## Changes 🏗️
Setup for the new Agent Runs page:
<img width="900" height="521" alt="Screenshot 2025-08-15 at 14 36 34"
src="https://github.com/user-attachments/assets/460d6611-4b15-4878-92d3-b477dc4453a9"
/>
It is behind a feature flag in Launch Darkly, `new-agent-runs`, so we
can progressively enable in staging and later on production.
### Other improvements
<img width="350" height="291" alt="Screenshot_2025-08-15_at_14 28 08"
src="https://github.com/user-attachments/assets/972d2a1a-a4cd-4e92-b6d7-2dcf7f57c2db"
/>
- Added a new `<ErrorCard />` component to paint gracefully API errors
when fetching data
- Moved some sub-components of the old library page to a nested
`/components` folder 📁
Behind a feature flag
## Checklist 📋
### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Tested with the feature flag ON and OFF
### For configuration changes:
None
---------
Co-authored-by: Abhimanyu Yadav <122007096+Abhi1992002@users.noreply.github.com>
In this project, I’ve added all the reusable, non-reactive components
that will be used in the new block menu. I’ve also included a new
library called `react-timeago` that helps us find related times.
### Checklist 📋
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Everything works perfectly locally
## Changes 🏗️
- Run the API query generation as part of the `dev` command
- update the `README` to reflect so
- Add CI job to generate queries and type-check to make sure we are not
out of sync
- the job is run both in Front-end and Back-end changes
- Generate the files via script to load the BE URL dynamically from the
env
- Remove generated files from Git
- rename the `type-check` command to `types`
## Checklist 📋
### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] CI passes
- [x] `README` updates make sense
#### For configuration changes:
None
---------
Co-authored-by: Zamil Majdy <zamil.majdy@agpt.co>
## Changes 🏗️
We had 2 flaky end-to-end tests:
- Build page → user can add two blocks and connect them
- this was failing sometimes because the `Run` button on the builder
does not work well, sometimes you need to click it twice for it to
work...
- Agent dashboard → edit actions
- some flaky tests asserting agent submissions not being there, pulled
the fixes from Abhi here on this PR
https://github.com/Significant-Gravitas/AutoGPT/pull/10545
## Checklist 📋
### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] E2E pass on the CI
- [x] Changes make sense
### For configuration changes:
None
## Changes 🏗️
Add the following caps to the **Agent Activity Dropdown**:
- display activity only from the last 72h
- display up to 1000 items
## Checklist 📋
### For code changes
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Open the agent activity with a big amount of times locally
- [x] It displays up to a 1000 and with 72h cap
### For configuration changes
None
Co-authored-by: Abhimanyu Yadav <122007096+Abhi1992002@users.noreply.github.com>
When the FirecrawlExtractBlock receives an output_schema, we currently
declare the field as a str.
Pydantic therefore serialises the JSON‐looking value into a string and
the Firecrawl API rejects the request with:
`400 Bad Request – Invalid JSON schema. path: ['schema']`
Direct curl requests work because the same structure is sent as a proper
JSON object.
### Changes 🏗️
- Changed the output_schema to dict instead of str
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Test firebase.extract(..., schema) works with dict rather than str
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
- Resolves#10444
Sometimes, the order of nodes and/or links isn't consistent between
frontend and backend, which currently can result in unnecessary
re-saving of the graph when the user tries to run it.
Also, `sub_graphs` was not included in the frontend `Graph` type, which
can cause unchecked code issues when the object is propragated using
spread operators.
### Changes 🏗️
- fix(frontend/builder): Make `graphsEquivalent` insensitive to link and
node order
- dx(frontend): Fix typing of `Graph.sub_graphs` (and its variants)
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- Import an agent and open it in the builder
- Run it without making any changes to the graph itself
- [x] -> graph shouldn't re-save
<!-- Clearly explain the need for these changes: -->
## 🚨 CRITICAL: Double Transaction Bug
**Critical Issue:** Top-up transactions were being applied TWICE to user
balances, causing severe accounting errors.
**Example:**
- User with $160 balance tops up $50
- Expected: $210 balance
- Actual: $260 balance (extra $50 incorrectly credited)
This compromises the financial integrity of our credit system and
requires immediate fix.
### Changes 🏗️
1. **Added double-checked locking pattern in `_enable_transaction`**
(backend/data/credit.py)
- Added transaction re-check INSIDE the locked transaction block (lines
294-298)
- Prevents race condition when concurrent requests try to activate the
same transaction
- Ensures transaction can only be activated once, even with webhook
retries
2. **Enhanced error messages in Stripe webhook handler**
(backend/server/routers/v1.py)
- Added detailed error messages for better debugging of webhook failures
- Helps identify issues with payload validation or signature
verification
### Root Cause Analysis 🔍
**TOCTOU (Time-of-Check to Time-of-Use) Race Condition:**
The original code checked `transaction.isActive` outside the database
lock. Between this check and acquiring the lock, another concurrent
request (webhook retry or duplicate) could enter, causing both to
proceed with activation.
**Sequence:**
1. Request A: Checks `isActive=False` ✅
2. Request B: Checks `isActive=False` ✅ (webhook retry)
3. Request A: Acquires lock, activates transaction, adds $50
4. Request B: Waits for lock, then ALSO adds $50 ❌
**Contributing Factors:**
- Stripe webhook retry mechanism
- `@func_retry` decorator (up to 5 attempts)
- No database-level unique constraint on active transactions
- Missing atomicity between check and update
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
<!-- Put your test plan here: -->
- [x] Verified the double-check prevents duplicate transaction
activation
- [x] Tested concurrent webhook calls - only one succeeds in activating
transaction
- [x] Confirmed balance is only incremented once per transaction
- [x] Verified idempotency - multiple calls with same transaction_key
are safe
- [x] All existing credit system tests pass
- [x] Tested webhook error handling with invalid payloads/signatures
#### For configuration changes:
- [x] `.env.example` is updated or already compatible with my changes
- [x] `docker-compose.yml` is updated or already compatible with my
changes
- [x] I have included a list of my configuration changes in the PR
description (under **Changes**)
*Note: No configuration changes required - this is a code-only fix*
I’ve added a new launch darkly flag to toggle between the new and old
block menu in the builder.
