    />
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/ToolAccordion/AccordionContent.tsx

@@ -0,0 +1,235 @@
+import { Link } from "@/components/atoms/Link/Link";
+import { Text } from "@/components/atoms/Text/Text";
+import { cn } from "@/lib/utils";
+
+/* ------------------------------------------------------------------ */
+/*  Layout                                                            */
+/* ------------------------------------------------------------------ */
+
+export function ContentGrid({
+  children,
+  className,
+}: {
+  children: React.ReactNode;
+  className?: string;
+}) {
+  return <div className={cn("grid gap-2", className)}>{children}</div>;
+}
+
+/* ------------------------------------------------------------------ */
+/*  Card                                                              */
+/* ------------------------------------------------------------------ */
+
+export function ContentCard({
+  children,
+  className,
+}: {
+  children: React.ReactNode;
+  className?: string;
+}) {
+  return (
+    <div
+      className={cn(
+        "rounded-lg bg-gradient-to-r from-purple-500/30 to-blue-500/30 p-[1px]",
+        className,
+      )}
+    >
+      <div className="rounded-lg bg-neutral-100 p-3">{children}</div>
+    </div>
+  );
+}
+
+/** Flex row with a left content area (`children`) and an optional right‑side `action`. */
+export function ContentCardHeader({
+  children,
+  action,
+  className,
+}: {
+  children: React.ReactNode;
+  action?: React.ReactNode;
+  className?: string;
+}) {
+  return (
+    <div className={cn("flex items-start justify-between gap-2", className)}>
+      <div className="min-w-0">{children}</div>
+      {action}
+    </div>
+  );
+}
+
+export function ContentCardTitle({
+  children,
+  className,
+}: {
+  children: React.ReactNode;
+  className?: string;
+}) {
+  return (
+    <Text
+      variant="body-medium"
+      className={cn("truncate text-zinc-800", className)}
+    >
+      {children}
+    </Text>
+  );
+}
+
+export function ContentCardSubtitle({
+  children,
+  className,
+}: {
+  children: React.ReactNode;
+  className?: string;
+}) {
+  return (
+    <Text
+      variant="small"
+      className={cn("mt-0.5 truncate font-mono text-zinc-800", className)}
+    >
+      {children}
+    </Text>
+  );
+}
+
+export function ContentCardDescription({
+  children,
+  className,
+}: {
+  children: React.ReactNode;
+  className?: string;
+}) {
+  return (
+    <Text variant="body" className={cn("mt-2 text-zinc-800", className)}>
+      {children}
+    </Text>
+  );
+}
+
+/* ------------------------------------------------------------------ */
+/*  Text                                                              */
+/* ------------------------------------------------------------------ */
+
+export function ContentMessage({
+  children,
+  className,
+}: {
+  children: React.ReactNode;
+  className?: string;
+}) {
+  return (
+    <Text variant="body" className={cn("text-zinc-800", className)}>
+      {children}
+    </Text>
+  );
+}
+
+export function ContentHint({
+  children,
+  className,
+}: {
+  children: React.ReactNode;
+  className?: string;
+}) {
+  return (
+    <Text variant="small" className={cn("text-neutral-500", className)}>
+      {children}
+    </Text>
+  );
+}
+
+/* ------------------------------------------------------------------ */
+/*  Code / data                                                       */
+/* ------------------------------------------------------------------ */
+
+export function ContentCodeBlock({
+  children,
+  className,
+}: {
+  children: React.ReactNode;
+  className?: string;
+}) {
+  return (
+    <pre
+      className={cn(
+        "whitespace-pre-wrap rounded-lg border bg-black p-3 text-xs text-neutral-200",
+        className,
+      )}
+    >
+      {children}
+    </pre>
+  );
+}
+
+/* ------------------------------------------------------------------ */
+/*  Inline elements                                                   */
+/* ------------------------------------------------------------------ */
+
+export function ContentBadge({
+  children,
+  className,
+}: {
+  children: React.ReactNode;
+  className?: string;
+}) {
+  return (
+    <Text
+      variant="small"
+      as="span"
+      className={cn(
+        "shrink-0 rounded-full border bg-muted px-2 py-0.5 text-[11px] text-zinc-800",
+        className,
+      )}
+    >
+      {children}
+    </Text>
+  );
+}
+
+export function ContentLink({
+  href,
+  children,
+  className,
+  ...rest
+}: Omit<React.ComponentProps<typeof Link>, "className"> & {
+  className?: string;
+}) {
+  return (
+    <Link
+      variant="primary"
+      isExternal
+      href={href}
+      className={cn("shrink-0 text-xs text-purple-500", className)}
+      {...rest}
+    >
+      {children}
+    </Link>
+  );
+}
+
+/* ------------------------------------------------------------------ */
+/*  Lists                                                             */
+/* ------------------------------------------------------------------ */
+
+export function ContentSuggestionsList({
+  items,
+  max = 5,
+  className,
+}: {
+  items: string[];
+  max?: number;
+  className?: string;
+}) {
+  if (items.length === 0) return null;
+  return (
+    <ul
+      className={cn(
+        "mt-2 list-disc space-y-1 pl-5 font-sans text-[0.75rem] leading-[1.125rem] text-zinc-800",
+        className,
+      )}
+    >
+      {items.slice(0, max).map((s) => (
+        <li key={s}>{s}</li>
+      ))}
+    </ul>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/ToolAccordion/ToolAccordion.tsx

@@ -0,0 +1,102 @@
+"use client";
+
+import { cn } from "@/lib/utils";
+import { CaretDownIcon } from "@phosphor-icons/react";
+import { AnimatePresence, motion, useReducedMotion } from "framer-motion";
+import { useId } from "react";
+import { useToolAccordion } from "./useToolAccordion";
+
+interface Props {
+  icon: React.ReactNode;
+  title: React.ReactNode;
+  titleClassName?: string;
+  description?: React.ReactNode;
+  children: React.ReactNode;
+  className?: string;
+  defaultExpanded?: boolean;
+  expanded?: boolean;
+  onExpandedChange?: (expanded: boolean) => void;
+}
+
+export function ToolAccordion({
+  icon,
+  title,
+  titleClassName,
+  description,
+  children,
+  className,
+  defaultExpanded,
+  expanded,
+  onExpandedChange,
+}: Props) {
+  const shouldReduceMotion = useReducedMotion();
+  const contentId = useId();
+  const { isExpanded, toggle } = useToolAccordion({
+    expanded,
+    defaultExpanded,
+    onExpandedChange,
+  });
+
+  return (
+    <div
+      className={cn(
+        "mt-2 w-full rounded-lg border border-slate-200 bg-slate-100 px-3 py-2",
+        className,
+      )}
+    >
+      <button
+        type="button"
+        aria-expanded={isExpanded}
+        aria-controls={contentId}
+        onClick={toggle}
+        className="flex w-full items-center justify-between gap-3 py-1 text-left"
+      >
+        <div className="flex min-w-0 items-center gap-3">
+          <span className="flex shrink-0 items-center text-gray-800">
+            {icon}
+          </span>
+          <div className="min-w-0">
+            <p
+              className={cn(
+                "truncate text-sm font-medium text-gray-800",
+                titleClassName,
+              )}
+            >
+              {title}
+            </p>
+            {description && (
+              <p className="truncate text-xs text-slate-800">{description}</p>
+            )}
+          </div>
+        </div>
+        <CaretDownIcon
+          className={cn(
+            "h-4 w-4 shrink-0 text-slate-500 transition-transform",
+            isExpanded && "rotate-180",
+          )}
+          weight="bold"
+        />
+      </button>
+
+      <AnimatePresence initial={false}>
+        {isExpanded && (
+          <motion.div
+            id={contentId}
+            initial={{ height: 0, opacity: 0, filter: "blur(10px)" }}
+            animate={{ height: "auto", opacity: 1, filter: "blur(0px)" }}
+            exit={{ height: 0, opacity: 0, filter: "blur(10px)" }}
+            transition={
+              shouldReduceMotion
+                ? { duration: 0 }
+                : { type: "spring", bounce: 0.35, duration: 0.55 }
+            }
+            className="overflow-hidden"
+            style={{ willChange: "height, opacity, filter" }}
+          >
+            <div className="pb-2 pt-3">{children}</div>
+          </motion.div>
+        )}
+      </AnimatePresence>
+    </div>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/components/ToolAccordion/useToolAccordion.ts

@@ -0,0 +1,32 @@
+import { useState } from "react";
+
+interface UseToolAccordionOptions {
+  expanded?: boolean;
+  defaultExpanded?: boolean;
+  onExpandedChange?: (expanded: boolean) => void;
+}
+
+interface UseToolAccordionResult {
+  isExpanded: boolean;
+  toggle: () => void;
+}
+
+export function useToolAccordion({
+  expanded,
+  defaultExpanded = false,
+  onExpandedChange,
+}: UseToolAccordionOptions): UseToolAccordionResult {
+  const [uncontrolledExpanded, setUncontrolledExpanded] =
+    useState(defaultExpanded);
+
+  const isControlled = typeof expanded === "boolean";
+  const isExpanded = isControlled ? expanded : uncontrolledExpanded;
+
+  function toggle() {
+    const next = !isExpanded;
+    if (!isControlled) setUncontrolledExpanded(next);
+    onExpandedChange?.(next);
+  }
+
+  return { isExpanded, toggle };
+}

autogpt_platform/frontend/src/app/(platform)/copilot/copilot-page-store.ts

@@ -1,56 +0,0 @@
-"use client";
-
-import { create } from "zustand";
-
-interface CopilotStoreState {
-  isStreaming: boolean;
-  isSwitchingSession: boolean;
-  isCreatingSession: boolean;
-  isInterruptModalOpen: boolean;
-  pendingAction: (() => void) | null;
-}
-
-interface CopilotStoreActions {
-  setIsStreaming: (isStreaming: boolean) => void;
-  setIsSwitchingSession: (isSwitchingSession: boolean) => void;
-  setIsCreatingSession: (isCreating: boolean) => void;
-  openInterruptModal: (onConfirm: () => void) => void;
-  confirmInterrupt: () => void;
-  cancelInterrupt: () => void;
-}
-
-type CopilotStore = CopilotStoreState & CopilotStoreActions;
-
-export const useCopilotStore = create<CopilotStore>((set, get) => ({
-  isStreaming: false,
-  isSwitchingSession: false,
-  isCreatingSession: false,
-  isInterruptModalOpen: false,
-  pendingAction: null,
-
-  setIsStreaming(isStreaming) {
-    set({ isStreaming });
-  },
-
-  setIsSwitchingSession(isSwitchingSession) {
-    set({ isSwitchingSession });
-  },
-
-  setIsCreatingSession(isCreatingSession) {
-    set({ isCreatingSession });
-  },
-
-  openInterruptModal(onConfirm) {
-    set({ isInterruptModalOpen: true, pendingAction: onConfirm });
-  },
-
-  confirmInterrupt() {
-    const { pendingAction } = get();
-    set({ isInterruptModalOpen: false, pendingAction: null });
-    if (pendingAction) pendingAction();
-  },
-
-  cancelInterrupt() {
-    set({ isInterruptModalOpen: false, pendingAction: null });
-  },
-}));

autogpt_platform/frontend/src/app/(platform)/copilot/helpers/convertChatSessionToUiMessages.ts

@@ -0,0 +1,128 @@
+import type { UIMessage, UIDataTypes, UITools } from "ai";
+
+interface SessionChatMessage {
+  role: string;
+  content: string | null;
+  tool_call_id: string | null;
+  tool_calls: unknown[] | null;
+}
+
+function coerceSessionChatMessages(
+  rawMessages: unknown[],
+): SessionChatMessage[] {
+  return rawMessages
+    .map((m) => {
+      if (!m || typeof m !== "object") return null;
+      const msg = m as Record<string, unknown>;
+
+      const role = typeof msg.role === "string" ? msg.role : null;
+      if (!role) return null;
+
+      return {
+        role,
+        content:
+          typeof msg.content === "string"
+            ? msg.content
+            : msg.content == null
+              ? null
+              : String(msg.content),
+        tool_call_id:
+          typeof msg.tool_call_id === "string"
+            ? msg.tool_call_id
+            : msg.tool_call_id == null
+              ? null
+              : String(msg.tool_call_id),
+        tool_calls: Array.isArray(msg.tool_calls) ? msg.tool_calls : null,
+      };
+    })
+    .filter((m): m is SessionChatMessage => m !== null);
+}
+
+function safeJsonParse(value: string): unknown {
+  try {
+    return JSON.parse(value) as unknown;
+  } catch {
+    return value;
+  }
+}
+
+function toToolInput(rawArguments: unknown): unknown {
+  if (typeof rawArguments === "string") {
+    const trimmed = rawArguments.trim();
+    return trimmed ? safeJsonParse(trimmed) : {};
+  }
+  if (rawArguments && typeof rawArguments === "object") return rawArguments;
+  return {};
+}
+
+export function convertChatSessionMessagesToUiMessages(
+  sessionId: string,
+  rawMessages: unknown[],
+): UIMessage<unknown, UIDataTypes, UITools>[] {
+  const messages = coerceSessionChatMessages(rawMessages);
+  const toolOutputsByCallId = new Map<string, unknown>();
+
+  for (const msg of messages) {
+    if (msg.role !== "tool") continue;
+    if (!msg.tool_call_id) continue;
+    if (msg.content == null) continue;
+    toolOutputsByCallId.set(msg.tool_call_id, msg.content);
+  }
+
+  const uiMessages: UIMessage<unknown, UIDataTypes, UITools>[] = [];
+
+  messages.forEach((msg, index) => {
+    if (msg.role === "tool") return;
+    if (msg.role !== "user" && msg.role !== "assistant") return;
+
+    const parts: UIMessage<unknown, UIDataTypes, UITools>["parts"] = [];
+
+    if (typeof msg.content === "string" && msg.content.trim()) {
+      parts.push({ type: "text", text: msg.content, state: "done" });
+    }
+
+    if (msg.role === "assistant" && Array.isArray(msg.tool_calls)) {
+      for (const rawToolCall of msg.tool_calls) {
+        if (!rawToolCall || typeof rawToolCall !== "object") continue;
+        const toolCall = rawToolCall as {
+          id?: unknown;
+          function?: { name?: unknown; arguments?: unknown };
+        };
+
+        const toolCallId = String(toolCall.id ?? "").trim();
+        const toolName = String(toolCall.function?.name ?? "").trim();
+        if (!toolCallId || !toolName) continue;
+
+        const input = toToolInput(toolCall.function?.arguments);
+        const output = toolOutputsByCallId.get(toolCallId);
+
+        if (output !== undefined) {
+          parts.push({
+            type: `tool-${toolName}`,
+            toolCallId,
+            state: "output-available",
+            input,
+            output: typeof output === "string" ? safeJsonParse(output) : output,
+          });
+        } else {
+          parts.push({
+            type: `tool-${toolName}`,
+            toolCallId,
+            state: "input-available",
+            input,
+          });
+        }
+      }
+    }
+
+    if (parts.length === 0) return;
+
+    uiMessages.push({
+      id: `${sessionId}-${index}`,
+      role: msg.role,
+      parts,
+    });
+  });
+
+  return uiMessages;
+}

autogpt_platform/frontend/src/app/(platform)/copilot/hooks/Untitled

@@ -7,4 +7,4 @@ export function useCopilotSessionId() {
   );
 
   return { urlSessionId, setUrlSessionId };
-}
+}

autogpt_platform/frontend/src/app/(platform)/copilot/hooks/useAsymptoticProgress.ts

