mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-10 14:27:00 -04:00
137 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
github-actions[bot]
|
660fa8cfb6
|
chore: release main (#1574)
Some checks failed
Docker / docker-manifest (map[bake_target:runtime name:]) (push) Blocked by required conditions
Docker / docker-manifest (map[bake_target:runtime-code name:code]) (push) Blocked by required conditions
Docker / docker-manifest (map[bake_target:runtime-code-nonroot name:code-nonroot]) (push) Blocked by required conditions
Docker / docker-manifest (map[bake_target:runtime-code-slim name:code-slim]) (push) Blocked by required conditions
Docker / docker-manifest (map[bake_target:runtime-code-slim-nonroot name:code-slim-nonroot]) (push) Blocked by required conditions
Docker / docker-manifest (map[bake_target:runtime-nonroot name:nonroot]) (push) Blocked by required conditions
Docker / docker-manifest (map[bake_target:runtime-slim name:slim]) (push) Blocked by required conditions
Docker / docker-manifest (map[bake_target:runtime-slim-nonroot name:slim-nonroot]) (push) Blocked by required conditions
Docker / promote-latest (push) Blocked by required conditions
Init Native E2E / init-native (ubuntu-latest, claude) (push) Failing after 7s
Init Native E2E / init-native (ubuntu-latest, codex) (push) Failing after 6s
Init E2E / docker-init-e2e (push) Failing after 9s
Init Native E2E / init-native (ubuntu-latest, copilot) (push) Failing after 6s
Install Native E2E / install-native (ubuntu-latest) (push) Failing after 6s
Merge Conflicts / merge-conflicts (push) Failing after 5s
Release Please / release-please (push) Failing after 4s
Security / CodeQL (javascript-typescript) (push) Failing after 30s
Security / CodeQL (python) (push) Failing after 18s
Wrap E2E / docker-wrap-e2e (push) Failing after 11s
Security / Dependency audit (pip-audit) (push) Failing after 54s
Wrap Native E2E / wrap-native (ubuntu-latest) (push) Failing after 5s
Security / Secret scan (gitleaks) (push) Failing after 27s
Dev Containers / validate (.devcontainer/devcontainer.json, default) (push) Failing after 14m26s
CI / windows-native-wrapper (push) Has been cancelled
CI / macos-native-wrapper (push) Has been cancelled
Init Native E2E / init-native (macos-latest, claude) (push) Has been cancelled
Init Native E2E / init-native (macos-latest, codex) (push) Has been cancelled
Init Native E2E / init-native (macos-latest, copilot) (push) Has been cancelled
Install Native E2E / install-native (macos-latest) (push) Has been cancelled
Wrap Native E2E / wrap-native (macos-latest) (push) Has been cancelled
🤖 I have created a release *beep* *boop* --- <details><summary>0.29.0</summary> ## [0.29.0](https://github.com/headroomlabs-ai/headroom/compare/v0.28.0...v0.29.0) (2026-07-03) ### Features * **proxy:** add --lossless no-CCR mode with format-native compaction ([#1721](https://github.com/headroomlabs-ai/headroom/issues/1721)) ([ |
||
|
github-actions[bot]
|
aea3c35177
|
chore: release main (#1441)
🤖 I have created a release *beep* *boop* --- <details><summary>0.28.0</summary> ## [0.28.0](https://github.com/headroomlabs-ai/headroom/compare/v0.27.0...v0.28.0) (2026-06-29) ### Features * add --disable-kompress-fallback to restore legacy PASSTHROUGH fallback ([#1185](https://github.com/headroomlabs-ai/headroom/issues/1185)) ([ |
||
|
Kenneth Wong
|
4db3bc91d9
|
fix(bedrock): add boto3 1.41 + CRT for aws login credentials (#1486)
## Description `pip install headroom-ai[bedrock]` cannot serve users who authenticate with `aws login` (IAM Identity Provider / console-login, DPoP). Resolving those credentials requires the AWS Common Runtime (CRT); without `awscrt`, botocore raises `MissingDependencyException`. The AWS docs state the requirement as: **"Boto3 version 1.41.0 or later with AWS Common Runtime (CRT)"** — i.e. both a modern boto3 floor and CRT (installed via the `[crt]` extra). ## Type of Change - [x] Bug fix (non-breaking) ## Changes Made - `pyproject.toml` `bedrock` extra: bump `boto3>=1.28.0` → `boto3>=1.41.0`, add `botocore[crt]>=1.41.0` (installs `awscrt`). - `uv.lock`: regenerated — adds `awscrt`, resolves `boto3` to 1.42.x. No code changes — the bedrock backend already passes `aws_profile_name` through to the LiteLLM calls (via #1456); this just makes the installed dependencies actually able to resolve `aws login` credentials. ## Impact - **`aws login` (IAM Identity Provider / DPoP):** now works — awscrt present. - **`aws sso login` (classic Identity Center):** unaffected (already worked). - **static keys (`~/.aws/credentials`):** unaffected. - Bumping the boto3 floor only affects the optional `[bedrock]` extra; bedrock users benefit from a current boto3 regardless. ## Testing Dependency-only change. `uv lock` resolves cleanly (257 packages, awscrt 0.29.2, boto3 1.42.38). No runtime code path altered, so existing bedrock tests are unaffected. ## Checklist - [x] Self-review performed - [x] No new warnings - [x] Linting passes ## Additional Notes Focused on the dependency gap only. ARN routing / named-profile wiring / docs are handled in #1456; pricing in #1485. |
||
|
Parideboy
|
80fa086660
|
fix(packaging): move hnswlib to optional [vector] extra so [all] needs no C++ toolchain (#1499)