### Changes 🏗️
- A new flag name `NEW_BLOCK_MENU` has been added.
- A new block menu block has been created, which is a normal component.
It will be expanded with more components in the future. Currently, it’s
just a one-line component.
- A new control panel has been created, which improves state
localisation and has a new design according to the design files.
<img width="1512" height="981" alt="Screenshot 2025-08-18 at 2 49 54 PM"
src="https://github.com/user-attachments/assets/3deeefe3-9e42-4178-9cf9-77773ed7e172"
/>
### Checklist 📋
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Everything works perfectly on local.
This should fix sub-agent execution issues with passed-in credentials after a crucial data path was removed in #10568.
Additionally, some of the changes are to ensure the `credentials_input_schema` gets refreshed correctly when saving a new version of a graph in the builder.
### Changes 🏗️
- Include `graph_credentials_inputs` in `nodes_input_masks` passed into sub-agent execution
- Fix credentials input schema in `update_graph` and `get_library_agent_by_graph_id` return
- Improve error message on sub-graph validation failure
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Import agent with sub-agent(s) with required credentials inputs & run it -> should work
Added language selection links to the README for easier access to
translated versions: German, Spanish, French, Japanese, Korean,
Portuguese, Russian, and Chinese.
<!-- Clearly explain the need for these changes: -->
### Changes 🏗️
<!-- Concisely describe all of the changes made in this pull request:
-->
### Checklist 📋
#### For code changes:
- [ ] I have clearly listed my changes in the PR description
- [ ] I have made a test plan
- [ ] I have tested my changes according to the test plan:
<!-- Put your test plan here: -->
- [ ] ...
<details>
<summary>Example test plan</summary>
- [ ] Create from scratch and execute an agent with at least 3 blocks
- [ ] Import an agent from file upload, and confirm it executes
correctly
- [ ] Upload agent to marketplace
- [ ] Import an agent from marketplace and confirm it executes correctly
- [ ] Edit an agent from monitor, and confirm it executes correctly
</details>
#### For configuration changes:
- [ ] `.env.example` is updated or already compatible with my changes
- [ ] `docker-compose.yml` is updated or already compatible with my
changes
- [ ] I have included a list of my configuration changes in the PR
description (under **Changes**)
<details>
<summary>Examples of configuration changes</summary>
- Changing ports
- Adding new services that need to communicate with each other
- Secrets or environment variable changes
- New or infrastructure changes such as databases
</details>
Co-authored-by: Zamil Majdy <zamil.majdy@agpt.co>
## Summary
- Fixes scheduler pod crashes during peak scheduling periods (e.g.,
03:00:00)
- Reduces APScheduler ThreadPoolExecutor max_workers from 10 to 3
(matching scheduler_db_pool_size)
- Prevents event loop saturation that blocks health checks and causes
pod restarts
## Root Cause Analysis
During peak scheduling periods, multiple jobs execute simultaneously and
compete for the shared event loop through `run_async()`. This creates a
resource bottleneck where:
1. **ThreadPoolExecutor** runs up to 10 jobs concurrently
2. Each job calls `run_async()` which submits to the **same event loop**
that FastAPI health check needs
3. **Health check blocks** waiting for event loop availability
4. **Liveness probe fails** after 5 consecutive timeouts (50s)
5. **Pod gets killed** with SIGKILL (exit code 137)
6. **Executions orphaned** - created in DB but never published to
RabbitMQ
## Solution
Match `max_workers` to `scheduler_db_pool_size` (3) to prevent more
concurrent jobs than the system can handle without blocking critical
health checks.
## Evidence
- Pod restart at exactly 03:05:48 when executions
e47cd564-ed87-4a52-999b-40804c41537a and
eae69811-4c7c-4cd5-b084-41872293185b were created
- 7 scheduled jobs triggered simultaneously at 03:00:00
- Health check normally responds in 0.007s but times out during high
concurrency
- Exit code 137 indicates SIGKILL from liveness probe failure
## Test Plan
- [ ] Monitor scheduler pod stability during peak scheduling periods
- [ ] Verify no executions remain QUEUED without being published to
RabbitMQ
- [ ] Confirm health checks remain responsive under load
- [ ] Check that job execution still works correctly with reduced
concurrency
🤖 Generated with [Claude Code](https://claude.ai/code)
---------
Co-authored-by: Claude <noreply@anthropic.com>
### Changes 🏗️
- Generate API client for orval v7.11.2
- Fix type error in `useAgentSelectStep.ts`
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Platform works
- [x] Updated codepath in `useAgentSelectStep.ts` works
## Summary
**HOTFIX for production** - Fixes executor being stuck in infinite retry
loop when RabbitMQ channels are closed
- Ensures proper reconnection by checking channel state before
attempting to consume messages
- Prevents accumulation of thousands of retry attempts (was seeing 7000+
retries)
## Changes
The executor was stuck repeatedly failing with "Channel is closed"
errors because the `continuous_retry` decorator was attempting to reuse
closed channels instead of creating new ones.
Added channel state checks (`is_ready`) before connecting in both:
- `_consume_execution_run()`
- `_consume_execution_cancel()`
When a channel is not ready (closed), the code now:
1. Disconnects the client (safe operation, checks if already
disconnected)
2. Establishes a fresh connection with new channel
3. Proceeds with message consumption
## Test plan
- [x] Verified the disconnect() method is safe to call on already
disconnected clients
- [x] Confirmed is_ready property checks both connection and channel
state
- [ ] Deploy to environment and verify executors reconnect properly
after channel failures
- [ ] Monitor logs to ensure no more "Channel is closed" retry loops
## Related Issues
Fixes critical production issue where:
- Executor pods show repeated "Channel is closed" errors
- 757 messages stuck in `graph_execution_queue`
- 102,286 messages in `failed_notifications` queue
- RabbitMQ logs show connections being closed due to missed heartbeats
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
## Summary
Fixes three critical issues in the admin dashboard spending page
(SECRT-1438):
- Fixed user search not working (P1) - query parameters weren't being
passed to backend
- Fixed broken pagination (P1) - server-side GET requests missing query
parameters
- Added visual feedback for credit updates (P3) - toast notifications,
loading states, auto-dismiss modal
## Root Cause
Server-side API requests weren't appending query parameters for
GET/DELETE requests in the `makeAuthenticatedRequest` function in
`helpers.ts`.
