Waleed Latif
c8f4df7683
scaffolding for blog post
2026-02-11 01:06:19 -08:00
Waleed
2f492cacc1
feat(providers): add Gemini Deep Research via Interactions API ( #3192 )
...
* feat(providers): add Gemini Deep Research via Interactions API
* fix(providers): hide memory UI for deep research models
* feat(providers): add multi-turn support and token logging for deep research
* fix(providers): only collect user messages as deep research input
* fix(providers): forward previousInteractionId to provider request
* fix(blocks): hide memory child fields for deep research models
* remove memory params from models that don't support it in provider requests
* update blog
2026-02-11 01:01:59 -08:00
Vikhyath Mondreti
5792e7e5f9
fix(auth): workflow system handler ( #3193 )
2026-02-10 22:25:48 -08:00
Waleed
3d5bd003ef
fix(triggers): add copilot as a trigger type ( #3191 )
...
* fix(triggers): add copilot as a trigger type
* update color
2026-02-10 21:36:38 -08:00
Waleed
13a91113fd
fix(logs): surface handled errors as info in logs ( #3190 )
...
* fix(logs): surface handled errors as info in logs
* pr comments
2026-02-10 21:21:45 -08:00
Vikhyath Mondreti
af01dce2c3
fix(terminal): subflow logs rendering ( #3189 )
2026-02-10 21:16:05 -08:00
Waleed
8a24b56f51
improvement(terminal): increase workflow logs limit from 1k to 5k per workflow ( #3188 )
2026-02-10 20:11:49 -08:00
Waleed
c471627ce1
fix(posthog): replace proxy rewrite with route handler for reliable body streaming ( #3187 )
...
* fix(posthog): replace proxy rewrite with route handler for reliable body streaming
* fix posthog
2026-02-10 20:05:38 -08:00
Waleed
f5dc180d9f
fix(memory): upgrade bun from 1.3.3 to 1.3.9 ( #3186 )
2026-02-10 19:30:31 -08:00
Waleed
78fef22d0e
fix(execution): scope execution state per workflow to prevent cross-workflow bleed ( #3183 )
...
* fix(execution): scope execution state per workflow to prevent cross-workflow bleed
* fix(execution): use validated workflowId param instead of non-null assertion in handleRunUntilBlock
* improvement(execution): use individual selectors to avoid unnecessary re-renders from unselectored store hook
* improvement(execution): use useShallow selector in workflow.tsx to avoid re-renders from lastRunPath/lastRunEdges changes
2026-02-10 18:17:50 -08:00
Waleed
6d16f216c8
improvement(mcp): improved mcp sse events notifs, update jira to handle files, fix UI issues in settings modal, fix org and workspace invitations when bundled ( #3182 )
...
* improvement(mcp): improved mcp sse events notifs, update jira to handle files, fix UI issues in settings modal, fix org and workspace invitations when bundled
* added back useMcpToolsEvents for event-driven discovery
* ack PR comments
* updated placeholder
* updated colors, error throwing in mcp modal
* ack comments
* updated error msg
2026-02-10 17:08:57 -08:00
Waleed
f8e9614c9c
improvement(helm): support copilot-only deployments ( #3185 )
2026-02-10 17:03:11 -08:00
Siddharth Ganesan
c5dd90e79d
feat(copilot): enterprise configuration ( #3184 )
...
* Copilot enterprise models
* Fix azure anthropic
* Fix
* Consolidation
* Cleanup
* Clean up code
* Fix lint
* cleanup
* Fix greptile
2026-02-10 16:37:30 -08:00
Vikhyath Mondreti
20b230d1aa
improvement(schema): centralize derivation of block schemas ( #3175 )
...
* improvement(schema): centralize derivation of block schemas
* address bugbot comments
* remove unused code
* address greptile comments
* merge conflict resolution
* fix
* update tests
* address greptile comments
* make evaluator metrics only
* return base and metrics for evaluator
2026-02-10 16:31:50 -08:00
Vikhyath Mondreti
be3cdcf981
Merge pull request #3179 from simstudioai/improvement/file-download-timeouts
...
improvement(timeouts): files/base64 should use max timeouts + auth centralization
2026-02-10 15:57:06 -08:00
Emir Karabeg
73540e3936
feat(logs): add skill icon to trace spans ( #3181 )
...
Adds the AgentSkillsIcon to trace spans in logs when displaying the
load_skill tool. Previously, skills appeared with a default gray color.
Now they display with the proper skill icon and a purple (#8B5CF6)
background color, consistent with the skills icon used in the settings
modal and skill input components.