## Description `pip install "headroom-ai[all]"` aborts on any machine without a C++ toolchain. `[all]` pulls `[memory]`, which was the only extra carrying `hnswlib>=0.8.0`. hnswlib compiles from source where no wheel matches the target, and that build failure rolls back the **entire** `[all]` install. hnswlib is already fully optional at runtime: `MemoryConfig` defaults to `VectorBackend.AUTO` → **sqlite-vec** (pure Python, no compiler), and only falls back to HNSW. So `[memory]` does not need hnswlib to function. This moves hnswlib into a dedicated optional `[vector]` extra, exactly like `[pytorch-mps]` is already kept out of `[all]`. Closes #1368 ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) - [ ] New feature (non-breaking change that adds functionality) - [ ] Breaking change (fix or feature that would cause existing functionality to change) - [ ] Documentation update - [ ] Performance improvement - [ ] Code refactoring (no functional changes) ## Changes Made - `pyproject.toml`: - Removed `hnswlib>=0.8.0` from `[memory]` (keeps `sqlite-vec` + `sentence-transformers`; the default sqlite-vec backend still works). - Added `vector = ["hnswlib>=0.8.0"]` for users who opt into the HNSW backend. - `[all]` still references `[memory]` (now hnswlib-free) and does **not** add `[vector]`, so it resolves with no compiler. - `[dev]` keeps `hnswlib`, so CI still installs and exercises the HNSW backend tests. - Docs: documented the new `[vector]` extra in `installation.mdx` and the README, and noted it is excluded from `[all]`; fixed the `[memory]` row that claimed to bundle hnswlib. No application code changed. ## Testing - [x] Linting passes (`ruff check .`) - [x] Manual testing performed (TOML resolution check — see proof) - [ ] Unit tests pass (`pytest`) — no app code changed; existing memory/HNSW tests are unaffected (the HNSW backend dependency moved extras but `[dev]`/CI still install it). ### Test Output ```text $ python - <<'PY' # resolve [all] transitively and check hnswlib placement memory has hnswlib: False vector has hnswlib: True dev has hnswlib: True [all] resolved has hnswlib: False [all] has sqlite-vec: True [all] has sentence-transformers: True PY $ ruff check headroom/ tests/ All checks passed! ``` ## Real Behavior Proof - Environment: Windows 11, Python 3.13.11; `tomllib` + a small transitive-extra resolver over the edited `pyproject.toml`. - Exact command / steps: parse `pyproject.toml`, expand `headroom-ai[...]` self-references in `[all]` recursively, then check which extras carry `hnswlib`. - Observed result: the resolved `[all]` set contains no hnswlib while `[vector]` and `[dev]` do. Full output: ```text memory has hnswlib: False vector has hnswlib: True dev has hnswlib: True [all] resolved has hnswlib: False [all] has sqlite-vec: True [all] has sentence-transformers: True ``` `[all]` now resolves with **no** hnswlib (so no compiler needed), while the HNSW backend stays installable via `[vector]` and still tested via `[dev]`. - Not tested: a real `pip install` on a compiler-less host (the failure is a build-time rollback that the resolver check captures deterministically); the native-wrapper e2e jobs that this `pyproject.toml` change triggers run `wrap` e2e, not the memory HNSW path, so dropping hnswlib from `[all]` does not affect them. ## Review Readiness - [x] I have performed a self-review - [x] This PR is ready for human review ## Additional Notes - Editing `pyproject.toml` trips the `e2e` path filter, so the Windows/macOS/Docker native-wrapper jobs also run on this PR. They install + run the `wrap` e2e flow (not the memory HNSW backend), so the extras change is safe for them. Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
Tejas Chopra
|
5771a8020e
|
fix(deps): remediate dependency CVEs and publish SBOM (#1509)
## Description
Supply-chain hardening: takes the **shipped** dependency surface from
**26 known CVEs to 0**. `pip install headroom-ai[all]` now resolves with
no known vulnerabilities (verified with Anchore syft + grype). Also
publishes a checked-in SBOM package (`sbom/`) so any user — especially
pilots running their own security review — can verify what's inside and
that we track it.
This addresses the Dependabot alerts on `main` (9 high / 4 moderate / 7
low at time of writing).
Closes #
## Type of Change
- [x] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [x] Documentation update
- [ ] Performance improvement
- [ ] Code refactoring (no functional changes)
## Changes Made
**Rust**
- `pyo3` 0.24 → 0.29 (GHSA-36hh-v3qg-5jq4 High, GHSA-chgr-c6px-7xpp
Med). Migrated `Python::allow_threads` → `Python::detach` (10 sites) and
added `from_py_object` to the `Clone`-deriving `#[pyclass]` types (both
required by the 0.25+ API).
- `pyo3-log` 0.12 → 0.13; `lru` 0.12 → 0.18 (GHSA-rhfx-m35p-ff5j).
**Python**
- `torch` → 2.12.1, `mem0ai` → 2.x.
- Floor-pinned transitive CVE deps via `[tool.uv]
constraint-dependencies`: `pygments>=2.20.0`,
`pydantic-settings>=2.14.2`, `gitpython>=3.1.50`, `langsmith>=0.9.0`.
- **Removed `benchmark` from the `[all]` aggregate** so the default
install is CVE-free. `lm-eval` is invoked as an external subprocess
(`python -m lm_eval`) and never imported, so it is not a true runtime
dep — it remains available via the opt-in `[benchmark]` extra. See
[Accepted Risks](#additional-notes).
**npm (build/test tooling — never shipped in the
wheel/container/published SDK)**
- `esbuild` override `>=0.28.1` in `sdk/typescript` + `plugins/openclaw`
(GHSA-g7r4-m6w7-qqqr).