## Changes
- Added missing `transaction_filter` parameter to API client's
`getUsersHistory` method
- Fixed server-side GET request query parameter handling by updating
`makeAuthenticatedRequest` to use `buildUrlWithQuery`
- Added Suspense key to force re-render on URL parameter changes
- Added toast notifications for success/error states when adding credits
- Modal now closes automatically after successful submission
- Added loading state with disabled buttons during credit submission
- Page refreshes automatically to show updated balances
- Added debug logging to help diagnose parameter passing issues
## Test Plan
- [x] Search for users by email in admin spending dashboard
- [x] Navigate through pagination (Next/Previous buttons)
- [x] Filter by transaction type (Grant, Usage, etc.)
- [x] Add credits to a user account
- [x] Verify toast notification appears
- [x] Verify modal closes after successful submission
- [x] Verify balance updates without manual refresh
## Linear Issue
Closes [SECRT-1438](https://linear.app/autogpt/issue/SECRT-1438)
🤖 Generated with [Claude Code](https://claude.ai/code)
---------
Co-authored-by: Claude <noreply@anthropic.com>
## Changes 🏗️
Update the Front-end `README` to clarify how to run the Front-end and
Back-end separately or together via Docker.
You can [preview the README
here](8f607ca852/autogpt_platform/frontend/README.md).
## Checklist 📋
### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] `README` makes sense and looks good formatting wise
### For configuration changes:
None
## Changes 🏗️
Not a helpful console log to land in production... We should disallow
console logs all together on the Front-end code, but that is a separate,
bigger PR...
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Go to the signup page
- [x] Play with the password inputs
- [x] Password is not printed in the console
#### For configuration changes:
None
## Summary
This PR adds support for v0 by Vercel's Model API to the AutoGPT
platform, enabling users to leverage v0's framework-aware AI models
optimized for React and Next.js code generation.
v0 provides OpenAI-compatible endpoints with models specifically trained
for frontend development, making them ideal for generating UI components
and web applications.
### Changes 🏗️
#### Backend Changes
- **Added v0 Provider**: Added `V0 = "v0"` to `ProviderName` enum in
`/backend/backend/integrations/providers.py`
- **Added v0 Models**: Added three v0 models to `LlmModel` enum in
`/backend/backend/blocks/llm.py`:
- `V0_1_5_MD = "v0-1.5-md"` - Everyday tasks and UI generation (128K
context, 64K output)
- `V0_1_5_LG = "v0-1.5-lg"` - Advanced reasoning (512K context, 64K
output)
- `V0_1_0_MD = "v0-1.0-md"` - Legacy model (128K context, 64K output)
- **Implemented v0 Provider**: Added v0 support in `llm_call()` function
using OpenAI-compatible client with base URL `https://api.v0.dev/v1`
- **Added Credentials Support**: Created `v0_credentials` in
`/backend/backend/integrations/credentials_store.py` with UUID
`c4e6d1a0-3b5f-4789-a8e2-9b123456789f`
- **Cost Configuration**: Added model costs in
`/backend/backend/data/block_cost_config.py`:
- v0-1.5-md: 1 credit
- v0-1.5-lg: 2 credits
- v0-1.0-md: 1 credit
#### Configuration Changes
- **Settings**: Added `v0_api_key` field to `Secrets` class in
`/backend/backend/util/settings.py`
- **Environment Variables**: Added `V0_API_KEY=` to
`/backend/.env.default`
### Features
- ✅ Full OpenAI-compatible API support
- ✅ Tool/function calling support
- ✅ JSON response format support
- ✅ Framework-aware completions optimized for React/Next.js
- ✅ Large context windows (up to 512K tokens)
- ✅ Integrated with platform credit system
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
<!-- Put your test plan here: -->
- [x] Run existing block tests to ensure no regressions: `poetry run
pytest backend/blocks/test/test_block.py`
- [x] Verify AITextGeneratorBlock works with v0 models
- [x] Confirm all model metadata is correctly configured
- [x] Validate cost configuration is properly set up
- [x] Check that v0_credentials has a valid UUID4
#### For configuration changes:
- [x] `.env.example` is updated or already compatible with my changes
- Added `V0_API_KEY=` to `/backend/.env.default`
- [x] `docker-compose.yml` is updated or already compatible with my
changes
- No changes needed - uses existing environment variable patterns
- [x] I have included a list of my configuration changes in the PR
description (under **Changes**)
### Configuration Requirements
Users need to:
1. Obtain a v0 API key from [v0.app](https://v0.app) (requires Premium
or Team plan)
2. Add `V0_API_KEY=your-api-key` to their `.env` file
### API Documentation
- v0 API Docs: https://v0.app/docs/api
- Model API Docs: https://v0.app/docs/api/model
### Testing
All existing tests pass with the new v0 integration:
```bash
poetry run pytest backend/blocks/test/test_block.py::test_available_blocks -k "AITextGeneratorBlock" -xvs
# Result: PASSED
```
<!-- Clearly explain the need for these changes: -->
We want to support ~~proxy curl~~ enrichlayer as an integration, and
this is a baseline way to get there
### Changes 🏗️
- Adds some subset of proxycurl blocks based on the API docs:
~~https://nubela.co/proxycurl/docs#people-api-person-profile-endpoint~~https://enrichlayer.com/docs/pc/#people-api
<!-- Concisely describe all of the changes made in this pull request:
-->
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
<!-- Put your test plan here: -->
- [x] manually test the blocks with an API key
- [x] make sure the automated tests pass
---------
Co-authored-by: SwiftyOS <craigswift13@gmail.com>
Co-authored-by: Claude <claude@users.noreply.github.com>
Co-authored-by: majdyz <zamil@agpt.co>
<!-- Clearly explain the need for these changes: -->
Our weekly summary emails are currently broken, hard-coded, and so ugly.
