mirror of
https://github.com/ComposioHQ/composio.git
synced 2026-09-22 11:46:35 +08:00
@composio/cli@0.2.32-beta.288
426 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Aditya Painuli
|
1ea8ad9b3f |
docs: migrate AutoGen provider examples to ag2's LLMConfig API (#3833)
## Summary
The AutoGen provider examples still used the legacy
`llm_config={"config_list": [...]}` dict form, which ag2 0.14 (the
distribution `composio-autogen` depends on since #3729) only keeps for
backport compatibility and marks deprecated in
`LLMConfig.ensure_config`. The install command also pulled
`autogen-agentchat` (Microsoft's next-gen AutoGen package), which the
provider never imports, while the `ag2` distribution the examples
actually import from was only installed transitively.
Fixes #3831
## Changes
- `docs/content/docs/providers/autogen.mdx`: example migrated to
`LLMConfig({...})`, install line changed to `composio composio_autogen
ag2`, added `ag2` keyword and a one-line note that the provider runs on
the ag2 distribution
- `python/providers/autogen/README.md`: same quickstart and install
fixes
- `python/providers/autogen/autogen_demo.py`: same `LLMConfig` migration
`initiate_chat` is left as is: it isn't deprecated in ag2 0.14, and it's
the flow `register_tools` (caller/executor) is verified against.
## Type of change
- [ ] Bug fix
- [ ] New feature
- [ ] Refactor/Chore
- [x] Documentation
- [ ] Breaking change
## How Has This Been Tested?
- Verified in a fresh venv with the local `composio` +
`composio-autogen` packages and `ag2==0.14.0`: the updated example
constructs both agents, wraps a Composio tool via `AutogenProvider`,
registers it with `register_tools`, and executes it through the
executor's function map
- `uv run nox -s chk` (ruff + mypy): green
- `ruff format --check providers/autogen/`: clean
- Docs: `bun run build` and `bun run lint:links` from `docs/`: green
## Screenshots (if applicable)
## Checklist
- [x] I have read the Code of Conduct and this PR adheres to it
- [x] I ran linters/tests locally and they passed
- [x] I updated documentation as needed
- [ ] I added tests or explain why not applicable
- [x] I added a changeset if this change affects published packages
## Additional context
No changeset added: docs and Python-only change, no published TypeScript
package affected. No tests added: example/docs change with no runtime
code paths; the updated example was exercised manually against ag2 0.14
as described above.
---------
Co-authored-by: Alberto Schiabel <jkomyno@users.noreply.github.com>
Co-authored-by: jkomyno <alberto@composio.dev>
|
||
|
Alberto Schiabel
|
c4071feab4 |
fix(py): guard URL uploads and redact telemetry (#3823)
This PR: - ports the TypeScript SDK's public-network guard to Python URL file uploads - rejects non-HTTP(S), private, loopback, link-local, reserved, and mixed DNS targets before a request is made - applies the guard to both `FileUploadable.from_url()` and Tool Router session-file URL uploads - redacts URL queries, Authorization credentials, and secret-like key/value pairs before error telemetry leaves the process - adds focused SSRF and redaction regressions alongside the existing file-upload coverage Validation: - `uv run --frozen pytest tests/test_url_safety.py tests/test_redaction.py tests/test_files.py -q` - `uv run --frozen ruff check …` - `uv run --frozen ruff format --check …` |
||
|
Alberto Schiabel
|
3a5e62feb4 |
fix(py): support list-valued schema types in tool signatures (#3815)
This PR: - builds on top of https://github.com/ComposioHQ/composio/pull/3754 - normalizes list-valued JSON Schema `type` fields before scalar type lookups - applies the handling to direct fields and `anyOf`/`oneOf` options - adds regressions for nullable, single, mixed, unknown, and combiner-nested type lists - credits @anxkhn as a Git co-author ## Context JSON Schema Draft 2020-12 and OpenAPI 3.1 allow `type` to be an array. The previous parser passed that list to a dictionary lookup, raising `TypeError: unhashable type: 'list'`. This replacement covers the direct case from #3754 and the same shape nested in a combiner. --------- Co-authored-by: Anas Khan <83116240+anxkhn@users.noreply.github.com> |
||
|
Alberto Schiabel
|
edd0bf0479 |
docs: centralize SDK release notes (#3814)
This PR: - Adds public docs changelog entries for the Python and TypeScript SDK releases since May 15, 2026, including the previously unmigrated Python 0.13.1 entry. - Removes the Python-local changelog and replaces it with canonical changelog links from the repository and Python READMEs. - Retargets the Python release guard to the docs changelog, documents its table contract, and covers prior-version plus PEP 440 version parsing. Validation: - pnpm test:release-workflow - docs: bun run test - docs: bun run lint:links - docs: bun run types:check - docs: bun run build - pnpm exec prettier --check test/release-workflow.test.ts docs/agent-guidance/guides/changelog.md docs/content/changelog/*.mdx Review: - ce-code-review completed with correctness, testing, maintainability, project-standards, agent-native, learnings, and adversarial passes. All actionable findings were fixed; final adversarial re-review found no remaining P0-P2 issue. |
||
|
MatinGathani
|
d5a37efb85 |
fix(python): handle title-less top-level schemas (#3325)
## Summary Fixes `json_schema_to_model` when a top-level JSON schema omits `title` or sets it to `null`. This is the remaining direct-helper path; anonymous nested objects from #2435 are already handled by `schema_converter.py`. - falls back to `GeneratedModel` only when the title is `None`, preserving intentionally empty string titles - adds regression coverage for missing, `null`, and empty titles, model construction, and required-field validation ## Validation - `ruff format --check python/composio/utils/shared.py python/tests/test_schema_parser.py` - `ruff check python/composio/utils/shared.py python/tests/test_schema_parser.py` - `PYTHONPATH="$PWD/python" /Users/jkomyno/work/composio/composio2/.venv/bin/pytest -q python/tests/test_schema_parser.py` This is a follow-up to #2435; it intentionally does not close that already-resolved issue. Co-authored-by: jkomyno <alberto@composio.dev> Co-authored-by: Alberto Schiabel <jkomyno@users.noreply.github.com> |
||
|
Rahul Tarak
|
a13c883845 |
docs: package-manager picker for install commands (#3802)
## What Two changes to the docs install experience: **1. Package-manager picker on install code blocks.** New `PackageInstall` client component (`docs/components/package-install.tsx`): the code block's copy button opens a dropdown of package managers. Selecting one rewrites the displayed command and copies it to the clipboard. - TypeScript blocks: npm (default, `npm install`) / pnpm / bun / yarn (`<pm> add`) - Python blocks: uv (default, `uv add`) / pip (`pip install`) - The menu is portaled to `document.body` so it isn't clipped by the `Tabs`/`CodeBlock` overflow containers, and closes on outside click, Escape, or real scroll movement. **2. `@composio/slim` callout in the quickstart.** The quickstart TypeScript install blocks carry display-only `#` comment lines noting that `@composio/core` ships its docs and TypeScript source in the package (inspectable to coding agents) and that `@composio/slim` is the smaller install with the same API. Comment lines are rendered muted and are **never copied** — the picker copies only the command. ## Where Converted every plain `npm install` / `pip install` code block under `docs/content` (quickstart, all provider pages, single-toolkit MCP, custom tools, migration guides, standup example, SDK reference indexes). The TS reference index's manual npm/pnpm/yarn/bun tabs collapse into one picker. The two SDK-reference generators (`ts/packages/core/scripts/generate-docs.ts`, `python/scripts/generate-docs.py`) emit the new component so regeneration keeps it. Flagged upgrade commands (`pip install -U/--upgrade`) and the bun-first examples were left as-is. ## Verification - `bun run types:check` — pass - `bun run build` — pass - `eslint` on touched TS files — clean (remaining repo lint errors are pre-existing on `next`) - Visual check via dev server + browser: comment lines render muted below the command, picker opens npm/pnpm/bun/yarn (uv/pip on Python tabs), selecting a manager rewrites the command, and the clipboard receives exactly the command with no comment lines. Docs-only behavior change; no changeset (generator-script edits don't touch published code). 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
|
Rahul Tarak
|
caef908075 |
docs: refresh README(s) (#3801)
## Summary Rewrites the stale root `README.md` against the current docs (structure modeled on [earendil-works/pi](https://github.com/earendil-works/pi)'s README). - **Quickstarts** now use the session-based API (`composio.create()` → `session.tools()`) that the docs treat as canonical, replacing the legacy `composio.tools.get()` flow - **Positioning** matches the docs welcome page: 1000+ pre-authenticated toolkits, per-user sessions, auth, triggers, and a sandbox - **New sections**: CLI install (curl / Homebrew / npm), sessions-via-MCP note, repository layout, minimum runtime versions - **Provider table** merged with package links; adds the Claude Agent SDK providers (both SDKs) and the experimental Pi provider (`@composio/experimental`); documents the Python `composio-gemini`/`composio-google`/`composio-google-adk` split - **Removed**: Rube section (no longer in docs), cover banner (replaced with theme-adaptive brand logomark from brand.composio.dev), master-branch pointer, internal OpenAPI-pull section, private `@composio/ts-builders` listing Docs-only change — no changeset needed. ## Preview Rendered view: [README.md on this branch](https://github.com/ComposioHQ/composio/blob/docs/refresh-root-readme/README.md) 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
|
Alberto Schiabel
|
15a03c10fb |
ci: add dead-code detection (knip + vulture + orphaned-CI check) (#3787)
## What Adds a **report-only** `Dead Code` CI workflow that surfaces likely-orphaned code on every PR, across all three surfaces — TypeScript, Python, and GitHub Actions. Follow-up to the root `Dockerfile` cleanup (#3783) and the dead-code sweep in #3786: instead of finding this stuff by hand, catch it automatically. | Surface | Tool | Wiring | |---|---|---| | TypeScript | [**knip**](https://knip.dev) | `knip.json`; runs via `pnpm dlx knip@5`. Finds unused files, exports, types, and dependencies. | | Python | [**vulture**](https://github.com/jendrikseipp/vulture) | `dead_code` nox session + `make dead-code`; allowlist at `python/config/vulture_allowlist.py`. Finds unused functions/classes/variables (complements Ruff's F401/F841). | | GitHub Actions | small bash script | `.github/scripts/check-orphan-ci.sh` — flags reusable workflows and composite actions with no callers. | ## Why report-only (not blocking) Every job writes findings to the run's **Step Summary** and **never fails the build**. These tools carry unavoidable false positives on a library monorepo — public API surface, dynamic imports, import-map targets (e.g. core's `#platform`), framework entry points. A red ❌ on false positives would just train everyone to ignore the check. Once a job's config is refined enough that a clean run is the steady state, it can be flipped to blocking. ## Validation (ran each locally) - **knip**: 0 unused *files* after scoping out the e2e-test workspaces (knip crashes traversing `ts/e2e-tests/**` — pre-existing knip bug, filed via `ignoreWorkspaces`) and build/docs artifacts. Export/dep categories surface advisory items. - **vulture**: clean run (report-only); allowlist suppresses the 3 `TYPE_CHECKING` re-exports in `custom_tool.py`; `build/`/`dist/` excluded. Surfaces 4 genuine minor items (`bases`, `desc`×3). - **orphan-CI script**: finds none — the repo has no orphaned CI plumbing today. - **Pinning**: `jk actions check` clean for this workflow; `actions/checkout` is SHA-pinned, the two local composite actions need no pin. Local usage is documented under **Dead code detection** in `CONTRIBUTING.md`. ## Note on scope These cover TS/Python/GHA — they would *not* have caught the root `Dockerfile` itself (an arbitrary root file no tool tracks). That class stays a manual-review concern; the orphan-CI script is the closest analogue for the CI surface. |
||