- `docs/`: `@anthropic-ai/sdk` → `^0.106.0` (GHSA-p7fg-763f-g4gf),
`postcss` override to force Next.js's bundled copy ≥8.5.10
(GHSA-qx2v-qp2m-jg93); regenerated a stale `bun.lock` that carried a
**Critical** vitest/vite.
**CI**
- Pinned `pypa/gh-action-pypi-publish` `@release/v1` → `@v1.13.0`
(GHSA-vxmw-7h4f-hqxh) in `release.yml` + `publish.yml`.
**SBOM**
- New `sbom/` directory: CycloneDX 1.7 + SPDX 2.3 SBOMs, grype scan
evidence, 330-package license inventory, and a regeneration guide.
## Testing
- [ ] Unit tests pass (`pytest`) — N/A, no Python source changed
(deps/config only)
- [x] Linting passes — `cargo fmt --check` + `cargo clippy` clean on the
changed crate; 0 `.py` files changed so `ruff`/`mypy` scope is
unaffected
- [x] Type checking passes — `cargo check --workspace` (0 errors)
- [ ] New tests added — N/A (dependency bumps; covered by existing
suites)
- [x] Manual testing performed — see Real Behavior Proof
### Test Output
```text
# headroom-ai[all] product surface — the number that matters
$ grype sbom:sbom/headroom-sbom-all-extra.cdx.json
No vulnerabilities found
# full repo scan (universal lock incl. opt-in [benchmark] + dev)
$ grype sbom:sbom/headroom-sbom.cdx.json
NAME INSTALLED TYPE VULNERABILITY SEVERITY
sqlitedict 2.1.0 python GHSA-g4r7-86gm-pgqc High # [benchmark]-only, unpatchable, accepted
nltk 3.9.4 python GHSA-p4gq-832x-fm9v High # [benchmark]-only, unpatchable, accepted
# pyo3 0.29 migration — extension builds + imports + runs
$ cargo check --workspace
Finished `dev` profile [unoptimized + debuginfo] target(s)
$ maturin develop && python -c "from headroom._core import DiffCompressor, SmartCrusher; ..."
extension OK — detach + from_py_object paths exercised
# lru 0.18 — eviction path
$ cargo test -p headroom-proxy --lib drift
14 passed, 213 filtered out
# per-ecosystem npm audits
$ (cd sdk/typescript && npm audit) -> found 0 vulnerabilities
$ (cd plugins/openclaw && npm audit) -> found 0 vulnerabilities
$ (cd docs && npm audit && bun audit) -> found 0 vulnerabilities / No vulnerabilities found
```
## Real Behavior Proof
- Environment: macOS (darwin 25.4.0, arm64), Python 3.12 `.venv`, Rust
1.95 toolchain, syft 1.46.0, grype 0.115.0, bun 1.3.14, maturin 1.13.3.
- Exact command / steps: (1) `uv export --extra all --no-dev
--no-emit-project | syft → grype` for the product surface; (2) `cargo
check --workspace` + `maturin develop` + extension import/compress smoke
test; (3) `cargo test -p headroom-proxy --lib drift`; (4) `cargo fmt
--check` + `cargo clippy -p headroom-py`; (5) `npm audit` in
sdk/openclaw/docs + `bun audit` in docs.
- Observed result: `headroom-ai[all]` resolution scans clean — "No
vulnerabilities found" (179 pkgs); full/prod SBOM shows only the 2
documented accepted CVEs; pyo3 0.29 extension imports and runs (detach +
from_py_object paths exercised); drift tests 14/14 pass; cargo fmt +
clippy clean; all npm/bun audits report 0.
- Not tested: full `pytest` suite (no Python source changed);
release-profile wheel build (used dev-profile `maturin develop` for the
import proof — the extension is semantically identical).
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
(`sbom/README.md`)
- [x] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective — N/A
(dependency bumps; existing suites + scans cover it)
- [x] New and existing unit tests pass locally with my changes
- [ ] I have updated the CHANGELOG.md — N/A (Release Please
auto-generates from the conventional commit)
## Additional Notes
**Accepted risks (the 2 residual CVEs).** Both originate solely from the
EleutherAI `lm-evaluation-harness` under the **opt-in `[benchmark]`
extra**, which Headroom invokes as a subprocess (never imports):
- `sqlitedict` CVE-2024-35515 (High) — pickle deserialization; package
abandoned (last release 2021), **no upstream fix exists**.
- `nltk` CVE-2026-54293 (High) — path traversal in `nltk.data.load()`;
affects ≤3.9.4 (current latest), **no patched release**.
Neither is in `[all]`, the published wheel, or the container. They are
documented in `sbom/README.md` and will be picked up automatically once
upstream ships fixes.
**Release/CHANGELOG:** N/A items above are because this is a
dependency/security PR with no Python source changes; CHANGELOG is
Release-Please-managed via the conventional commit message.
