* auto fixes
* auto fix pt2 and transitive deps and undefined var checking locals()
* manual fixes (ignored or letta-code fixed)
* fix circular import
* remove all ignores, add FastAPI rules and Ruff rules
* add ty and precommit
* ruff stuff
* ty check fixes
* ty check fixes pt 2
* error on invalid
* fix(core): strip quotes from MCP server header keys and values
Users pasting JSON-formatted env vars into MCP server config end up with
quoted header names like `"CONTEXT7_API_KEY":` which causes
httpx.LocalProtocolError. Sanitize keys (strip surrounding quotes and
trailing colons) and values (strip surrounding quotes) in
resolve_custom_headers, resolve_environment_variables for HTTP configs,
and stdio env dicts.
Datadog: https://us5.datadoghq.com/error-tracking/issue/4a2f4af6-f2d8-11f0-930c-da7ad0900000🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix: revert stdio env sanitization to pass-through
The stdio path doesn't need header/env sanitization - that's only
relevant for SSE/streamable HTTP servers with auth headers.
🐾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
---------
Co-authored-by: Letta <noreply@letta.com>
The A2A messaging tools were instructing receiving agents to use the
send_message tool to reply, but that tool is often not attached to
agents anymore. This caused agents confusion when they couldn't find
the required tool.
For synchronous functions (send_message_to_agent_and_wait_for_reply,
send_message_to_agents_matching_tags, send_message_to_all_agents_in_group),
the system already captures AssistantMessage automatically, so agents
just need to respond normally.
For the async/fire-and-forget function (send_message_to_agent_async),
updated to indicate it's a one-way notification and hint that messaging
tools exist without requiring a specific one.
🤖 Generated with [Letta Code](https://letta.com)
Co-authored-by: Letta <noreply@letta.com>
Models (especially Opus) take this instruction literally and re-call
the memory edit tool in a loop — one user saw 96 consecutive rethink
calls. Dropping the sentence stops the feedback loop while still
asking the agent to review the result.
👾 Generated with [Letta Code](https://letta.com)
Co-authored-by: Letta <noreply@letta.com>
* mvp
* perfrom type coercion in sandbox
* fix: safely resolve typing annotations on host
Use an AST whitelist for generic annotations to avoid eval while keeping list/dict coercion working.
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
---------
Co-authored-by: Letta <noreply@letta.com>
* fix: replace all 'PRODUCTION' references with 'prod' for consistency
Problem: Codebase had 11 references to 'PRODUCTION' (uppercase) that should
use 'prod' (lowercase) for consistency with the deployment workflows and
environment normalization.
Changes across 8 files:
1. Source files (using settings.environment):
- letta/functions/function_sets/multi_agent.py
- letta/services/tool_manager.py
- letta/services/tool_executor/multi_agent_tool_executor.py
- letta/services/helpers/agent_manager_helper.py
All checks changed from: settings.environment == "PRODUCTION"
To: settings.environment == "prod"
2. OTEL resource configuration:
- letta/otel/resource.py
- Updated _normalize_environment_tag() to handle 'prod' directly
- Removed 'PRODUCTION' -> 'prod' mapping (no longer needed)
- Updated device.id check from _env != "PRODUCTION" to _env != "prod"
3. Test files:
- tests/managers/conftest.py
- Fixture parameter changed from "PRODUCTION" to "prod"
- tests/managers/test_agent_manager.py (3 occurrences)
- tests/managers/test_tool_manager.py (2 occurrences)
All test checks changed to use "prod"
Result: Complete consistency across the codebase:
- All environment checks use "prod" instead of "PRODUCTION"
- Normalization function simplified (no special case for PRODUCTION)
- Tests use correct "prod" value
- Matches deployment workflow configuration from PR #6626
This completes the environment naming standardization effort.
* fix: update settings.py environment description to use 'prod' instead of 'PRODUCTION'
The field description still referenced PRODUCTION as an example value.
Updated to use lowercase 'prod' for consistency with actual usage.
Before: "Application environment (PRODUCTION, DEV, CANARY, etc. - normalized to lowercase for OTEL tags)"
After: "Application environment (prod, dev, canary, etc. - lowercase values used for OTEL tags)"
The docstring incorrectly stated that fetch_webpage uses Jina AI reader.
Updated to accurately describe the actual implementation which uses:
1. Exa API (if EXA_API_KEY is available)
2. Trafilatura (fallback)
3. Readability + html2text (final fallback)
🐾 Generated with [Letta Code](https://letta.com)
Co-authored-by: Letta <noreply@letta.com>
* Update archival memory docstrings for clarity
Improved docstrings for archival_memory_insert and archival_memory_search to:
- Better explain when and how to use these tools
- Provide clearer best practices
- Include more realistic examples (meeting notes, project updates)
- Emphasize semantic search vs keyword matching
- Clarify tag filtering behavior
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* examples
---------
Co-authored-by: Letta <noreply@letta.com>
Co-authored-by: Kevin Lin <kl2806@columbia.edu>
* refactor not to use warnings.warn
* temp circular import fix maybe unecessary/bnad
* fix Deprecation warning
* fix deprecation warning and mcp thing?
* revert changes to mcp server test
* fix deprecation warning
* refactored version of MCP routs
* feat: revise MCP routes
* working through new routes spec
* refining
* add necessary patch for config
* mcp servers progress
* small fixes
* updates
* finished
* just stage and publish api
* make update static
---------
Co-authored-by: Ari Webb <ari@letta.com>
Co-authored-by: Ari Webb <arijwebb@gmail.com>
* add anthropic memory tools
* memory view working
* update memory examples
* tools
* feat: some changes (#5003)
* feat: added the ability to modify and add descriptions on creation
* fix: kill dead code & write into core_tool_executor instead
* fix: use block_manager not agent_manager where possible, also turn the return string errors into raising exceptions
* fix: cleanup, get rid of more return string errors replaced with valueerror, also drop deadcode
---------
Co-authored-by: Charles Packer <packercharles@gmail.com>
* remove apps/core and apps/fern
* fix precommit
* add submodule updates in workflows
* submodule
* remove core tests
* update core revision
* Add submodules: true to all GitHub workflows
- Ensure all workflows can access git submodules
- Add submodules support to deployment, test, and CI workflows
- Fix YAML syntax issues in workflow files
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* remove core-lint
* upgrade core with latest main of oss
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat: increase the verbosity of the heartbeat kwarg
* chore: strip docstrings out from the file in which they are not parsed (duplicates inside base.py
* feat: add examples to the docstrings for memory_replace and memory_insert
* feat: add more examples
* feat: increase the verbosity of the heartbeat kwarg
* chore: strip docstrings out from the file in which they are not parsed (duplicates inside base.py
* feat: add examples to the docstrings for memory_replace and memory_insert
* feat: add more examples