@@ -5,17 +5,16 @@ import { useEffect, useRef, useState } from "react";
  * asymptotically approaching but never reaching the max value.
  *
  * Uses a half-life formula: progress = max * (1 - 0.5^(time/halfLife))
- * This creates the "game loading bar" effect where:
+ * This creates a "loading bar" effect where:
  * - 50% is reached at halfLifeSeconds
  * - 75% is reached at 2 * halfLifeSeconds
  * - 87.5% is reached at 3 * halfLifeSeconds
- * - and so on...
  *
  * @param isActive - Whether the progress should be animating
  * @param halfLifeSeconds - Time in seconds to reach 50% progress (default: 30)
  * @param maxProgress - Maximum progress value to approach (default: 100)
  * @param intervalMs - Update interval in milliseconds (default: 100)
- * @returns Current progress value (0-maxProgress)
+ * @returns Current progress value (0–maxProgress)
  */
 export function useAsymptoticProgress(
   isActive: boolean,
@@ -35,8 +34,6 @@ export function useAsymptoticProgress(
 
     const interval = setInterval(() => {
       elapsedTimeRef.current += intervalMs / 1000;
-      // Half-life approach: progress = max * (1 - 0.5^(time/halfLife))
-      // At t=halfLife: 50%, at t=2*halfLife: 75%, at t=3*halfLife: 87.5%, etc.
       const newProgress =
         maxProgress *
         (1 - Math.pow(0.5, elapsedTimeRef.current / halfLifeSeconds));

autogpt_platform/frontend/src/app/(platform)/copilot/layout.tsx

@@ -1,13 +0,0 @@
-"use client";
-import { FeatureFlagPage } from "@/services/feature-flags/FeatureFlagPage";
-import { Flag } from "@/services/feature-flags/use-get-flag";
-import { type ReactNode } from "react";
-import { CopilotShell } from "./components/CopilotShell/CopilotShell";
-
-export default function CopilotLayout({ children }: { children: ReactNode }) {
-  return (
-    <FeatureFlagPage flag={Flag.CHAT} whenDisabled="/library">
-      <CopilotShell>{children}</CopilotShell>
-    </FeatureFlagPage>
-  );
-}

autogpt_platform/frontend/src/app/(platform)/copilot/page.tsx

@@ -1,149 +1,13 @@
 "use client";
 
-import { Button } from "@/components/atoms/Button/Button";
-import { Skeleton } from "@/components/atoms/Skeleton/Skeleton";
-import { Text } from "@/components/atoms/Text/Text";
-import { Chat } from "@/components/contextual/Chat/Chat";
-import { ChatInput } from "@/components/contextual/Chat/components/ChatInput/ChatInput";
-import { Dialog } from "@/components/molecules/Dialog/Dialog";
-import { useEffect, useState } from "react";
-import { useCopilotStore } from "./copilot-page-store";
-import { getInputPlaceholder } from "./helpers";
-import { useCopilotPage } from "./useCopilotPage";
-
-export default function CopilotPage() {
-  const { state, handlers } = useCopilotPage();
-  const isInterruptModalOpen = useCopilotStore((s) => s.isInterruptModalOpen);
-  const confirmInterrupt = useCopilotStore((s) => s.confirmInterrupt);
-  const cancelInterrupt = useCopilotStore((s) => s.cancelInterrupt);
-
-  const [inputPlaceholder, setInputPlaceholder] = useState(
-    getInputPlaceholder(),
-  );
-
-  useEffect(() => {
-    const handleResize = () => {
-      setInputPlaceholder(getInputPlaceholder(window.innerWidth));
-    };
-
-    handleResize();
-
-    window.addEventListener("resize", handleResize);
-    return () => window.removeEventListener("resize", handleResize);
-  }, []);
-
-  const { greetingName, quickActions, isLoading, hasSession, initialPrompt } =
-    state;
-
-  const {
-    handleQuickAction,
-    startChatWithPrompt,
-    handleSessionNotFound,
-    handleStreamingChange,
-  } = handlers;
-
-  if (hasSession) {
-    return (
-      <div className="flex h-full flex-col">
-        <Chat
-          className="flex-1"
-          initialPrompt={initialPrompt}
-          onSessionNotFound={handleSessionNotFound}
-          onStreamingChange={handleStreamingChange}
-        />
-        <Dialog
-          title="Interrupt current chat?"
-          styling={{ maxWidth: 300, width: "100%" }}
-          controlled={{
-            isOpen: isInterruptModalOpen,
-            set: (open) => {
-              if (!open) cancelInterrupt();
-            },
-          }}
-          onClose={cancelInterrupt}
-        >
-          <Dialog.Content>
-            <div className="flex flex-col gap-4">
-              <Text variant="body">
-                The current chat response will be interrupted. Are you sure you
-                want to continue?
-              </Text>
-              <Dialog.Footer>
-                <Button
-                  type="button"
-                  variant="outline"
-                  onClick={cancelInterrupt}
-                >
-                  Cancel
-                </Button>
-                <Button
-                  type="button"
-                  variant="primary"
-                  onClick={confirmInterrupt}
-                >
-                  Continue
-                </Button>
-              </Dialog.Footer>
-            </div>
-          </Dialog.Content>
-        </Dialog>
-      </div>
-    );
-  }
+import { FeatureFlagPage } from "@/services/feature-flags/FeatureFlagPage";
+import { Flag } from "@/services/feature-flags/use-get-flag";
+import { CopilotPage } from "./CopilotPage";
 
+export default function Page() {
   return (
-    <div className="flex h-full flex-1 items-center justify-center overflow-y-auto bg-[#f8f8f9] px-3 py-5 md:px-6 md:py-10">
-      <div className="w-full text-center">
-        {isLoading ? (
-          <div className="mx-auto max-w-2xl">
-            <Skeleton className="mx-auto mb-3 h-8 w-64" />
-            <Skeleton className="mx-auto mb-8 h-6 w-80" />
-            <div className="mb-8">
-              <Skeleton className="mx-auto h-14 w-full rounded-lg" />
-            </div>
-            <div className="flex flex-wrap items-center justify-center gap-3">
-              {Array.from({ length: 4 }).map((_, i) => (
-                <Skeleton key={i} className="h-9 w-48 rounded-md" />
-              ))}
-            </div>
-          </div>
-        ) : (
-          <>
-            <div className="mx-auto max-w-3xl">
-              <Text
-                variant="h3"
-                className="mb-1 !text-[1.375rem] text-zinc-700"
-              >
-                Hey, <span className="text-violet-600">{greetingName}</span>
-              </Text>
-              <Text variant="h3" className="mb-8 !font-normal">
-                Tell me about your work — I&apos;ll find what to automate.
-              </Text>
-
-              <div className="mb-6">
-                <ChatInput
-                  onSend={startChatWithPrompt}
-                  placeholder={inputPlaceholder}
-                />
-              </div>
-            </div>
-            <div className="flex flex-wrap items-center justify-center gap-3 overflow-x-auto [-ms-overflow-style:none] [scrollbar-width:none] [&::-webkit-scrollbar]:hidden">
-              {quickActions.map((action) => (
-                <Button
-                  key={action}
-                  type="button"
-                  variant="outline"
-                  size="small"
-                  onClick={() => handleQuickAction(action)}
-                  className="h-auto shrink-0 border-zinc-300 px-3 py-2 text-[.9rem] text-zinc-600"
-                >
-                  {action}
-                </Button>
-              ))}
-            </div>
-          </>
-        )}
-      </div>
-    </div>
+    <FeatureFlagPage flag={Flag.CHAT} whenDisabled="/library">
+      <CopilotPage />
+    </FeatureFlagPage>
   );
 }

autogpt_platform/frontend/src/app/(platform)/copilot/tools/CreateAgent/CreateAgent.tsx

@@ -0,0 +1,237 @@
+"use client";
+
+import { WarningDiamondIcon } from "@phosphor-icons/react";
+import type { ToolUIPart } from "ai";
+import { useCopilotChatActions } from "../../components/CopilotChatActionsProvider/useCopilotChatActions";
+import { MorphingTextAnimation } from "../../components/MorphingTextAnimation/MorphingTextAnimation";
+import { OrbitLoader } from "../../components/OrbitLoader/OrbitLoader";
+import { ProgressBar } from "../../components/ProgressBar/ProgressBar";
+import {
+  ContentCardDescription,
+  ContentCodeBlock,
+  ContentGrid,
+  ContentHint,
+  ContentLink,
+  ContentMessage,
+} from "../../components/ToolAccordion/AccordionContent";
+import { ToolAccordion } from "../../components/ToolAccordion/ToolAccordion";
+import { useAsymptoticProgress } from "../../hooks/useAsymptoticProgress";
+import {
+  ClarificationQuestionsCard,
+  ClarifyingQuestion,
+} from "./components/ClarificationQuestionsCard";
+import {
+  AccordionIcon,
+  formatMaybeJson,
+  getAnimationText,
+  getCreateAgentToolOutput,
+  isAgentPreviewOutput,
+  isAgentSavedOutput,
+  isClarificationNeededOutput,
+  isErrorOutput,
+  isOperationInProgressOutput,
+  isOperationPendingOutput,
+  isOperationStartedOutput,
+  ToolIcon,
+  truncateText,
+  type CreateAgentToolOutput,
+} from "./helpers";
+
+export interface CreateAgentToolPart {
+  type: string;
+  toolCallId: string;
+  state: ToolUIPart["state"];
+  input?: unknown;
+  output?: unknown;
+}
+
+interface Props {
+  part: CreateAgentToolPart;
+}
+
+function getAccordionMeta(output: CreateAgentToolOutput): {
+  icon: React.ReactNode;
+  title: React.ReactNode;
+  titleClassName?: string;
+  description?: string;
+} {
+  const icon = <AccordionIcon />;
+
+  if (isAgentSavedOutput(output)) {
+    return { icon, title: output.agent_name };
+  }
+  if (isAgentPreviewOutput(output)) {
+    return {
+      icon,
+      title: output.agent_name,
+      description: `${output.node_count} block${output.node_count === 1 ? "" : "s"}`,
+    };
+  }
+  if (isClarificationNeededOutput(output)) {
+    const questions = output.questions ?? [];
+    return {
+      icon,
+      title: "Needs clarification",
+      description: `${questions.length} question${questions.length === 1 ? "" : "s"}`,
+    };
+  }
+  if (
+    isOperationStartedOutput(output) ||
+    isOperationPendingOutput(output) ||
+    isOperationInProgressOutput(output)
+  ) {
+    return {
+      icon: <OrbitLoader size={32} />,
+      title: "Creating agent, this may take a few minutes. Sit back and relax.",
+    };
+  }
+  return {
+    icon: (
+      <WarningDiamondIcon size={32} weight="light" className="text-red-500" />
+    ),
+    title: "Error",
+    titleClassName: "text-red-500",
+  };
+}
+
+export function CreateAgentTool({ part }: Props) {
+  const text = getAnimationText(part);
+  const { onSend } = useCopilotChatActions();
+  const isStreaming =
+    part.state === "input-streaming" || part.state === "input-available";
+
+  const output = getCreateAgentToolOutput(part);
+  const isError =
+    part.state === "output-error" || (!!output && isErrorOutput(output));
+  const isOperating =
+    !!output &&
+    (isOperationStartedOutput(output) ||
+      isOperationPendingOutput(output) ||
+      isOperationInProgressOutput(output));
+  const progress = useAsymptoticProgress(isOperating);
+  const hasExpandableContent =
+    part.state === "output-available" &&
+    !!output &&
+    (isOperationStartedOutput(output) ||
+      isOperationPendingOutput(output) ||
+      isOperationInProgressOutput(output) ||
+      isAgentPreviewOutput(output) ||
+      isAgentSavedOutput(output) ||
+      isClarificationNeededOutput(output) ||
+      isErrorOutput(output));
+
+  function handleClarificationAnswers(answers: Record<string, string>) {
+    const questions =
+      output && isClarificationNeededOutput(output)
+        ? (output.questions ?? [])
+        : [];
+
+    const contextMessage = questions
+      .map((q) => {
+        const answer = answers[q.keyword] || "";
+        return `> ${q.question}\n\n${answer}`;
+      })
+      .join("\n\n");
+
+    onSend(
+      `**Here are my answers:**\n\n${contextMessage}\n\nPlease proceed with creating the agent.`,
+    );
+  }
+
+  return (
+    <div className="py-2">
+      <div className="flex items-center gap-2 text-sm text-muted-foreground">
+        <ToolIcon isStreaming={isStreaming} isError={isError} />
+        <MorphingTextAnimation
+          text={text}
+          className={isError ? "text-red-500" : undefined}
+        />
+      </div>
+
+      {hasExpandableContent && output && (
+        <ToolAccordion
+          {...getAccordionMeta(output)}
+          defaultExpanded={isOperating || isClarificationNeededOutput(output)}
+        >
+          {isOperating && (
+            <ContentGrid>
+              <ProgressBar value={progress} />
+              <ContentHint>
+                This could take a few minutes, grab a coffee ☕
+              </ContentHint>
+            </ContentGrid>
+          )}
+
+          {isAgentSavedOutput(output) && (
+            <ContentGrid>
+              <ContentMessage>{output.message}</ContentMessage>
+              <div className="flex flex-wrap gap-2">
+                <ContentLink href={output.library_agent_link}>
+                  Open in library
+                </ContentLink>
+                <ContentLink href={output.agent_page_link}>
+                  Open in builder
+                </ContentLink>
+              </div>
+              <ContentCodeBlock>
+                {truncateText(
+                  formatMaybeJson({ agent_id: output.agent_id }),
+                  800,
+                )}
+              </ContentCodeBlock>
+            </ContentGrid>
+          )}
+
+          {isAgentPreviewOutput(output) && (
+            <ContentGrid>
+              <ContentMessage>{output.message}</ContentMessage>
+              {output.description?.trim() && (
+                <ContentCardDescription>
+                  {output.description}
+                </ContentCardDescription>
+              )}
+              <ContentCodeBlock>
+                {truncateText(formatMaybeJson(output.agent_json), 1600)}
+              </ContentCodeBlock>
+            </ContentGrid>
+          )}
+
+          {isClarificationNeededOutput(output) && (
+            <ClarificationQuestionsCard
+              questions={(output.questions ?? []).map((q) => {
+                const item: ClarifyingQuestion = {
+                  question: q.question,
+                  keyword: q.keyword,
+                };
+                const example =
+                  typeof q.example === "string" && q.example.trim()
+                    ? q.example.trim()
+                    : null;
+                if (example) item.example = example;
+                return item;
+              })}
+              message={output.message}
+              onSubmitAnswers={handleClarificationAnswers}
+            />
+          )}
+
+          {isErrorOutput(output) && (
+            <ContentGrid>
+              <ContentMessage>{output.message}</ContentMessage>
+              {output.error && (
+                <ContentCodeBlock>
+                  {formatMaybeJson(output.error)}
+                </ContentCodeBlock>
+              )}
+              {output.details && (
+                <ContentCodeBlock>
+                  {formatMaybeJson(output.details)}
+                </ContentCodeBlock>
+              )}
+            </ContentGrid>
+          )}
+        </ToolAccordion>
+      )}
+    </div>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/CreateAgent/components/ClarificationQuestionsCard.tsx