### Changes 🏗️
Update the email template to look better
Update the way we queue messages to work after other changes have
occurred
<!-- Concisely describe all of the changes made in this pull request:
-->
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
<!-- Put your test plan here: -->
- [x] Test by sending a self email with the cron job set to every
minute, so you can see what it would look like
---------
Co-authored-by: Claude <claude@users.noreply.github.com>
Co-authored-by: Zamil Majdy <zamil.majdy@agpt.co>
## Summary
Streamline Supabase stack from 13 services to 3 core services for faster
startup and lower resource usage while maintaining full API
compatibility.
## Changes Made
### Core Services (Always Running)
- **Kong**: API gateway providing standard `/auth/v1/` endpoints and API
key validation
- **Auth**: GoTrue authentication service for user management
- **Database**: PostgreSQL with pgvector support for data persistence
### Removed Services (9 services eliminated)
- `rest` (PostgREST API) - not needed for auth-only usage
- `realtime` (real-time subscriptions) - not used by platform
- `storage` (file storage) - platform uses separate file handling
- `imgproxy` (image processing) - not required for core functionality
- `meta` (database metadata) - not needed for runtime operations
- `functions` (edge functions) - not utilized
- `analytics` (Logflare) - monitoring overhead not needed locally
- `vector` (log collection) - not required for basic operation
- `supavisor` (connection pooler) - direct DB access sufficient for
local dev
### Studio (Development Only)
- Moved to `local` profile: `docker compose --profile local up`
- Available for database management during development
- Excluded from normal startup for cleaner production-like environment
## Benefits
- **80% faster startup**: 3 services vs 13 services
- **Lower resource usage**: Significant reduction in memory/CPU
consumption
- **Simpler debugging**: Fewer moving parts, cleaner logs, easier
troubleshooting
- **Maintained compatibility**: All auth functionality preserved through
Kong
## Backwards Compatibility
✅ **No breaking changes**
- All existing auth endpoints (`/auth/v1/*`) work unchanged
- API key authentication (`anon`/`service_role`) preserved
- CORS and security policies maintained via Kong
- No application code changes required
## Testing
- [x] Docker compose starts successfully with minimal services
- [x] Auth endpoints accessible via Kong at `/auth/v1/`
- [x] Database connectivity maintained
- [x] Studio accessible with `--profile local` flag
- [x] All existing environment variables preserved
## File Changes
- `autogpt_platform/docker-compose.yml`: Removed unnecessary Supabase
services, moved studio to local profile
- `autogpt_platform/db/docker/docker-compose.yml`: Cleaned up service
dependencies on analytics/vector
🤖 Generated with [Claude Code](https://claude.ai/code)
## Summary
This PR adds the frontend service to the Docker Compose configuration,
enabling `docker compose up` to run the complete stack, including the
frontend. It also implements comprehensive environment variable
improvements, unified .env file support, and fixes Docker networking
issues.
## Key Changes
### 🐳 Docker Compose Improvements
- **Added frontend service** to `docker-compose.yml` and
`docker-compose.platform.yml`
- **Production build**: Uses `pnpm build + serve` instead of dev server
for better stability and lower memory usage
- **Service dependencies**: Frontend now waits for backend services
(`rest_server`, `websocket_server`) to be ready
- **YAML anchors**: Implemented DRY configuration to avoid duplicating
environment values
### 📁 Unified .env File Support
- **Frontend .env loading**: Automatically loads `.env` file during
Docker build and runtime
- **Backend .env loading**: Optional `.env` file support with fallback
to sensible defaults in `settings.py`
- **Single source of truth**: All `NEXT_PUBLIC_*` and API keys can be
defined in respective `.env` files
- **Docker integration**: Updated `.dockerignore` to include `.env`
files in build context
- **Git tracking**: Frontend and backend `.env` files are now trackable
(removed from gitignore)
### 🔧 Environment Variable Architecture
- **Dual environment strategy**:
- Server-side code uses Docker service names
(`http://rest_server:8006/api`)
- Client-side code uses localhost URLs (`http://localhost:8006/api`)
- **Comprehensive config**: Added build args and runtime environment
variables
- **Network compatibility**: Fixes connection issues between frontend
and backend containers
- **Shared backend variables**: Common environment variables (service
hosts, auth settings) centralized using YAML anchors
### 🛠️ Code Improvements
- **Centralized env-config helper** (`/frontend/src/lib/env-config.ts`)
with server-side priority
- **Updated all frontend code** to use shared environment helpers
instead of direct `process.env` access
- **Consistent API**: All environment variable access now goes through
helper functions
- **Settings.py improvements**: Better defaults for CORS origins and
optional .env file loading
### 🔗 Files Changed
- `docker-compose.yml` & `docker-compose.platform.yml` - Added frontend
service and shared backend env vars
- `frontend/Dockerfile` - Simplified build process to use .env files
directly
- `backend/settings.py` - Optional .env loading and better defaults
- `frontend/src/lib/env-config.ts` - New centralized environment
configuration
- `.dockerignore` - Allow .env files in build context
- `.gitignore` - Updated to allow frontend/backend .env files
- Multiple frontend files - Updated to use env helpers
- Updates to both auto installer scripts to work with the latest setup!
## Benefits
- ✅ **Single command deployment**: `docker compose up` now runs
everything
- ✅ **Better reliability**: Production build reduces memory usage and
crashes
- ✅ **Network compatibility**: Proper container-to-container
communication
- ✅ **Maintainable config**: Centralized environment variable management
with .env files
- ✅ **Development friendly**: Works in both Docker and local development
- ✅ **API key management**: Easy configuration through .env files for
all services
- ✅ **No more manual env vars**: Frontend and backend automatically load
their respective .env files
## Testing
- ✅ Verified Docker service communication works correctly
- ✅ Frontend responds and serves content properly
- ✅ Environment variables are correctly resolved in both server and
client contexts
- ✅ No connection errors after implementing service dependencies
- ✅ .env file loading works correctly in both build and runtime phases
- ✅ Backend services work with and without .env files present
### Checklist 📋
#### For configuration changes:
- [x] `.env.default` is updated or already compatible with my changes
- [x] `docker-compose.yml` is updated or already compatible with my
changes
- [x] I have included a list of my configuration changes in the PR
description (under **Changes**)
🤖 Generated with [Claude Code](https://claude.ai/code)
---------
Co-authored-by: Lluis Agusti <hi@llu.lu>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co>
Co-authored-by: Claude <claude@users.noreply.github.com>
Co-authored-by: Bentlybro <Github@bentlybro.com>
## Problem
After applying the CloudLoggingHandler fix to use
BackgroundThreadTransport (#10634), scheduler pods entered a new
deadlock during startup when uvicorn reconfigures logging.