|
||
|
github-actions[bot]
|
95b2333ee5
|
chore: release main (#1274)
🤖 I have created a release *beep* *boop* --- <details><summary>0.27.0</summary> ## [0.27.0](https://github.com/chopratejas/headroom/compare/v0.26.0...v0.27.0) (2026-06-22) ### Features * **cli:** add headroom doctor setup diagnostics ([#926](https://github.com/chopratejas/headroom/issues/926)) ([ |
||
|
Tufan ALIN
|
f11a271229
|
fix(code): pin tree-sitter-language-pack <1.0 so code compression works (#1234)
## Description The `[code]` extra requires `tree-sitter-language-pack>=0.10.0` with no upper bound, so it now resolves to the 1.x line. tree-sitter-language-pack 1.0 (2026-03-21) is a breaking rewrite whose `get_language()` / `get_parser()` return the pack's own binding types instead of standalone `tree_sitter.Language` / `tree_sitter.Parser`. As a result `headroom/transforms/code_compressor.py::_get_parser()` raises, the exception is caught upstream, and AST code compression silently falls back to passthrough (0% reduction, no error surfaced) on a fresh `pip install headroom-ai[code]`. This caps the dependency below the breaking rewrite and pins the matching tree-sitter range, which is the line the existing code is written against. Closes #1232 ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) - [ ] New feature (non-breaking change that adds functionality) - [ ] Breaking change (fix or feature that would cause existing functionality to change) - [ ] Documentation update - [ ] Performance improvement - [ ] Code refactoring (no functional changes) ## Changes Made - Pin `tree-sitter-language-pack>=0.10.0,<1.0` in the `[code]` extra (was `>=0.10.0`). - Add an explicit `tree-sitter>=0.25.2,<0.26` pin to document the supported range (0.13.0 already requires `tree-sitter>=0.25.2`). - Add an inline comment explaining why the `<1.0` cap is required, to prevent a future re-bump. ## Testing <!-- Check what you actually ran, then paste the real command output below. --> - [ ] Unit tests pass (`pytest`) - [ ] Linting passes (`ruff check .`) - [ ] Type checking passes (`mypy headroom`) - [ ] New tests added for new functionality - [x] Manual testing performed I did not run the full pytest / ruff / mypy suite for this change (it is a dependency-constraint pin); I verified the actual runtime behavior the pin restores. See Real Behavior Proof. ### Test Output ```text # BEFORE (resolved tree-sitter-language-pack 1.9.1): code compression no-ops CodeAwareCompressor().compress(<real .py>) -> compression_ratio = 1.0 (0% on every file sampled) # AFTER (tree-sitter-language-pack 0.13.0 + tree-sitter 0.25.2), headroom code unchanged: is_tree_sitter_available(): True # 60 varied real Python files (headroom, litellm, pydantic, openai), default CodeCompressorConfig: compressed OK (valid + reduced): 31 (52%) rejected for invalid syntax: 17 (28%) -> returns original, never serves broken code no reduction / too small: 12 (20%) reduction when it worked: min 4.4% median 37.2% max 88.8% # All compressed outputs re-parsed clean with ast.parse(). ``` ## Real Behavior Proof - Environment: Python 3.12, headroom-ai 0.26.0. Before: tree-sitter-language-pack 1.9.1 (what `[code]` resolves today). After: tree-sitter-language-pack 0.13.0 + tree-sitter 0.25.2 (what this pin resolves). - Exact command / steps: `pip install "headroom-ai[code]"`; then run `CodeAwareCompressor(CodeCompressorConfig()).compress(src)` over a sample of real `.py` files and re-tokenize before/after with tiktoken (cl100k_base), re-parsing each output with `ast.parse`. - Observed result: with the unpinned (1.x) resolution, every sampled file returned `compression_ratio == 1.0` (0%, silent passthrough). With the pinned (0.x) resolution and no code changes, `is_tree_sitter_available()` is True and 31/60 files compressed validly at a ~37% median (up to ~89%); all compressed outputs re-parsed clean. - Not tested: the full pytest / ruff / mypy suite; per-language rates for JS/TS/Go/Rust/Java/C/C++ (they share the same `_get_parser()` path, so the fix applies, but I measured Python specifically); the ~28% invalid-syntax rejections are a separate pre-existing robustness issue tracked in #1233, not addressed here. ## Review Readiness - [x] I have performed a self-review - [x] This PR is ready for human review ## Checklist - [x] My code follows the project's style guidelines - [x] I have performed a self-review of my code - [x] I have commented my code, particularly in hard-to-understand areas - [ ] I have made corresponding changes to the documentation - [x] My changes generate no new warnings - [ ] I have added tests that prove my fix is effective or that my feature works - [ ] New and existing unit tests pass locally with my changes - [ ] I have updated the CHANGELOG.md if applicable ## Screenshots (if applicable) N/A (dependency-constraint change). ## Additional Notes - This is the minimal fix to restore functionality. The proper longer-term fix is to migrate `_get_parser()` and the AST walker to the tree-sitter-language-pack 1.x API, after which the `<1.0` cap can be lifted; happy to follow up with that if preferred. - Unchecked checklist items, with rationale: no docs change needed (constraint-only); no new tests added (a corpus-based compress-and-reparse regression test would be valuable but belongs with the robustness work in #1233); I did not run the full local unit-test suite for a dependency pin; CHANGELOG appears to be release-please managed, so I left it untouched. - I am not a maintainer; this came out of an independent evaluation of the `[code]` path. Pinning `<1.0` parks the project on the now-superseded 0.x pack, which is the tradeoff for a one-line fix today. Co-authored-by: mitralone <5514599+mitralone@users.noreply.github.com> |
||