Co-authored-by: Cursor Agent <cursoragent@cursor.com >
Co-authored-by: Emir Karabeg <emir-karabeg@users.noreply.github.com >
2026-02-10 12:46:21 -08:00
Waleed
e321f883b0
improvement(preview): added trigger mode context for deploy preview ( #3177 )
...
* improvement(preview): added trigger mode context for deploy preview
* use existing helper
* enhance disabled mode for subblocks
* update
* update all subblocks to allow scrolling in read only mode
* updated short and long input to match others, reverted triggerutils change
2026-02-09 20:32:30 -08:00
Waleed
8b4b3af120
fix(mcp): harden notification system against race conditions ( #3168 )
...
* fix(mcp): harden notification system against race conditions
- Guard concurrent connect() calls in connection manager with connectingServers Set
- Suppress post-disconnect notification handler firing in MCP client
- Clean up Redis event listeners in pub/sub dispose()
- Add tests for all three hardening fixes (11 new tests)
* updated tests
* plugged in new mcp event based system and create sse route to publish notifs
* ack commetns
* fix reconnect timer
* cleanup when running onClose
* fixed spacing on mcp settings tab
* keep error listeners before quiet in redis
2026-02-09 19:36:01 -08:00
Siddharth Ganesan
190f12fd77
feat(copilot): copilot mcp + server side copilot execution ( #3173 )
...
* v0
* v1
* Basic ss tes
* Ss tests
* Stuff
* Add mcp
* mcp v1
* Improvement
* Fix
* BROKEN
* Checkpoint
* Streaming
* Fix abort
* Things are broken
* Streaming seems to work but copilot is dumb
* Fix edge issue
* LUAAAA
* Fix stream buffer
* Fix lint
* Checkpoint
* Initial temp state, in the middle of a refactor
* Initial test shows diff store still working
* Tool refactor
* First cleanup pass complete - untested
* Continued cleanup
* Refactor
* Refactor complete - no testing yet
* Fix - cursor makes me sad
* Fix mcp
* Clean up mcp
* Updated mcp
* Add respond to subagents
* Fix definitions
* Add tools
* Add tools
* Add copilot mcp tracking
* Fix lint
* Fix mcp
* Fix
* Updates
* Clean up mcp
* Fix copilot mcp tool names to be sim prefixed
* Add opus 4.6
* Fix discovery tool
* Fix
* Remove logs
* Fix go side tool rendering
* Update docs
* Fix hydration
* Fix tool call resolution
* Fix
* Fix lint
* Fix superagent and autoallow integrations
* Fix always allow
* Update block
* Remove plan docs
* Fix hardcoded ff
* Fix dropped provider
* Fix lint
* Fix tests
* Fix dead messages array
* Fix discovery
* Fix run workflow
* Fix run block
* Fix run from block in copilot
* Fix lint
* Fix skip and mtb
* Fix typing
* Fix tool call
* Bump api version
* Fix bun lock
* Nuke bad files
2026-02-09 19:33:29 -08:00
Waleed
e5d30494cb
fix(slack): resolve file metadata via files.info when event payload is partial ( #3176 )
2026-02-09 19:29:38 -08:00
Waleed
b3dbb4487f
improvement(jsm): destructured outputs for jsm, jira, and added 1password integration ( #3174 )
...
* improvement(jsm): destructured outputs for jsm, jira, and added 1password integration
* update 1password to support cloud & locally hosted
* updated & tested 1pass
* added an additional wandConfig for OnePassword & jira search issues
* finished jira
* removed unused route
* updated types
* restore old outputs
* updated types
2026-02-09 19:28:34 -08:00
Waleed
622d0cad22
Merge pull request #3172 from simstudioai/fix/notifs
...
fix(notifications): throw notification on runtime errors, move predeploy checks to update in deploy modal
2026-02-09 11:49:58 -08:00
Vikhyath Mondreti
c74922997c
fix(triggers): id resolution for tools with trigger mode ( #3170 )
2026-02-09 10:28:34 -08:00
Emir Karabeg
4193007ab7
improvement(ui): deploy modal, terminal ( #3167 )
...
* improvement(deploy-modal): error and warning ui
* fix(ui): terminal top border render
2026-02-08 11:08:54 -08:00
Waleed
f9b885f6d5
fix(models): add request sanitization ( #3165 )
2026-02-07 19:04:15 -08:00
Vikhyath Mondreti
0cb6714496
fix(rooms): cleanup edge case for 1hr ttl ( #3163 )
...