## Root Cause
When uvicorn starts with a log_config parameter, it calls
`logging.config.dictConfig()` which:
1. Calls `_clearExistingHandlers()`
2. Which calls `logging.shutdown()`
3. Which tries to `flush()` all handlers including CloudLoggingHandler
4. CloudLoggingHandler with BackgroundThreadTransport tries to flush its
queue
5. The background worker thread tries to acquire the logging module lock
to check log levels
6. **Deadlock**: shutdown holds lock waiting for flush to complete,
worker thread needs lock to continue
## Thread Dump Evidence
From py-spy analysis of the stuck pod:
- **Thread 21 (FastAPI)**: Stuck in `flush()` waiting for background
thread to drain queue
- **Thread 13 (google.cloud.logging.Worker)**: Waiting for logging lock
in `isEnabledFor()`
- **Thread 1 (MainThread)**: Waiting for logging lock in `getLogger()`
during SQLAlchemy import
- **Threads 30, 31 (Sentry)**: Also waiting for logging lock
## Solution
Set `log_config=None` for all uvicorn servers. This prevents uvicorn
from calling `dictConfig()` and avoids the deadlock entirely.
**Trade-off**: Uvicorn will use its default logging configuration which
may produce duplicate log entries (one from uvicorn, one from the app),
but the application will start successfully without deadlocks.
## Changes
- Set `log_config=None` in all uvicorn.Config() calls
- Remove unused `generate_uvicorn_config` imports
## Testing
- [x] Verified scheduler pods can start and become healthy
- [x] Health checks respond properly
- [x] No deadlocks during startup
- [x] Application logs still appear (though may be duplicated)
## Related Issues
- Fixes the startup deadlock introduced after #10634
### Summary
Added a new documentation page and images for integrating AI/ML API with
AutoGPT, including step-by-step instructions. Updated LLM block to send
additional headers for requests to aimlapi.com. Improved provider
listing in index.md and added the new guide to mkdocs navigation. Builds
on and extends the integration work from
https://github.com/Significant-Gravitas/AutoGPT/pull/9996
### Changes 🏗️
This PR introduces official support and documentation for using **AI/ML
API** with the **AutoGPT platform**:
* 📄 **Added a new documentation page** `platform/aimlapi.md` with a
detailed step-by-step integration guide.
* 🖼️ **Added 12+ reference images** to `docs/content/imgs/aimlapi/` for
clear visual walkthrough.
* 🧠 **Updated the LLM block** (`llm.py`) to send extra headers
(`X-Project`, `X-Title`, `Referer`) in requests to `aimlapi.com` for
analytics and source attribution.
* 📚 **Improved provider listing** in `index.md` — added section about
AI/ML API models and benefits.
* 🧭 **Added the new guide to the mkdocs navigation** via `mkdocs.yml`.
---
### Checklist 📋
#### For code changes:
* [x] I have clearly listed my changes in the PR description
* [x] I have made a test plan
* [x] I have tested my changes according to the test plan:
* [x] Successfully authenticated against `api.aimlapi.com`
* [x] Verified requests use correct headers
* [x] Confirmed `AI Text Generator` block returns completions for all
supported models
* [x] End-to-end tested: created, saved, and ran agent with AI/ML API
successfully
* [x] Verified outputs render correctly in the Output panel
No breaking changes introduced. Let me know if you'd like this guide
cross-referenced from other onboarding pages. ✅
---------
Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co>
Refactored Windows and Linux setup scripts to streamline prerequisite checks, repository detection, and service startup. Removed Sentry configuration and related prompts for a simpler setup experience. Updated user messaging and improved error handling for common Docker issues.
## Changes 🏗️
<img width="800" height="687" alt="Screenshot 2025-08-12 at 15 52 41"
src="https://github.com/user-attachments/assets/0d2d70b8-e727-428b-915e-d4c108ab7245"
/>
<img width="800" height="772" alt="Screenshot 2025-08-12 at 15 52 53"
src="https://github.com/user-attachments/assets/b9790616-3754-455e-b8f6-58cd7f6b5a18"
/>
Update the Account Settings ( `profile/settings` ) form so that:
- it uses the new Design System components
- it is split into 2 forms ( update email & notifications )
- the change password inputs have been removed instead we link to the
`/reset-password` page
- uses a normal API route and client query to update the email
This might fix as well an error we are seeing when updating email
preferences on dev. My guess is it is failing because previously it was
using a server action + supabase and it didn't have access to the
cookies auth 🍪
## Checklist 📋
### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Navigate to `/profile/settings`
- [x] Can update the email
- [x] Can change notification preferences
- [x] New E2E tests pass on the CI and make sense
### For configuration changes:
None
### Changes 🏗️
Calls to the moderation API now strip whitespace from the API key before
including it in the 'X-API-Key' header, preventing authentication issues
due to accidental leading or trailing spaces.
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
<!-- Put your test plan here: -->
- [x] Setup and run the platform with moderation and test it works
## Changes 🏗️
Use a skeleton for the martkeplace loading state, representing visually
how the place should looks. Looks a bit more stylish than the previous
`Loading...` text.
### Before
<img width="800" height="774" alt="Screenshot 2025-08-12 at 16 01 22"
src="https://github.com/user-attachments/assets/29e44a1a-2089-468c-a253-3a6b763ada5a"
/>
### After
<img width="800" height="761" alt="Screenshot 2025-08-12 at 16 01 01"
src="https://github.com/user-attachments/assets/5ad362ae-df1d-4a1b-90ae-9349a81a4d75"
/>
## Checklist 📋
### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Martketplace loading state looks good across screen sizes
### For configuration changes:
None
## Summary
This PR refactors all Gmail blocks to share a common base class
(`GmailBase`) and adds several improvements to email handling, including
proper HTML content support, async API calls, and fixing the
78-character line wrapping issue for plain text emails.