@@ -6,7 +6,7 @@ import { Input } from "@/components/atoms/Input/Input";
 import { Text } from "@/components/atoms/Text/Text";
 import { cn } from "@/lib/utils";
 import { CheckCircleIcon, QuestionIcon } from "@phosphor-icons/react";
-import { useState, useEffect, useRef } from "react";
+import { useEffect, useRef, useState } from "react";
 
 export interface ClarifyingQuestion {
   question: string;
@@ -24,12 +24,7 @@ interface Props {
   className?: string;
 }
 
-function getStorageKey(sessionId?: string): string | null {
-  if (!sessionId) return null;
-  return `clarification_answers_${sessionId}`;
-}
-
-export function ClarificationQuestionsWidget({
+export function ClarificationQuestionsCard({
   questions,
   message,
   sessionId,
@@ -241,3 +236,8 @@ export function ClarificationQuestionsWidget({
     </div>
   );
 }
+
+function getStorageKey(sessionId?: string): string | null {
+  if (!sessionId) return null;
+  return `clarification_answers_${sessionId}`;
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/CreateAgent/helpers.tsx

@@ -0,0 +1,186 @@
+import type { AgentPreviewResponse } from "@/app/api/__generated__/models/agentPreviewResponse";
+import type { AgentSavedResponse } from "@/app/api/__generated__/models/agentSavedResponse";
+import type { ClarificationNeededResponse } from "@/app/api/__generated__/models/clarificationNeededResponse";
+import type { ErrorResponse } from "@/app/api/__generated__/models/errorResponse";
+import type { OperationInProgressResponse } from "@/app/api/__generated__/models/operationInProgressResponse";
+import type { OperationPendingResponse } from "@/app/api/__generated__/models/operationPendingResponse";
+import type { OperationStartedResponse } from "@/app/api/__generated__/models/operationStartedResponse";
+import { ResponseType } from "@/app/api/__generated__/models/responseType";
+import {
+  PlusCircleIcon,
+  PlusIcon,
+  WarningDiamondIcon,
+} from "@phosphor-icons/react";
+import type { ToolUIPart } from "ai";
+import { OrbitLoader } from "../../components/OrbitLoader/OrbitLoader";
+
+export type CreateAgentToolOutput =
+  | OperationStartedResponse
+  | OperationPendingResponse
+  | OperationInProgressResponse
+  | AgentPreviewResponse
+  | AgentSavedResponse
+  | ClarificationNeededResponse
+  | ErrorResponse;
+
+function parseOutput(output: unknown): CreateAgentToolOutput | null {
+  if (!output) return null;
+  if (typeof output === "string") {
+    const trimmed = output.trim();
+    if (!trimmed) return null;
+    try {
+      return parseOutput(JSON.parse(trimmed) as unknown);
+    } catch {
+      return null;
+    }
+  }
+  if (typeof output === "object") {
+    const type = (output as { type?: unknown }).type;
+    if (
+      type === ResponseType.operation_started ||
+      type === ResponseType.operation_pending ||
+      type === ResponseType.operation_in_progress ||
+      type === ResponseType.agent_preview ||
+      type === ResponseType.agent_saved ||
+      type === ResponseType.clarification_needed ||
+      type === ResponseType.error
+    ) {
+      return output as CreateAgentToolOutput;
+    }
+    if ("operation_id" in output && "tool_name" in output)
+      return output as OperationStartedResponse | OperationPendingResponse;
+    if ("tool_call_id" in output) return output as OperationInProgressResponse;
+    if ("agent_json" in output && "agent_name" in output)
+      return output as AgentPreviewResponse;
+    if ("agent_id" in output && "library_agent_id" in output)
+      return output as AgentSavedResponse;
+    if ("questions" in output) return output as ClarificationNeededResponse;
+    if ("error" in output || "details" in output)
+      return output as ErrorResponse;
+  }
+  return null;
+}
+
+export function getCreateAgentToolOutput(
+  part: unknown,
+): CreateAgentToolOutput | null {
+  if (!part || typeof part !== "object") return null;
+  return parseOutput((part as { output?: unknown }).output);
+}
+
+export function isOperationStartedOutput(
+  output: CreateAgentToolOutput,
+): output is OperationStartedResponse {
+  return (
+    output.type === ResponseType.operation_started ||
+    ("operation_id" in output && "tool_name" in output)
+  );
+}
+
+export function isOperationPendingOutput(
+  output: CreateAgentToolOutput,
+): output is OperationPendingResponse {
+  return output.type === ResponseType.operation_pending;
+}
+
+export function isOperationInProgressOutput(
+  output: CreateAgentToolOutput,
+): output is OperationInProgressResponse {
+  return (
+    output.type === ResponseType.operation_in_progress ||
+    "tool_call_id" in output
+  );
+}
+
+export function isAgentPreviewOutput(
+  output: CreateAgentToolOutput,
+): output is AgentPreviewResponse {
+  return output.type === ResponseType.agent_preview || "agent_json" in output;
+}
+
+export function isAgentSavedOutput(
+  output: CreateAgentToolOutput,
+): output is AgentSavedResponse {
+  return (
+    output.type === ResponseType.agent_saved || "agent_page_link" in output
+  );
+}
+
+export function isClarificationNeededOutput(
+  output: CreateAgentToolOutput,
+): output is ClarificationNeededResponse {
+  return (
+    output.type === ResponseType.clarification_needed || "questions" in output
+  );
+}
+
+export function isErrorOutput(
+  output: CreateAgentToolOutput,
+): output is ErrorResponse {
+  return output.type === ResponseType.error || "error" in output;
+}
+
+export function getAnimationText(part: {
+  state: ToolUIPart["state"];
+  input?: unknown;
+  output?: unknown;
+}): string {
+  switch (part.state) {
+    case "input-streaming":
+    case "input-available":
+      return "Creating a new agent";
+    case "output-available": {
+      const output = parseOutput(part.output);
+      if (!output) return "Creating a new agent";
+      if (isOperationStartedOutput(output)) return "Agent creation started";
+      if (isOperationPendingOutput(output)) return "Agent creation in progress";
+      if (isOperationInProgressOutput(output))
+        return "Agent creation already in progress";
+      if (isAgentSavedOutput(output)) return `Saved "${output.agent_name}"`;
+      if (isAgentPreviewOutput(output)) return `Preview "${output.agent_name}"`;
+      if (isClarificationNeededOutput(output)) return "Needs clarification";
+      return "Error creating agent";
+    }
+    case "output-error":
+      return "Error creating agent";
+    default:
+      return "Creating a new agent";
+  }
+}
+
+export function ToolIcon({
+  isStreaming,
+  isError,
+}: {
+  isStreaming?: boolean;
+  isError?: boolean;
+}) {
+  if (isError) {
+    return (
+      <WarningDiamondIcon size={14} weight="regular" className="text-red-500" />
+    );
+  }
+  if (isStreaming) {
+    return <OrbitLoader size={24} />;
+  }
+  return <PlusIcon size={14} weight="regular" className="text-neutral-400" />;
+}
+
+export function AccordionIcon() {
+  return <PlusCircleIcon size={32} weight="light" />;
+}
+
+export function formatMaybeJson(value: unknown): string {
+  if (typeof value === "string") return value;
+  try {
+    return JSON.stringify(value, null, 2);
+  } catch {
+    return String(value);
+  }
+}
+
+export function truncateText(text: string, maxChars: number): string {
+  const trimmed = text.trim();
+  if (trimmed.length <= maxChars) return trimmed;
+  return `${trimmed.slice(0, maxChars).trimEnd()}…`;
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/EditAgent/EditAgent.tsx

@@ -0,0 +1,234 @@
+"use client";
+
+import { WarningDiamondIcon } from "@phosphor-icons/react";
+import type { ToolUIPart } from "ai";
+import { useCopilotChatActions } from "../../components/CopilotChatActionsProvider/useCopilotChatActions";
+import { MorphingTextAnimation } from "../../components/MorphingTextAnimation/MorphingTextAnimation";
+import { OrbitLoader } from "../../components/OrbitLoader/OrbitLoader";
+import { ProgressBar } from "../../components/ProgressBar/ProgressBar";
+import {
+  ContentCardDescription,
+  ContentCodeBlock,
+  ContentGrid,
+  ContentHint,
+  ContentLink,
+  ContentMessage,
+} from "../../components/ToolAccordion/AccordionContent";
+import { ToolAccordion } from "../../components/ToolAccordion/ToolAccordion";
+import { useAsymptoticProgress } from "../../hooks/useAsymptoticProgress";
+import {
+  ClarificationQuestionsCard,
+  ClarifyingQuestion,
+} from "../CreateAgent/components/ClarificationQuestionsCard";
+import {
+  AccordionIcon,
+  formatMaybeJson,
+  getAnimationText,
+  getEditAgentToolOutput,
+  isAgentPreviewOutput,
+  isAgentSavedOutput,
+  isClarificationNeededOutput,
+  isErrorOutput,
+  isOperationInProgressOutput,
+  isOperationPendingOutput,
+  isOperationStartedOutput,
+  ToolIcon,
+  truncateText,
+  type EditAgentToolOutput,
+} from "./helpers";
+
+export interface EditAgentToolPart {
+  type: string;
+  toolCallId: string;
+  state: ToolUIPart["state"];
+  input?: unknown;
+  output?: unknown;
+}
+
+interface Props {
+  part: EditAgentToolPart;
+}
+
+function getAccordionMeta(output: EditAgentToolOutput): {
+  icon: React.ReactNode;
+  title: string;
+  titleClassName?: string;
+  description?: string;
+} {
+  const icon = <AccordionIcon />;
+
+  if (isAgentSavedOutput(output)) {
+    return { icon, title: output.agent_name };
+  }
+  if (isAgentPreviewOutput(output)) {
+    return {
+      icon,
+      title: output.agent_name,
+      description: `${output.node_count} block${output.node_count === 1 ? "" : "s"}`,
+    };
+  }
+  if (isClarificationNeededOutput(output)) {
+    const questions = output.questions ?? [];
+    return {
+      icon,
+      title: "Needs clarification",
+      description: `${questions.length} question${questions.length === 1 ? "" : "s"}`,
+    };
+  }
+  if (
+    isOperationStartedOutput(output) ||
+    isOperationPendingOutput(output) ||
+    isOperationInProgressOutput(output)
+  ) {
+    return { icon: <OrbitLoader size={32} />, title: "Editing agent" };
+  }
+  return {
+    icon: (
+      <WarningDiamondIcon size={32} weight="light" className="text-red-500" />
+    ),
+    title: "Error",
+    titleClassName: "text-red-500",
+  };
+}
+
+export function EditAgentTool({ part }: Props) {
+  const text = getAnimationText(part);
+  const { onSend } = useCopilotChatActions();
+  const isStreaming =
+    part.state === "input-streaming" || part.state === "input-available";
+
+  const output = getEditAgentToolOutput(part);
+  const isError =
+    part.state === "output-error" || (!!output && isErrorOutput(output));
+  const isOperating =
+    !!output &&
+    (isOperationStartedOutput(output) ||
+      isOperationPendingOutput(output) ||
+      isOperationInProgressOutput(output));
+  const progress = useAsymptoticProgress(isOperating);
+  const hasExpandableContent =
+    part.state === "output-available" &&
+    !!output &&
+    (isOperationStartedOutput(output) ||
+      isOperationPendingOutput(output) ||
+      isOperationInProgressOutput(output) ||
+      isAgentPreviewOutput(output) ||
+      isAgentSavedOutput(output) ||
+      isClarificationNeededOutput(output) ||
+      isErrorOutput(output));
+
+  function handleClarificationAnswers(answers: Record<string, string>) {
+    const questions =
+      output && isClarificationNeededOutput(output)
+        ? (output.questions ?? [])
+        : [];
+
+    const contextMessage = questions
+      .map((q) => {
+        const answer = answers[q.keyword] || "";
+        return `> ${q.question}\n\n${answer}`;
+      })
+      .join("\n\n");
+
+    onSend(
+      `**Here are my answers:**\n\n${contextMessage}\n\nPlease proceed with editing the agent.`,
+    );
+  }
+
+  return (
+    <div className="py-2">
+      <div className="flex items-center gap-2 text-sm text-muted-foreground">
+        <ToolIcon isStreaming={isStreaming} isError={isError} />
+        <MorphingTextAnimation
+          text={text}
+          className={isError ? "text-red-500" : undefined}
+        />
+      </div>
+
+      {hasExpandableContent && output && (
+        <ToolAccordion
+          {...getAccordionMeta(output)}
+          defaultExpanded={isOperating || isClarificationNeededOutput(output)}
+        >
+          {isOperating && (
+            <ContentGrid>
+              <ProgressBar value={progress} className="max-w-[280px]" />
+              <ContentHint>
+                This could take a few minutes, grab a coffee ☕
+              </ContentHint>
+            </ContentGrid>
+          )}
+
+          {isAgentSavedOutput(output) && (
+            <ContentGrid>
+              <ContentMessage>{output.message}</ContentMessage>
+              <div className="flex flex-wrap gap-2">
+                <ContentLink href={output.library_agent_link}>
+                  Open in library
+                </ContentLink>
+                <ContentLink href={output.agent_page_link}>
+                  Open in builder
+                </ContentLink>
+              </div>
+              <ContentCodeBlock>
+                {truncateText(
+                  formatMaybeJson({ agent_id: output.agent_id }),
+                  800,
+                )}
+              </ContentCodeBlock>
+            </ContentGrid>
+          )}
+
+          {isAgentPreviewOutput(output) && (
+            <ContentGrid>
+              <ContentMessage>{output.message}</ContentMessage>
+              {output.description?.trim() && (
+                <ContentCardDescription>
+                  {output.description}
+                </ContentCardDescription>
+              )}
+              <ContentCodeBlock>
+                {truncateText(formatMaybeJson(output.agent_json), 1600)}
+              </ContentCodeBlock>
+            </ContentGrid>
+          )}
+
+          {isClarificationNeededOutput(output) && (
+            <ClarificationQuestionsCard
+              questions={(output.questions ?? []).map((q) => {
+                const item: ClarifyingQuestion = {
+                  question: q.question,
+                  keyword: q.keyword,
+                };
+                const example =
+                  typeof q.example === "string" && q.example.trim()
+                    ? q.example.trim()
+                    : null;
+                if (example) item.example = example;
+                return item;
+              })}
+              message={output.message}
+              onSubmitAnswers={handleClarificationAnswers}
+            />
+          )}
+
+          {isErrorOutput(output) && (
+            <ContentGrid>
+              <ContentMessage>{output.message}</ContentMessage>
+              {output.error && (
+                <ContentCodeBlock>
+                  {formatMaybeJson(output.error)}
+                </ContentCodeBlock>
+              )}
+              {output.details && (
+                <ContentCodeBlock>
+                  {formatMaybeJson(output.details)}
+                </ContentCodeBlock>
+              )}
+            </ContentGrid>
+          )}
+        </ToolAccordion>
+      )}
+    </div>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/EditAgent/helpers.tsx

