* make favorite tag a const
* add favorite:user:{userId} for favorites
* favorite agent upon initial creation
* rename const
* add eslint ignore
* expect favorite tag
* test: add comprehensive provider trace telemetry tests
Add two test files for provider trace telemetry:
1. test_provider_trace.py - Integration tests for:
- Basic agent steps (streaming and non-streaming)
- Tool calls
- Telemetry context fields (agent_id, agent_tags, step_id, run_id)
- Multi-step conversations
- Request/response JSON content
2. test_provider_trace_summarization.py - Unit tests for:
- simple_summary() telemetry context passing
- summarize_all() telemetry pass-through
- summarize_via_sliding_window() telemetry pass-through
- Summarizer class runtime vs constructor telemetry
- LLMClient.set_telemetry_context() method
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* test: add telemetry tests for tool generation, adapters, and agent versions
Add comprehensive unit tests for provider trace telemetry:
- TestToolGenerationTelemetry: Verify /generate-tool endpoint sets
call_type="tool_generation" and has no agent context
- TestLLMClientTelemetryContext: Verify LLMClient.set_telemetry_context
accepts all telemetry fields
- TestAdapterTelemetryAttributes: Verify base adapter and subclasses
(LettaLLMRequestAdapter, LettaLLMStreamAdapter) support telemetry attrs
- TestSummarizerTelemetry: Verify Summarizer stores and passes telemetry
- TestAgentAdapterInstantiation: Verify LettaAgentV2 creates Summarizer
with correct agent_id
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* ci: add provider trace telemetry tests to unit test workflow
Add the new provider trace test files to the CI matrix:
- test_provider_trace_backends.py
- test_provider_trace_summarization.py
- test_provider_trace_agents.py
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix: update socket backend test to match new record structure
The socket backend record structure changed - step_id/run_id are now
at top level, and model/usage are nested in request/response objects.
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix: add step_id to V1 agent telemetry context
Pass step_id to set_telemetry_context in both streaming and non-streaming
paths in LettaAgent (v1). The step_id is available via step_metrics.id
in the non-streaming path and passed explicitly in the streaming path.
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
---------
Co-authored-by: Letta <noreply@letta.com>
* feat: add agent_id, run_id, step_id to summarization provider traces
Summarization LLM calls were missing telemetry context (agent_id,
agent_tags, run_id, step_id), making it impossible to attribute
summarization costs to specific agents or trace them back to the
step that triggered compaction.
Changes:
- Add step_id param to simple_summary() and set_telemetry_context()
- Add agent_id, agent_tags, run_id, step_id to summarize_all() and
summarize_via_sliding_window()
- Update Summarizer class to accept and pass telemetry context
- Update LettaAgentV3.compact() to pass full telemetry context
- Update LettaAgentV2.summarize_conversation_history() with run_id/step_id
- Update LettaAgent (v1) streaming methods with run_id param
- Add run_id/step_id to SummarizeParams for Temporal activities
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix: update test mock to accept new summarization params
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@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>
* feat(core): add image support in tool returns [LET-7140]
Enable tool_return to support both string and ImageContent content parts,
matching the pattern used for user message inputs. This allows tools
executed client-side to return images back to the agent.
Changes:
- Add LettaToolReturnContentUnion type for text/image content parts
- Update ToolReturn schema to accept Union[str, List[content parts]]
- Update converters for each provider:
- OpenAI Chat Completions: placeholder text for images
- OpenAI Responses API: full image support
- Anthropic: full image support with base64
- Google: placeholder text for images
- Add resolve_tool_return_images() for URL-to-base64 conversion
- Make create_approval_response_message_from_input() async
🐾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix(core): support images in Google tool returns as sibling parts
Following the gemini-cli pattern: images in tool returns are sent as
sibling inlineData parts alongside the functionResponse, rather than
inside it.
🐾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* test(core): add integration tests for multi-modal tool returns [LET-7140]
Tests verify that:
- Models with image support (Anthropic, OpenAI Responses API) can see
images in tool returns and identify the secret text
- Models without image support (Chat Completions) get placeholder text
and cannot see the actual image content
- Tool returns with images persist correctly in the database
Uses secret.png test image containing hidden text "FIREBRAWL" that
models must identify to pass the test.