|
eeshsaxena
|
3e37f3c7a4 |
test: add unit tests for the mimetypes utility (#3750)
## Summary `composio/utils/mimetypes.py` had no test coverage. This adds a suite for both of its public helpers: **`guess()`** (filename/extension → MIME type): - known extensions resolve correctly (json, html, png, mp4, …) - the lookup table is lower-case, so an upper-case suffix (`photo.PNG`) falls back to the default - unknown / missing extensions return `application/octet-stream` - only the final suffix is used (`archive.tar.gz` == `archive.gz`) - `Path` objects are accepted, not just strings **`get_extension_from_mime_type()`** (MIME type → extension): - direct mappings (`image/png` → `png`, `application/vnd.ms-excel` → `xls`, …) - parameters are stripped (`text/plain; charset=utf-8` → `txt`) and matching is case-insensitive - structured `+suffix` handling: known prefixes win (`application/atom+xml` → `atom`), otherwise the suffix is used (`application/vnd.api+json` → `json`, `application/foo+bar` → `bar`) - subtype fallback (`application/x-custom` → `x-custom`), empty subtype → `txt`, and malformed/empty input → `bin` Tests only — no library code changed. `pytest python/tests/test_mimetypes.py` passes (`32 passed`); `ruff check` / `ruff format --check` are clean. Co-authored-by: Alberto Schiabel <jkomyno@users.noreply.github.com> |
||
|
Alberto Schiabel
|
fc17c37bf9 |
fix(cli): enforce sensitive-file upload denylist (GHSA-hp3h-89pf-5q58) (#3763)
This PR: - fixes #3746 / GHSA-hp3h-89pf-5q58 — the CLI's tool file-upload path bypassed the sensitive-file denylist - **root cause:** the denylist was enforced at the *caller* layer, so `@composio/cli`'s duplicate upload path (`readFileFromDisk`) read and uploaded any local path a tool argument pointed at — `~/.ssh/id_rsa`, `~/.aws/credentials`, `.env`, etc. — enabling credential exfiltration via `composio execute` / `composio run` (incl. LLM-driven agents hit by prompt injection) - **unified fix:** one canonical guard, exported from `@composio/core` and enforced at the read primitive in every SDK - `core`: the guard now routes fs/path access through the internal `#platform` abstraction (adds a `realpathSync` method), so it carries **no static `node:*` imports** and is exported from the package root: `assertSafeFileUploadPath`, `isBlockedSensitiveFileUploadPath`, `BUILTIN_FILE_UPLOAD_PATH_DENY_SEGMENTS` - `cli`: `readFileFromDisk` calls the shared `assertSafeFileUploadPath` before `fs.readFile`; URLs and `File` objects are unaffected (matches core) - `python`: already routes all uploads through the guarded `FileUploadable.from_path` — no functional change; adds regression tests for parity - supersedes #3755, which exported the then-node-only guard from core's **main** `index.ts` and would have injected `node:fs` into the shared `dist/index.mjs` (the workerd/edge-light entry), likely breaking Cloudflare Workers / Vercel Edge - changesets: `@composio/core` minor (new public exports), `@composio/cli` patch (security fix) ## Verification - core: full suite passes (997), incl. new root-export + realpath-symlink cases - **edge bundle stays clean**: built `dist/index.mjs` has no static `node:*` imports and reaches the platform only via `#platform` - cli: new regression test drives the real `uploadToolInputFiles → readFileFromDisk → guard` chain — `~/.ssh/id_rsa` and `.env` throw `ComposioSensitiveFilePathBlockedError` before any `createPresignedURL` call; a normal file still uploads - python: `test_files.py` + sensitive-path suite pass (145), incl. 3 new `from_path` guard tests - `tsgo` typecheck + eslint clean for core and cli |
||
|
Alberto Schiabel
|
820abb9072 |
fix(sdk): resolve toolkit versions case-insensitively in both SDKs (#3762)
## Summary
Toolkit version maps are keyed by **normalized (lowercase) slugs** on
the *write* side — env vars (`COMPOSIO_TOOLKIT_VERSION_*`) and
user-supplied dicts both get their keys lowercased when the map is
built. But the *lookup* read the map with the **raw slug**. A pin
configured under a different casing (e.g. `{ "GitHub": "20250101_00" }`
or `COMPOSIO_TOOLKIT_VERSION_GITHUB` looked up as `GitHub`) therefore
missed the map and silently fell back to `"latest"`, which
`Tools.execute` then rejects with a version-required error — discarding
the user's explicit pin.
Rather than patch only the read side, this **centralizes the
normalization rule** into a single helper per SDK and routes **both**
the map-building (write) and lookup (read) paths through it, so the two
sides can never drift apart again:
- **Python** — `normalize_toolkit_slug()` in
`python/composio/utils/toolkit_version.py`
- **TypeScript** — `normalizeToolkitSlug()` in
`ts/packages/core/src/utils/toolkitVersion.ts`, imported by
`getToolkitVersionsFromEnv` in `sdk.ts`
Behavior is now identical across the two SDKs. This **supersedes
#3759**, which patched only the Python read side and left TS diverging.
## Backend verification
Confirmed against the backend (staging, **1403 toolkits across 15
pages**): every toolkit `slug` is already lowercase (the mixed-case
`name` field is display-only). So the *primary* execute path — which
resolves via `tool.toolkit.slug` — was never broken in practice. This
change:
- **hardens** the direct-util and mixed-case-config paths (a user
passing `{ "GitHub": "…" }` now resolves as expected), and
- **removes a latent cross-SDK divergence**: the TS suite previously
asserted `getToolkitVersion` was *case-sensitive* (`versions.test.ts`),
locking in the bug for an input the production code path can't actually
produce. That test is flipped to assert case-insensitive resolution.
## Tests
- **Python** (`python/tests/test_toolkit_version.py`): case-insensitive
lookup via `get_toolkit_versions` round-trip, and against a raw
pre-normalized map. `18 passed`.
- **TypeScript** (`ts/packages/core/test/core/versions.test.ts`):
replaced the case-sensitivity assertion with case-insensitive resolution
+ a write→read round-trip of a mixed-case user pin. Full core suite `997
passed`.
- Typecheck (`tsc --noEmit`) clean; `ruff` clean.
## Notes
- Changeset added: `@composio/core` patch.
- No public API change; the fix is behavioral (case-insensitive) plus an
internal shared helper.
|
||
|
Alberto Schiabel
|
58bc93b2d9 |
chore(deps): consolidate dependency updates (#3760)
This PR: - consolidates https://github.com/ComposioHQ/composio/pull/3733, https://github.com/ComposioHQ/composio/pull/3735 through https://github.com/ComposioHQ/composio/pull/3744, and https://github.com/ComposioHQ/composio/pull/3752 - refreshes the pnpm workspace dependencies under the existing `minimumReleaseAge` supply-chain gate - keeps latest compatible pins for ESLint 9, AI SDK 6, and Cloudflare workers types 4 where latest majors conflict with the current workspace - keeps zod-v3 runtime fixtures on `zod@3.25.76` while bumping the workspace catalog to zod 4 - bumps Python `composio-client` to `1.42.0` and refreshes `uv.lock` - updates the SHA-pinned Claude and Codex workflow actions from the Dependabot action group - adds a patch changeset for the versioned package manifests touched by dependency updates - verifies the rollup with frozen pnpm/uv locks, peer checks, audit threshold checks, typecheck, lint, builds, TypeScript tests, and Python `nox -s chk` ## Context `pnpm audit --prod --audit-level=moderate` passes. The remaining production audit item is a low `@ai-sdk/provider-utils` advisory through Mastra transitive dependencies; forcing it higher would require leaving the compatible stable Mastra dependency path. |
||
|
Alberto Schiabel
|
2e42d75259 |
fix(py): apply skip_default to agentic provider signatures (langchain, langgraph, autogen) (#3730)
## Summary
Agentic providers honor `schema_config={"skip_defaults": True}` for
`args_schema` (defaults stripped, fields become required) but were
**not** applying the same `skip_default` to the function
`__signature__`, so the wrapped tool's signature and `args_schema`
disagreed about which defaulted params were optional. The sibling
`llamaindex` provider already passed it to both.
**Supersedes #3727.** This is the polished version, now that the ag2
migration (#3729) landed and `composio-autogen` imports again — so the
autogen case uses a real import instead of the earlier source-load stub,
and the parity tests run in CI.
## Changes
- **langchain / langgraph** (original commit by @anxkhn): pass
`skip_default=self.skip_default` to
`get_signature_format_from_schema_params`.
- **autogen**: same one-line alignment. autogen builds **only**
`__signature__` (no `args_schema`), so it never had the *mismatch* — but
its signature still ignored `skip_defaults`. Aligned for consistency;
verified on the signature alone.
- **tests**: `TestAgenticSkipDefaultsParity` guards each provider with
`pytest.importorskip`; adds real-import autogen regression tests (no
stub).
- **CI + nox**: install `providers/autogen` in the unit-test job
(`py.test.yml`) and the nox `tst` session so the autogen parity tests
actually run, plus a **hard `import composio_autogen` smoke check** in
CI.
## Why the CI import guard (not just the tests)
The `importorskip`-guarded unit tests **skip** when a provider can't be
imported — which is the correct behavior for optional providers, but
means they'd *silently skip* if autogen broke on a fresh install
(exactly the failure that #3729 just fixed). The extra `python -c
"import composio_autogen"` in the import step is a **hard** check that
fails loudly, so a future dependency breakage can't slip through as a
green build.
`providers/langchain` + `providers/autogen` co-install cleanly
(verified: 59 packages, ag2 0.14.0, no conflict). langgraph continues to
skip in CI — its code path is identical to langchain's, which runs.
## Type of change
- [x] Bug fix
## How Has This Been Tested?
- Base venv (langchain only): langchain parity **passes**, langgraph +
autogen **skip** (no error).
- CI-mirror (langchain + autogen, editable): **4 passed, 2 skipped
(langgraph)** — autogen tests actually run and pass.
- Regression proof, each provider: reverting only the provider line
fails the skip-defaults case with `assert 5 is Parameter.empty`;
restoring passes. Verified for langchain **and** autogen.
- `ruff check`, `ruff format --check`, `mypy`, and full
`tests/test_provider.py` (29 passed, 4 skipped) → clean. `py.test.yml`
parses.
## Checklist
- [x] I ran linters/tests locally and they passed
- [x] I added tests: langchain/langgraph parity + regression, and
autogen parity that runs in CI
- [ ] Changeset: not applicable — Python-only change.
## Credits
Original fix by @anxkhn (#3713 → #3727), preserved as the first commit
and co-authored on the follow-up.