@@ -0,0 +1,188 @@
+import type { AgentPreviewResponse } from "@/app/api/__generated__/models/agentPreviewResponse";
+import type { AgentSavedResponse } from "@/app/api/__generated__/models/agentSavedResponse";
+import type { ClarificationNeededResponse } from "@/app/api/__generated__/models/clarificationNeededResponse";
+import type { ErrorResponse } from "@/app/api/__generated__/models/errorResponse";
+import type { OperationInProgressResponse } from "@/app/api/__generated__/models/operationInProgressResponse";
+import type { OperationPendingResponse } from "@/app/api/__generated__/models/operationPendingResponse";
+import type { OperationStartedResponse } from "@/app/api/__generated__/models/operationStartedResponse";
+import { ResponseType } from "@/app/api/__generated__/models/responseType";
+import {
+  NotePencilIcon,
+  PencilLineIcon,
+  WarningDiamondIcon,
+} from "@phosphor-icons/react";
+import type { ToolUIPart } from "ai";
+import { OrbitLoader } from "../../components/OrbitLoader/OrbitLoader";
+
+export type EditAgentToolOutput =
+  | OperationStartedResponse
+  | OperationPendingResponse
+  | OperationInProgressResponse
+  | AgentPreviewResponse
+  | AgentSavedResponse
+  | ClarificationNeededResponse
+  | ErrorResponse;
+
+function parseOutput(output: unknown): EditAgentToolOutput | null {
+  if (!output) return null;
+  if (typeof output === "string") {
+    const trimmed = output.trim();
+    if (!trimmed) return null;
+    try {
+      return parseOutput(JSON.parse(trimmed) as unknown);
+    } catch {
+      return null;
+    }
+  }
+  if (typeof output === "object") {
+    const type = (output as { type?: unknown }).type;
+    if (
+      type === ResponseType.operation_started ||
+      type === ResponseType.operation_pending ||
+      type === ResponseType.operation_in_progress ||
+      type === ResponseType.agent_preview ||
+      type === ResponseType.agent_saved ||
+      type === ResponseType.clarification_needed ||
+      type === ResponseType.error
+    ) {
+      return output as EditAgentToolOutput;
+    }
+    if ("operation_id" in output && "tool_name" in output)
+      return output as OperationStartedResponse | OperationPendingResponse;
+    if ("tool_call_id" in output) return output as OperationInProgressResponse;
+    if ("agent_json" in output && "agent_name" in output)
+      return output as AgentPreviewResponse;
+    if ("agent_id" in output && "library_agent_id" in output)
+      return output as AgentSavedResponse;
+    if ("questions" in output) return output as ClarificationNeededResponse;
+    if ("error" in output || "details" in output)
+      return output as ErrorResponse;
+  }
+  return null;
+}
+
+export function getEditAgentToolOutput(
+  part: unknown,
+): EditAgentToolOutput | null {
+  if (!part || typeof part !== "object") return null;
+  return parseOutput((part as { output?: unknown }).output);
+}
+
+export function isOperationStartedOutput(
+  output: EditAgentToolOutput,
+): output is OperationStartedResponse {
+  return (
+    output.type === ResponseType.operation_started ||
+    ("operation_id" in output && "tool_name" in output)
+  );
+}
+
+export function isOperationPendingOutput(
+  output: EditAgentToolOutput,
+): output is OperationPendingResponse {
+  return output.type === ResponseType.operation_pending;
+}
+
+export function isOperationInProgressOutput(
+  output: EditAgentToolOutput,
+): output is OperationInProgressResponse {
+  return (
+    output.type === ResponseType.operation_in_progress ||
+    "tool_call_id" in output
+  );
+}
+
+export function isAgentPreviewOutput(
+  output: EditAgentToolOutput,
+): output is AgentPreviewResponse {
+  return output.type === ResponseType.agent_preview || "agent_json" in output;
+}
+
+export function isAgentSavedOutput(
+  output: EditAgentToolOutput,
+): output is AgentSavedResponse {
+  return (
+    output.type === ResponseType.agent_saved || "agent_page_link" in output
+  );
+}
+
+export function isClarificationNeededOutput(
+  output: EditAgentToolOutput,
+): output is ClarificationNeededResponse {
+  return (
+    output.type === ResponseType.clarification_needed || "questions" in output
+  );
+}
+
+export function isErrorOutput(
+  output: EditAgentToolOutput,
+): output is ErrorResponse {
+  return output.type === ResponseType.error || "error" in output;
+}
+
+export function getAnimationText(part: {
+  state: ToolUIPart["state"];
+  input?: unknown;
+  output?: unknown;
+}): string {
+  switch (part.state) {
+    case "input-streaming":
+    case "input-available":
+      return "Editing the agent";
+    case "output-available": {
+      const output = parseOutput(part.output);
+      if (!output) return "Editing the agent";
+      if (isOperationStartedOutput(output)) return "Agent update started";
+      if (isOperationPendingOutput(output)) return "Agent update in progress";
+      if (isOperationInProgressOutput(output))
+        return "Agent update already in progress";
+      if (isAgentSavedOutput(output)) return `Saved "${output.agent_name}"`;
+      if (isAgentPreviewOutput(output)) return `Preview "${output.agent_name}"`;
+      if (isClarificationNeededOutput(output)) return "Needs clarification";
+      return "Error editing agent";
+    }
+    case "output-error":
+      return "Error editing agent";
+    default:
+      return "Editing the agent";
+  }
+}
+
+export function ToolIcon({
+  isStreaming,
+  isError,
+}: {
+  isStreaming?: boolean;
+  isError?: boolean;
+}) {
+  if (isError) {
+    return (
+      <WarningDiamondIcon size={14} weight="regular" className="text-red-500" />
+    );
+  }
+  if (isStreaming) {
+    return <OrbitLoader size={24} />;
+  }
+  return (
+    <PencilLineIcon size={14} weight="regular" className="text-neutral-400" />
+  );
+}
+
+export function AccordionIcon() {
+  return <NotePencilIcon size={32} weight="light" />;
+}
+
+export function formatMaybeJson(value: unknown): string {
+  if (typeof value === "string") return value;
+  try {
+    return JSON.stringify(value, null, 2);
+  } catch {
+    return String(value);
+  }
+}
+
+export function truncateText(text: string, maxChars: number): string {
+  const trimmed = text.trim();
+  if (trimmed.length <= maxChars) return trimmed;
+  return `${trimmed.slice(0, maxChars).trimEnd()}…`;
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/FindAgents/FindAgents.tsx

@@ -0,0 +1,127 @@
+"use client";
+
+import { ToolUIPart } from "ai";
+import { MorphingTextAnimation } from "../../components/MorphingTextAnimation/MorphingTextAnimation";
+import {
+  ContentBadge,
+  ContentCard,
+  ContentCardDescription,
+  ContentCardHeader,
+  ContentCardTitle,
+  ContentGrid,
+  ContentLink,
+} from "../../components/ToolAccordion/AccordionContent";
+import { ToolAccordion } from "../../components/ToolAccordion/ToolAccordion";
+import {
+  AccordionIcon,
+  getAgentHref,
+  getAnimationText,
+  getFindAgentsOutput,
+  getSourceLabelFromToolType,
+  isAgentsFoundOutput,
+  isErrorOutput,
+  ToolIcon,
+} from "./helpers";
+
+export interface FindAgentsToolPart {
+  type: string;
+  toolCallId: string;
+  state: ToolUIPart["state"];
+  input?: unknown;
+  output?: unknown;
+}
+
+interface Props {
+  part: FindAgentsToolPart;
+}
+
+export function FindAgentsTool({ part }: Props) {
+  const text = getAnimationText(part);
+  const output = getFindAgentsOutput(part);
+  const isStreaming =
+    part.state === "input-streaming" || part.state === "input-available";
+  const isError =
+    part.state === "output-error" || (!!output && isErrorOutput(output));
+
+  const query =
+    typeof part.input === "object" && part.input !== null
+      ? String((part.input as { query?: unknown }).query ?? "").trim()
+      : "";
+
+  const agentsFoundOutput =
+    part.state === "output-available" && output && isAgentsFoundOutput(output)
+      ? output
+      : null;
+
+  const hasAgents =
+    !!agentsFoundOutput &&
+    agentsFoundOutput.agents.length > 0 &&
+    (typeof agentsFoundOutput.count !== "number" ||
+      agentsFoundOutput.count > 0);
+  const totalCount = agentsFoundOutput ? agentsFoundOutput.count : 0;
+  const { source } = getSourceLabelFromToolType(part.type);
+  const scopeText =
+    source === "library"
+      ? "in your library"
+      : source === "marketplace"
+        ? "in marketplace"
+        : "";
+  const accordionDescription = `Found ${totalCount}${scopeText ? ` ${scopeText}` : ""}${
+    query ? ` for "${query}"` : ""
+  }`;
+
+  return (
+    <div className="py-2">
+      <div className="flex items-center gap-2 text-sm text-muted-foreground">
+        <ToolIcon
+          toolType={part.type}
+          isStreaming={isStreaming}
+          isError={isError}
+        />
+        <MorphingTextAnimation
+          text={text}
+          className={isError ? "text-red-500" : undefined}
+        />
+      </div>
+
+      {hasAgents && agentsFoundOutput && (
+        <ToolAccordion
+          icon={<AccordionIcon toolType={part.type} />}
+          title="Agent results"
+          description={accordionDescription}
+        >
+          <ContentGrid className="sm:grid-cols-2">
+            {agentsFoundOutput.agents.map((agent) => {
+              const href = getAgentHref(agent);
+              const agentSource =
+                agent.source === "library"
+                  ? "Library"
+                  : agent.source === "marketplace"
+                    ? "Marketplace"
+                    : null;
+              return (
+                <ContentCard key={agent.id}>
+                  <ContentCardHeader
+                    action={
+                      href ? <ContentLink href={href}>Open</ContentLink> : null
+                    }
+                  >
+                    <div className="flex items-center gap-2">
+                      <ContentCardTitle>{agent.name}</ContentCardTitle>
+                      {agentSource && (
+                        <ContentBadge>{agentSource}</ContentBadge>
+                      )}
+                    </div>
+                    <ContentCardDescription className="mt-1 line-clamp-2">
+                      {agent.description}
+                    </ContentCardDescription>
+                  </ContentCardHeader>
+                </ContentCard>
+              );
+            })}
+          </ContentGrid>
+        </ToolAccordion>
+      )}
+    </div>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/FindAgents/helpers.tsx

@@ -0,0 +1,187 @@
+import type { AgentInfo } from "@/app/api/__generated__/models/agentInfo";
+import type { AgentsFoundResponse } from "@/app/api/__generated__/models/agentsFoundResponse";
+import type { ErrorResponse } from "@/app/api/__generated__/models/errorResponse";
+import type { NoResultsResponse } from "@/app/api/__generated__/models/noResultsResponse";
+import { ResponseType } from "@/app/api/__generated__/models/responseType";
+import {
+  FolderOpenIcon,
+  MagnifyingGlassIcon,
+  SquaresFourIcon,
+  StorefrontIcon,
+} from "@phosphor-icons/react";
+import { ToolUIPart } from "ai";
+
+export interface FindAgentInput {
+  query: string;
+}
+
+export type FindAgentsOutput =
+  | AgentsFoundResponse
+  | NoResultsResponse
+  | ErrorResponse;
+
+export type FindAgentsToolType =
+  | "tool-find_agent"
+  | "tool-find_library_agent"
+  | (string & {});
+
+function parseOutput(output: unknown): FindAgentsOutput | null {
+  if (!output) return null;
+  if (typeof output === "string") {
+    const trimmed = output.trim();
+    if (!trimmed) return null;
+    try {
+      return parseOutput(JSON.parse(trimmed) as unknown);
+    } catch {
+      return null;
+    }
+  }
+  if (typeof output === "object") {
+    const type = (output as { type?: unknown }).type;
+    if (
+      type === ResponseType.agents_found ||
+      type === ResponseType.no_results ||
+      type === ResponseType.error
+    ) {
+      return output as FindAgentsOutput;
+    }
+    if ("agents" in output && "count" in output)
+      return output as AgentsFoundResponse;
+    if ("suggestions" in output && !("error" in output))
+      return output as NoResultsResponse;
+    if ("error" in output || "details" in output)
+      return output as ErrorResponse;
+  }
+  return null;
+}
+
+export function getFindAgentsOutput(part: unknown): FindAgentsOutput | null {
+  if (!part || typeof part !== "object") return null;
+  return parseOutput((part as { output?: unknown }).output);
+}
+
+export function isAgentsFoundOutput(
+  output: FindAgentsOutput,
+): output is AgentsFoundResponse {
+  return output.type === ResponseType.agents_found || "agents" in output;
+}
+
+export function isNoResultsOutput(
+  output: FindAgentsOutput,
+): output is NoResultsResponse {
+  return (
+    output.type === ResponseType.no_results ||
+    ("suggestions" in output && !("error" in output))
+  );
+}
+
+export function isErrorOutput(
+  output: FindAgentsOutput,
+): output is ErrorResponse {
+  return output.type === ResponseType.error || "error" in output;
+}
+
+export function getSourceLabelFromToolType(toolType?: FindAgentsToolType): {
+  source: "marketplace" | "library" | "unknown";
+  label: string;
+} {
+  if (toolType === "tool-find_library_agent") {
+    return { source: "library", label: "Library" };
+  }
+  if (toolType === "tool-find_agent") {
+    return { source: "marketplace", label: "Marketplace" };
+  }
+  return { source: "unknown", label: "Agents" };
+}
+
+export function getAnimationText(part: {
+  type?: FindAgentsToolType;
+  state: ToolUIPart["state"];
+  input?: unknown;
+  output?: unknown;
+}): string {
+  const { source } = getSourceLabelFromToolType(part.type);
+  const query = (part.input as FindAgentInput | undefined)?.query?.trim();
+
+  // Action phrase matching legacy ToolCallMessage
+  const actionPhrase =
+    source === "library"
+      ? "Looking for library agents"
+      : "Looking for agents in the marketplace";
+
+  const queryText = query ? ` matching "${query}"` : "";
+
+  switch (part.state) {
+    case "input-streaming":
+    case "input-available":
+      return `${actionPhrase}${queryText}`;
+
+    case "output-available": {
+      const output = parseOutput(part.output);
+      if (!output) {
+        return `${actionPhrase}${queryText}`;
+      }
+      if (isNoResultsOutput(output)) {
+        return `No agents found${queryText}`;
+      }
+      if (isAgentsFoundOutput(output)) {
+        const count = output.count ?? output.agents?.length ?? 0;
+        return `Found ${count} agent${count === 1 ? "" : "s"}${queryText}`;
+      }
+      if (isErrorOutput(output)) {
+        return `Error finding agents${queryText}`;
+      }
+      return `${actionPhrase}${queryText}`;
+    }
+
+    case "output-error":
+      return `Error finding agents${queryText}`;
+
+    default:
+      return actionPhrase;
+  }
+}
+
+export function getAgentHref(agent: AgentInfo): string | null {
+  if (agent.source === "library") {
+    return `/library/agents/${encodeURIComponent(agent.id)}`;
+  }
+
+  const [creator, slug, ...rest] = agent.id.split("/");
+  if (!creator || !slug || rest.length > 0) return null;
+  return `/marketplace/agent/${encodeURIComponent(creator)}/${encodeURIComponent(slug)}`;
+}
+
+export function ToolIcon({
+  toolType,
+  isStreaming,
+  isError,
+}: {
+  toolType?: FindAgentsToolType;
+  isStreaming?: boolean;
+  isError?: boolean;
+}) {
+  const { source } = getSourceLabelFromToolType(toolType);
+  const IconComponent =
+    source === "library" ? MagnifyingGlassIcon : SquaresFourIcon;
+
+  return (
+    <IconComponent
+      size={14}
+      weight="regular"
+      className={
+        isError
+          ? "text-red-500"
+          : isStreaming
+            ? "text-neutral-500"
+            : "text-neutral-400"
+      }
+    />
+  );
+}
+
+export function AccordionIcon({ toolType }: { toolType?: FindAgentsToolType }) {
+  const { source } = getSourceLabelFromToolType(toolType);
+  const IconComponent = source === "library" ? FolderOpenIcon : StorefrontIcon;
+  return <IconComponent size={32} weight="light" />;
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/FindBlocks/FindBlocks.tsx