Also fixes misleading comment about Anthropic only supporting base64
images - they support URLs too, we just pre-resolve for consistency.
🐾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* refactor: simplify tool return image support implementation
Reduce code verbosity while maintaining all functionality:
- Extract _resolve_url_to_base64() helper in message_helper.py (eliminates duplication)
- Add _get_text_from_part() helper for text extraction
- Add _get_base64_image_data() helper for image data extraction
- Add _tool_return_to_google_parts() to simplify Google implementation
- Add _image_dict_to_data_url() for OpenAI Responses format
- Use walrus operator and list comprehensions where appropriate
- Add integration_test_multi_modal_tool_returns.py to CI workflow
Net change: -120 lines while preserving all features and test coverage.
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix(tests): improve prompt for multi-modal tool return tests
Make prompts more direct to reduce LLM flakiness:
- Simplify tool description: "Retrieves a secret image with hidden text. Call this function to get the image."
- Change user prompt from verbose request to direct command: "Call the get_secret_image function now."
- Apply to both test methods
This reduces ambiguity and makes tool calling more reliable across different LLM models.
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix bugs
* test(core): add google_ai/gemini-2.0-flash-exp to multi-modal tests
Add Gemini model to test coverage for multi-modal tool returns. Google AI already supports images in tool returns via sibling inlineData parts.
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix(ui): handle multi-modal tool_return type in frontend components
Convert Union<string, LettaToolReturnContentUnion[]> to string for display:
- ViewRunDetails: Convert array to '[Image here]' placeholder
- ToolCallMessageComponent: Convert array to '[Image here]' placeholder
Fixes TypeScript errors in web, desktop-ui, and docker-ui type-checks.
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
---------
Co-authored-by: Letta <noreply@letta.com>
Co-authored-by: Caren Thomas <carenthomas@gmail.com>
* feat: byok provider models in db also
* make tests and sync api
* fix inconsistent state with recreating provider of same name
* fix sync on byok creation
* update revision
* move stripe code for testing purposes
* revert
* add refresh byok models endpoint
* just stage publish api
* add tests
* reorder revision
* add test for name clashes
* fix(core): disable MCP stdio servers by default
Stdio MCP servers spawn local processes on the host, which is not
suitable for multi-tenant or shared server deployments. This change:
- Changes `mcp_disable_stdio` default from False to True
- Enforces the setting in `get_mcp_client()` and `create_mcp_server_from_config()`
- Users running local/single-user deployments can set MCP_DISABLE_STDIO=false
to enable stdio-based MCP servers (e.g., for npx/uvx tools)
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* update ci
* push
---------
Co-authored-by: Letta <noreply@letta.com>
Co-authored-by: jnjpng <jin@letta.com>
Co-authored-by: Letta Bot <jinjpeng@gmail.com>
* feat: enable bedrock for anthropic models
* parallel tool calls in ade
* attempt add to ci
* update tests
* add env vars
* hardcode region
* get it working
* debugging
* add bedrock extra
* default env var [skip ci]
* run ci
* reasoner model update
* secrets
* clean up log
* clean up
Adds validation to the fetch_webpage tool to ensure only HTTP/HTTPS URLs
are accepted. Previously, passing a file:// URL would cause an unhandled
requests.exceptions.InvalidSchema error. Now it raises a clear ValueError
with a helpful error message.
Fixes: requests.exceptions.InvalidSchema: No connection adapters were found for 'file://...'
🤖 Generated with [Letta Code](https://letta.com)
Co-authored-by: letta-code <248085862+letta-code@users.noreply.github.com>
Co-authored-by: datadog-official[bot] <datadog-official[bot]@users.noreply.github.com>
Co-authored-by: Letta <noreply@letta.com>
Co-authored-by: Kian Jones <11655409+kianjones9@users.noreply.github.com>
- Added `claude-haiku-4-5-20251001` and `claude-haiku-4-5-latest` to MODEL_LIST
in anthropic.py to fix context window lookup for the newly released model
- Added prefix stripping in anthropic_client.py to handle cases where the
model name incorrectly includes the `anthropic/` provider prefix
Fixes the production error:
anthropic.NotFoundError: Error code: 404 - model: anthropic/claude-haiku-4-5-20251001
Fixes#8907🤖 Generated with [Letta Code](https://letta.com)
Co-authored-by: letta-code <248085862+letta-code@users.noreply.github.com>
Co-authored-by: datadog-official[bot] <datadog-official[bot]@users.noreply.github.com>
Co-authored-by: Kian Jones <11655409+kianjones9@users.noreply.github.com>
Change the log level for expected MCP tool execution failures (ToolError,
McpError) from warning to debug in fastmcp_client.py to match base_client.py.