---------
Co-authored-by: Anas Khan <83116240+anxkhn@users.noreply.github.com>
|
||
|
Alberto Schiabel
|
5ac2de2431 |
fix(py): migrate composio-autogen off abandoned pyautogen to ag2 (#3729)
## Summary `composio-autogen` fails to import on a fresh install: the provider depended on the abandoned `pyautogen` distribution, whose latest release (`0.10.0`) ships **no top-level `autogen` module**. The pin `pyautogen>=0.2.19,<0.11` resolves straight to it, so `import composio_autogen` raises `ModuleNotFoundError: No module named 'autogen'`. The autogen 0.2 lineage moved to the **`ag2`** distribution (`0.14.x`), which provides the same `autogen` package the provider uses (`ConversableAgent`, `autogen.agentchat.register_function`) alongside `autogen-core`. This swaps the dependency. Closes #3728. ## Changes - `providers/autogen/pyproject.toml` and `providers/autogen/setup.py`: `pyautogen>=0.2.19,<0.11` → `ag2>=0.14,<1.0`. `flaml` and `autogen_core` unchanged. **No provider code changes** — the imports and runtime API are identical across the two distributions. ## Type of change - [x] Bug fix ## How Has This Been Tested? Verified in isolation via `uv run --with ./providers/autogen` (a real fresh install of the provider with its new deps → resolves `ag2 0.14.0`): 1. **Import** — `import composio_autogen` now succeeds (previously `ModuleNotFoundError`). 2. **`wrap_tool`** — returns a real `autogen_core.tools.FunctionTool` with the expected signature. 3. **`register_tools` → `autogen.agentchat.register_function`** — the AG2 runtime path works end to end: - caller (LLM side): `caller.llm_config.tools` advertises the tool, - executor (execution side): the function lands in `executor._function_map`. `flaml==2.6.0` + `autogen-core==0.7.5` resolve cleanly alongside `ag2 0.14` (no conflict). ## Notes / follow-up This class of bug (a provider silently un-importable on fresh install) slipped through because **CI never installs or imports the autogen provider** — the unit-test job only installs `providers/langchain`. Worth a small follow-up: add a fresh-install import smoke test for the agentic providers so this can't recur silently. Left out here to keep this PR to the dependency fix and avoid adding ag2's install weight to the main test matrix. ## Checklist - [x] I ran the migration verification locally (isolation) and it passed - [ ] Changeset: not applicable — Python-only change. |
||
|
Alberto Schiabel
|
e78ed312c6 |
fix(core): run all parallel OpenAI tool calls from the first choice (#3726)
This PR: - supersedes https://github.com/ComposioHQ/composio/pull/3712, preserving the original commits by @serhiizghama (kept as author/co-author) - fixes `OpenAIProvider.handleToolCalls` to execute **every** tool call in an assistant message — it previously only read `tool_calls[0]`, so parallel tool calls (on by default) were dropped and their `tool_call_id`s went unanswered, failing the next request with the "must be followed by tool messages responding to each `tool_call_id`" error - limits execution to the **first choice** — with `n > 1` the previous loop ran each tool call once per choice and orphaned the `tool_call_id`s belonging to the alternative completions - aligns the Python SDK (`OpenAIProvider.handle_tool_calls`) with the same first-choice behavior so both SDKs stay in parity - fixes the stale `@composio/openai` test that modeled "multiple tool calls" as separate `n` choices rather than one message's `tool_calls` array - clarifies in the changeset that the calls run **sequentially**, in the order the model returned them (here "parallel" means the model issued several calls in one turn, not concurrent execution), so each `tool_call_id` is answered exactly once and deterministically - adds regression tests (TS + Python): both calls run for parallel tool calls in one message, and only the first choice runs when `n > 1` Full `@composio/core` (996) and `@composio/openai` suites green; Python `handle_tool_calls` tests, Ruff, and mypy clean; `tsc` clean. --------- Co-authored-by: serhiizghama <zmrser@gmail.com> |
||
|
Alberto Schiabel
|
a69c3edea3 |
fix(triggers): align create() user_id resolution across SDKs (#3723)
This PR: - builds on top of https://github.com/ComposioHQ/composio/pull/3714 — addresses its code-review findings - restores TS/Python parity on slug validation: Python `create()` now validates the slug up-front and raises a new `TriggerTypeNotFound`, mirroring the TS `ComposioTriggerTypeNotFoundError` - switches both SDKs to the native `user_id` upsert field — TS drops the `& { user_id }` intersection and Python drops the `extra_body` shim (both pinned clients already expose the field) - treats a blank/whitespace `userId` (TS) or `user_id`/`connected_account_id` (Python) as missing instead of forwarding it to the backend - documents the error-contract change (`create()` no longer throws `ComposioConnectedAccountNotFoundError` — that case now surfaces from the backend) in the changeset and `ts/docs/api/triggers.md`, and bumps the changeset from `patch` to `minor` - adds Python tests for the 2FA (both-provided) path, unknown-slug, and blank `userId`; tightens the TS auto-resolve assertion and adds an empty-`userId` case ## ⚠️ Release gating Since #3714, `triggers.create()` (both SDKs) relies on the backend resolving the trigger connection from `user_id` on upsert ([ComposioHQ/platform#10932](https://github.com/ComposioHQ/platform/pull/10932)). There is **no client-side fallback** — reintroducing one would undo #3714's intent, so this is a release-sequencing requirement, not a code change here. - Do not release `@composio/core` or the Python SDK until #10932 is live in all regions. - Self-hosted / on-prem deployments must be on a backend version that includes #10932. ## Review findings addressed | # | Finding | Resolution | |---|---------|------------| | P1-1 | Coupled to unreleased backend, no fallback | Documented dependency in changeset; flagged release-gating above (no fallback by design) | | P2-2 | Cross-SDK parity on slug validation | Kept `getType` in both; added Python `TriggerTypeNotFound` mirroring TS | | P2-3 | `user_id` bridge redundant in both SDKs | TS uses native field directly; Python uses `user_id=` kwarg | | P2-4 | Error-contract change shipped silently | Documented in changeset + docs `Throws` section; `minor` bump | | P2-5 | Python missing 2FA (both-provided) test | Added `test_create_with_user_id_and_connected_account_id` | | P3 6–13 | Cleanups | undefined-assertion, `none_to_omit`, docstring, `parsedBody.data`, redundant `else`, stale comments, blank-string guard | ## Verification - TS: `vitest` 59 passed, `typecheck` clean, `eslint`/`prettier` clean - Python: `pytest tests/test_triggers.py` 69 passed, `nox -s chk` (ruff + mypy) clean |
||
|
Anas Khan
|
c660007c71 |
fix(py): handle typeless and empty combiner schemas in openapi signatures (#3710)
### Summary
`function_signature_from_jsonschema` in
`python/composio/utils/openapi.py` builds the `__signature__` for tools
wrapped by the `google_adk` provider
(`providers/google_adk/composio_google_adk/provider.py:66`). It already
falls back to `Any` for a top-level property with no `type`, but the
nested combiner helpers do not, so real combiner shapes crash at wrap
time:
- a `oneOf`/`anyOf` option with no `type` key -> `KeyError: 'type'`
- an empty `oneOf`/`anyOf` list -> `TypeError: Cannot take a Union of no
types`
- an empty `allOf` list -> `KeyError: 'type'` (merges to `{}`)
This extends the existing "default to Any" intent to nested options.
Follow-up to #3708, which fixed the same bug family in `shared.py` and
noted this `openapi.py` case for a separate PR.
Fixes #
### Changes
- `_type_to_parameter`: read `schema.get("type")` instead of
`schema["type"]`; when the type is missing, return `t.Any` (mirrors the
top-level fallback). An unknown *string* type still raises
`InvalidSchemaError`.
- `_handle_composite_type`: return `t.Any` for an empty option list
instead of building an empty `Union`. Empty `allOf` merges to `{}` and
resolves to `Any` via the above.
- New `python/tests/test_openapi.py` (11 tests): this builder had none.
Asserts the five former crashes now resolve to `Any`, and that existing
shapes are unchanged.
### Type of change
- [x] Bug fix
- [ ] New feature
- [ ] Refactor/Chore
- [ ] Documentation
- [ ] Breaking change
### How Has This Been Tested?
From `python/`:
```
uv run pytest tests/test_openapi.py -q # 11 passed
make chk # ruff + mypy -> clean
```
To confirm the tests guard the fix, the five former crashes (typeless
`anyOf`/`oneOf` option, empty `anyOf`/`oneOf`/`allOf`) raise on the
unmodified file and now resolve to `Any`; regressions cover
`anyOf:[str,null]` -> `Optional[str]`, a 4-member union, enum, array,
object, and a typeless property.
### Checklist
- [x] I have read the Code of Conduct and this PR adheres to it
- [x] I ran linters/tests locally and they passed
- [ ] I updated documentation as needed (internal util)
- [x] I added tests (new test_openapi.py)
- [ ] I added a changeset (Python-only, not needed)
Co-authored-by: Alberto Schiabel <jkomyno@users.noreply.github.com>
|
||
|
Anas Khan
|
b0ab8eacff |
fix(py): handle 4+ option and typeless anyOf/oneOf unions in tool signatures (#3708)
## Summary
`get_signature_format_from_schema_params` in
`python/composio/utils/shared.py` builds the `__signature__` for the
tool wrappers used by the langchain, langgraph, llamaindex, and autogen
providers. Its `oneOf`/`anyOf` handling hardcoded a ladder for exactly
1, 2, or 3 union members and raised `ValueError("Invalid 'oneOf'
schema")` for any union with four or more options. It also indexed
`PYDANTIC_TYPE_TO_PYTHON_TYPE[ptype.get("type")]` directly, so any
combiner option missing a `type` key produced `None` and raised
`KeyError(None)`.
Both shapes are valid JSON Schema and appear in real tool input schemas,
so a tool with a 4-way union, or a combiner option without an explicit
`type`, makes those four providers raise at tool-wrap time. This
replaces the ladder with a single map + `functools.reduce` path that
mirrors the existing `_build_union_from_options` in
`schema_converter.py`, keeping the 1/2/3-member and nullable `[type,
null]` outputs identical to before.
Fixes #
## Changes
- `python/composio/utils/shared.py`: in
`get_signature_format_from_schema_params`, replace the 1/2/3-member
`oneOf`/`anyOf` ladder (which raised `ValueError` for 4+ members) with a
map-each-option-to-a-Python-type + `functools.reduce` Union build that
supports any member count. Unknown/missing option types map to
`typing.Any` instead of raising `KeyError`. Adds `from functools import
reduce` and removes three now-unnecessary `# type: ignore` comments.
- `python/tests/test_schema_parser.py`: add
`TestGetSignatureFormatFromSchemaParams` (8 cases) covering 4- and
5-member unions, an `anyOf` option missing `type`, an all-typeless
`anyOf`, and regressions for the previously supported single/2/3-member
and nullable `[type, null]` shapes.
## Type of change
- [x] Bug fix
- [ ] New feature
- [ ] Refactor/Chore
- [ ] Documentation
- [ ] Breaking change
## How Has This Been Tested?
From `python/`:
```
uv run pytest tests/test_schema_parser.py::TestGetSignatureFormatFromSchemaParams -v # 8 passed
uv run pytest tests/test_schema_parser.py -q # 75 passed
make chk # ruff + mypy -> clean, no new ignores
```
To confirm the tests guard the fix, the new test class was also run
against the unmodified `shared.py`: 4 of the 8 fail there
(`ValueError`/`KeyError` on the 4+/typeless cases), and all 8 pass with
this change. The nullable `anyOf [type, null]` case still resolves to
`Union[str, Any, NoneType]` (its pre-existing behavior); collapsing
`null` into `Optional` lives in `schema_converter` and is intentionally
left out of this minimal fix, with the test documenting current
behavior.