|
Ashish
|
d789a7c528
|
feat(transforms): tabular + spreadsheet (.xlsx/.xls) compression (#1128)
## Description Adds a content-type-aware path for **tabular data** — CSV/TSV, markdown tables, fixed-width text, and binary `.xlsx`/`.xls` spreadsheets — by routing them through the existing, battle-tested `SmartCrusher` instead of letting them fall through to `PLAIN_TEXT → Kompress`. The pipeline already compressed tables losslessly when handed a JSON array of records. This wires up the missing front door: detect tabular text (and ingest binary spreadsheets), convert to JSON records, and reuse `SmartCrusher.crush()`. No new compression algorithm. Closes # ## Type of Change - [ ] Bug fix (non-breaking change that fixes an issue) - [x] New feature (non-breaking change that adds functionality) - [ ] Breaking change (fix or feature that would cause existing functionality to change) - [ ] Documentation update - [ ] Performance improvement - [ ] Code refactoring (no functional changes) ## Changes Made - **Detection** (`content_detector.py`): new `ContentType.TABULAR` + `_try_detect_tabular()` for CSV/TSV, markdown tables, and fixed-width columns. Ordered after search/log (which also look "delimited") and before code, with a prose-rejection guard so it never steals `file:line:content` search output, `key: value` logs, or sentences with incidental commas. Rust backend returns `plain_text` for unknown types and the router already falls back to the Python detector, so **no Rust change**. - **Bridge** (`tabular_ingest.py`): stdlib parsers + `to_records()` + a `TabularCompressor` that parses → JSON records → `SmartCrusher` (lossless `csv-schema` first; lossy row-drop with reversible `<<ccr:HASH>>` markers stays SmartCrusher's built-in fallback). Only adopts a result when it actually saves bytes. - **Spreadsheets** (`spreadsheet_ingest.py`): `.xlsx`/`.xls` → per-sheet CSV text at the SDK boundary. Optional deps (`pip install headroom-ai[spreadsheet]`) fail loudly with an install hint, never silently degrade. - **Routing** (`content_router.py`): `CompressionStrategy.TABULAR`, `enable_tabular_compressor` flag, lazy getter, apply branch, strategy maps, Kompress fallback eligibility. - **SDK** (`compress.py`): `compress_spreadsheet(path, ...)` helper (one message per sheet). - **Packaging** (`pyproject.toml`): new `[spreadsheet]` extra; `openpyxl` added to `[dev]` so the xlsx path is exercised in CI. - **Docs/demo**: `examples/tabular_compression_demo.py` + README entry. ### Design note: lossless-only Compact, all-unique tables with no query yield ~0 savings — this is correct, not a bug. SmartCrusher returns `skip:unique_entities_no_signal` and won't drop unique rows without a duplicate/relevance signal. Real wins come from verbose/redundant tables and query-driven selection. A pressure-driven lossy row sampler was considered and intentionally not added. ## Testing - [x] Unit tests pass (`pytest`) - [x] Linting passes (`ruff check .`) - [x] Type checking passes (`mypy headroom`) - [x] New tests added for new functionality - [x] Manual testing performed ### Test Output ```text $ python -m pytest tests/test_transforms_tabular.py -q collected 20 items tests/test_transforms_tabular.py .................... [100%] ============================== 20 passed in 7.15s ============================== $ ruff check headroom/transforms/tabular_ingest.py headroom/transforms/spreadsheet_ingest.py All checks passed! $ mypy headroom/transforms/tabular_ingest.py headroom/transforms/spreadsheet_ingest.py Success: no issues found in 2 source files ``` `tests/test_transforms_tabular.py` (20 tests): detection true positives + no-misroute negatives (search/log/JSON/prose), parser units (incl. fixed-width), the CSV→SmartCrusher bridge, router routing + disable flag, and `.xlsx` ingestion (skipif openpyxl missing) + error paths. `spreadsheet_ingest` 100% / `tabular_ingest` 90% line coverage. ## Real Behavior Proof - **Environment:** local checkout of `feat/tabular-compression`, Python 3.x, `pip install -e ".[dev]"`. - **Exact command / steps:** `python examples/tabular_compression_demo.py` (no API key required). - **Observed result:** ```text === Raw tabular text (ContentRouter, char-level) === compact unique CSV strat=tabular chars 1306 -> 1072 ( 17.9% saved) redundant CSV strat=tabular chars 2661 -> 1350 ( 49.3% saved) verbose markdown strat=tabular chars 2019 -> 1580 ( 21.7% saved) === Full pipeline (real tokenizer) === redundant CSV tokens 768 -> 394 ( 48.7% saved) === Binary spreadsheet (.xlsx) === 2-sheet workbook tokens 1092 -> 683 ( 37.5% saved) ``` - **Not tested:** legacy `.xls` binary path (needs optional `xlrd` + binary fixture; `# pragma: no cover`); base64-embedded `.xlsx` inside multimodal blocks (out of scope, noted as a follow-up). ## Review Readiness - [x] I have performed a self-review - [x] This PR is ready for human review ## Checklist - [x] My code follows the project's style guidelines - [x] I have performed a self-review of my code - [x] I have commented my code, particularly in hard-to-understand areas - [x] I have made corresponding changes to the documentation - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective or that my feature works - [x] New and existing unit tests pass locally with my changes - [ ] I have updated the CHANGELOG.md if applicable ## Additional Notes - CHANGELOG/version are intentionally untouched: this repo uses **release-please**, which bumps the version and CHANGELOG via automated `chore: release main` PRs, not per-feature PRs. - The `.xls` path is `# pragma: no cover` (legacy, needs optional `xlrd` + a binary fixture). - Follow-up (out of scope): base64-embedded `.xlsx` inside tool-result/multimodal blocks; porting tabular parsers into the Rust core for parity. --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
Eyal Mizrachi