* fix(rooms): cleanup edge case for 1hr ttl
* revert feature flags
* address comments
* remove console log
2026-02-07 12:18:07 -08:00
Waleed
7b36f9257e
improvement(models): reorder models dropdown ( #3164 )
2026-02-07 12:05:10 -08:00
Waleed
99ae5435e3
feat(models): updated model configs, updated anthropic provider to propagate errors back to user if any ( #3159 )
...
* feat(models): updated model configs, updated anthropic provider to propagate errors back to user if any
* moved max tokens to advanced
* updated model configs and testesd
* removed default in max config for output tokens
* moved more stuff to advanced mode in the agent block
* stronger typing
* move api key under model, update mistral and groq
* update openrouter, fixed serializer to allow ollama/vllm models without api key
* removed ollama handling
2026-02-06 22:35:57 -08:00
Vikhyath Mondreti
925f06add7
improvement(preview): render nested values like input format correctly in workflow execution preview ( #3154 )
...
* improvement(preview): nested workflow snapshots/preview when not executed
* improvements to resolve nested subblock values
* few more things
* add try catch
* fix fallback case
* deps
2026-02-06 22:12:40 -08:00
Vikhyath Mondreti
193b95cfec
fix(auth): swap out hybrid auth in relevant callsites ( #3160 )
...
* fix(logs): execution files should always use our internal route
* correct degree of access control
* fix tests
* fix tag defs flag
* fix type check
* fix mcp tools
* make webhooks consistent
* fix ollama and vllm visibility
* remove dup test
2026-02-06 22:07:55 -08:00
Waleed
0ca25bbab6
fix(function): isolated-vm worker pool to prevent single-worker bottleneck + execution user id resolution ( #3155 )
...
* fix(executor): isolated-vm worker pool to prevent single-worker bottleneck
* chore(helm): add isolated-vm worker pool env vars to values.yaml
* fix(userid): resolution for fair scheduling
* add fallback back
* add to helm charts
* remove constant fallbacks
* fix
* address bugbot comments
* fix fallbacks
* one more bugbot comment
---------
Co-authored-by: Vikhyath Mondreti <vikhyath@simstudio.ai >
2026-02-06 18:34:03 -08:00
Waleed
1edaf197b2
fix(azure): add azure-anthropic support to router, evaluator, copilot, and tokenization ( #3158 )
...
* fix(azure): add azure-anthropic support to router, evaluator, copilot, and tokenization
* added azure anthropic values to env
* fix(azure): make anthropic-version configurable for azure-anthropic provider
* fix(azure): thread provider credentials through guardrails and fix translate missing bedrockAccessKeyId
* updated guardrails
* ack'd PR comments
* fix(azure): unify credential passing pattern across all LLM handlers
- Pass all provider credentials unconditionally in router, evaluator (matching agent pattern)
- Remove conditional if-branching on providerId for credential fields
- Thread workspaceId through guardrails → hallucination validator for BYOK key resolution
- Remove getApiKey() from hallucination validator, let executeProviderRequest handle it
- Resolve vertex OAuth credentials in hallucination validator matching agent handler pattern
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-06 15:26:10 -08:00
Waleed
474b1af145
improvement(ui): improved skills UI, validation, and permissions ( #3156 )
...
* improvement(ui): improved skills UI, validation, and permissions
* stronger typing for Skill interface
* added missing docs description
* ack comment
2026-02-06 13:11:56 -08:00
Ewan Tauran
1e21ec1fa3
feat(airweave): add airweave block ( #3079 )
...
* feat(icons): add Airweave icon and update registry with Airweave block and tool
* feat(icons): add Airweave icon and update icon mapping and metadata
* fix(search): update API key header from Authorization to X-API-Key for Airweave search tool
* refactor(icon-mapping): reorder icon imports for consistency and formatting improvements; update airweave block retrieval strategy description formatting; add newline at end of meta.json
* refactor(search): update visibility settings for retrieval strategy and query options to allow access for both users and LLMs
2026-02-06 11:43:06 -08:00
Waleed
71bd535d04
feat(skills): added skills to agent block ( #3149 )
...
* feat(skills): added skills to agent block
* improvement(skills): audit fixes, docs, icon, and UX polish
* fix(skills): consolidate redundant permission checks in POST and DELETE
* more friendly error for duplicate skills in the same workspace
* fix(executor): loop sentinel-end wrongly queued (#3148 )
* fix(executor): loop sentinel-end wrongly queued
* fix nested subflow error highlighting
* fix(linear): align tool outputs, queries, and pagination with API (#3150 )
* fix(linear): align tool outputs, queries, and pagination with API
* fix(linear): coerce first param to number, remove duplicate conditions, add null guard
* fix(resolver): response format and evaluator metrics in deactivated branch (#3152 )
* fix(resolver): response format in deactivated branch
* add evaluator metrics too
* add child workflow id to the workflow block outputs
* cleanup typing
* feat(slack): add file attachment support to slack webhook trigger (#3151 )
* feat(slack): add file attachment support to slack webhook trigger
* additional file handling
* lint
* ack comment
* fix(skills): hide skill selection when disabled, remove dead code
---------
Co-authored-by: Vikhyath Mondreti <vikhyathvikku@gmail.com >
2026-02-06 11:38:38 -08:00
Waleed
ed5ed97c07
feat(slack): add file attachment support to slack webhook trigger ( #3151 )
...