## Screenshots (if applicable)
N/A
## Checklist
- [x] I have read the Code of Conduct and this PR adheres to it
- [x] I ran linters/tests locally and they passed
- [ ] I updated documentation as needed
- [x] I added tests or explain why not applicable
- [ ] I added a changeset if this change affects published packages
## Additional context
No linked issue: this is a self-identified, reproduced bug in the older
schema->signature path. The fix deliberately mirrors
`schema_converter._build_union_from_options` so the two schema paths
agree on N-ary union handling. The same bug family exists in
`python/composio/utils/openapi.py`
(`function_signature_from_jsonschema`, used by the google_adk provider)
but is kept out of this PR to stay single-purpose; happy to follow up on
it separately.
|
||
|
Anshu Garg
|
20a4711ee0 |
feat(triggers): resolve connection from user_id server-side in create() (#3714)
## What `triggers.create()` used to make an extra **`connectedAccounts.list()`** call to turn a `user_id` into a `connected_account_id` before calling upsert. The backend now resolves the connection from `user_id` directly (picks the first active connection for the user + the trigger's toolkit, parity with tool execution), so the SDK passes `user_id` straight through and drops the round-trip. - **TS** (`ts/packages/core`): removed the `connectedAccounts.list()` block in `Triggers.create()`. `user_id` was already forwarded to upsert (for 2FA); this just removes the now-redundant lookup. `getType` is kept for an early, clear "trigger type not found" error. `connected_account_id` is passed when the caller pins one. - **Python** (`python/composio`): dropped `_get_connected_account_for_user`; `user_id` is sent via `extra_body` and `connected_account_id` is omitted when not provided. ## Why The SDK only ever holds a `user_id`, so every `triggers.create()` paid an extra API call to find a connection. The backend change (ComposioHQ/platform#10932) makes trigger upsert accept `user_id` and auto-resolve — this PR consumes that. ## Behavior notes - When `connected_account_id` is omitted, the backend picks the first active connection ordered by `created_at desc`. The TS SDK's old `list()[0]` ordering was unspecified — selection is now deterministic and consistent with tool execution. - "No connected account found" / "connected account not found" now surface from the **backend** instead of a client-side pre-check. - When 2FA is enabled and `connected_account_id` is pinned, the backend validates that `user_id` owns it (unchanged; `user_id` was already forwarded). - The `extra_body` / `& { user_id }` bridges are still needed only until `@composio/client` / `composio_client` regenerate with `user_id` on the upsert type (the field is already in the OpenAPI contract). ## Tests - TS: `vitest run test/models/triggers.test.ts` → **58 passed** (create tests rewritten to assert no `connectedAccounts.list()` call + `user_id` forwarded). - Python: `pytest tests/test_triggers.py` → **66 passed** (same). ## Depends on Backend: ComposioHQ/platform#10932 (`feat(apollo): resolve trigger connection from user_id on upsert (PLEN-2580)`). 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
Alberto Schiabel
|
03cb181fdb |
chore(deps): roll up dependency bumps (#3711)
This PR: - rolls up https://github.com/ComposioHQ/composio/pull/3695, https://github.com/ComposioHQ/composio/pull/3696, https://github.com/ComposioHQ/composio/pull/3697, and https://github.com/ComposioHQ/composio/pull/3698 into one dependency-bump branch - updates Python dependency metadata for `langchain-openai`, `pyautogen`, and `crewai` - updates npm production dependency metadata for `zod-to-json-schema`, `openai`, and `@modelcontextprotocol/sdk` - refreshes `uv.lock` and `pnpm-lock.yaml` with the repo-pinned package managers - leaves Changesets unchanged because the touched TS package manifests are private/ignored and no published TS SDK package metadata changes - verified with `pnpm install --frozen-lockfile`, `pnpm lint`, `pnpm typecheck`, focused TS builds/tests, clean-worktree `pnpm test:examples`, Python import tests, and Python nox checks - note: local `pnpm build:packages` hit a pre-existing broad-build race around `@composio/slim` rebuilding `@composio/core`; focused dependent builds pass --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> |
||
|
Alberto Schiabel
|
9901e01a80 |
feat(py): add tool router session deletion
Release Python 0.17.1 with Tool Router session deletion support. |
||
|
Alberto Schiabel
|
956f9be9b4 |
chore(agents): normalize repo guidance skills (#3666)
This PR: - replaces the duplicated repo-local skill set with the requested canonical `.agents/skills` taxonomy and short router `SKILL.md` files backed by first-level references - makes `.claude/skills` a compatibility symlink to `.agents/skills` and removes hand-maintained Claude skill/rule copies - moves docs agent guidance and decisions into neutral `docs/agent-guidance/` and `docs/decisions/`, with `docs/CLAUDE.md` reduced to a shim - retires CLI Cursor rules after migrating CLI design, Effect source, and client-cache sync guidance into `AGENTS.md` and `cli-command` - adds nested `AGENTS.md` files for TS, core, providers, e2e, Python, Python providers, and docs - adds `pnpm validate:agent-skills` to validate skill frontmatter, taxonomy, references, symlink invariants, stale paths, and command names - implements missing Python `tst` and `snt` nox sessions that existing Makefile targets already exposed - no changeset: repository guidance/tooling only, no published SDK package behavior ## Verification - `pnpm validate:agent-skills` -> `Validated 14 canonical agent skills and guidance invariants.` - `for skill in .agents/skills/*; do python /Users/jkomyno/.codex/skills/.system/skill-creator/scripts/quick_validate.py "$skill" || exit 1; done` -> 14x `Skill is valid!` - `pnpm --dir ts/packages/cli validate:skills` -> `Validated composio-cli skill builds for stable and beta.` - `cd python && uv run nox --list` -> includes `tst` and `snt` - `cd python && uv run nox -s snt` -> 18 passed - `cd python && uv run nox -s tst -- tests/test_imports.py` -> 8 passed - `git diff --check` / `git diff --cached --check` -> clean - stale reference search for retired docs/Claude/Cursor paths -> no matches ## Forward Tests - TypeScript core bug: loaded `bug-fixing`, `typescript-sdk`, `typescript-testing`; found correct root/ts/core `AGENTS.md` route. - Python provider: loaded `python-providers`, `python-testing`; found missing nox sessions, fixed here. - CLI command: loaded `cli-command`; found recording/changeset wording gaps, fixed here. - Cross-SDK drift: loaded `cross-sdk-parity`; again found Python nox drift, fixed here. - Docs + decision: loaded `docs-decisions`; found decision template/index and Twoslash path gaps, fixed here. ## Notes The first normal `git commit` attempt hit a lint-staged/Git stash limitation while replacing `.claude/skills/` with a symlink (`path ... beyond a symbolic link`). The final commit used `--no-verify` after the validators and formatting checks above passed. |
||
|
Alberto Schiabel
|
e7bb45f449 |
fix(py): normalize generated SDK doc examples (#3689)
This PR: - normalizes Python SDK reference examples generated from source docstrings - rewrites the `Triggers.parse()` docstring so the generated Flask/FastAPI examples are copy-pasteable - strips nested Markdown fences before wrapping generated examples in MDX code fences - regenerates `docs/content/reference/sdk-reference/python/` - adds regression coverage for the `Triggers.parse()` generated example and fenced example normalization - does not include a changeset because this only changes docs generation, generated docs, and tests ## Verification - `cd python && .venv/bin/python -m pytest tests/test_generate_docs.py -q` - `cd python && .venv/bin/ruff check --config config/ruff.toml composio/core/models/triggers.py scripts/generate-docs.py tests/test_generate_docs.py` - `cd python && .venv/bin/ruff format --check --config config/ruff.toml composio/core/models/triggers.py scripts/generate-docs.py tests/test_generate_docs.py` - `cd python && .venv/bin/python scripts/generate-docs.py` - `cd docs && bun install --frozen-lockfile` - `cd docs && bun run types:check` |
||
|
Rahul Tarak
|
9df19b46cc |
chore(python): release 0.17.0 (#3678)
Python SDK 0.17.0 (mirrors the TS `@composio/core` 0.13.0 surface). `make bump` (minor) bumped `pyproject.toml` + all provider packages to 0.17.0; this PR also syncs `composio/__version__.py` and adds the `## [0.17.0]` CHANGELOG entry so the release guard (`__version__` == `pyproject` == `CHANGELOG[0]`) passes — verified locally (`release workflow test passed`). ## 0.17.0 surface - `triggers.parse()` (parse + optionally verify a webhook; empty `verify_secret` now raises instead of silently skipping) and `triggers.set_webhook_subscription()` - `composio.sessions` is the canonical sessions mount; `composio.tool_router` deprecated alias - MCP is opt-in (`mcp=True`); default sessions return native tools - Prefer the `sandbox` session config key (`workbench` still accepted) - `connected_accounts.update_acl()` (graduated from experimental) Merging this triggers the Python publish. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Rahul Tarak
|
d17a268d3f |
docs: sessions-first rewrite — new guides, examples & components (+ core 0.13.0 SDK changes) (#3637)
Integration branch for the next docs release: a **sessions-first
documentation rewrite** — new and rewritten guides, example pages,
interactive components, and docs tooling — plus the supporting SDK
changes that the new docs describe.
The bulk of this PR is docs (~24k lines across ~150 commits); the SDK
changes (~5k lines) back the new guides.
## Documentation (the bulk)
- **Sessions-first restructure** — reorganized navigation and section
structure (incl. the "Sandbox (prev workbench)" section), with
v3-reorganization redirects so old URLs keep resolving.
- **Rewritten core guides** — quickstart, configuring sessions, triggers
(creating + subscribing to events), proxy-execute, toolkits
enable/disable, and common FAQ, rewritten in the house voice.
- **New example pages** — local-sandbox PR reviewer, daily standup bot,
and slack bot, with runnable build-ups.
- **New interactive components & diagrams** — triggers flow animation,
manage-connections visual, connection-refresh visual, and the
terminal-kit components.
- **Docs tooling** — a docs-graph link-graph connectivity checker,
search reprioritization (deprioritize legacy pages), and SDK-reference
regeneration.
## Supporting SDK changes
**`@composio/core` → 0.13.0 (minor)**
- `composio.sessions.create()` as the first-class sessions API
(`composio.create()` kept as an alias).
- **MCP is opt-in:** default `create()` / `use()` return native-tool
sessions (`SessionWithoutMcp`); pass `{ mcp: true }` to surface
`session.mcp`. _Migration: read `session.mcp` only after creating with
`{ mcp: true }`._
- `session.sandbox` is the canonical resolved config;
`session.workbench` kept as a deprecated alias. `sandbox` is the
preferred session-config key (`workbench` still accepted).
- `connectedAccounts.updateAcl()` graduated from experimental (alias
kept).
- `triggers.parse()` (parse + optionally verify an incoming webhook) and
`triggers.setWebhookSubscription()`.
**`@composio/experimental` → minor** — local-workbench helpers moved
onto the `@composio/experimental/workbench` subpath (out of
`@composio/core/experimental`), keeping the ~14 KB embedded Python
helper out of core. Plus the experimental Pi provider.