|
b2f04e4ef7
|
fix(deps): make litellm optional on Python 3.14 (#956) (#993)
## Description `litellm` is a hard dependency and its metadata caps `Requires-Python >=3.10,<3.14`, so `pip install headroom-ai` is unsatisfiable on Python 3.14. But litellm is only used for model registry / pricing / non-core providers — all lazily imported behind `ImportError` guards — never on the core compression or Anthropic proxy path. Refs #956 (install half). ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) ## Changes Made - Add a `python_version < '3.14'` marker to both litellm declarations (core deps + dev extra); installs unchanged on <=3.13, skipped on 3.14 (matches the existing rapidocr/tomli marker pattern). ## Testing - [x] Unit tests pass (`pytest`) - [x] New tests added for new functionality - [x] Manual testing performed ### Test Output ```text $ pytest tests/test_litellm_optional.py -q 2 passed in 0.10s $ python3.14 -m pip install dist/headroom_ai-0.25.0-cp310-abi3-linux_x86_64.whl Successfully installed headroom-ai-0.25.0 ... # litellm NOT installed $ python3.14 -c "import importlib.util as u; print(u.find_spec('litellm') is not None)" False ``` ## Real Behavior Proof - Environment: fresh venv on CPython 3.14.5, Linux - Exact command / steps: built the abi3 wheel, `pip install` it on Python 3.14, then `import headroom` + start the proxy + send a compressible request - Observed result: install exits 0 with litellm skipped; `import headroom` works; the proxy compresses (29913 -> 27626 tokens). Stock 0.25.0 cannot install on 3.14 at all. - Not tested: litellm-backed features on 3.14 (intentionally unavailable there until litellm supports 3.14) ## Review Readiness - [x] I have performed a self-review - [x] This PR is ready for human review --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
github-actions[bot]
|
b81a4a7a16
|
chore: release main (#931)
🤖 I have created a release *beep* *boop* --- <details><summary>0.26.0</summary> ## [0.26.0](https://github.com/chopratejas/headroom/compare/v0.25.0...v0.26.0) (2026-06-16) ### Features * add Copilot BYOK provider wrapper utilities and CLI support ([#1041](https://github.com/chopratejas/headroom/issues/1041)) ([ |
||
|
github-actions[bot]
|
8a53c8ec3b
|
chore: release main (#891)
🤖 I have created a release *beep* *boop* --- <details><summary>0.25.0</summary> ## [0.25.0](https://github.com/chopratejas/headroom/compare/v0.24.0...v0.25.0) (2026-06-12) ### Features * add differential network capture harness ([#761](https://github.com/chopratejas/headroom/issues/761)) ([ |
||
|
Logan Kang
|
c71592d421
|
feat(memory): add opt-in Apple-GPU (MPS) embedding runtime (#766)
## Description
On Apple-Silicon Macs — especially fanless models like the MacBook Air
(M5) — running the proxy with memory context injection can pin the CPU
while embedding. The embedding work runs an uncapped session on the CPU,
saturating multiple cores, which starves the proxy's asyncio loop and
leads to request timeouts.
This PR adds an **opt-in** runtime that offloads the memory embedder to
the Apple GPU (MPS). Setting `HEADROOM_EMBEDDER_RUNTIME=pytorch_mps`
routes embedding through the torch `sentence-transformers` backend on
MPS instead of the default ONNX CPU embedder, moving the work off the
CPU and keeping the proxy responsive.
The default behavior is unchanged — the feature is strictly opt-in,
env-var only, and falls through to the existing default embedder
selection (with a warning) whenever MPS or the torch dependencies are
unavailable.
Fixes: N/A — no tracking issue (surfaced while running codex auto-review
through
the proxy on a fanless MacBook Air (M5)).
## Type of Change
- [ ] Bug fix (non-breaking change that fixes an issue)
- [x] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [x] Performance improvement
- [ ] Code refactoring (no functional changes)
## Changes Made
- **Runtime selection** (`headroom/proxy/memory_handler.py`): read
`HEADROOM_EMBEDDER_RUNTIME`; when set to `pytorch_mps` **and** MPS is
actually available, route the memory embedder to the torch
`sentence-transformers` backend (Apple GPU).
- If MPS is unavailable or torch/sentence-transformers is not installed,
log a warning and fall through to the existing default embedder
selection (ONNX when available, else the pre-existing local
sentence-transformers fallback) — no crash. The default (env var unset)
is unchanged. Env-var only
- **MPS serialization** (`headroom/memory/adapters/embedders.py`):
`LocalEmbedder` now funnels every `encode()` through a dedicated
single-worker `ThreadPoolExecutor` when the resolved device is MPS.
torch-MPS is not thread-safe, and the existing `run_in_executor(None,
...)` dispatch would otherwise let concurrent proxy requests call MPS
from multiple threads. CPU/CUDA keep the shared default executor
(behavior unchanged). `close()` also drops the cached model so re-use
after close re-initializes cleanly.
- **Packaging** (`pyproject.toml`): new `pytorch-mps` extra (`torch` +
`sentence-transformers`), **platform-gated to macOS** (`; sys_platform
== 'darwin'`) since MPS is Apple-Silicon-only. Deliberately left out of
`[all]` (its deps already arrive via `[ml]`/`[memory]`).
- **Tests** (`tests/test_memory/test_embedder_mps_serialization.py`):
regression coverage for the serialized executor, concurrency safety (no
SIGABRT), CPU-path default behavior, and close/re-use re-initialization.
- **Docs**: `wiki/{configuration,memory,macos-deployment}.md`,
`docs/content/docs/{configuration,installation,memory}.mdx`,
`README.md`, `CHANGELOG.md`.