## Changes
### Architecture Improvements
- **Unified base class**: Created `GmailBase` abstract class that
consolidates common functionality across all Gmail blocks
- **Async API calls**: Converted all Gmail API calls to use
`asyncio.to_thread` for better performance and non-blocking operations
- **Code deduplication**: Moved shared methods like `_build_service`,
`_get_email_body`, `_get_attachments`, and `_get_label_id` to the base
class
### Email Content Handling
- **Smart content type detection**: Added automatic detection of HTML vs
plain text content
- **Fix 78-char line wrapping**: Plain text emails now use a no-wrap
policy (`max_line_length=0`) to prevent Gmail's default 78-character
hard line wrapping
- **Content type parameter**: Added optional `content_type` field to
Send, Draft, Reply, and Forward blocks allowing manual override ("auto",
"plain", or "html")
- **Proper MIME handling**: Created `_make_mime_text` helper function to
properly configure MIME types and policies
### New Features
- **Gmail Forward Block**: Added new `GmailForwardBlock` for forwarding
emails with proper thread preservation
- **Reply improvements**: Reply block now properly reads the original
email content when replying
### Bug Fixes
- Fixed issue where reply block wasn't reading the email it was replying
to
- Fixed attachment handling in multipart messages
- Improved error handling for base64 decoding
## Technical Details
The refactoring introduces:
- `NO_WRAP_POLICY = SMTP.clone(max_line_length=0)` to prevent line
wrapping in plain text emails
- UTF-8 charset support for proper Unicode/emoji handling
- Consistent async patterns using `asyncio.to_thread` for all Gmail API
calls
- Proper HTML to text conversion using html2text library when available
## Testing
All existing tests pass. The changes maintain backward compatibility
while adding new optional parameters.
## Breaking Changes
None - all changes are backward compatible. The new `content_type`
parameter is optional and defaults to "auto" detection.
---------
Co-authored-by: Claude <claude@users.noreply.github.com>
This PR consolidates LaunchDarkly feature flag management by moving it
from autogpt_libs to backend and fixing several issues with boolean
handling and configuration management.
### Changes 🏗️
**Code Structure:**
- Move LaunchDarkly client from `autogpt_libs/feature_flag` to
`backend/util/feature_flag.py`
- Delete redundant `config.py` file and merge LaunchDarkly settings into
`backend/util/settings.py`
- Update all imports throughout the codebase to use
`backend.util.feature_flag`
- Move test file to `backend/util/feature_flag_test.py`
**Bug Fixes:**
- Fix `is_feature_enabled` function to properly return boolean values
instead of arbitrary objects that were always evaluating to `True`
- Add proper async/await handling for all `is_feature_enabled` calls
- Add better error handling when LaunchDarkly client is not initialized
**Performance & Architecture:**
- Load Settings at module level instead of creating new instances inside
functions
- Remove unnecessary `sdk_key` parameter from
`initialize_launchdarkly()` function
- Simplify initialization by using centralized settings management
**Configuration:**
- Add `launch_darkly_sdk_key` field to `Secrets` class in settings.py
with proper validation alias
- Remove environment variable fallback in favor of centralized settings
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] All existing feature flag tests pass (6/6 tests passing)
- [x] LaunchDarkly initialization works correctly with settings
- [x] Boolean feature flags return correct values instead of objects
- [x] Non-boolean flag values are properly handled with warnings
- [x] Async/await calls work correctly in AutoMod and activity status
generator
- [x] Code formatting and imports are correct
#### For configuration changes:
- [x] `.env.example` is updated or already compatible with my changes
- [x] `docker-compose.yml` is updated or already compatible with my
changes
- [x] I have included a list of my configuration changes in the PR
description (under **Changes**)
**Configuration Changes:**
- LaunchDarkly SDK key is now managed through the centralized Settings
system instead of a separate config file
- Uses existing `LAUNCH_DARKLY_SDK_KEY` environment variable (no changes
needed to env files)
🤖 Generated with [Claude Code](https://claude.ai/code)
---------
Co-authored-by: Claude <noreply@anthropic.com>
## Summary
Fixed Smart Decision Maker's function signature generation to properly
handle dynamic fields (e.g., `values_#_*`, `items_$_*`) when connecting
to any block as a tool.
### Context
When Smart Decision Maker calls other blocks as tools, it needs to
generate OpenAI-compatible function signatures. Previously, when
connected to blocks via dynamic fields (which get merged by the executor
at runtime), the signature generation would fail because blocks don't
inherently know about these dynamic field patterns.
### Changes 🏗️
- **Modified
`SmartDecisionMakerBlock._create_block_function_signature()`** to detect
and handle dynamic fields:
- Detects fields containing `_#_` (dict merge), `_$_` (list merge), or
`_@_` (object merge)
- Provides generic string schema for dynamic fields (OpenAI API
compatible)
- Falls back gracefully for unknown fields
- **Added comprehensive tests** for dynamic field handling with both
dictionary and list patterns
- **No changes needed to individual blocks** - this solution works
universally
### Why This Approach
Instead of modifying every block to handle dynamic fields (original PR
approach), we handle it centrally in Smart Decision Maker where the
function signatures are generated. This is cleaner and more
maintainable.
### Test Plan 📋
- [x] Created test cases for Smart Decision Maker generating function
signatures with dynamic dict fields (`_#_`)
- [x] Created test cases for Smart Decision Maker generating function
signatures with dynamic list fields (`_$_`)
- [x] Verified Smart Decision Maker can successfully call blocks like
CreateDictionaryBlock via dynamic connections
- [x] All existing Smart Decision Maker tests pass
- [x] Linting and formatting pass
---------
Co-authored-by: Claude <claude@users.noreply.github.com>
We're forcing this note to the end of the system prompt SDM block:
Only provide EXACTLY one function call; multiple tool calls are strictly
prohibited., this is being interpreted by GPT5 as "Only call one tool
per task," which is resulting in many agent runs that only use a tool
once (i.e., useless low low-effort answers)
### Changes 🏗️
Remove parallel tool-call system prompting entirely.