**`@composio/slim` → minor.**
**Python → 0.17.0** — mirrors the TS surface: `composio.sessions` mount
(`tool_router` deprecated), `triggers.parse()` /
`set_webhook_subscription()`, the `sandbox` config key, and
`connected_accounts.update_acl()`.
## Review response (#3664)
Addressed the `@composio/core` review:
- **Security:** `triggers.parse()` no longer fails open — a
present-but-empty `verifySecret` (e.g. unset `COMPOSIO_WEBHOOK_SECRET`)
now throws instead of silently skipping verification; omitting it stays
an explicit opt-out (both SDKs).
- Removed snake_case leakage from `transformWebhookSubscription` (+ the
index signature that allowed it).
- **Removed** the TS-only `connectedAccounts.link()` toolkit
auto-resolve (shipped with cancellability / orphaned-auth-config bugs
and was effectively undocumented; to be reintroduced properly later).
- Unified Python error types on `ValidationError`; added `mcp=True`
Python tests; fixed runtime-portability + error-type test assertions.
- Polished deprecation messages; fixed the backwards `/experimental`
`@deprecated` note and the `SessionWithMcp` JSDoc.
## Testing
- **TS:** `@composio/core` + `@composio/experimental` typecheck pass;
vitest green for the touched suites.
- **Python:** `test_tool_router.py` + `test_triggers.py` pass (161
tests).
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Kshitij Jhunjhunwala <kj@composio.dev>
Co-authored-by: Malay Vasa <malayvasa@gmail.com>
Co-authored-by: Sarah Simionescu <sarah@composio.dev>
Co-authored-by: Kshitij Jhunjhunwala <113939507+KJ-11@users.noreply.github.com>
|
||
|
Alberto Schiabel
|
0ece269c73 |
docs(py): complete 0.16.0 CHANGELOG before release (#3660)
This PR: - completes the Python `0.16.0` CHANGELOG entry, which previously documented only the version + dependency bump even though six user-facing fixes landed on the unreleased `0.16.0` since the entry was written (`py@0.15.0..HEAD`) - refreshes the `0.16.0` date to its actual release date (`2026-06-25`) - is a prerequisite for tagging `py@0.16.0` and publishing to PyPI — PyPI is currently at `0.15.0`; `0.16.0` was bumped in-repo but never tagged or published, and no further version bump was made for the six follow-up fixes ## Context `0.16.0` is unreleased (PyPI's latest stable is `0.15.0`, there is no `py@0.16.0` tag), and `pyproject.toml` / `__version__.py` were never bumped past `0.16.0`. So these six fixes belong to `0.16.0`, not a new version. The newly documented changes: - file `$ref`/`$defs` dereferencing so auto upload/download flags behind a reference aren't dropped (e.g. `GMAIL_GET_ATTACHMENT`) - disabling retries on non-idempotent `tools.execute()` / `tools.proxy()` writes to prevent duplicate side effects - bounded `(connect, read)` timeouts on session file transfers and presigned S3 paths - centralized provider-visible tool schema aliasing across Anthropic, Claude Agent SDK, Gemini, Google ADK, and OpenAI Agents - deep-copying the OpenAI Agents tool schema before stripping `examples`/`default` Plus the already-noted `composio-client` `1.39.0` → `1.41.0` bump and the dependency-range / uv-lock refresh. Once merged, release with: \`\`\`bash git tag py@0.16.0 <merge-commit> && git push origin py@0.16.0 \`\`\` |
||
|
Alberto Schiabel
|
31315357dd |
fix(py): correct without_retries rationale, preserve strict validation, pin copy() contract (#3658)
Review follow-up to #3657 (squash-merged before these review fixes could land on it). No behaviour change to the retry scoping itself — this tightens correctness, docs, and test coverage around the `without_retries` mechanism. - **Correct the `without_retries` caching rationale.** The previous docstring justified caching with "each clone creates a new `ContextVar`, and dynamically-created `ContextVar`s are never garbage-collected." That is false for this code path: `request_ctx` is only ever `.get()`, never `.set()`, so it is reclaimed by refcounting on drop (measured: 500k get-only clones leak ~0 KiB; the CPython leak only occurs with `.set()`). Caching is kept because it avoids constructing a fresh `HttpClient` on every `execute`/`proxy` (the hottest path) — the real, stated justification now. - **Preserve `_strict_response_validation` on the clone.** The Stainless-generated `copy()` drops it, so the no-retry sibling silently reverted to the default (`False`) even when the parent had it enabled. The `copy()` override now threads it through `_extra_kwargs` alongside `provider`, so the sibling differs from the parent only in `max_retries`. - **Document the scope boundary.** The `without_retries` docstring now states that only `tools.execute` / `tools.proxy` are de-retried; other non-idempotent writes (`auth_configs.create`/`update`/`delete`, `mcp.update`/`delete`, `connected_accounts.delete`/`refresh`, `link.create`) keep the default retries (most are naturally idempotent on retry; the durable fix is backend idempotency keys). - **Add regression coverage:** the clone preserves `_strict_response_validation`, plus contract guards pinning the Stainless `copy`/`_extra_kwargs`/`with_options` internals the override relies on — so a `composio_client` regen that breaks the contract fails as an obvious assertion rather than a cryptic `TypeError`. - Minor: fix the `x-sdk-version` `"unknwon"` → `"unknown"` typo and tighten `te.Self` typing on the cache field/property. No changeset (Python-only change; changesets are TypeScript-only). |
||
|
Alberto Schiabel
|
09b552aa03 |
fix(py): disable retries on non-idempotent tool writes to prevent duplicate side effects (#3657)
This PR: - stops the Python SDK from silently retrying `tools.execute` and `tools.proxy`, which are non-idempotent POST writes. The Stainless-generated client retries POSTs by default (`max_retries=2`) on read timeouts, 429, 5xx, and connection errors. A read timeout is unsafe to retry — the request may already be in flight on the backend — so a retry can duplicate the side effect, e.g. send an email twice. Reported in https://github.com/ComposioHQ/composio/issues/3586 - routes both write paths through a new `client.without_retries` — a cached, retry-disabled (`max_retries=0`) clone of the `HttpClient`. Reads and lists keep the default retries, so resilience is unchanged for idempotent calls - overrides `HttpClient.copy()` to re-inject the required `provider` keyword and re-aliases `with_options`, since the generated `copy()` rebuilds via `self.__class__(...)` without `provider` — previously `with_options(max_retries=0)` raised `TypeError` on the subclass - caches the no-retry sibling instead of cloning per call: each clone creates a new `ContextVar`, and dynamically-created `ContextVar`s are never garbage-collected - adds `tests/test_no_retry_writes.py`: writes hit the transport exactly once on a retryable 5xx, reads still retry-then-succeed (proving the scoping), and a regression guard for the `copy()` override - interim fix only — the durable solution is idempotency keys, tracked in https://github.com/ComposioHQ/composio/issues/3654 (gated on backend support), which supersedes this once available No changeset (Python-only change; changesets are TypeScript-only). |
||
|
ly-wang19
|
95b7b7f649 |
fix(openai_agents): deep-copy tool schema before stripping examples/default (#3632)
## Problem `OpenAIAgentsProvider.wrap_tool` mutates the caller's `Tool.input_parameters`. It shallow-copies the schema and then strips keys from the nested property dicts **in place**: ```python modified_schema = tool.input_parameters.copy() # shallow copy modified_schema["additionalProperties"] = False _remove_examples_from_schema(modified_schema) # del prop["examples"/"pattern"/"default"] ``` `_remove_examples_from_schema` recurses into `schema["properties"][*]` and does `del prop_value["examples"]`, `del prop_value["pattern"]`, `del prop_value["default"]`. Because `dict.copy()` is shallow, `modified_schema["properties"]` (and every nested property dict) is the **same object** as the original, so those deletions strip `examples`/`pattern`/**`default`** out of the caller's `Tool.input_parameters`. Since essentially every Composio tool carries `default`/`examples` on its properties, wrapping a tool silently corrupts its schema. Wrapping the same `Tool` twice, reusing it with another provider, or inspecting it after wrapping then sees the defaults gone. This is the only wrap path using a shallow `.copy()` + nested mutation — the rest of the codebase deep-copies before mutating schemas, e.g. `composio/utils/shared.py` (`schema = copy.deepcopy(schema)`, with the docstring *"The schema is deep-copied before any mutation so the caller's original is never modified."*) and `Tools._get` (`tool.model_copy(deep=True)`). ## Fix Deep-copy the schema before mutating (`copy.deepcopy(tool.input_parameters)`), so `_remove_examples_from_schema` only edits the provider-local copy. One-line change + `import copy`. ## Test Added `python/providers/openai_agents/tests/test_provider.py::test_wrap_tool_does_not_mutate_input_parameters` — builds a tool whose properties carry `default`/`examples`/`pattern`, snapshots `input_parameters`, calls `wrap_tool`, and asserts both sides of the contract: - the caller's original `Tool.input_parameters` is unchanged - the returned `FunctionTool.params_json_schema` is still normalized for OpenAI Agents (`additionalProperties: false`, with `default`/`examples`/`pattern` stripped) - **Before:** the assertion fails — `owner` loses `default`/`examples`, `repo` loses `pattern`. - **After:** `Tool.input_parameters` is untouched while the wrapped schema remains sanitized. Verification: - `uv run pytest python/providers/openai_agents/tests/test_provider.py -q` → **1 passed** - `uv run ruff check python/providers/openai_agents/composio_openai_agents/provider.py python/providers/openai_agents/tests/test_provider.py` → clean - `uv run ruff format --check python/providers/openai_agents/composio_openai_agents/provider.py python/providers/openai_agents/tests/test_provider.py` → clean Co-authored-by: ly-wang19 <ly-wang19@users.noreply.github.com> |
||
|
Alberto Schiabel
|
d94a49ff43 |
fix(py): centralize tool schema aliasing (#3652)
This PR: - supersedes https://github.com/ComposioHQ/composio/pull/3625, https://github.com/ComposioHQ/composio/pull/3629, and the Python SDK/provider-side fix proposed by https://github.com/ComposioHQ/composio/pull/3504 - adds `alias_tool_input_schema` / `restore_tool_arguments` for provider-visible schemas and backend argument restoration - keeps `substitute_reserved_python_keywords` / `reinstate_reserved_python_keywords` as compatibility wrappers - preserves the existing Python keyword alias style (`from` -> `from_rs`), aliases invalid Python parameter names like `$top`, avoids leading-underscore aliases so Pydantic-backed providers can build models, and caps aliases at 64 characters for Anthropic-style tool schema validators - dereferences internal `$ref` / `$defs` before aliasing so referenced object properties are exposed through the same safe provider-visible names - restores Gemini manual `handle_response` arguments with the per-tool alias map before execution - wraps Google ADK tools with aliased callable signatures and restores original backend argument names - wraps Anthropic and Claude Agent SDK tool schemas with the same shared alias map and restores original backend argument names before execution - fixes the package-local Claude Agent SDK provider tests so they run without `pytest-asyncio` and keep using the provider-visible schema conversion hook - adds dependency-light core tests for helper behavior, `$ref` aliasing, Pydantic model compatibility, Gemini manual response, Google ADK wrapping, Anthropic wrapping, and Claude Agent SDK wrapping Local validation: - `uv run --project python pytest python/tests/test_tool_schema_aliasing.py python/tests/test_schema_parser.py python/tests/test_json_schema.py python/tests/test_imports.py -q` -> 112 passed - `PYTHONPATH=python uv run --project python --with-editable ./python/providers/claude_agent_sdk pytest python/providers/claude_agent_sdk/tests/test_provider.py -q --timeout=20` -> 16 passed - `uv run --project python --with-editable ./python/providers/langchain pytest --ignore-glob='python/tests/test_type_inference*.py' python/tests/ -q` -> 742 passed, 31 skipped - `uv run --project python --with-editable ./python --with-editable ./python/providers/langchain python <LangChain $top wrap smoke>` -> wrapped args schema field `param_top` - `uv run --project python --with-editable ./python --with-editable ./python/providers/langgraph python <LangGraph $top wrap smoke>` -> wrapped args schema field `param_top` - `uv run --project python ruff check --config python/config/ruff.toml python/composio/utils/shared.py python/tests/test_tool_schema_aliasing.py` -> passed - `uv run --project python ruff format --check --config python/config/ruff.toml python/composio/utils/shared.py python/tests/test_tool_schema_aliasing.py` -> passed - `git diff --check` -> passed Note: #3500's hosted MCP emission-layer report is already closed; this PR covers the Python SDK/provider surface rather than changing hosted MCP schema emission. |
||
|
Alberto Schiabel
|
aeeb471c63 |
fix(py): resolve $ref/$defs so file flags behind a reference aren't dropped (#3653)
## Problem
Tools whose parameter schemas express their file fields through a
`$ref`/`$defs` indirection lose auto file handling. With
`dangerously_allow_auto_upload_download_files=True`, a
`file_downloadable` output behind a `$ref` is never downloaded (the raw
`{name, mimetype, s3url}` object is passed through), and a
`file_uploadable` input behind a `$ref` is never staged — silently, with
no error.