## Testing
- [x] Unit tests pass (`pytest`)
- [x] Linting passes (`ruff check .`)
- [x] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed (CPU-offload + concurrency profiling on
Apple Silicon)
## Test Output
```
$ pytest -v tests/test_memory/test_embedder_mps_serialization.py
collected 4 items
tests/test_memory/test_embedder_mps_serialization.py::test_cpu_uses_shared_executor PASSED [ 25%]
tests/test_memory/test_embedder_mps_serialization.py::test_mps_creates_single_worker_executor PASSED [ 50%]
tests/test_memory/test_embedder_mps_serialization.py::test_mps_concurrent_embeds_do_not_crash PASSED [ 75%]
tests/test_memory/test_embedder_mps_serialization.py::test_mps_reembed_after_close_recreates_executor PASSED [100%]
============================== 4 passed in 6.92s ===============================
$ ruff check headroom/memory/adapters/embedders.py headroom/proxy/memory_handler.py tests/test_memory/test_embedder_mps_serialization.py
All checks passed!
$ mypy headroom/memory/adapters/embedders.py headroom/proxy/memory_handler.py
Success: no issues found in 2 source files
$ pytest -q tests/test_memory/ tests/test_memory_handler_concurrent_init.py tests/test_memory_handler_native_ops.py
553 passed, 1 skipped in 13.51s
```
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] I have updated the CHANGELOG.md if applicable
## Additional Notes
**Why MPS (and not CoreML or a thread cap):** measured on an
Apple-Silicon Mac, the default uncapped CPU embedding session saturates
the cores; the same model on MPS runs at a fraction of the CPU (≈8x
lower sustained CPU utilization in profiling) while producing
**byte-identical embeddings** (cosine distance ≈ 0 across runtimes), so
relevance/ranking is unchanged. A CoreML execution-provider path was
evaluated and rejected: the default optimized ONNX model uses fused ops
that fall back to CPU under CoreML (no offload), and a full-precision
re-export was impractical (very low throughput + multi-GB memory). MPS
via `sentence-transformers` was the only practical GPU offload.
**Why serialization is mandatory:** torch-MPS is not thread-safe —
concurrent encode calls from a multi-worker executor abort with
`-[IOGPUMetalCommandBuffer validate]: failed assertion 'commit an
already committed command buffer'` (reproduced deterministically; a
single-worker executor resolves it).
Under concurrent load the serialized single-GPU-stream throughput meets
or exceeds the parallel CPU path while using a fraction of the cores.
**Scope / boundary:** this targets the Python **memory** embedder, which
is live on the proxy request path (memory context injection). The
Rust-backed SmartCrusher compression path is unaffected and remains
non-configurable from Python by design.
**Safety:** default behavior is unchanged (ONNX, no torch). The feature
is opt-in, env-var only, macOS-gated at the packaging layer, and
degrades gracefully (warn + the existing default embedder selection)
when MPS or the dependencies are unavailable.
|
||
|
Patrick A
|
2ad300aff8
|
fix(transforms): use thread-local tree-sitter parsers to prevent pyo3 Unsendable panic (#604)
## Problem
pyo3 marks `_native::Parser` as `#[pyclass(unsendable)]`, which causes a
hard thread-assertion panic when a parser created on one thread is
accessed from another:
```
thread '<unnamed>' panicked at pyo3-0.28.3/src/impl_/pyclass.rs:1055:9:
assertion `left == right` failed: _native::Parser is unsendable, but sent to another thread
left: ThreadId(2)
right: ThreadId(1)
```
The prior implementation stored parsers in a module-level `dict[str,
Any]` (`_tree_sitter_languages`). When `_run_compression_in_executor`
dispatched compression work to a `ThreadPoolExecutor`, pool workers
grabbed parsers from that shared dict that were originally created on
the main asyncio thread and panicked.
This produces a 500 on every request where code compression is attempted
via a pool thread.
## Fix
Replace the global dict with `threading.local()` so each thread creates
and owns its own parser instances. No cross-thread parser access is
possible.
```python
# before
_tree_sitter_languages: dict[str, Any] = {} # shared — crosses threads
# after
_tree_sitter_local = threading.local() # per-thread — isolated
```
`is_tree_sitter_loaded()` and `unload_tree_sitter()` updated to operate
on the current thread's local cache (semantics unchanged for
single-threaded callers).
## Tests
9 regression tests added in
`tests/test_transforms/test_tree_sitter_thread_safety.py`:
- Thread isolation: two threads get distinct parser instances
- Within-thread reuse: same thread gets the same cached instance
- Thread pool: parsers usable from `ThreadPoolExecutor` workers without
panic
- Concurrent workers: each distinct pool thread owns a unique parser
- `is_tree_sitter_loaded` / `unload_tree_sitter` lifecycle
Also adds a `filterwarnings` entry for
`PytestUnraisableExceptionWarning`: pyo3 emits this when short-lived
test threads drop parsers at teardown; it does not occur in production
where pool threads are long-lived.
## Relation to #564
PR #564 proposes the same `threading.local()` approach but was blocked
on missing tests (`CHANGES_REQUESTED`). This PR includes the full test
suite.