@@ -0,0 +1,92 @@
+"use client";
+
+import { MorphingTextAnimation } from "../../components/MorphingTextAnimation/MorphingTextAnimation";
+import { ToolAccordion } from "../../components/ToolAccordion/ToolAccordion";
+import {
+  ContentCard,
+  ContentCardDescription,
+  ContentCardTitle,
+} from "../../components/ToolAccordion/AccordionContent";
+import type { BlockListResponse } from "@/app/api/__generated__/models/blockListResponse";
+import type { BlockInfoSummary } from "@/app/api/__generated__/models/blockInfoSummary";
+import { ToolUIPart } from "ai";
+import { HorizontalScroll } from "@/app/(platform)/build/components/NewControlPanel/NewBlockMenu/HorizontalScroll";
+import {
+  AccordionIcon,
+  getAnimationText,
+  parseOutput,
+  ToolIcon,
+} from "./helpers";
+
+export interface FindBlockInput {
+  query: string;
+}
+
+export type FindBlockOutput = BlockListResponse;
+
+export interface FindBlockToolPart {
+  type: string;
+  toolName?: string;
+  toolCallId: string;
+  state: ToolUIPart["state"];
+  input?: FindBlockInput | unknown;
+  output?: string | FindBlockOutput | unknown;
+  title?: string;
+}
+
+interface Props {
+  part: FindBlockToolPart;
+}
+
+function BlockCard({ block }: { block: BlockInfoSummary }) {
+  return (
+    <ContentCard className="w-48 shrink-0">
+      <ContentCardTitle>{block.name}</ContentCardTitle>
+      <ContentCardDescription className="mt-1 line-clamp-2">
+        {block.description}
+      </ContentCardDescription>
+    </ContentCard>
+  );
+}
+
+export function FindBlocksTool({ part }: Props) {
+  const text = getAnimationText(part);
+  const isStreaming =
+    part.state === "input-streaming" || part.state === "input-available";
+  const isError = part.state === "output-error";
+
+  const parsed =
+    part.state === "output-available" ? parseOutput(part.output) : null;
+  const hasBlocks = !!parsed && parsed.blocks.length > 0;
+
+  const query = (part.input as FindBlockInput | undefined)?.query?.trim();
+  const accordionDescription = parsed
+    ? `Found ${parsed.count} block${parsed.count === 1 ? "" : "s"}${query ? ` for "${query}"` : ""}`
+    : undefined;
+
+  return (
+    <div className="py-2">
+      <div className="flex items-center gap-2 text-sm text-muted-foreground">
+        <ToolIcon isStreaming={isStreaming} isError={isError} />
+        <MorphingTextAnimation
+          text={text}
+          className={isError ? "text-red-500" : undefined}
+        />
+      </div>
+
+      {hasBlocks && parsed && (
+        <ToolAccordion
+          icon={<AccordionIcon />}
+          title="Block results"
+          description={accordionDescription}
+        >
+          <HorizontalScroll dependencyList={[parsed.blocks.length]}>
+            {parsed.blocks.map((block) => (
+              <BlockCard key={block.id} block={block} />
+            ))}
+          </HorizontalScroll>
+        </ToolAccordion>
+      )}
+    </div>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/FindBlocks/helpers.tsx

@@ -0,0 +1,75 @@
+import type { BlockListResponse } from "@/app/api/__generated__/models/blockListResponse";
+import { ResponseType } from "@/app/api/__generated__/models/responseType";
+import { CubeIcon, PackageIcon } from "@phosphor-icons/react";
+import { FindBlockInput, FindBlockToolPart } from "./FindBlocks";
+
+export function parseOutput(output: unknown): BlockListResponse | null {
+  if (!output) return null;
+  if (typeof output === "string") {
+    const trimmed = output.trim();
+    if (!trimmed) return null;
+    try {
+      return parseOutput(JSON.parse(trimmed) as unknown);
+    } catch {
+      return null;
+    }
+  }
+  if (typeof output === "object") {
+    const type = (output as { type?: unknown }).type;
+    if (type === ResponseType.block_list || "blocks" in output) {
+      return output as BlockListResponse;
+    }
+  }
+  return null;
+}
+
+export function getAnimationText(part: FindBlockToolPart): string {
+  const query = (part.input as FindBlockInput | undefined)?.query?.trim();
+  const queryText = query ? ` matching "${query}"` : "";
+
+  switch (part.state) {
+    case "input-streaming":
+    case "input-available":
+      return `Searching for blocks${queryText}`;
+
+    case "output-available": {
+      const parsed = parseOutput(part.output);
+      if (parsed) {
+        return `Found ${parsed.count} block${parsed.count === 1 ? "" : "s"}${queryText}`;
+      }
+      return `Searching for blocks${queryText}`;
+    }
+
+    case "output-error":
+      return `Error finding blocks${queryText}`;
+
+    default:
+      return "Searching for blocks";
+  }
+}
+
+export function ToolIcon({
+  isStreaming,
+  isError,
+}: {
+  isStreaming?: boolean;
+  isError?: boolean;
+}) {
+  return (
+    <PackageIcon
+      size={14}
+      weight="regular"
+      className={
+        isError
+          ? "text-red-500"
+          : isStreaming
+            ? "text-neutral-500"
+            : "text-neutral-400"
+      }
+    />
+  );
+}
+
+export function AccordionIcon() {
+  return <CubeIcon size={32} weight="light" />;
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunAgent/RunAgent.tsx

@@ -0,0 +1,93 @@
+"use client";
+
+import type { ToolUIPart } from "ai";
+import { MorphingTextAnimation } from "../../components/MorphingTextAnimation/MorphingTextAnimation";
+import { ToolAccordion } from "../../components/ToolAccordion/ToolAccordion";
+import { ContentMessage } from "../../components/ToolAccordion/AccordionContent";
+import {
+  getAccordionMeta,
+  getAnimationText,
+  getRunAgentToolOutput,
+  isRunAgentAgentDetailsOutput,
+  isRunAgentErrorOutput,
+  isRunAgentExecutionStartedOutput,
+  isRunAgentNeedLoginOutput,
+  isRunAgentSetupRequirementsOutput,
+  ToolIcon,
+} from "./helpers";
+import { ExecutionStartedCard } from "./components/ExecutionStartedCard/ExecutionStartedCard";
+import { AgentDetailsCard } from "./components/AgentDetailsCard/AgentDetailsCard";
+import { SetupRequirementsCard } from "./components/SetupRequirementsCard/SetupRequirementsCard";
+import { ErrorCard } from "./components/ErrorCard/ErrorCard";
+
+export interface RunAgentToolPart {
+  type: string;
+  toolCallId: string;
+  state: ToolUIPart["state"];
+  input?: unknown;
+  output?: unknown;
+}
+
+interface Props {
+  part: RunAgentToolPart;
+}
+
+export function RunAgentTool({ part }: Props) {
+  const text = getAnimationText(part);
+  const isStreaming =
+    part.state === "input-streaming" || part.state === "input-available";
+
+  const output = getRunAgentToolOutput(part);
+  const isError =
+    part.state === "output-error" ||
+    (!!output && isRunAgentErrorOutput(output));
+  const hasExpandableContent =
+    part.state === "output-available" &&
+    !!output &&
+    (isRunAgentExecutionStartedOutput(output) ||
+      isRunAgentAgentDetailsOutput(output) ||
+      isRunAgentSetupRequirementsOutput(output) ||
+      isRunAgentNeedLoginOutput(output) ||
+      isRunAgentErrorOutput(output));
+
+  return (
+    <div className="py-2">
+      <div className="flex items-center gap-2 text-sm text-muted-foreground">
+        <ToolIcon isStreaming={isStreaming} isError={isError} />
+        <MorphingTextAnimation
+          text={text}
+          className={isError ? "text-red-500" : undefined}
+        />
+      </div>
+
+      {hasExpandableContent && output && (
+        <ToolAccordion
+          {...getAccordionMeta(output)}
+          defaultExpanded={
+            isRunAgentExecutionStartedOutput(output) ||
+            isRunAgentSetupRequirementsOutput(output) ||
+            isRunAgentAgentDetailsOutput(output)
+          }
+        >
+          {isRunAgentExecutionStartedOutput(output) && (
+            <ExecutionStartedCard output={output} />
+          )}
+
+          {isRunAgentAgentDetailsOutput(output) && (
+            <AgentDetailsCard output={output} />
+          )}
+
+          {isRunAgentSetupRequirementsOutput(output) && (
+            <SetupRequirementsCard output={output} />
+          )}
+
+          {isRunAgentNeedLoginOutput(output) && (
+            <ContentMessage>{output.message}</ContentMessage>
+          )}
+
+          {isRunAgentErrorOutput(output) && <ErrorCard output={output} />}
+        </ToolAccordion>
+      )}
+    </div>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunAgent/components/AgentDetailsCard/AgentDetailsCard.tsx

@@ -0,0 +1,116 @@
+"use client";
+
+import type { AgentDetailsResponse } from "@/app/api/__generated__/models/agentDetailsResponse";
+import { Button } from "@/components/atoms/Button/Button";
+import { Text } from "@/components/atoms/Text/Text";
+import { FormRenderer } from "@/components/renderers/InputRenderer/FormRenderer";
+import { AnimatePresence, motion } from "framer-motion";
+import { useState } from "react";
+import { useCopilotChatActions } from "../../../../components/CopilotChatActionsProvider/useCopilotChatActions";
+import { ContentMessage } from "../../../../components/ToolAccordion/AccordionContent";
+import { buildInputSchema } from "./helpers";
+
+interface Props {
+  output: AgentDetailsResponse;
+}
+
+export function AgentDetailsCard({ output }: Props) {
+  const { onSend } = useCopilotChatActions();
+  const [showInputForm, setShowInputForm] = useState(false);
+  const [inputValues, setInputValues] = useState<Record<string, unknown>>({});
+
+  function handleRunWithExamples() {
+    onSend(
+      `Run the agent "${output.agent.name}" with placeholder/example values so I can test it.`,
+    );
+  }
+
+  function handleRunWithInputs() {
+    const nonEmpty = Object.fromEntries(
+      Object.entries(inputValues).filter(
+        ([, v]) => v !== undefined && v !== null && v !== "",
+      ),
+    );
+    onSend(
+      `Run the agent "${output.agent.name}" with these inputs: ${JSON.stringify(nonEmpty, null, 2)}`,
+    );
+    setShowInputForm(false);
+    setInputValues({});
+  }
+
+  return (
+    <div className="grid gap-2">
+      <ContentMessage>
+        Run this agent with example values or your own inputs.
+      </ContentMessage>
+
+      <div className="flex gap-2 pt-4">
+        <Button size="small" className="w-fit" onClick={handleRunWithExamples}>
+          Run with example values
+        </Button>
+        <Button
+          variant="outline"
+          size="small"
+          className="w-fit"
+          onClick={() => setShowInputForm((prev) => !prev)}
+        >
+          Run with my inputs
+        </Button>
+      </div>
+
+      <AnimatePresence initial={false}>
+        {showInputForm && buildInputSchema(output.agent.inputs) && (
+          <motion.div
+            initial={{ height: 0, opacity: 0, filter: "blur(6px)" }}
+            animate={{ height: "auto", opacity: 1, filter: "blur(0px)" }}
+            exit={{ height: 0, opacity: 0, filter: "blur(6px)" }}
+            transition={{
+              height: { type: "spring", bounce: 0.15, duration: 0.5 },
+              opacity: { duration: 0.25 },
+              filter: { duration: 0.2 },
+            }}
+            className="overflow-hidden"
+            style={{ willChange: "height, opacity, filter" }}
+          >
+            <div className="mt-4 rounded-2xl border bg-background p-3 pt-4">
+              <Text variant="body-medium">Enter your inputs</Text>
+              <FormRenderer
+                jsonSchema={buildInputSchema(output.agent.inputs)!}
+                handleChange={(v) => setInputValues(v.formData ?? {})}
+                uiSchema={{
+                  "ui:submitButtonOptions": { norender: true },
+                }}
+                initialValues={inputValues}
+                formContext={{
+                  showHandles: false,
+                  size: "small",
+                }}
+              />
+              <div className="-mt-8 flex gap-2">
+                <Button
+                  variant="primary"
+                  size="small"
+                  className="w-fit"
+                  onClick={handleRunWithInputs}
+                >
+                  Run
+                </Button>
+                <Button
+                  variant="secondary"
+                  size="small"
+                  className="w-fit"
+                  onClick={() => {
+                    setShowInputForm(false);
+                    setInputValues({});
+                  }}
+                >
+                  Cancel
+                </Button>
+              </div>
+            </div>
+          </motion.div>
+        )}
+      </AnimatePresence>
+    </div>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunAgent/components/AgentDetailsCard/helpers.ts

@@ -0,0 +1,8 @@
+import type { RJSFSchema } from "@rjsf/utils";
+
+export function buildInputSchema(inputs: unknown): RJSFSchema | null {
+  if (!inputs || typeof inputs !== "object") return null;
+  const properties = inputs as RJSFSchema["properties"];
+  if (!properties || Object.keys(properties).length === 0) return null;
+  return inputs as RJSFSchema;
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunAgent/components/ErrorCard/ErrorCard.tsx

@@ -0,0 +1,27 @@
+"use client";
+
+import type { ErrorResponse } from "@/app/api/__generated__/models/errorResponse";
+import {
+  ContentCodeBlock,
+  ContentGrid,
+  ContentMessage,
+} from "../../../../components/ToolAccordion/AccordionContent";
+import { formatMaybeJson } from "../../helpers";
+
+interface Props {
+  output: ErrorResponse;
+}
+
+export function ErrorCard({ output }: Props) {
+  return (
+    <ContentGrid>
+      <ContentMessage>{output.message}</ContentMessage>
+      {output.error && (
+        <ContentCodeBlock>{formatMaybeJson(output.error)}</ContentCodeBlock>
+      )}
+      {output.details && (
+        <ContentCodeBlock>{formatMaybeJson(output.details)}</ContentCodeBlock>
+      )}
+    </ContentGrid>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunAgent/components/ExecutionStartedCard/ExecutionStartedCard.tsx

@@ -0,0 +1,39 @@
+"use client";
+
+import type { ExecutionStartedResponse } from "@/app/api/__generated__/models/executionStartedResponse";
+import { Button } from "@/components/atoms/Button/Button";
+import { useRouter } from "next/navigation";
+import {
+  ContentCard,
+  ContentCardDescription,
+  ContentCardSubtitle,
+  ContentCardTitle,
+  ContentGrid,
+} from "../../../../components/ToolAccordion/AccordionContent";
+
+interface Props {
+  output: ExecutionStartedResponse;
+}
+
+export function ExecutionStartedCard({ output }: Props) {
+  const router = useRouter();
+
+  return (
+    <ContentGrid>
+      <ContentCard>
+        <ContentCardTitle>Execution started</ContentCardTitle>
+        <ContentCardSubtitle>{output.execution_id}</ContentCardSubtitle>
+        <ContentCardDescription>{output.message}</ContentCardDescription>
+        {output.library_agent_link && (
+          <Button
+            size="small"
+            className="mt-3"
+            onClick={() => router.push(output.library_agent_link!)}
+          >
+            View Execution
+          </Button>
+        )}
+      </ContentCard>
+    </ContentGrid>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunAgent/components/SetupRequirementsCard/SetupRequirementsCard.tsx