`GMAIL_GET_ATTACHMENT` is the canonical shape — the flag sits two `$ref`
hops deep:
```
data → $ref → #/$defs/GetAttachmentResponse → file → $ref → #/$defs/FileDownloadable (file_downloadable: true)
```
**Root cause:** the hand-rolled walkers in
`composio/core/models/_files.py` (`_has_file_property`,
`_substitute_file_upload_value`, `_substitute_file_download_value`, …)
recurse through `properties`/`anyOf`/`oneOf`/`allOf`/`items` but **never
dereference `$ref`**, so a flagged node reachable only through a
reference is invisible to them.
Fixes https://github.com/ComposioHQ/composio/issues/3506
## Approach
Rather than teach each walker to dereference — which means threading a
root schema through ~10 methods, re-deriving `$ref` handling in each,
and risking unbounded recursion on cyclic schemas — this introduces a
single **`dereference_json_schema`** utility and inlines references
**once at the `FileHelper` boundary** (`process_file_uploadable_schema`,
`substitute_file_uploads`, `substitute_file_downloads`). The walkers
stay reference-agnostic.
This mirrors the TypeScript SDK's `dereferenceJsonSchema` (the
counterpart fix in #3566 for the TS twin of this bug, #3307) so both
SDKs share one behavioral contract. Resolving once at the boundary also
gives every walker `$ref` support for free — including keywords they
never special-cased (`additionalProperties`, `patternProperties`,
`prefixItems`, `not`), because the resolver walks containers
reflectively.
## What's in the utility (`composio/utils/json_schema.py`)
Faithful port of the TS guards:
- **Cycle safety** — breaks both `$ref` cycles and live-object identity
cycles with a permissive `{type: object, additionalProperties: true}`
sentinel. (A per-node lazy resolver without threaded cycle tracking
infinite-loops on a self-referential schema; there's a regression test
for exactly this.)
- **Depth caps** — `MAX_REF_CHAIN_DEPTH=100` / `MAX_NODE_DEPTH=512`
raise a typed `JSONSchemaRefResolutionError` instead of exhausting the
interpreter (with a `RecursionError` backstop converted to the same
typed error).
- **Sibling-keyword merge** — Draft 2020-12 semantics (siblings win on
collision), so a `description`/`default` next to a `$ref` survives.
- **External-ref passthrough** — `http(s)://` refs are left untouched
and logged once for audit.
- **`sentinel` mode** — a dangling `$ref` (an API schema that emits
`$ref` with no `$defs` block,
https://github.com/ComposioHQ/composio/issues/3307) degrades to the
permissive sentinel + an LLM-visible hint, instead of aborting the tool
call. The `FileHelper` uses this mode for API-sourced schemas.
- **Non-mutating** — returns a new schema; `$defs`/`definitions` are
stripped from the inlined root.
## Tests
- `python/tests/test_json_schema.py` — 30 cases mirroring the TS
`jsonSchema.test.ts` contract (chains, reflective container walk, legacy
`definitions`, sibling merge, cycles, depth caps, pointer-escape
decoding, array-index pointers, full `sentinel`-mode suite).
- `python/tests/test_files.py` — end-to-end regressions through the
public methods: download/upload behind `$ref`/`$defs` (the #3506 repro),
the LLM-facing input transform, graceful degradation of a dangling
`$ref`, and a **self-referential schema that must not recurse
infinitely**.
- `nox -s chk` (ruff + mypy) green; `nox -s tst` for the file/execution
suites green.
## Notes
Supersedes #3545 (third-party PR that fixed the same bug by threading
`root_schema` through each walker). That diagnosis was correct; this
takes the centralized route consistent with the TS SDK and adds the
cycle/depth guards. No changeset — Python-package change.
|
||
|
Xiaoju
|
dd40a9bb6f |
fix(py): bound file transfer requests with timeouts (#3563)
## Summary - add bounded `(connect, read)` timeouts to Python SDK session file downloads and uploads - add the same timeout coverage to presigned S3 upload/download paths used by file helpers - convert timeout/request failures into the SDK's existing file errors and cover them with tests Fixes #3560 Fixes #3561 Fixes #3562 ## Changes - `RemoteFile.buffer()` now uses the existing file transfer timeout constants and preserves file context on request failures - `ToolRouterSessionFilesMount.upload()` and S3 upload helpers now bound presigned `PUT` requests - `FileDownloadable.download()` now bounds streaming `GET` requests, wraps streaming read failures, and closes the response - added regression tests for request timeouts and timeout arguments - added a changeset for the published SDK change ## Type of change - [x] Bug fix - [ ] New feature - [ ] Refactor/Chore - [ ] Documentation - [ ] Breaking change ## How Has This Been Tested? - [x] `D:\anaconda3\envs\yolov12\python.exe -m ruff check python\composio\core\models\tool_router_session_files.py python\composio\core\models\_files.py python\tests\test_tool_router_session_files.py python\tests\test_files.py` - [x] `D:\anaconda3\envs\yolov12\python.exe -m ruff format --check python\composio\core\models\tool_router_session_files.py python\composio\core\models\_files.py python\tests\test_tool_router_session_files.py python\tests\test_files.py` - [x] `COMPOSIO_CACHE_DIR=<repo>\.tmp-composio-cache D:\anaconda3\envs\yolov12\python.exe -m pytest python\tests\test_tool_router_session_files.py python\tests\test_files.py::TestUploadBytesToS3 python\tests\test_files.py::TestFileDownloadablePathTraversal::test_safe_filename_passes_through python\tests\test_files.py::TestFileDownloadablePathTraversal::test_download_uses_timeout python\tests\test_files.py::TestFileDownloadablePathTraversal::test_download_timeout_raises_error python\tests\test_files.py::TestFileDownloadablePathTraversal::test_download_stream_timeout_raises_error` Note: I also ran the full `python\tests\test_tool_router_session_files.py python\tests\test_files.py` pair locally. The new and related tests passed, but the full run has one pre-existing Windows-specific failure in `TestFileDownloadablePathTraversal::test_empty_name_safe_fails_at_write_time`: opening a directory for writing raises `PermissionError` on Windows instead of the test's expected `IsADirectoryError`. ## Screenshots (if applicable) N/A ## Checklist - [x] I have read the Code of Conduct and this PR adheres to it - [x] I ran linters/tests locally and they passed - [ ] I updated documentation as needed - [x] I added tests or explain why not applicable - [x] I added a changeset if this change affects published packages ## Additional context This keeps the existing `(5s connect, 60s read)` timeout convention already used by the Python SDK's URL fetch helpers. --------- Co-authored-by: jkomyno <alberto@composio.dev> |
||
|
Alberto Schiabel
|
e408af962a |
fix(py): align Python release metadata (#3634)
This PR: - fixes https://github.com/ComposioHQ/composio/actions/runs/27964338497/job/82754032484 - aligns `python/composio/__version__.py` with the current Python package version `0.16.0` - adds the missing `0.16.0` Python changelog entry for the dependency refresh - restores `pnpm run test:release-workflow` on `next` |
||
|
Alberto Schiabel
|
a423a799c4 |
chore(py): refresh Python dependencies (#3627)
Refreshes the Python SDK's core + provider dependency ranges and uv locks to the **newest cutoff-compatible** versions, and makes the locks self-consistent. ## What changed - Bumps core + provider dependency ranges (`pyproject.toml` / `setup.py`) and regenerates all three uv locks (root, `openai`, `claude_agent_sdk`) to the newest available versions. - Keeps `composio-client==1.41.0` (the current newest, released 2026-06-19). - Caps `crewai>=0.134.0,<0.135.0`: crewai 1.x requires `pydantic>=2.11.9,<2.13`, which conflicts with composio core's `pydantic>=2.13.4`. Staying on crewai 0.x keeps the newest pydantic for everything else; the provider only uses `crewai.tools.BaseTool`, which is unaffected. - Drops the one-shot `--exclude-newer` cutoff that had been recorded in the lock `[options]` but was not backed by any `[tool.uv]` config — it broke `uv lock --check` and held packages a few releases behind newest. - Pins nox-installed tools/stubs in `noxfile.py` to the matching newest versions. ## Resolution result - Root lock: **161 upgrades, 0 downgrades** vs `next`. - Provider locks: **0 downgrades** vs `next` (openai +14, claude_agent_sdk +29). ## Verification - `uv lock --check` — clean on all three locks. - `uv run --frozen --all-packages pytest python/tests/test_imports.py` — 8/8 passing. - `uv run --frozen nox -s chk` — ruff clean + mypy 0 issues across 80 source files. Supersedes https://github.com/ComposioHQ/composio/pull/3622 (which was opened from a fork). |
||
|
Alberto Schiabel
|
a0bef5d986 |
chore(deps): bump composio client SDKs (TS alpha.74, Py 1.41.0) (#3609)
This PR: - bumps the TS catalog `@composio/client` from `0.1.0-alpha.72` to `0.1.0-alpha.74` (published from ComposioHQ/composio-base-ts#84) and refreshes `pnpm-lock.yaml` - bumps the Python `composio-client` pin from `1.39.0` to `1.41.0` (published from ComposioHQ/composio-base-py#69) - adds a patch changeset for `@composio/core` and `@composio/cli` so the client bump actually ships in the next release ## Context Neither client is auto-bumped in this repo — there is no Stainless→consumer bot, and Dependabot does not touch the pnpm `catalog:` pin (TS) or the exact `composio-client==` pin (Py), so these were a manual catch-up. The Python `1.41.0` PyPI publish initially failed with a `403 Forbidden` (stale `PYPI_TOKEN`); it was re-run successfully before this bump, so `1.41.0` is live on PyPI. |
||
|
jkomyno
|
0720b760e2 | fix(docs): stabilize SDK reference auto PR checks | ||
|
Alberto Schiabel
|
eeaac651d8 |
chore(py): document pending releases (#3583)
This PR: - documents the pending Python `0.14.0` and `0.15.0` releases in `python/CHANGELOG.md` - aligns `python/composio/__version__.py` with `python/pyproject.toml` at `0.15.0` - adds a release guard so Python package/provider versions, runtime version, and changelog entries cannot drift silently - leaves Python release tags and PyPI publishing untouched; `py@0.14.0` should still be published before `py@0.15.0` |
||
|
Anshu Garg
|
56e0d781f3 |
fix(triggers): handle V3 envelope in realtime subscribe path [SUP-392] (#3567)