These errors occur when an LLM calls an MCP tool with missing/invalid
arguments - they are expected user-facing issues from external MCP servers,
not system errors that should trigger production alerts.
Fixes#8845🤖 Generated with [Letta Code](https://letta.com)
Co-authored-by: letta-code <248085862+letta-code@users.noreply.github.com>
Co-authored-by: datadog-official[bot] <datadog-official[bot]@users.noreply.github.com>
Co-authored-by: Kian Jones <11655409+kianjones9@users.noreply.github.com>
MCP tool errors (ToolError, McpError) are expected user-facing errors
from external MCP servers (e.g., "No connected account found"). These
were propagating through @trace_method decorator and being recorded
as errors in Datadog APM.
Changes:
- Add try/except to catch expected MCP errors in ExternalMCPToolExecutor
- Return ToolExecutionResult with status="error" instead of re-raising
- Log expected errors at INFO level instead of letting them trace as ERROR
- Remove stray 'pass' statement that was a no-op
Fixes#8685🤖 Generated with [Letta Code](https://letta.com)
Co-authored-by: letta-code <248085862+letta-code@users.noreply.github.com>
Co-authored-by: datadog-official[bot] <datadog-official[bot]@users.noreply.github.com>
Co-authored-by: Kian Jones <11655409+kianjones9@users.noreply.github.com>
When Ollama providers are synced to DB via sync_base_providers(), the
default_prompt_formatter field is lost because ProviderCreate doesn't
include it. When loading from DB and calling cast_to_subtype(), Pydantic
validation fails because the field is required.
This was a latent bug exposed when provider models persistence was
re-enabled in 0.16.2. The field was always required but never persisted.
Adding a default value ("chatml") fixes the issue. The field isn't
actually used in the current implementation - the model_wrapper line
is commented out in list_llm_models_async() since Ollama now uses
OpenAI-compatible endpoints.
Fixes: letta-ai/letta-code#587👾 Generated with [Letta Code](https://letta.com)
Co-authored-by: Letta <noreply@letta.com>
* feat: centralize telemetry logging at LLM client level
Moves telemetry logging from individual adapters to LLMClientBase:
- Add TelemetryStreamWrapper for streaming telemetry on stream close
- Add request_async_with_telemetry() for non-streaming requests
- Add stream_async_with_telemetry() for streaming requests
- Add set_telemetry_context() to configure agent_id, run_id, step_id
Updates adapters and agents to use new pattern:
- LettaLLMAdapter now accepts agent_id/run_id in constructor
- Adapters call set_telemetry_context() before LLM requests
- Removes duplicate telemetry logging from adapters
- Enriches traces with agent_id, run_id, call_type metadata
🐙 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix: accumulate streaming response content for telemetry
TelemetryStreamWrapper now extracts actual response data from chunks:
- Content text (concatenated from deltas)
- Tool calls (id, name, arguments)
- Model name, finish reason, usage stats
🐙 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* refactor: move streaming telemetry to caller (option 3)
- Remove TelemetryStreamWrapper class
- Add log_provider_trace_async() helper to LLMClientBase
- stream_async_with_telemetry() now just returns raw stream
- Callers log telemetry after processing with rich interface data
Updated callers:
- summarizer.py: logs content + usage after stream processing
- letta_agent.py: logs tool_call, reasoning, model, usage
🐙 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix: pass agent_id and run_id to parent adapter class
LettaLLMStreamAdapter was not passing agent_id/run_id to parent,
causing "unexpected keyword argument" errors.