@@ -0,0 +1,105 @@
+"use client";
+
+import { useState } from "react";
+import { CredentialsGroupedView } from "@/components/contextual/CredentialsInput/components/CredentialsGroupedView/CredentialsGroupedView";
+import { Button } from "@/components/atoms/Button/Button";
+import type { CredentialsMetaInput } from "@/lib/autogpt-server-api/types";
+import type { SetupRequirementsResponse } from "@/app/api/__generated__/models/setupRequirementsResponse";
+import { useCopilotChatActions } from "../../../../components/CopilotChatActionsProvider/useCopilotChatActions";
+import {
+  ContentBadge,
+  ContentCardDescription,
+  ContentCardTitle,
+  ContentMessage,
+} from "../../../../components/ToolAccordion/AccordionContent";
+import { coerceCredentialFields, coerceExpectedInputs } from "./helpers";
+
+interface Props {
+  output: SetupRequirementsResponse;
+}
+
+export function SetupRequirementsCard({ output }: Props) {
+  const { onSend } = useCopilotChatActions();
+
+  const [inputCredentials, setInputCredentials] = useState<
+    Record<string, CredentialsMetaInput | undefined>
+  >({});
+  const [hasSent, setHasSent] = useState(false);
+
+  const { credentialFields, requiredCredentials } = coerceCredentialFields(
+    output.setup_info.user_readiness?.missing_credentials,
+  );
+
+  const expectedInputs = coerceExpectedInputs(
+    (output.setup_info.requirements as Record<string, unknown>)?.inputs,
+  );
+
+  function handleCredentialChange(key: string, value?: CredentialsMetaInput) {
+    setInputCredentials((prev) => ({ ...prev, [key]: value }));
+  }
+
+  const isAllComplete =
+    credentialFields.length > 0 &&
+    [...requiredCredentials].every((key) => !!inputCredentials[key]);
+
+  function handleProceed() {
+    setHasSent(true);
+    onSend(
+      "I've configured the required credentials. Please check if everything is ready and proceed with running the agent.",
+    );
+  }
+
+  return (
+    <div className="grid gap-2">
+      <ContentMessage>{output.message}</ContentMessage>
+
+      {credentialFields.length > 0 && (
+        <div className="rounded-2xl border bg-background p-3">
+          <CredentialsGroupedView
+            credentialFields={credentialFields}
+            requiredCredentials={requiredCredentials}
+            inputCredentials={inputCredentials}
+            inputValues={{}}
+            onCredentialChange={handleCredentialChange}
+          />
+          {isAllComplete && !hasSent && (
+            <Button
+              variant="primary"
+              size="small"
+              className="mt-3 w-full"
+              onClick={handleProceed}
+            >
+              Proceed
+            </Button>
+          )}
+        </div>
+      )}
+
+      {expectedInputs.length > 0 && (
+        <div className="rounded-2xl border bg-background p-3">
+          <ContentCardTitle className="text-xs">
+            Expected inputs
+          </ContentCardTitle>
+          <div className="mt-2 grid gap-2">
+            {expectedInputs.map((input) => (
+              <div key={input.name} className="rounded-xl border p-2">
+                <div className="flex items-center justify-between gap-2">
+                  <ContentCardTitle className="text-xs">
+                    {input.title}
+                  </ContentCardTitle>
+                  <ContentBadge>
+                    {input.required ? "Required" : "Optional"}
+                  </ContentBadge>
+                </div>
+                <ContentCardDescription className="mt-1">
+                  {input.name} &bull; {input.type}
+                  {input.description ? ` \u2022 ${input.description}` : ""}
+                </ContentCardDescription>
+              </div>
+            ))}
+          </div>
+        </div>
+      )}
+    </div>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunAgent/components/SetupRequirementsCard/helpers.ts

@@ -0,0 +1,116 @@
+import type { CredentialField } from "@/components/contextual/CredentialsInput/components/CredentialsGroupedView/helpers";
+
+const VALID_CREDENTIAL_TYPES = new Set([
+  "api_key",
+  "oauth2",
+  "user_password",
+  "host_scoped",
+]);
+
+/**
+ * Transforms raw missing_credentials from SetupRequirementsResponse
+ * into CredentialField[] tuples compatible with CredentialsGroupedView.
+ *
+ * Each CredentialField is [key, schema] where schema matches
+ * BlockIOCredentialsSubSchema shape.
+ */
+export function coerceCredentialFields(rawMissingCredentials: unknown): {
+  credentialFields: CredentialField[];
+  requiredCredentials: Set<string>;
+} {
+  const missing =
+    rawMissingCredentials && typeof rawMissingCredentials === "object"
+      ? (rawMissingCredentials as Record<string, unknown>)
+      : {};
+
+  const credentialFields: CredentialField[] = [];
+  const requiredCredentials = new Set<string>();
+
+  Object.entries(missing).forEach(([key, value]) => {
+    if (!value || typeof value !== "object") return;
+    const cred = value as Record<string, unknown>;
+
+    const provider =
+      typeof cred.provider === "string" ? cred.provider.trim() : "";
+    if (!provider) return;
+
+    const types =
+      Array.isArray(cred.types) && cred.types.length > 0
+        ? cred.types
+        : typeof cred.type === "string"
+          ? [cred.type]
+          : [];
+
+    const credentialTypes = types
+      .map((t) => (typeof t === "string" ? t.trim() : ""))
+      .filter((t) => VALID_CREDENTIAL_TYPES.has(t));
+
+    if (credentialTypes.length === 0) return;
+
+    const scopes = Array.isArray(cred.scopes)
+      ? cred.scopes.filter((s): s is string => typeof s === "string")
+      : undefined;
+
+    const schema = {
+      type: "object" as const,
+      properties: {},
+      credentials_provider: [provider],
+      credentials_types: credentialTypes,
+      credentials_scopes: scopes,
+    };
+
+    credentialFields.push([key, schema]);
+    requiredCredentials.add(key);
+  });
+
+  return { credentialFields, requiredCredentials };
+}
+
+export function coerceExpectedInputs(rawInputs: unknown): Array<{
+  name: string;
+  title: string;
+  type: string;
+  description?: string;
+  required: boolean;
+}> {
+  if (!Array.isArray(rawInputs)) return [];
+  const results: Array<{
+    name: string;
+    title: string;
+    type: string;
+    description?: string;
+    required: boolean;
+  }> = [];
+
+  rawInputs.forEach((value, index) => {
+    if (!value || typeof value !== "object") return;
+    const input = value as Record<string, unknown>;
+
+    const name =
+      typeof input.name === "string" && input.name.trim()
+        ? input.name.trim()
+        : `input-${index}`;
+    const title =
+      typeof input.title === "string" && input.title.trim()
+        ? input.title.trim()
+        : name;
+    const type = typeof input.type === "string" ? input.type : "unknown";
+    const description =
+      typeof input.description === "string" && input.description.trim()
+        ? input.description.trim()
+        : undefined;
+    const required = Boolean(input.required);
+
+    const item: {
+      name: string;
+      title: string;
+      type: string;
+      description?: string;
+      required: boolean;
+    } = { name, title, type, required };
+    if (description) item.description = description;
+    results.push(item);
+  });
+
+  return results;
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunAgent/helpers.tsx

@@ -0,0 +1,248 @@
+import type { AgentDetailsResponse } from "@/app/api/__generated__/models/agentDetailsResponse";
+import type { ErrorResponse } from "@/app/api/__generated__/models/errorResponse";
+import type { ExecutionStartedResponse } from "@/app/api/__generated__/models/executionStartedResponse";
+import type { NeedLoginResponse } from "@/app/api/__generated__/models/needLoginResponse";
+import { ResponseType } from "@/app/api/__generated__/models/responseType";
+import type { SetupRequirementsResponse } from "@/app/api/__generated__/models/setupRequirementsResponse";
+import {
+  PlayIcon,
+  RocketLaunchIcon,
+  WarningDiamondIcon,
+} from "@phosphor-icons/react";
+import type { ToolUIPart } from "ai";
+import { SpinnerLoader } from "../../components/SpinnerLoader/SpinnerLoader";
+
+export interface RunAgentInput {
+  username_agent_slug?: string;
+  library_agent_id?: string;
+  inputs?: Record<string, unknown>;
+  use_defaults?: boolean;
+  schedule_name?: string;
+  cron?: string;
+  timezone?: string;
+}
+
+export type RunAgentToolOutput =
+  | SetupRequirementsResponse
+  | ExecutionStartedResponse
+  | AgentDetailsResponse
+  | NeedLoginResponse
+  | ErrorResponse;
+
+const RUN_AGENT_OUTPUT_TYPES = new Set<string>([
+  ResponseType.setup_requirements,
+  ResponseType.execution_started,
+  ResponseType.agent_details,
+  ResponseType.need_login,
+  ResponseType.error,
+]);
+
+export function isRunAgentSetupRequirementsOutput(
+  output: RunAgentToolOutput,
+): output is SetupRequirementsResponse {
+  return (
+    output.type === ResponseType.setup_requirements ||
+    ("setup_info" in output && typeof output.setup_info === "object")
+  );
+}
+
+export function isRunAgentExecutionStartedOutput(
+  output: RunAgentToolOutput,
+): output is ExecutionStartedResponse {
+  return (
+    output.type === ResponseType.execution_started || "execution_id" in output
+  );
+}
+
+export function isRunAgentAgentDetailsOutput(
+  output: RunAgentToolOutput,
+): output is AgentDetailsResponse {
+  return output.type === ResponseType.agent_details || "agent" in output;
+}
+
+export function isRunAgentNeedLoginOutput(
+  output: RunAgentToolOutput,
+): output is NeedLoginResponse {
+  return output.type === ResponseType.need_login;
+}
+
+export function isRunAgentErrorOutput(
+  output: RunAgentToolOutput,
+): output is ErrorResponse {
+  return output.type === ResponseType.error || "error" in output;
+}
+
+function parseOutput(output: unknown): RunAgentToolOutput | null {
+  if (!output) return null;
+  if (typeof output === "string") {
+    const trimmed = output.trim();
+    if (!trimmed) return null;
+    try {
+      return parseOutput(JSON.parse(trimmed) as unknown);
+    } catch {
+      return null;
+    }
+  }
+  if (typeof output === "object") {
+    const type = (output as { type?: unknown }).type;
+    if (typeof type === "string" && RUN_AGENT_OUTPUT_TYPES.has(type)) {
+      return output as RunAgentToolOutput;
+    }
+    if ("execution_id" in output) return output as ExecutionStartedResponse;
+    if ("setup_info" in output) return output as SetupRequirementsResponse;
+    if ("agent" in output) return output as AgentDetailsResponse;
+    if ("error" in output || "details" in output)
+      return output as ErrorResponse;
+    if (type === ResponseType.need_login) return output as NeedLoginResponse;
+  }
+  return null;
+}
+
+export function getRunAgentToolOutput(
+  part: unknown,
+): RunAgentToolOutput | null {
+  if (!part || typeof part !== "object") return null;
+  return parseOutput((part as { output?: unknown }).output);
+}
+
+function getAgentIdentifierText(
+  input: RunAgentInput | undefined,
+): string | null {
+  if (!input) return null;
+  const slug = input.username_agent_slug?.trim();
+  if (slug) return slug;
+  const libraryId = input.library_agent_id?.trim();
+  if (libraryId) return `Library agent ${libraryId}`;
+  return null;
+}
+
+export function getAnimationText(part: {
+  state: ToolUIPart["state"];
+  input?: unknown;
+  output?: unknown;
+}): string {
+  const input = part.input as RunAgentInput | undefined;
+  const agentIdentifier = getAgentIdentifierText(input);
+  const isSchedule = Boolean(
+    input?.schedule_name?.trim() || input?.cron?.trim(),
+  );
+  const actionPhrase = isSchedule
+    ? "Scheduling the agent to run"
+    : "Running the agent";
+  const identifierText = agentIdentifier ? ` "${agentIdentifier}"` : "";
+
+  switch (part.state) {
+    case "input-streaming":
+    case "input-available":
+      return `${actionPhrase}${identifierText}`;
+    case "output-available": {
+      const output = parseOutput(part.output);
+      if (!output) return `${actionPhrase}${identifierText}`;
+      if (isRunAgentExecutionStartedOutput(output)) {
+        return `Started "${output.graph_name}"`;
+      }
+      if (isRunAgentAgentDetailsOutput(output)) {
+        return `Agent inputs needed for "${output.agent.name}"`;
+      }
+      if (isRunAgentSetupRequirementsOutput(output)) {
+        return `Setup needed for "${output.setup_info.agent_name}"`;
+      }
+      if (isRunAgentNeedLoginOutput(output))
+        return "Sign in required to run agent";
+      return "Error running agent";
+    }
+    case "output-error":
+      return "Error running agent";
+    default:
+      return actionPhrase;
+  }
+}
+
+export function ToolIcon({
+  isStreaming,
+  isError,
+}: {
+  isStreaming?: boolean;
+  isError?: boolean;
+}) {
+  if (isError) {
+    return (
+      <WarningDiamondIcon size={14} weight="regular" className="text-red-500" />
+    );
+  }
+  if (isStreaming) {
+    return <SpinnerLoader size={40} className="text-neutral-700" />;
+  }
+  return <PlayIcon size={14} weight="regular" className="text-neutral-400" />;
+}
+
+export function AccordionIcon() {
+  return <RocketLaunchIcon size={28} weight="light" />;
+}
+
+export function formatMaybeJson(value: unknown): string {
+  if (typeof value === "string") return value;
+  try {
+    return JSON.stringify(value, null, 2);
+  } catch {
+    return String(value);
+  }
+}
+
+export function getAccordionMeta(output: RunAgentToolOutput): {
+  icon: React.ReactNode;
+  title: string;
+  titleClassName?: string;
+  description?: string;
+} {
+  const icon = <AccordionIcon />;
+
+  if (isRunAgentExecutionStartedOutput(output)) {
+    const statusText =
+      typeof output.status === "string" && output.status.trim()
+        ? output.status.trim()
+        : "started";
+    return {
+      icon: <SpinnerLoader size={28} className="text-neutral-700" />,
+      title: output.graph_name,
+      description: `Status: ${statusText}`,
+    };
+  }
+
+  if (isRunAgentAgentDetailsOutput(output)) {
+    return {
+      icon,
+      title: output.agent.name,
+      description: "Inputs required",
+    };
+  }
+
+  if (isRunAgentSetupRequirementsOutput(output)) {
+    const missingCredsCount = Object.keys(
+      (output.setup_info.user_readiness?.missing_credentials ?? {}) as Record<
+        string,
+        unknown
+      >,
+    ).length;
+    return {
+      icon,
+      title: output.setup_info.agent_name,
+      description:
+        missingCredsCount > 0
+          ? `Missing ${missingCredsCount} credential${missingCredsCount === 1 ? "" : "s"}`
+          : output.message,
+    };
+  }
+
+  if (isRunAgentNeedLoginOutput(output)) {
+    return { icon, title: "Sign in required" };
+  }
+
+  return {
+    icon: (
+      <WarningDiamondIcon size={28} weight="light" className="text-red-500" />
+    ),
+    title: "Error",
+    titleClassName: "text-red-500",
+  };
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunBlock/RunBlock.tsx