## Summary `triggers.subscribe()` crashes with `KeyError: 'nanoId'` on the **first event** for any project configured with webhook version **V3**. The realtime (Pusher) channel now delivers the modern V3 envelope (snake_case: `metadata.trigger_id` / `connected_account_id` / `auth_config_id`, with no top-level `nanoId`), but the realtime parser (`TriggerSubscription._parse_payload`) only understood the **legacy** envelope and accessed `data["metadata"]["nanoId"]` directly — so the very first inbound frame raises inside the Pusher `_on_message` callback and the registered handler is never invoked. The SDK already knows how to normalize the V3 envelope — it does so on the webhook path (`_normalize_v3_payload`) — that logic was simply never wired into the realtime path. This has affected the realtime subscribe path for V3 projects since the V3 trigger payload format was introduced; webhook-version V1/V2 projects are unaffected (they still receive the legacy realtime envelope). ## Changes - Extract the V3 → `TriggerEvent` normalization into a shared module-level helper (`_build_trigger_event_from_v3`) plus an envelope detector (`_is_v3_envelope`); the webhook path's `_normalize_v3_payload` now delegates to it, so webhook and realtime share one source of truth. - `TriggerSubscription._parse_payload` now detects the V3 envelope and normalizes it, and keeps the existing legacy mapping for V1/V2 payloads. - Harden `_parse_payload`: unknown/malformed frames are logged and skipped (return `None`) instead of raising, so a single bad frame can no longer tear down an active subscription. - Add tests covering V3 realtime parsing, legacy realtime parsing, and malformed-frame handling. ## Type of change - [x] Bug fix - [ ] New feature - [ ] Refactor/Chore - [ ] Documentation - [ ] Breaking change ## How Has This Been Tested? - `ruff check` + `ruff format` (config/ruff.toml) — clean. - `uv run pytest tests/test_triggers.py` — **52 passed** (49 existing + 3 new). - New tests: - `test_parse_payload_v3_realtime_envelope` — a V3 realtime frame parses to a `TriggerEvent` (no `KeyError`). - `test_parse_payload_legacy_envelope` — V1/V2 legacy frame still parses correctly. - `test_parse_payload_malformed_returns_none` — bad/partial frames are skipped, not raised. ## Checklist - [x] I have read the Code of Conduct and this PR adheres to it - [x] I ran linters/tests locally and they passed - [ ] I updated documentation as needed - [x] I added tests or explain why not applicable - [ ] I added a changeset if this change affects published packages ## Additional context The realtime envelope is identical in shape to the V3 webhook envelope, so the shared normalizer keeps the two delivery channels consistent. No public API changes. --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: jkomyno <alberto@composio.dev> Co-authored-by: Alberto Schiabel <jkomyno@users.noreply.github.com> |
||
|
Anshu Garg
|
a94715f577 |
feat(sdk): forward user_id on triggers.create for trigger 2FA (#3576)
## What `triggers.create(userId/user_id, ...)` already accepts a user id and uses it to resolve the connected account, but **dropped it** when building the `trigger_instances.upsert` body. With [2FA for triggers](https://linear.app/composio/issue/PLEN-2580) on the backend, 2FA-enabled projects need `user_id` on the upsert to verify the pinned connected account belongs to the caller's user. This forwards `user_id` to upsert in **both SDKs**: - **TS** (`ts/packages/core/src/models/Triggers.ts`): adds `user_id` to the upsert params via a `& { user_id?: string }` bridge. - **Python** (`python/composio/core/models/triggers.py`): forwards `user_id` via the client's supported `extra_body` escape hatch. Both bridges exist only until `@composio/client` / `composio-client` regenerate from the updated OpenAPI spec with a native `user_id` field — drop them then. ## Safety Backends without trigger 2FA ignore the extra field, so this is safe to land ahead of / alongside the backend rollout (hermes PR #10635). ## Tests - TS: upsert-body assertion added. - Python: `tests/test_triggers.py::test_create_with_user_id` asserts `extra_body == {"user_id": ...}`. 49 tests pass. Closes part of PLEN-2580 (SDK follow-up to the agreed approach). 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> Co-authored-by: jkomyno <alberto@composio.dev> |
||
|
Alberto Schiabel
|
ce4b213361 |
fix(providers): normalize string tool-call arguments across all providers (TS + Python) (#3514)
## Summary Models — and some MCP transports — occasionally emit tool-call arguments as a **JSON string instead of an object/dict**. The most visible trigger is `COMPOSIO_MULTI_EXECUTE_TOOL` on the Vercel AI SDK, where streaming fails with: > `messages.3.content.1.tool_use.input: Input should be a valid dictionary` Until now only a handful of providers guarded against this, each with its own slightly different inline check, leaving most providers vulnerable and behaviour inconsistent across the SDK. This PR centralizes the coercion into **one helper per language** and routes **every** provider through it, in both the TypeScript and Python SDKs. Closes https://github.com/ComposioHQ/composio/issues/2406 ## What changed **TypeScript** — new `normalizeToolArguments` in `@composio/core` (exported), used by every provider: `vercel`, `cloudflare`, `openai-agents`, `openai` (ChatCompletions + Responses), `anthropic`, `google`, `langchain`, `llamaindex`, `claude-agent-sdk`, `mastra`. **Python** — new `normalize_tool_arguments` in `composio.utils.shared`, used by every provider: `openai`, `openai-responses`, `anthropic`, `google`, `langchain`, `langgraph`, `crewai`, `autogen`, `llamaindex`, `gemini`, `google-adk`, `openai-agents`, `claude-agent-sdk`. Shared semantics (identical in both languages): | Input | Result | | --- | --- | | object / dict | returned unchanged | | JSON string | parsed to object | | empty / whitespace string | `{}` | | `null` / `undefined` / `None` | `{}` | | array, primitive, unparseable string, JSON that isn't an object | **typed error** (`ComposioInvalidToolArgumentsError` / `InvalidParams`) with the original parse error as cause | The typed error replaces the previous grab-bag of behaviours: a raw `SyntaxError`/`JSONDecodeError`, or — worse — silently forwarding a malformed string downstream. ## Why this supersedes the open PRs This consolidates and extends three open PRs that each addressed a slice of the problem inconsistently. Their authors are credited as co-authors on the relevant commits: - **#3489** (LlamaIndex + Claude Agent SDK, TS) — @srijanarya - **#3438** (Anthropic, Google, LangChain, TS) — @aptsalt - **#3437** (Google ADK empty schemas + name fix, Python) — @pragnyanramtha — its empty-`input_parameters` / missing-description handling and the `gemini` → `google_adk` provider-name fix are folded in here. Compared to the three combined, this PR additionally: covers **every** provider in **both** SDKs (not a subset of one), defines a single source of truth instead of per-provider snippets, normalizes empty/`null` payloads to `{}`, and raises an actionable typed error instead of leaking `SyntaxError` or forwarding a bad string. ## Tests - Exhaustive unit tests for both helpers (object passthrough, JSON-string parse, empty/null → `{}`, malformed/non-object → typed error). - Per-provider regression tests across the touched TypeScript providers (string path, malformed-string path, empty-payload path). - Full `@composio/core` + touched-provider TS suites pass; `typecheck` and `lint` clean. Python `ruff` clean and new test green. ## Changeset Patch bump for all affected TypeScript packages (`@composio/core` + the providers). Python follows its own versioning, so no changeset there. --------- Co-authored-by: srijanarya <74669415+srijanarya@users.noreply.github.com> Co-authored-by: Deepak Singh Kandari <deepaksinghkandari07@gmail.com> Co-authored-by: Pragnyan Ramtha <pragnyanramtha@gmail.com> |
||
|
Alberto Schiabel
|
4fe776898a |
chore(toolchain): finish mise migration (#3493)
## Summary Depends on #3492. This completes the Phase 2 migration by removing the transitional version-file layer and making `mise.toml` plus `mise.lock` the repository toolchain source of truth. It also moves runtime test matrices into `toolchain-versions.json`, so CI matrix changes are explicit and reviewable without reintroducing `.nvmrc`, `.dvmrc`, `.bun-version`, or `.python-version`. The Node.js e2e matrix now starts at the latest Node 22 LTS line and also covers the latest Node 24 and Node 25 lines. That removes Node 20 from the well-known e2e versions while keeping us covered on the runtimes SDK users are moving toward. ## Rationale Phase 1 introduced mise side by side with the existing version files to keep the first PR low-risk. Phase 2 removes that compatibility layer so there is one place to update tool versions. That avoids silent drift between local setup, GitHub Actions, Docker E2E images, release docs, and install-time checks. The composite setup actions now install Node, Bun, Python, and uv through mise by default, with explicit version overrides only where a matrix needs them. New GitHub actions added in this PR are pinned by release commit SHA and include the release version comment. ## What changed - Deleted the transitional root/version files: `.nvmrc`, `.bun-version`, `.dvmrc`, root `.python-version`, and `python/.python-version`. - Removed `idiomatic_version_file_enable_tools` from `mise.toml` and added a committed `mise.lock` for linux/macOS x64/arm64 tool resolution. - Replaced `BYPASS_BUN_VERSION_CHECK` with `BYPASS_TOOLCHAIN_CHECK`, and made Docker E2E image installs use that bypass because they receive explicit build args instead of installing mise. - Updated Node/Bun and Python/uv composite actions to default to mise, remove `*-version-file` inputs, report resolved versions, and cache pnpm after `corepack enable`. - Centralized CI runtime matrices in `toolchain-versions.json` for TS E2E, Python tests, and CLI npm fallback coverage. - Updated the Node E2E matrix to `22.22.3`, `24.16.0`, and `25.9.0`, removing Node 20 from the well-known runtime versions. - Updated workflows, docs, E2E helpers, Dockerfiles, and release guidance to reference `mise.toml` / `mise.lock`. ## Verification - Verified latest Node 22/24/25 releases from the official Node dist index: `22.22.3`, `24.16.0`, `25.9.0` (https://nodejs.org/dist/index.json). - `pnpm install --frozen-lockfile` - `pnpm --filter @e2e-tests/utils typecheck` - `pnpm --filter @e2e-tests/utils exec tsc --noEmit --target es2022 --module esnext --moduleResolution bundler --types bun --resolveJsonModule --skipLibCheck --strict scripts/docker-build.ts` - `bash -n ts/scripts/pre-install.sh && bun run ts/scripts/pre-install/check-toolchain.ts && BYPASS_TOOLCHAIN_CHECK=1 bash ts/scripts/pre-install.sh` - `pnpm exec prettier --check ...` on touched YAML/Markdown/TS/JSON files - `ruby -e "require \"yaml\"; ARGV.each { |f| YAML.load_file(f) }" ...` on touched actions/workflows - `mise lock --platform linux-x64,linux-arm64,macos-arm64,macos-x64 && git diff --exit-code mise.lock` - `mise exec node@22.22.3 -- pnpm --filter @e2e-tests/utils typecheck` - `mise exec node@22.22.3 -- pnpm --filter @e2e-tests/node-esm-basic typecheck` - `mise exec node@22.22.3 -- pnpm --filter @e2e-tests/node-cjs-basic typecheck` - `docker manifest inspect node:24.16.0-slim` - `docker manifest inspect node:25.9.0-slim` - `git diff --check` |
||
|
Alberto Schiabel
|