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
<!-- Put your test plan here: -->
- [x] automated tests.
Add py-spy for production-safe Python profiling across all backend services:
- Add py-spy dependency to pyproject.toml
- Grant SYS_PTRACE capability to Docker services for profiling access
- Enable low-overhead performance monitoring in development and production
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
This PR has added end-to-end tests for the profile form page. These
tests include:
- Redirects to the login page when the user is not authenticated.
- Can save profile changes successfully.
- Can cancel profile changes (skipped because we need to fix the form
for this test).
### Changes 🏗️
- Added test-id's inside the ProfileInfoForm.
- Created a page object for the profile form page.
- Added a test for this page in `profile-form.spec.ts`.
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] All test are working perfectly locally
Copy of [feat(backend/AM): Integrate AutoMod content moderation - By
Bentlybro - PR
#10490](https://github.com/Significant-Gravitas/AutoGPT/pull/10490) cos
i messed it up 🤦
Adds AutoMod input and output moderation to the execution flow.
Introduces a new AutoMod manager and models, updates settings for
moderation configuration, and modifies execution result handling to
support moderation-cleared data. Moderation failures now clear sensitive
data and mark executions as failed.
<img width="921" height="816" alt="image"
src="https://github.com/user-attachments/assets/65c0fee8-d652-42bc-9553-ff507bc067c5"
/>
### Changes 🏗️
I have made some small changes to
``autogpt_platform\backend\backend\executor\manager.py`` to send the
needed into to the AutoMod system which collects the data, combines and
makes the api call to AM and based on its reply lets it run or not!
I also had to make small changes to
``autogpt_platform\backend\backend\data\execution.py`` to add checks
that allow me to clear the content from the blocks if it was flagged
I am working on finalizing the AM repo then that will be public
To note: we will want to set this up behind launch darkly first for
testing on the team before we roll it out any more
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
<!-- Put your test plan here: -->
- [x] Setup and run the platform with ``automod_enabled`` set to False
and it works normally
- [x] Setup and run the platform with ``automod_enabled`` set to True,
set the AM URL and API Key and test it runs safe blocks normally
- [x] Test AM with content that would trigger it to flag and watch it
stop and clear all the blocks outputs
Message @Bentlybro for the URL and an API key to AM for local testing!
## Changes made to Settings.py
I have added a few new options to the settings.py for AutoMod Config!
```
# AutoMod configuration
automod_enabled: bool = Field(
default=False,
description="Whether AutoMod content moderation is enabled",
)
automod_api_url: str = Field(
default="",
description="AutoMod API base URL - Make sure it ends in /api",
)
automod_timeout: int = Field(
default=30,
description="Timeout in seconds for AutoMod API requests",
)
automod_retry_attempts: int = Field(
default=3,
description="Number of retry attempts for AutoMod API requests",
)
automod_retry_delay: float = Field(
default=1.0,
description="Delay between retries for AutoMod API requests in seconds",
)
automod_fail_open: bool = Field(
default=False,
description="If True, allow execution to continue if AutoMod fails",
)
automod_moderate_inputs: bool = Field(
default=True,
description="Whether to moderate block inputs",
)
automod_moderate_outputs: bool = Field(
default=True,
description="Whether to moderate block outputs",
)
```
and
```
automod_api_key: str = Field(default="", description="AutoMod API key")
```
---------
Co-authored-by: Zamil Majdy <zamil.majdy@agpt.co>
## Summary
Fix critical deadlock issue where scheduler pods would freeze completely
and become unresponsive to health checks, causing pod restarts and stuck
QUEUED executions.
## Root Cause Analysis
The scheduler was using `BlockingScheduler` which blocked the main
thread, and when concurrent jobs deadlocked in the async event loop, the
entire process would freeze - unable to respond to health checks or
process any requests.
From crash analysis:
- At 01:18:00, two jobs started executing concurrently
- At 01:18:01.482, last successful health check
- Process completely froze - no more logs until pod was killed at
01:18:46
- Execution `8174c459-c975-4308-bc01-331ba67f26ab` was created in DB but
never published to RabbitMQ
## Changes Made
### Core Deadlock Fix
- **Switch from BlockingScheduler to BackgroundScheduler**: Prevents
main thread blocking, allows health checks to work even if scheduler
jobs deadlock
- **Make all health_check methods async**: Makes health checks
completely independent of thread pools and more resilient to blocking
operations
### Enhanced Monitoring & Debugging
- **Add execution timing**: Track and log how long each graph execution
takes to create and publish
- **Warn on slow operations**: Alert when operations take >10 seconds,
indicating resource contention
- **Enhanced error logging**: Include elapsed time and exception types
in error messages
- **Better APScheduler event listeners**: Add listeners for missed jobs
and max instances with actionable messages
### Files Modified
- `backend/executor/scheduler.py` - Switch to BackgroundScheduler, async
health_check, timing monitoring
- `backend/util/service.py` - Base async health_check method
- `backend/executor/database.py` - Async health_check override
- `backend/notifications/notifications.py` - Async health_check override
## Test Plan
- [x] All existing tests pass (914 passed, 1 failed unrelated connection
issue)
- [x] Scheduler starts correctly with BackgroundScheduler
- [x] Health checks respond properly under load
- [x] Enhanced logging provides visibility into execution timing
## Impact
- **Prevents pod freezes**: Scheduler remains responsive even when jobs
deadlock
- **Better observability**: Clear visibility into slow operations and
failures
- **No dropped executions**: Jobs won't get stuck in QUEUED state due to
process freezes
- **Faster incident response**: Health checks and logs provide
actionable debugging info
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
# Enhanced Discord Integration Blocks
Introduces new blocks for sending DMs, embeds, files, and replies in
Discord, as well as blocks for retrieving user and channel information.
Enhances existing message blocks with additional metadata fields and
server/channel identification. Improves test coverage and input/output
schemas for all Discord-related blocks.