@@ -0,0 +1,76 @@
+"use client";
+
+import type { ToolUIPart } from "ai";
+import { MorphingTextAnimation } from "../../components/MorphingTextAnimation/MorphingTextAnimation";
+import { ToolAccordion } from "../../components/ToolAccordion/ToolAccordion";
+import { BlockOutputCard } from "./components/BlockOutputCard/BlockOutputCard";
+import { ErrorCard } from "./components/ErrorCard/ErrorCard";
+import { SetupRequirementsCard } from "./components/SetupRequirementsCard/SetupRequirementsCard";
+import {
+  getAccordionMeta,
+  getAnimationText,
+  getRunBlockToolOutput,
+  isRunBlockBlockOutput,
+  isRunBlockErrorOutput,
+  isRunBlockSetupRequirementsOutput,
+  ToolIcon,
+} from "./helpers";
+
+export interface RunBlockToolPart {
+  type: string;
+  toolCallId: string;
+  state: ToolUIPart["state"];
+  input?: unknown;
+  output?: unknown;
+}
+
+interface Props {
+  part: RunBlockToolPart;
+}
+
+export function RunBlockTool({ part }: Props) {
+  const text = getAnimationText(part);
+  const isStreaming =
+    part.state === "input-streaming" || part.state === "input-available";
+
+  const output = getRunBlockToolOutput(part);
+  const isError =
+    part.state === "output-error" ||
+    (!!output && isRunBlockErrorOutput(output));
+  const hasExpandableContent =
+    part.state === "output-available" &&
+    !!output &&
+    (isRunBlockBlockOutput(output) ||
+      isRunBlockSetupRequirementsOutput(output) ||
+      isRunBlockErrorOutput(output));
+
+  return (
+    <div className="py-2">
+      <div className="flex items-center gap-2 text-sm text-muted-foreground">
+        <ToolIcon isStreaming={isStreaming} isError={isError} />
+        <MorphingTextAnimation
+          text={text}
+          className={isError ? "text-red-500" : undefined}
+        />
+      </div>
+
+      {hasExpandableContent && output && (
+        <ToolAccordion
+          {...getAccordionMeta(output)}
+          defaultExpanded={
+            isRunBlockBlockOutput(output) ||
+            isRunBlockSetupRequirementsOutput(output)
+          }
+        >
+          {isRunBlockBlockOutput(output) && <BlockOutputCard output={output} />}
+
+          {isRunBlockSetupRequirementsOutput(output) && (
+            <SetupRequirementsCard output={output} />
+          )}
+
+          {isRunBlockErrorOutput(output) && <ErrorCard output={output} />}
+        </ToolAccordion>
+      )}
+    </div>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunBlock/components/BlockOutputCard/BlockOutputCard.tsx

@@ -0,0 +1,133 @@
+"use client";
+
+import React, { useState } from "react";
+import { getGetWorkspaceDownloadFileByIdUrl } from "@/app/api/__generated__/endpoints/workspace/workspace";
+import { Button } from "@/components/atoms/Button/Button";
+import type { BlockOutputResponse } from "@/app/api/__generated__/models/blockOutputResponse";
+import {
+  globalRegistry,
+  OutputItem,
+} from "@/components/contextual/OutputRenderers";
+import type { OutputMetadata } from "@/components/contextual/OutputRenderers";
+import {
+  ContentBadge,
+  ContentCard,
+  ContentCardTitle,
+  ContentGrid,
+  ContentMessage,
+} from "../../../../components/ToolAccordion/AccordionContent";
+
+interface Props {
+  output: BlockOutputResponse;
+}
+
+const COLLAPSED_LIMIT = 3;
+
+function isWorkspaceRef(value: unknown): value is string {
+  return typeof value === "string" && value.startsWith("workspace://");
+}
+
+function resolveForRenderer(value: unknown): {
+  value: unknown;
+  metadata?: OutputMetadata;
+} {
+  if (!isWorkspaceRef(value)) return { value };
+
+  const withoutPrefix = value.replace("workspace://", "");
+  const fileId = withoutPrefix.split("#")[0];
+  const apiPath = getGetWorkspaceDownloadFileByIdUrl(fileId);
+  const url = `/api/proxy${apiPath}`;
+
+  const hashIndex = value.indexOf("#");
+  const mimeHint =
+    hashIndex !== -1 ? value.slice(hashIndex + 1) || undefined : undefined;
+
+  const metadata: OutputMetadata = {};
+  if (mimeHint) {
+    metadata.mimeType = mimeHint;
+    if (mimeHint.startsWith("image/")) metadata.type = "image";
+    else if (mimeHint.startsWith("video/")) metadata.type = "video";
+  }
+
+  return { value: url, metadata };
+}
+
+function RenderOutputValue({ value }: { value: unknown }) {
+  const resolved = resolveForRenderer(value);
+  const renderer = globalRegistry.getRenderer(
+    resolved.value,
+    resolved.metadata,
+  );
+
+  if (renderer) {
+    return (
+      <OutputItem
+        value={resolved.value}
+        metadata={resolved.metadata}
+        renderer={renderer}
+      />
+    );
+  }
+
+  // Fallback for audio workspace refs
+  if (
+    isWorkspaceRef(value) &&
+    resolved.metadata?.mimeType?.startsWith("audio/")
+  ) {
+    return (
+      <audio controls src={String(resolved.value)} className="mt-2 w-full" />
+    );
+  }
+
+  return null;
+}
+
+function OutputKeySection({
+  outputKey,
+  items,
+}: {
+  outputKey: string;
+  items: unknown[];
+}) {
+  const [expanded, setExpanded] = useState(false);
+  const hasMoreItems = items.length > COLLAPSED_LIMIT;
+  const visibleItems = expanded ? items : items.slice(0, COLLAPSED_LIMIT);
+
+  return (
+    <ContentCard>
+      <div className="flex items-center justify-between gap-2">
+        <ContentCardTitle className="text-xs">{outputKey}</ContentCardTitle>
+        <ContentBadge>
+          {items.length} item{items.length === 1 ? "" : "s"}
+        </ContentBadge>
+      </div>
+      <div className="mt-2">
+        {visibleItems.map((item, i) => (
+          <RenderOutputValue key={i} value={item} />
+        ))}
+      </div>
+      {hasMoreItems && (
+        <Button
+          variant="ghost"
+          size="small"
+          className="mt-1 h-auto px-0 py-0.5 text-[11px] text-muted-foreground"
+          onClick={() => setExpanded((prev) => !prev)}
+        >
+          {expanded ? "Show less" : `Show all ${items.length} items`}
+        </Button>
+      )}
+    </ContentCard>
+  );
+}
+
+export function BlockOutputCard({ output }: Props) {
+  return (
+    <ContentGrid>
+      <ContentMessage>{output.message}</ContentMessage>
+
+      {Object.entries(output.outputs ?? {}).map(([key, items]) => (
+        <OutputKeySection key={key} outputKey={key} items={items} />
+      ))}
+    </ContentGrid>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunBlock/components/ErrorCard/ErrorCard.tsx

@@ -0,0 +1,27 @@
+"use client";
+
+import type { ErrorResponse } from "@/app/api/__generated__/models/errorResponse";
+import {
+  ContentCodeBlock,
+  ContentGrid,
+  ContentMessage,
+} from "../../../../components/ToolAccordion/AccordionContent";
+import { formatMaybeJson } from "../../helpers";
+
+interface Props {
+  output: ErrorResponse;
+}
+
+export function ErrorCard({ output }: Props) {
+  return (
+    <ContentGrid>
+      <ContentMessage>{output.message}</ContentMessage>
+      {output.error && (
+        <ContentCodeBlock>{formatMaybeJson(output.error)}</ContentCodeBlock>
+      )}
+      {output.details && (
+        <ContentCodeBlock>{formatMaybeJson(output.details)}</ContentCodeBlock>
+      )}
+    </ContentGrid>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunBlock/components/SetupRequirementsCard/SetupRequirementsCard.tsx

@@ -0,0 +1,197 @@
+"use client";
+
+import type { SetupRequirementsResponse } from "@/app/api/__generated__/models/setupRequirementsResponse";
+import { Button } from "@/components/atoms/Button/Button";
+import { Text } from "@/components/atoms/Text/Text";
+import { CredentialsGroupedView } from "@/components/contextual/CredentialsInput/components/CredentialsGroupedView/CredentialsGroupedView";
+import { FormRenderer } from "@/components/renderers/InputRenderer/FormRenderer";
+import type { CredentialsMetaInput } from "@/lib/autogpt-server-api/types";
+import { AnimatePresence, motion } from "framer-motion";
+import { useState } from "react";
+import { useCopilotChatActions } from "../../../../components/CopilotChatActionsProvider/useCopilotChatActions";
+import {
+  ContentBadge,
+  ContentCardDescription,
+  ContentCardTitle,
+  ContentMessage,
+} from "../../../../components/ToolAccordion/AccordionContent";
+import {
+  buildExpectedInputsSchema,
+  coerceCredentialFields,
+  coerceExpectedInputs,
+} from "./helpers";
+
+interface Props {
+  output: SetupRequirementsResponse;
+}
+
+export function SetupRequirementsCard({ output }: Props) {
+  const { onSend } = useCopilotChatActions();
+
+  const [inputCredentials, setInputCredentials] = useState<
+    Record<string, CredentialsMetaInput | undefined>
+  >({});
+  const [hasSentCredentials, setHasSentCredentials] = useState(false);
+
+  const [showInputForm, setShowInputForm] = useState(false);
+  const [inputValues, setInputValues] = useState<Record<string, unknown>>({});
+
+  const { credentialFields, requiredCredentials } = coerceCredentialFields(
+    output.setup_info.user_readiness?.missing_credentials,
+  );
+
+  const expectedInputs = coerceExpectedInputs(
+    (output.setup_info.requirements as Record<string, unknown>)?.inputs,
+  );
+
+  const inputSchema = buildExpectedInputsSchema(expectedInputs);
+
+  function handleCredentialChange(key: string, value?: CredentialsMetaInput) {
+    setInputCredentials((prev) => ({ ...prev, [key]: value }));
+  }
+
+  const isAllCredentialsComplete =
+    credentialFields.length > 0 &&
+    [...requiredCredentials].every((key) => !!inputCredentials[key]);
+
+  function handleProceedCredentials() {
+    setHasSentCredentials(true);
+    onSend(
+      "I've configured the required credentials. Please re-run the block now.",
+    );
+  }
+
+  function handleRunWithInputs() {
+    const nonEmpty = Object.fromEntries(
+      Object.entries(inputValues).filter(
+        ([, v]) => v !== undefined && v !== null && v !== "",
+      ),
+    );
+    onSend(
+      `Run the block with these inputs: ${JSON.stringify(nonEmpty, null, 2)}`,
+    );
+    setShowInputForm(false);
+    setInputValues({});
+  }
+
+  return (
+    <div className="grid gap-2">
+      <ContentMessage>{output.message}</ContentMessage>
+
+      {credentialFields.length > 0 && (
+        <div className="rounded-2xl border bg-background p-3">
+          <CredentialsGroupedView
+            credentialFields={credentialFields}
+            requiredCredentials={requiredCredentials}
+            inputCredentials={inputCredentials}
+            inputValues={{}}
+            onCredentialChange={handleCredentialChange}
+          />
+          {isAllCredentialsComplete && !hasSentCredentials && (
+            <Button
+              variant="primary"
+              size="small"
+              className="mt-3 w-full"
+              onClick={handleProceedCredentials}
+            >
+              Proceed
+            </Button>
+          )}
+        </div>
+      )}
+
+      {inputSchema && (
+        <div className="flex gap-2 pt-2">
+          <Button
+            variant="outline"
+            size="small"
+            className="w-fit"
+            onClick={() => setShowInputForm((prev) => !prev)}
+          >
+            {showInputForm ? "Hide inputs" : "Fill in inputs"}
+          </Button>
+        </div>
+      )}
+
+      <AnimatePresence initial={false}>
+        {showInputForm && inputSchema && (
+          <motion.div
+            initial={{ height: 0, opacity: 0, filter: "blur(6px)" }}
+            animate={{ height: "auto", opacity: 1, filter: "blur(0px)" }}
+            exit={{ height: 0, opacity: 0, filter: "blur(6px)" }}
+            transition={{
+              height: { type: "spring", bounce: 0.15, duration: 0.5 },
+              opacity: { duration: 0.25 },
+              filter: { duration: 0.2 },
+            }}
+            className="overflow-hidden"
+            style={{ willChange: "height, opacity, filter" }}
+          >
+            <div className="rounded-2xl border bg-background p-3 pt-4">
+              <Text variant="body-medium">Block inputs</Text>
+              <FormRenderer
+                jsonSchema={inputSchema}
+                handleChange={(v) => setInputValues(v.formData ?? {})}
+                uiSchema={{
+                  "ui:submitButtonOptions": { norender: true },
+                }}
+                initialValues={inputValues}
+                formContext={{
+                  showHandles: false,
+                  size: "small",
+                }}
+              />
+              <div className="-mt-8 flex gap-2">
+                <Button
+                  variant="primary"
+                  size="small"
+                  className="w-fit"
+                  onClick={handleRunWithInputs}
+                >
+                  Run
+                </Button>
+                <Button
+                  variant="secondary"
+                  size="small"
+                  className="w-fit"
+                  onClick={() => {
+                    setShowInputForm(false);
+                    setInputValues({});
+                  }}
+                >
+                  Cancel
+                </Button>
+              </div>
+            </div>
+          </motion.div>
+        )}
+      </AnimatePresence>
+
+      {expectedInputs.length > 0 && !inputSchema && (
+        <div className="rounded-2xl border bg-background p-3">
+          <ContentCardTitle className="text-xs">
+            Expected inputs
+          </ContentCardTitle>
+          <div className="mt-2 grid gap-2">
+            {expectedInputs.map((input) => (
+              <div key={input.name} className="rounded-xl border p-2">
+                <div className="flex items-center justify-between gap-2">
+                  <ContentCardTitle className="text-xs">
+                    {input.title}
+                  </ContentCardTitle>
+                  <ContentBadge>
+                    {input.required ? "Required" : "Optional"}
+                  </ContentBadge>
+                </div>
+                <ContentCardDescription className="mt-1">
+                  {input.name} &bull; {input.type}
+                  {input.description ? ` \u2022 ${input.description}` : ""}
+                </ContentCardDescription>
+              </div>
+            ))}
+          </div>
+        </div>
+      )}
+    </div>
+  );
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunBlock/components/SetupRequirementsCard/helpers.ts