🐙 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
---------
Co-authored-by: Letta <noreply@letta.com>
* feat: add provider trace backend abstraction for multi-backend telemetry
Introduces a pluggable backend system for provider traces:
- Base class with async/sync create and read interfaces
- PostgreSQL backend (existing behavior)
- ClickHouse backend (via OTEL instrumentation)
- Socket backend (writes to Unix socket for crouton sidecar)
- Factory for instantiating backends from config
Refactors TelemetryManager to use backends with support for:
- Multi-backend writes (concurrent via asyncio.gather)
- Primary backend for reads (first in config list)
- Graceful error handling per backend
Config: LETTA_TELEMETRY_PROVIDER_TRACE_BACKEND (comma-separated)
Example: "postgres,socket" for dual-write to Postgres and crouton
🐙 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* feat: add protocol version to socket backend records
Adds PROTOCOL_VERSION constant to socket backend:
- Included in every telemetry record sent to crouton
- Must match ProtocolVersion in apps/crouton/main.go
- Enables crouton to detect and reject incompatible messages
🐙 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix: remove organization_id from ProviderTraceCreate calls
The organization_id is now handled via the actor parameter in the
telemetry manager, not through ProviderTraceCreate schema. This fixes
validation errors after changing ProviderTraceCreate to inherit from
BaseProviderTrace which forbids extra fields.
🐙 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* consolidate provider trace
* add clickhouse-connect to fix bug on main lmao
* auto generated sdk changes, and deployment details, and clikchouse prefix bug and added fields to runs trace return api
* auto generated sdk changes, and deployment details, and clikchouse prefix bug and added fields to runs trace return api
* consolidate provider trace
* consolidate provider trace bug fix
---------
Co-authored-by: Letta <noreply@letta.com>
* feat: add TypeScript tool support for E2B sandbox execution
This change implements TypeScript tool support using the same E2B path as Python tools:
- Add TypeScript execution script generator (typescript_generator.py)
- Modify E2B sandbox to detect TypeScript tools and use language='ts'
- Add npm package installation for TypeScript tool dependencies
- Add validation requiring json_schema for TypeScript tools
- Add comprehensive integration tests for TypeScript tools
TypeScript tools:
- Require explicit json_schema (no docstring parsing)
- Use JSON serialization instead of pickle for results
- Support async functions with top-level await
- Support npm package dependencies via npm_requirements field
Closes#8793
Co-authored-by: Sarah Wooders <sarahwooders@users.noreply.github.com>
* fix: disable AgentState for TypeScript tools & add letta-client injection
Based on Sarah's feedback:
1. AgentState is a legacy Python-only feature, disabled for TS tools
2. Added @letta-ai/letta-client npm package injection for TypeScript
(similar to letta_client for Python)
Changes:
- base.py: Explicitly set inject_agent_state=False for TypeScript tools
- typescript_generator.py: Inject LettaClient initialization code
- e2b_sandbox.py: Auto-install @letta-ai/letta-client for TS tools
- Added tests verifying both behaviors
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Sarah Wooders <sarahwooders@users.noreply.github.com>
Co-Authored-By: Letta <noreply@letta.com>
* Update core-integration-tests.yml
* fix: convert TypeScript test fixtures to async
The OrganizationManager and UserManager no longer have sync methods,
only async variants. Updated all fixtures to use:
- create_organization_async
- create_actor_async
- create_or_update_tool_async
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix: skip Python AST parsing for TypeScript tools in sandbox base
The _init_async method was calling parse_function_arguments (which uses
Python's ast.parse) before checking if the tool was TypeScript, causing
SyntaxError when running TypeScript tools.
Moved the is_typescript_tool() check to happen first, skipping Python
AST parsing entirely for TypeScript tools.
🤖 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* letta_agent_id
* skip ast parsing for s
* add tool execution test
---------
Co-authored-by: letta-code <248085862+letta-code@users.noreply.github.com>
Co-authored-by: Sarah Wooders <sarahwooders@users.noreply.github.com>
Co-authored-by: Letta <noreply@letta.com>
Co-authored-by: Kian Jones <kian@letta.com>
The import was `from datetime import datetime` but the code used
`datetime.timezone.utc` which is incorrect - timezone is a sibling
class in the datetime module, not an attribute of the datetime class.
This caused the error: "type object 'datetime.datetime' has no
attribute 'timezone'"