2758287c87 |
feat(py): remove legacy custom tools (#3508)
This PR is **part 1 of 3** splitting https://github.com/ComposioHQ/composio/pull/3505 to make the removal of the old 2025 custom tools easier to review. It carries the **Python** slice. - removes the legacy `composio.tools.custom_tool` registry path: `core.models.custom_tools`, `ExecuteRequestFn`, the old fallback execution wiring, the security tests, and the example - preserves the 2026 tool-router APIs: `composio.experimental.tool()`, `composio.experimental.Toolkit`, inline custom-tool execution, preload/attach/use flows, and `session.custom_tools()` - bumps the Python workspace and all provider packages `0.13.1` → `0.14.0` ## Notes - This slice is a byte-identical subset of #3505 — the three split branches recombine to that PR's exact tree. See #3505 for the original local verification logs (`uv run --frozen nox -s chk`, targeted pytest); CI re-runs per PR. |
||
|
Alberto Schiabel
|
4367513f82 |
fix(python): guard enhance_schema_descriptions against empty schemas (#3398)
Stacked on #3397 · refs https://github.com/ComposioHQ/composio/issues/3354 ## Summary The TS fix in #3397 handled the reported case (`output_parameters: {}` from MCP toolkits) by normalizing empty schemas at `transformToolCases`. While verifying the Python SDK didn't have the equivalent Zod check, I found an **adjacent** crash on the input side. The Python SDK does not have the same Pydantic check** — `composio_client` types `input_parameters` / `output_parameters` as `Dict[str, Optional[object]]`, which accepts `{}` trivially. However, `Tools._get()` pipes every fetched tool's `input_parameters` unconditionally through `FileHelper.enhance_schema_descriptions` (`python/composio/core/models/tools.py:361-363`), which does: ```python for _param, _schema in schema["properties"].items(): ``` That crashes with `KeyError: 'properties'` on `schema={}`. Not reachable for the specific `granola_mcp` tools in the original report (they all have populated `input_parameters`), but it's the same API contract — any MCP tool with no required inputs would hit this through the public `Composio.tools.get(...)` call. The sibling `FileHelper.process_file_uploadable_schema` (`_files.py:760`) already guards this with `if "properties" not in schema: return schema`. This applies the same guard to `enhance_schema_descriptions`. ## Fix ```diff def enhance_schema_descriptions(self, schema: t.Dict) -> t.Dict: ... + if "properties" not in schema: + return schema required = schema.get("required") or [] for _param, _schema in schema["properties"].items(): ``` ## Testing Red → green confirmed locally. New `TestEnhanceSchemaDescriptionsEmptySchema` class in `tests/test_files.py` covers: 1. `schema={}` → returns `{}` (the bug repro). 2. Schema with metadata but no `properties` key → returned unchanged (mirrors the sibling method). 3. Schema with `properties: {}` (empty dict) → already works today; pinning behavior. 4. Populated schema → still enhanced (regression guard for the type-hint / required-marker enhancement). Cases 1–2 **fail on `next`** with `KeyError: 'properties'`. All 4 pass with the guard. Full `tests/test_files.py` stays green (116 tests). ```bash cd python .venv/bin/python -m pytest tests/test_files.py::TestEnhanceSchemaDescriptionsEmptySchema -v # → 4 passed .venv/bin/python -m pytest tests/test_files.py -q # → 116 passed ``` ## Stacked PR notes - Base: `jkomyno/fix-mcp-empty-output-parameters` (#3397). - This PR's diff against that base shows **only** the Python changes (`_files.py` + `tests/test_files.py`). - After #3397 merges, this should be retargeted to `next` (or rebased automatically by GitHub). --------- Co-authored-by: jkomyno <12381818+jkomyno@users.noreply.github.com> |
||
|
Alberto Schiabel
|
5dcb363446 |
docs(py): add 0.13.1 entry to CHANGELOG (#3427)
Adds a `0.13.1` entry to `python/CHANGELOG.md` covering the changes accumulated on `next` since the last Python release (`py@0.13.0`, May 7). The CHANGELOG had been quietly abandoned since `0.8.11` (Sept 2025); rather than try to backfill the 4-minor gap, this PR draws a line and adds a banner pointing readers at the git log for that window. Future releases start fresh from here. ## What's in 0.13.1 - **SHARED connected accounts (experimental)** — `composio.experimental.update_acl`, `experimental={...}` on `link()` / `session.authorize()`, `account_type` filter on `list()`. Mirrors `@composio/core@0.10.0` shipping in #3425. - **`initiate()` deprecation warning** — gated on response `Deprecation` header (RFC 9745) instead of `auth_scheme`, eliminating false positives for custom auth configs and non-OAuth schemes. - **Schema converter** — preserves nullability on `null`-only `anyOf` blocks. - **Dep bump** — `composio-client` 1.36.0 → 1.39.0. ## Release plan Documentation only — does NOT trigger a release on its own. The Python release flow is tag-triggered: ```bash # After this PR merges and after #3425 ships: git tag py@0.13.1 <next HEAD sha> git push origin py@0.13.1 ``` That fires `.github/workflows/py.release.yml` which builds and publishes to PyPI. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: jkomyno <12381818+jkomyno@users.noreply.github.com> |
||
|
Shrey Singla
|
fccec8b143 |
fix(python-sdk): handle file upload list unions (#3373)
## Summary
This updates the Python SDK's automatic file upload/download
substitution so it can handle tool schemas that accept either a single
file or a list of files.
Tools can expose file inputs as a union such as:
```json
{
"anyOf": [
{ "type": "object", "file_uploadable": true },
{ "type": "array", "items": { "type": "object", "file_uploadable": true } }
]
}
```
When auto-upload is enabled, the SDK presents those file-uploadable
objects to models as file path strings. If the model supplies a list of
local paths, the old resolver selected the first file-bearing union
branch, usually the single-file branch, and attempted to upload the
entire Python list as one path. That fails before the backend ever
receives the intended list of staged file descriptors.
## Changes
- Refactors upload substitution into a value/schema recursive walker via
`_substitute_file_upload_value`.
- Adds the same value/schema traversal shape for downloads via
`_substitute_file_download_value`.
- Selects composed-schema variants by runtime shape when possible, so
list values choose array branches and string/dict values keep the
single-value behavior.
- Preserves the existing fallback behavior: if no runtime shape matches,
use the first file-bearing variant.
- Treats `anyOf`, `oneOf`, and `allOf` consistently with the SDK's
existing composed-schema convention.
- Preserves root request/response dict mutation behavior for existing
call sites.
- Adds regression coverage for single-file vs multi-file unions, nested
array-item unions, download parity, and first-match fallback.
## Why
This is needed for file-capable tool schemas that are backward
compatible at the API level by accepting both a single file and multiple
files. The Python SDK should transform a list of local paths into a list
of staged `{name, mimetype, s3key}` descriptors, just as it already does
for direct array schemas.
## Verification
- `python -m ruff check python/tests/test_files.py
python/composio/core/models/_files.py`
- `python -m pytest python/tests/test_files.py -q` -> 119 passed
- `python -m pytest python/tests/test_files.py
python/tests/test_auto_upload_download_files.py
python/tests/test_upload_dir_allowlist.py
python/tests/test_tool_router_session_files.py -q` -> 166 passed
- Manual playground verification with a Gmail send using two local
attachments: both files were staged and sent successfully as an
attachment array.
Note: a full local `python/tests` run still has three unrelated failures
because `composio_langchain` is not installed in this environment; the
affected file-upload suites pass.
---------
Co-authored-by: Zen <zen@composio.dev>
|
||
|
venkat82
|
44972d90ad |
Merge remote-tracking branch 'origin/next' into feat/connected-accounts-experimental-py
# Conflicts: # python/composio/utils/schema_converter.py |
||
|
venkat82
|
1645634866 |
fix(schema-converter): silence mypy on null-only-anyOf fallback return
The `return t.Optional[t.Any] if has_null else str` line introduced in |
||
|
venkat82
|
ed3bb936d2 |
fix(connected-accounts-py): address review feedback on #3412
Six code-review nits from the multi-agent review on PR #3412: P1.1 — python/setup.py was still pinning composio-client==1.36.0 while pyproject.toml is on 1.39.0. The Experimental TypedDict that the new link() docstring imports only exists in 1.39+, so anyone installing via the legacy setup.py path would crash at import. Bumped to 1.39.0. P1.2 — exceptions.py ComposioSharedAccessDeniedError and ComposioSharedConnectionNotAccessibleError docstrings told users to call composio.connected_accounts.update_acl(), which no longer exists. Rewrote both to composio.experimental.update_acl(). P2.5 — ExperimentalAPI.update_acl returned t.Any; restored the typed ConnectedAccountPatchResponse return so callers reading .id / .status / .success keep type-safety at the API boundary. P2.6 — ExperimentalAPI.__init__(client: Optional[Any]) tightened to Optional[HttpClient]. The None branch stays for the one test that exercises it; production code in sdk.py always passes a real client. P2.7 — Dropped redundant alias=omit / connection=omit on the patch() call. Verified against the composio-client==1.39.0 wheel: both default to omit. Sibling ConnectedAccounts.update() already follows the cleaner pattern. Test assertions updated to match. P2.10 — Extracted the substring "acl_config_for_shared is only valid on SHARED" into ACL_ONLY_FOR_SHARED_ERROR_FRAGMENT in experimental.py, and reused it from connected_accounts.py + tool_router_session.py. Single source of truth so a server-side message tweak doesn't silently downgrade three call sites to generic BadRequestError. Tests: 201/201 pass. mypy on composio/ clean. Pushed back on the remaining P2 (TS divergence) in the review — the companion TS PR #3424 ships the exact same restructure, so parity is preserved once both land together. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Abir Taheer
|
d676cd8b30 |
chore(py): bump all packages to 0.13.1
Patch release matching TS 0.9.1 — includes account_type + per-user ACL on SHARED connections, SEC-339 deprecation header fix, nullability fix in schema converter, and docstring cleanup. Core was erroneously bumped to 0.14.0 in #3401 without a release; since 0.14.0 was never published to PyPI, all packages align at 0.13.1. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
Yizuki_Ame
|
630038ab83 |
fix: preserve nullability in null-only anyOf and fix validate param alias
Merge PR #3173 as the preferred fix for the null-only anyOf schema behavior and validate alias handling. |