@@ -0,0 +1,156 @@
+import type { CredentialField } from "@/components/contextual/CredentialsInput/components/CredentialsGroupedView/helpers";
+import type { RJSFSchema } from "@rjsf/utils";
+
+const VALID_CREDENTIAL_TYPES = new Set([
+  "api_key",
+  "oauth2",
+  "user_password",
+  "host_scoped",
+]);
+
+export function coerceCredentialFields(rawMissingCredentials: unknown): {
+  credentialFields: CredentialField[];
+  requiredCredentials: Set<string>;
+} {
+  const missing =
+    rawMissingCredentials && typeof rawMissingCredentials === "object"
+      ? (rawMissingCredentials as Record<string, unknown>)
+      : {};
+
+  const credentialFields: CredentialField[] = [];
+  const requiredCredentials = new Set<string>();
+
+  Object.entries(missing).forEach(([key, value]) => {
+    if (!value || typeof value !== "object") return;
+    const cred = value as Record<string, unknown>;
+
+    const provider =
+      typeof cred.provider === "string" ? cred.provider.trim() : "";
+    if (!provider) return;
+
+    const types =
+      Array.isArray(cred.types) && cred.types.length > 0
+        ? cred.types
+        : typeof cred.type === "string"
+          ? [cred.type]
+          : [];
+
+    const credentialTypes = types
+      .map((t) => (typeof t === "string" ? t.trim() : ""))
+      .filter((t) => VALID_CREDENTIAL_TYPES.has(t));
+
+    if (credentialTypes.length === 0) return;
+
+    const scopes = Array.isArray(cred.scopes)
+      ? cred.scopes.filter((s): s is string => typeof s === "string")
+      : undefined;
+
+    const schema = {
+      type: "object" as const,
+      properties: {},
+      credentials_provider: [provider],
+      credentials_types: credentialTypes,
+      credentials_scopes: scopes,
+    };
+
+    credentialFields.push([key, schema]);
+    requiredCredentials.add(key);
+  });
+
+  return { credentialFields, requiredCredentials };
+}
+
+export function coerceExpectedInputs(rawInputs: unknown): Array<{
+  name: string;
+  title: string;
+  type: string;
+  description?: string;
+  required: boolean;
+}> {
+  if (!Array.isArray(rawInputs)) return [];
+  const results: Array<{
+    name: string;
+    title: string;
+    type: string;
+    description?: string;
+    required: boolean;
+  }> = [];
+
+  rawInputs.forEach((value, index) => {
+    if (!value || typeof value !== "object") return;
+    const input = value as Record<string, unknown>;
+
+    const name =
+      typeof input.name === "string" && input.name.trim()
+        ? input.name.trim()
+        : `input-${index}`;
+    const title =
+      typeof input.title === "string" && input.title.trim()
+        ? input.title.trim()
+        : name;
+    const type = typeof input.type === "string" ? input.type : "unknown";
+    const description =
+      typeof input.description === "string" && input.description.trim()
+        ? input.description.trim()
+        : undefined;
+    const required = Boolean(input.required);
+
+    const item: {
+      name: string;
+      title: string;
+      type: string;
+      description?: string;
+      required: boolean;
+    } = { name, title, type, required };
+    if (description) item.description = description;
+    results.push(item);
+  });
+
+  return results;
+}
+
+/**
+ * Build an RJSF schema from expected inputs so they can be rendered
+ * as a dynamic form via FormRenderer.
+ */
+export function buildExpectedInputsSchema(
+  expectedInputs: Array<{
+    name: string;
+    title: string;
+    type: string;
+    description?: string;
+    required: boolean;
+  }>,
+): RJSFSchema | null {
+  if (expectedInputs.length === 0) return null;
+
+  const TYPE_MAP: Record<string, string> = {
+    string: "string",
+    str: "string",
+    text: "string",
+    number: "number",
+    int: "integer",
+    integer: "integer",
+    float: "number",
+    boolean: "boolean",
+    bool: "boolean",
+  };
+
+  const properties: Record<string, Record<string, unknown>> = {};
+  const required: string[] = [];
+
+  for (const input of expectedInputs) {
+    properties[input.name] = {
+      type: TYPE_MAP[input.type.toLowerCase()] ?? "string",
+      title: input.title,
+      ...(input.description ? { description: input.description } : {}),
+    };
+    if (input.required) required.push(input.name);
+  }
+
+  return {
+    type: "object",
+    properties,
+    ...(required.length > 0 ? { required } : {}),
+  };
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunBlock/helpers.tsx

@@ -0,0 +1,185 @@
+import type { BlockOutputResponse } from "@/app/api/__generated__/models/blockOutputResponse";
+import type { ErrorResponse } from "@/app/api/__generated__/models/errorResponse";
+import { ResponseType } from "@/app/api/__generated__/models/responseType";
+import type { SetupRequirementsResponse } from "@/app/api/__generated__/models/setupRequirementsResponse";
+import {
+  PlayCircleIcon,
+  PlayIcon,
+  WarningDiamondIcon,
+} from "@phosphor-icons/react";
+import type { ToolUIPart } from "ai";
+import { SpinnerLoader } from "../../components/SpinnerLoader/SpinnerLoader";
+
+export interface RunBlockInput {
+  block_id?: string;
+  input_data?: Record<string, unknown>;
+}
+
+export type RunBlockToolOutput =
+  | SetupRequirementsResponse
+  | BlockOutputResponse
+  | ErrorResponse;
+
+const RUN_BLOCK_OUTPUT_TYPES = new Set<string>([
+  ResponseType.setup_requirements,
+  ResponseType.block_output,
+  ResponseType.error,
+]);
+
+export function isRunBlockSetupRequirementsOutput(
+  output: RunBlockToolOutput,
+): output is SetupRequirementsResponse {
+  return (
+    output.type === ResponseType.setup_requirements ||
+    ("setup_info" in output && typeof output.setup_info === "object")
+  );
+}
+
+export function isRunBlockBlockOutput(
+  output: RunBlockToolOutput,
+): output is BlockOutputResponse {
+  return output.type === ResponseType.block_output || "block_id" in output;
+}
+
+export function isRunBlockErrorOutput(
+  output: RunBlockToolOutput,
+): output is ErrorResponse {
+  return output.type === ResponseType.error || "error" in output;
+}
+
+function parseOutput(output: unknown): RunBlockToolOutput | null {
+  if (!output) return null;
+  if (typeof output === "string") {
+    const trimmed = output.trim();
+    if (!trimmed) return null;
+    try {
+      return parseOutput(JSON.parse(trimmed) as unknown);
+    } catch {
+      return null;
+    }
+  }
+  if (typeof output === "object") {
+    const type = (output as { type?: unknown }).type;
+    if (typeof type === "string" && RUN_BLOCK_OUTPUT_TYPES.has(type)) {
+      return output as RunBlockToolOutput;
+    }
+    if ("block_id" in output) return output as BlockOutputResponse;
+    if ("setup_info" in output) return output as SetupRequirementsResponse;
+    if ("error" in output || "details" in output)
+      return output as ErrorResponse;
+  }
+  return null;
+}
+
+export function getRunBlockToolOutput(
+  part: unknown,
+): RunBlockToolOutput | null {
+  if (!part || typeof part !== "object") return null;
+  return parseOutput((part as { output?: unknown }).output);
+}
+
+export function getAnimationText(part: {
+  state: ToolUIPart["state"];
+  input?: unknown;
+  output?: unknown;
+}): string {
+  const input = part.input as RunBlockInput | undefined;
+  const blockId = input?.block_id?.trim();
+  const blockText = blockId ? ` "${blockId}"` : "";
+
+  switch (part.state) {
+    case "input-streaming":
+    case "input-available":
+      return `Running the block${blockText}`;
+    case "output-available": {
+      const output = parseOutput(part.output);
+      if (!output) return `Running the block${blockText}`;
+      if (isRunBlockBlockOutput(output)) return `Ran "${output.block_name}"`;
+      if (isRunBlockSetupRequirementsOutput(output)) {
+        return `Setup needed for "${output.setup_info.agent_name}"`;
+      }
+      return "Error running block";
+    }
+    case "output-error":
+      return "Error running block";
+    default:
+      return "Running the block";
+  }
+}
+
+export function ToolIcon({
+  isStreaming,
+  isError,
+}: {
+  isStreaming?: boolean;
+  isError?: boolean;
+}) {
+  if (isError) {
+    return (
+      <WarningDiamondIcon size={14} weight="regular" className="text-red-500" />
+    );
+  }
+  if (isStreaming) {
+    return <SpinnerLoader size={40} className="text-neutral-700" />;
+  }
+  return <PlayIcon size={14} weight="regular" className="text-neutral-400" />;
+}
+
+export function AccordionIcon() {
+  return <PlayCircleIcon size={32} weight="light" />;
+}
+
+export function formatMaybeJson(value: unknown): string {
+  if (typeof value === "string") return value;
+  try {
+    return JSON.stringify(value, null, 2);
+  } catch {
+    return String(value);
+  }
+}
+
+export function getAccordionMeta(output: RunBlockToolOutput): {
+  icon: React.ReactNode;
+  title: string;
+  titleClassName?: string;
+  description?: string;
+} {
+  const icon = <AccordionIcon />;
+
+  if (isRunBlockBlockOutput(output)) {
+    const keys = Object.keys(output.outputs ?? {});
+    return {
+      icon: <SpinnerLoader size={32} className="text-neutral-700" />,
+      title: output.block_name,
+      description:
+        keys.length > 0
+          ? `${keys.length} output key${keys.length === 1 ? "" : "s"}`
+          : output.message,
+    };
+  }
+
+  if (isRunBlockSetupRequirementsOutput(output)) {
+    const missingCredsCount = Object.keys(
+      (output.setup_info.user_readiness?.missing_credentials ?? {}) as Record<
+        string,
+        unknown
+      >,
+    ).length;
+    return {
+      icon,
+      title: output.setup_info.agent_name,
+      description:
+        missingCredsCount > 0
+          ? `Missing ${missingCredsCount} credential${missingCredsCount === 1 ? "" : "s"}`
+          : output.message,
+    };
+  }
+
+  return {
+    icon: (
+      <WarningDiamondIcon size={32} weight="light" className="text-red-500" />
+    ),
+    title: "Error",
+    titleClassName: "text-red-500",
+  };
+}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/SearchDocs/SearchDocs.tsx

@@ -0,0 +1,186 @@
+"use client";
+
+import type { ToolUIPart } from "ai";
+import { useMemo } from "react";
+
+import { MorphingTextAnimation } from "../../components/MorphingTextAnimation/MorphingTextAnimation";
+import {
+  ContentCard,
+  ContentCardDescription,
+  ContentCardHeader,
+  ContentCardSubtitle,
+  ContentCardTitle,
+  ContentGrid,
+  ContentLink,
+  ContentMessage,
+  ContentSuggestionsList,
+} from "../../components/ToolAccordion/AccordionContent";
+import { ToolAccordion } from "../../components/ToolAccordion/ToolAccordion";
+import {
+  AccordionIcon,
+  getAnimationText,
+  getDocsToolOutput,
+  getDocsToolTitle,
+  getToolLabel,
+  isDocPageOutput,
+  isDocSearchResultsOutput,
+  isErrorOutput,
+  isNoResultsOutput,
+  toDocsUrl,
+  ToolIcon,
+  type DocsToolType,
+} from "./helpers";
+
+export interface DocsToolPart {
+  type: DocsToolType;
+  toolCallId: string;
+  state: ToolUIPart["state"];
+  input?: unknown;
+  output?: unknown;
+}
+
+interface Props {
+  part: DocsToolPart;
+}
+
+function truncate(text: string, maxChars: number): string {
+  const trimmed = text.trim();
+  if (trimmed.length <= maxChars) return trimmed;
+  return `${trimmed.slice(0, maxChars).trimEnd()}…`;
+}
+
+export function SearchDocsTool({ part }: Props) {
+  const output = getDocsToolOutput(part);
+  const text = getAnimationText(part);
+  const isStreaming =
+    part.state === "input-streaming" || part.state === "input-available";
+  const isError =
+    part.state === "output-error" || (!!output && isErrorOutput(output));
+
+  const normalized = useMemo(() => {
+    if (!output) return null;
+    const title = getDocsToolTitle(part.type, output);
+    const label = getToolLabel(part.type);
+    return { title, label };
+  }, [output, part.type]);
+
+  const isOutputAvailable = part.state === "output-available" && !!output;
+
+  const docSearchOutput =
+    isOutputAvailable && output && isDocSearchResultsOutput(output)
+      ? output
+      : null;
+  const docPageOutput =
+    isOutputAvailable && output && isDocPageOutput(output) ? output : null;
+  const noResultsOutput =
+    isOutputAvailable && output && isNoResultsOutput(output) ? output : null;
+  const errorOutput =
+    isOutputAvailable && output && isErrorOutput(output) ? output : null;
+
+  const hasExpandableContent =
+    isOutputAvailable &&
+    ((!!docSearchOutput && docSearchOutput.count > 0) ||
+      !!docPageOutput ||
+      !!noResultsOutput ||
+      !!errorOutput);
+
+  const accordionDescription =
+    hasExpandableContent && docSearchOutput
+      ? `Found ${docSearchOutput.count} result${docSearchOutput.count === 1 ? "" : "s"} for "${docSearchOutput.query}"`
+      : hasExpandableContent && docPageOutput
+        ? docPageOutput.path
+        : hasExpandableContent && (noResultsOutput || errorOutput)
+          ? ((noResultsOutput ?? errorOutput)?.message ?? null)
+          : null;
+
+  return (
+    <div className="py-2">
+      <div className="flex items-center gap-2 text-sm text-muted-foreground">
+        <ToolIcon
+          toolType={part.type}
+          isStreaming={isStreaming}
+          isError={isError}
+        />
+        <MorphingTextAnimation
+          text={text}
+          className={isError ? "text-red-500" : undefined}
+        />
+      </div>
+
+      {hasExpandableContent && normalized && (
+        <ToolAccordion
+          icon={<AccordionIcon toolType={part.type} />}
+          title={normalized.title}
+          description={accordionDescription}
+        >
+          {docSearchOutput && (
+            <ContentGrid>
+              {docSearchOutput.results.map((r) => {
+                const href = r.doc_url ?? toDocsUrl(r.path);
+                return (
+                  <ContentCard key={r.path}>
+                    <ContentCardHeader
+                      action={<ContentLink href={href}>Open</ContentLink>}
+                    >
+                      <ContentCardTitle>{r.title}</ContentCardTitle>
+                      <ContentCardSubtitle>
+                        {r.path}
+                        {r.section ? ` • ${r.section}` : ""}
+                      </ContentCardSubtitle>
+                      <ContentCardDescription>
+                        {truncate(r.snippet, 240)}
+                      </ContentCardDescription>
+                    </ContentCardHeader>
+                  </ContentCard>
+                );
+              })}
+            </ContentGrid>
+          )}
+
+          {docPageOutput && (
+            <div>
+              <ContentCardHeader
+                action={
+                  <ContentLink
+                    href={
+                      docPageOutput.doc_url ?? toDocsUrl(docPageOutput.path)
+                    }
+                  >
+                    Open
+                  </ContentLink>
+                }
+              >
+                <ContentCardTitle>{docPageOutput.title}</ContentCardTitle>
+                <ContentCardSubtitle>{docPageOutput.path}</ContentCardSubtitle>
+              </ContentCardHeader>
+              <ContentCardDescription className="whitespace-pre-wrap">
+                {truncate(docPageOutput.content, 800)}
+              </ContentCardDescription>
+            </div>
+          )}
+
+          {noResultsOutput && (
+            <div>
+              <ContentMessage>{noResultsOutput.message}</ContentMessage>
+              {noResultsOutput.suggestions &&
+                noResultsOutput.suggestions.length > 0 && (
+                  <ContentSuggestionsList items={noResultsOutput.suggestions} />
+                )}
+            </div>
+          )}
+
+          {errorOutput && (
+            <div>
+              <ContentMessage>{errorOutput.message}</ContentMessage>
+              {errorOutput.error && (
+                <ContentCardDescription>
+                  {errorOutput.error}
+                </ContentCardDescription>
+              )}
+            </div>
+          )}
+        </ToolAccordion>
+      )}
+    </div>
+  );
+}