Co-Authored-By: Claude <claude@users.noreply.github.com>
## Why These Changes Are Needed 🎯
The existing Discord integration was limited to basic message sending
and reading. Users needed more sophisticated Discord functionality to
build comprehensive automation workflows:
1. **Limited messaging options** - Could only send plain text to
channels, no DMs, embeds, or file attachments
2. **Poor graph connectivity** - Blocks didn't output IDs needed for
chaining operations (e.g., couldn't reply to a message after sending it)
3. **No user management** - Couldn't get user information or send direct
messages
4. **Type safety issues** - Discord.py's incomplete type hints caused
linting errors
5. **No channel resolution** - Had to manually find channel IDs instead
of using names
### Changes 🏗️
#### New Blocks Added
- **SendDiscordDMBlock** - Send direct messages to users via their
Discord ID
- **SendDiscordEmbedBlock** - Create rich embedded messages with images,
fields, and formatting
- **SendDiscordFileBlock** - Upload any file type (images, PDFs, videos,
etc.) using MediaFileType
- **ReplyToDiscordMessageBlock** - Reply to specific messages in threads
- **DiscordUserInfoBlock** - Retrieve user profile information
(username, avatar, creation date, etc.)
- **DiscordChannelInfoBlock** - Resolve channel names to IDs and get
channel metadata
#### Enhanced Existing Blocks
- **ReadDiscordMessagesBlock**:
- Now outputs: `message_id`, `channel_id`, `user_id` (previously missing
all IDs)
- Enables workflows like: read message → reply to it, or read message →
DM the author
- **SendDiscordMessageBlock**:
- Now outputs: `message_id`, `channel_id` (previously had no outputs
except status)
- Enables tracking sent messages and replying to them later
#### Technical Improvements
- **MediaFileType Support**: SendDiscordFileBlock accepts data URIs,
URLs, or local paths
- **Defensive Programming**: Added runtime type checks for Discord.py's
incomplete typing
- **ID Passthrough**: DiscordUserInfoBlock passes through user_id for
chaining
- **Better Error Messages**: Clear feedback when operations fail (e.g.,
"Channel cannot receive messages")
- **Channel Flexibility**: Blocks accept both channel names and IDs
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
#### Test Plan 🧪
- [x] **Import and initialization**: All 8 Discord blocks import and
initialize without errors
- [x] **Type checking**: `poetry run format` passes with no type errors
- [x] **Interface connectivity**: Verified blocks can chain together:
- [x] ReadDiscordMessages → ReplyToDiscordMessage (via message_id,
channel_id)
- [x] ReadDiscordMessages → SendDiscordDM (via user_id)
- [x] SendDiscordMessage → ReplyToDiscordMessage (via message_id,
channel_id)
- [x] DiscordUserInfo → SendDiscordDM (via user_id passthrough)
- [x] DiscordChannelInfo → SendDiscordEmbed/File (via channel_id)
- [x] **MediaFileType handling**: SendDiscordFileBlock correctly
processes:
- [x] Data URIs (base64 encoded files)
- [x] URLs (downloads from web)
- [x] Local paths (from other blocks)
- [x] **Defensive checks**: Verified error handling for:
- [x] Non-text channels (forums, categories)
- [x] Private/DM channels without guilds
- [x] Missing attributes on channel objects
- [x] **Mock test data**: All blocks have appropriate test
inputs/outputs defined
## Example Workflows Now Possible 🚀
1. **Auto-reply to mentions**: Read messages → Check if bot mentioned →
Reply in thread
2. **File distribution**: Generate report → Send as PDF to Discord
channel
3. **User notifications**: Get user info → Check if online → Send DM
with alert
4. **Cross-platform sync**: Receive email attachment → Forward to
Discord channel
5. **Rich notifications**: Create embed with thumbnail → Add fields →
Send to announcement channel
## Breaking Changes ⚠️
None - all changes are backward compatible. Existing workflows using
SendDiscordMessageBlock and ReadDiscordMessagesBlock will continue to
work, they just now have additional outputs available.
## Dependencies 📦
No new dependencies added. Uses existing:
- `discord.py` (already in project)
- `aiohttp` (already in project)
- Backend utilities: `MediaFileType`, `store_media_file` (already in
project)
---------
Co-authored-by: Claude <claude@users.noreply.github.com>
## Summary
Corrects the context window for GPT5_CHAT, fixes provider for
CLAUDE_4_1_OPUS from 'openai' to 'anthropic', and adds a 600s timeout to
the Anthropic client call in llm_call.
## Changes 🏗️
- changed gpt5's context limit to be smaller, 16k
- changed claude's provider from openai to anthropic
- Adding a 600s timeout to the Anthropic client call
## Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] test all models and they work
### Summary
Implemented 5 additional GitHub blocks on top of the existing GitHub
Integration to enhance CI/CD workflows and code review automation
capabilities.
[New Github
Blocks_v41.json](https://github.com/user-attachments/files/21684665/New.Github.Blocks_v41.json)
<img width="902" height="1073" alt="Screenshot 2025-08-08 at 15 09 40"
src="https://github.com/user-attachments/assets/ebb6d33b-f3cd-4a56-acc6-56ace5a01274"
/>
### Changes 🏗️
- Added **GitHub CI Results Block** (`github/ci.py`): Fetch and analyze
CI/CD check runs, workflow statuses, and logs
- Added **GitHub Review Blocks** (`github/reviews.py`):
- Create PR reviews with comments
- Approve/request changes on PRs
- Add review comments to specific lines
- Fetch existing reviews and comments
- Dismiss stale reviews
### Related Tickets
- SECRT-1423: GitHub CI Results Integration
- SECRT-1426: GitHub PR Review Creation
- SECRT-1425: GitHub Review Comments
- SECRT-1424: GitHub Review Approval/Changes
- SECRT-1427: GitHub Review Management
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Created and tested CI results block with various repositories
- [x] Tested PR review creation with comments
- [x] Verified review approval and change request functionality
- [x] Tested adding line-specific review comments
- [x] Confirmed fetching and dismissing reviews works correctly
Bently