* feat(slack): add file attachment support to slack webhook trigger
* additional file handling
* lint
* ack comment
2026-02-06 00:27:17 -08:00
Vikhyath Mondreti
65de27330e
fix(resolver): response format and evaluator metrics in deactivated branch ( #3152 )
...
* fix(resolver): response format in deactivated branch
* add evaluator metrics too
* add child workflow id to the workflow block outputs
* cleanup typing
2026-02-06 00:14:43 -08:00
Waleed
c0b22a6490
fix(linear): align tool outputs, queries, and pagination with API ( #3150 )
...
* fix(linear): align tool outputs, queries, and pagination with API
* fix(linear): coerce first param to number, remove duplicate conditions, add null guard
2026-02-05 18:44:24 -08:00
Vikhyath Mondreti
9dcf92bd14
fix(executor): loop sentinel-end wrongly queued ( #3148 )
...
* fix(executor): loop sentinel-end wrongly queued
* fix nested subflow error highlighting
2026-02-05 15:31:15 -08:00
Waleed
1d4d61a10a
feat(azure): added azure anthropic, added backwards compat support for chat completions API, added opus 4.6 ( #3145 )
...
* feat(azure): added azure anthropic, added backwards compat support for chat completions API, added opus 4.6
* added max thinking level
* update tests
* ack comments
* update cql validation
2026-02-05 10:52:18 -08:00
Vikhyath Mondreti
2d7e6c9796
fix(client-exec): send correct client workflow state override ( #3143 )
2026-02-04 23:53:09 -08:00
Vikhyath Mondreti
ea3bab1f76
fix(inputs): canonical params + manual validations + params resolution cleanups ( #3141 )
...
* fix(onedrive): canonical param required validation
* fix onedrive
* cleanup canonical tool param resolution code
* fix type
* fix jira type checks
* remove manual validations
2026-02-04 22:58:51 -08:00
Waleed
552dc56fc3
feat(confluence): added more confluence endpoints ( #3139 )
...
* feat(confluence): added more confluence endpoints
* update license
* updated
* updated docs
2026-02-04 19:46:28 -08:00
Waleed
2147309365
fix(tracespans): update tracespans tool calls to accurately display inputs for successive identical tool calls ( #3140 )
2026-02-04 19:32:18 -08:00
Waleed
36ec68d93e
fix(serializer): validate required fields for blocks without tools ( #3137 )
2026-02-04 16:47:18 -08:00
Vikhyath Mondreti
fce566cc2f
fix(mistral): restore mistral configs for v2 version ( #3138 )
2026-02-04 16:03:04 -08:00
Siddharth Ganesan
1933e1aad5
improvement(openai): migrate to responses api ( #3135 )
...
* Migrate openai to use responses api
* Consolidate azure
* Fix streaming
* Bug fixes
* Bug fixes
* Fix responseformat
* Refactor
* Fix bugs
* Fix
* Fix azure openai response format with tool calls
* Fixes
* Fixes
* Fix temp
2026-02-04 15:50:18 -08:00
Waleed
793adda986
fix(limits): updated rate limiter to match execution timeouts, adjusted timeouts fallback to be free plan ( #3136 )
...
* fix(limits): updated rate limiter to match execution timeouts, adjusted timeouts fallback to be free plan
* upgrade turborepo
2026-02-04 15:31:53 -08:00
Waleed
8d846c5983
feat(async-jobs): async execution with job queue backends ( #3134 )
...
* feat(async-jobs): async execution with job queue backends
* added migration
* remove unused envvar, remove extraneous comments
* ack comment
* same for db
* added dedicated async envvars for timeouts, updated helm
* updated comment
* ack comment
* migrated routes to be more restful
* ack comments
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-04 14:52:33 -08:00
Vikhyath Mondreti
362f4c2918
improvement(timeouts): sync to 50 min, self-hosted maxed out ( #3133 )
...
* improvement(timeouts): sync to 50 min, self-hosted maxed out
* update env vars
2026-02-04 11:27:41 -08:00