* feat(core): add git-backed memory repos and block manager
Introduce a GCS-backed git repository per agent as the source of truth for core
memory blocks. Add a GitEnabledBlockManager that writes block updates to git and
syncs values back into Postgres as a cache.
Default newly-created memory repos to the `main` branch.
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* feat(core): serve memory repos over git smart HTTP
Run dulwich's WSGI HTTPGitApplication on a local sidecar port and proxy
/v1/git/* through FastAPI to support git clone/fetch/push directly against
GCS-backed memory repos.
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix(core): create memory repos on demand and stabilize git HTTP
- Ensure MemoryRepoManager creates the git repo on first write (instead of 500ing)
and avoids rewriting history by only auto-creating on FileNotFoundError.
- Simplify dulwich-thread async execution and auto-create empty repos on first
git clone.
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix(core): make dulwich optional for CI installs
Guard dulwich imports in the git smart HTTP router so the core server can boot
(and CI tests can run) without installing the memory-repo extra.
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix(core): guard git HTTP WSGI init when dulwich missing
Avoid instantiating dulwich's HTTPGitApplication at import time when dulwich
isn't installed (common in CI installs).
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix(core): avoid masking send_message errors in finally
Initialize `result` before the agent loop so error paths (e.g. approval
validation) don't raise UnboundLocalError in the run-tracking finally block.
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix(core): stop event loop watchdog on FastAPI shutdown
Ensure the EventLoopWatchdog thread is stopped during FastAPI lifespan
shutdown to avoid daemon threads logging during interpreter teardown (seen in CI
unit tests).
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* chore(core): remove send_*_message_to_agent from SyncServer
Drop send_message_to_agent and send_group_message_to_agent from SyncServer and
route internal fire-and-forget messaging through send_messages helpers instead.
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix(core): backfill git memory repo when tag added
When an agent is updated to include the git-memory-enabled tag, ensure the
git-backed memory repo is created and initialized from the agent's current
blocks. Also support configuring the memory repo object store via
LETTA_OBJECT_STORE_URI.
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix(core): preserve block tags on git-enabled updates
When updating a block for a git-memory-enabled agent, keep block tags in sync
with PostgreSQL (tags are not currently stored in the git repo).
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* chore(core): remove git-state legacy shims
- Rename optional dependency extra from memory-repo to git-state
- Drop legacy object-store env aliases and unused region config
- Simplify memory repo metadata to a single canonical format
- Remove unused repo-cache invalidation helper
👾 Generated with [Letta Code](https://letta.com)
Co-Authored-By: Letta <noreply@letta.com>
* fix(core): keep PR scope for git-backed blocks
- Revert unrelated change in fire-and-forget multi-agent send helper
- Route agent block updates-by-label through injected block manager only when needed
👾 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>
* Revert "chore: temp revert to public ddtrace (#8462)"
This reverts commit 09e541b7732fdc03be4cd9c00cc2c8518300acf1.
* Update ddtrace version requirement in pyproject.toml
Removed specific ddtrace versions for profiling and updated to a minimum version requirement.
* feat: add support for new model
* fix: just stage-api && just publish-api (anthropic model settings changed)
* fix: just stage-api && just publish-api (anthropic model settings changed)
* fix: make kevlar have default reasoning on
* fix: bump anthropic sdk version
* fix: patch name
* pin newer version anthropic
---------
Co-authored-by: Ari Webb <ari@letta.com>
* add memory tracking to core
* move to asyncio from threading.Thread
* remove threading.thread all the way
* delay decorator monitoring initialization until after event loop is registered
* context manager to decorator
* add psutil
* feat: add gemini streaming to new agent loop
* add google as required dependency
* support storing all content parts
* remove extra google references
* 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>
* fix: approval request for streaming
* fix: claude code attempt, unit test passing (add on to #4445) (#4448)
* fix: claude code attempt, unit test passing
* chore: update locks to 0.1.314 from 0.1.312
* chore: just stage-api && just publish-api
* chore: drop dead poetry lock
---------
Co-authored-by: Charles Packer <packercharles@gmail.com>
* base requirements
* autofix
* Configure ruff for Python linting and formatting
- Set up minimal ruff configuration with basic checks (E, W, F, I)
- Add temporary ignores for common issues during migration
- Configure pre-commit hooks to use ruff with pass_filenames
- This enables gradual migration from black to ruff
* Delete sdj
* autofixed only
* migrate lint action
* more autofixed
* more fixes
* change precommit
* try changing the hook
* try this stuff
* uv migration
smaller runners, freeze test runs, remove dev, ruff,hatchling, previw,
poetry, generates wheel, installs wheel, docker
* fix tests and dependency groups
* test fixes
* test fixing and main
* resolve merge conflict
* dev + test dependency group
* Test
* trigger CI
* trigger CI
* add debugging info
* trigger CI
* uv for reusable and sdk preview
* resolve mc and reformat black
* staged-api
* mypy
* fix fern
* prod Dockerfile
* model sweep, and project.toml and uvlock
* --group test -> --extra dev
* remove redundant --extra dev and rename tests to dev
* sdk backwards compat install sqlite
* install sqlite group for sdk-backwards-compat
* install uv on gh runner for cloud-api-integration-tests
* stage+publish
* pytest asyncio
* bug causing pytest package to get removed
* try to fix async event loop issues
* migrate to --with google-cloud-secret-manager
---------
Co-authored-by: Kian Jones <kian@letta.com>
* cherrypick just relevant commits?
* make work with poetry
* update poetry?
* regen?
* change tests and dev to dependency groups instead of optional extras
* Fix Poetry/UV compatibility issues
- Fix sqlite-vec dependency: Remove optional flag from Poetry section to match main deps
- Regenerate poetry.lock to sync with pyproject.toml changes
- Test both package managers successfully:
- Poetry: `poetry install --with dev --with test -E postgres -E external-tools -E cloud-tool-sandbox`
- UV: `uv sync --group dev --group test --extra postgres --extra external-tools --extra cloud-tool-sandbox`
Resolves Poetry lock sync errors and ensures sqlite-vec is available for tests.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* more robust pip install
* Fix fern SDK wheel installation in CI workflow
Replace unreliable command substitution with proper error handling:
- Check if directory exists before attempting to find wheels
- Store wheel file path in variable to avoid empty arguments
- Provide clear error messages when directory/wheels are missing
- Prevents "required arguments were not provided" error in uv pip install
Fixes: error: the following required arguments were not provided: <PACKAGE>
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* debugging
* trigger CI
* ls
* revert whl installation to -e
* programmatic HIT version insertion
* version templating properly
* set var properly
* labelling
* remove version insertion
* ?
* try using sed '2r /dev/stdin'
* version
* try again smh
* not trigger on poetry version
* only add once
* filter only for project not poetry
* hand re-construct the file
* save tail?
* fix docker command
* please please please
* rename test -> tests
* update poetry and rename group to -E
* move async into tests extra and regen lock files and add sqlite extra
* remove loading cached venv from cloud api integration
* add uv dependency to CI runners
* test removing the custom event loop
* regen poetry.lock and try to fix async tests
* wrap async pg exception and event loop tweak in plugins
* remove event loop from plugins test and remove caching from cloud-api-integration-test
* migrate all tests away from event loop for pytest-asyncio
* pin firecrawl
* pin e2b
* take claude's suggestion
* deeper down the claude rabbit hole
* increase timeout for httpbin.org
---------
Co-authored-by: Claude <noreply@anthropic.com>