|
||
|
Frank Borkin
|
19eac8e00d
|
feat: support Python 3.14+ via pyo3 abi3 stable ABI (#516)
## Description Sets pyo3 params to support python above 3.13 Fixes #(408 ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) - [ ] New feature (non-breaking change that adds functionality) - [ ] Breaking change (fix or feature that would cause existing functionality to change) - [ ] Documentation update - [ ] Performance improvement - [ ] Code refactoring (no functional changes) ## Changes Made - Updated Cargo.toml ## Testing Describe the tests you ran to verify your changes: - [ ] Unit tests pass (`pytest`) - [ ] Linting passes (`ruff check .`) - [ ] Type checking passes (`mypy headroom`) - [ ] New tests added for new functionality - [x] Manual testing performed ## Test Output ``` Compiles ``` ## Checklist - [x] My code follows the project's style guidelines - [x] I have performed a self-review of my code - [ ] I have commented my code, particularly in hard-to-understand areas - [ ] I have made corresponding changes to the documentation - [x] My changes generate no new warnings - [ ] I have added tests that prove my fix is effective or that my feature works - [x] New and existing unit tests pass locally with my changes - [ ] I have updated the CHANGELOG.md if applicable Co-authored-by: Tejas Chopra <chopratejas@gmail.com> |
||
|
Patrick A
|
9579567b7d
|
chore(deps): loosen over-pinned constraints and add upper bounds (#538)
## What Loosen over-pinned Python dependency constraints and add missing upper bounds in `pyproject.toml`. Also bump the neo4j Docker image and uv builder version. ## Why Several dependencies had constraints that either blocked security patches or allowed silent major-version jumps: - `litellm==1.82.3` was an exact pin — every security patch release requires a manual lockfile bump - `transformers`, `sentence-transformers` had no upper bound and have already crossed major version boundaries without a constraint gate - `neo4j>=5.20.0` had no upper cap; the driver has already reached 6.x in the wild - `mem0ai>=0.1.100` had a pre-1.0 floor while the locked version is already 1.0.11 - `langchain-core`, `langchain-openai`, `qdrant-client`, `uvicorn` had no upper bound on a range with active major-version churn - `docker-compose.yml` pinned neo4j at `5.15.0`, which is 11 patch releases behind the current 5.x LTS - `Dockerfile` pinned uv at `0.11.16`; latest stable is `0.11.18` ## How Constraint changes only — no code changes, no `uv lock --upgrade`. The existing locked versions all satisfy the new bounds (we added caps, not floors). `uv` re-resolved the lockfile to format revision 3 (adds `upload-time` metadata fields) and cleaned up the defunct `llmlingua` extra entries. | Dependency | Before | After | |---|---|---| | `litellm` | `==1.82.3` | `>=1.82.3,<2.0` | | `transformers` | `>=4.30.0` | `>=4.30.0,<6.0` | | `sentence-transformers` | `>=2.2.0` | `>=2.2.0,<6.0` | | `neo4j` | `>=5.20.0` | `>=5.20.0,<7.0` | | `mem0ai` | `>=0.1.100` | `>=1.0.0,<2.0` | | `langchain-core` | `>=0.2.0` | `>=0.2.0,<4.0` | | `langchain-openai` | `>=0.1.0` | `>=0.1.0,<2.0` | | `qdrant-client` | `>=1.9.0` | `>=1.9.0,<2.0` | | `uvicorn` | `>=0.23.0` | `>=0.23.0,<1.0` | | neo4j Docker image | `5.15.0` | `5.26` | | uv (Dockerfile ARG) | `0.11.16` | `0.11.18` | ## Breaking changes None. All currently installed versions fall within the new ranges. Installers that previously resolved `litellm` to an older exact pin may now resolve newer patch releases — which is the desired behavior. --------- Co-authored-by: Tejas Chopra <chopratejas@gmail.com> |
||
|
github-actions[bot]
|
01762b1ec7
|
chore: release main (#607)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Patrick A
|
fa558c5647
|
fix(deps): move gunicorn to [proxy-prod] extra, add Windows guard (#537)
* fix(deps): add missing runtime deps to [code] and [proxy] extras - Add gunicorn>=21.0.0 to the [proxy] extra The proxy docs (docs/content/docs/proxy.mdx and wiki/proxy.md) show gunicorn as the recommended production deployment server: pip install gunicorn gunicorn headroom.proxy.server:app --worker-class uvicorn.workers.UvicornWorker Users installing headroom-ai[proxy] for production get uvicorn (already declared) but had to discover and install gunicorn manually. Adding it to [proxy] removes that friction. Investigation notes: - [code] only needs tree-sitter-language-pack (already declared). code_compressor.py has zero numpy imports. The kompress fallback inside code_compressor.py is guarded by ImportError and requires [ml]. - numpy is correctly declared in [relevance] (numpy>=1.24.0) and pulled transitively by sentence-transformers in [memory]. It is NOT needed under [code]. - tree-sitter is a transitive dep of tree-sitter-language-pack (requires tree-sitter>=0.25.2) so it does not need an explicit entry. * docs(changelog): add entry for gunicorn proxy dep fix style(tests): ruff format test_provider_proxy_routes.py (blank lines after docstrings) * fix(deps): move gunicorn to [proxy-prod] extra, add Windows guard - Remove gunicorn from [proxy] so dev, CI, and Windows users are not forced to install a Unix-only package that does nothing on Windows - Add new [proxy-prod] extra that includes [proxy] + gunicorn with a sys_platform != 'win32' environment marker - Production users: pip install 'headroom-ai[proxy,proxy-prod]' - Update CHANGELOG to reflect the new extra name * fix(devcontainer): bump uv floor to >=0.11.0 for lockfile compatibility uv 0.6.17 (previously pinned) cannot parse lockfiles generated by uv >= 0.11.x. The validate CI job (triggered by pyproject.toml changes) was failing with 'Failed to parse uv.lock'. Loosening the pin to >=0.11.0 picks up the matching format parser while keeping the Docker layer cacheable with a range rather than an exact pin. * fix(devcontainer): skip gitpython wheel filename check in uv sync gitpython 3.1.47 on PyPI has wheel gitpython-3.1.46-py3-none-any.whl (wrong filename). uv >=0.11.19 strict filename validation rejects this lockfile entry. UV_SKIP_WHEEL_FILENAME_CHECK=1 bypasses the check until the upstream lockfile is regenerated with a corrected entry. * fix(deps): correct gitpython version in uv.lock to match actual wheel gitpython 3.1.47 on PyPI was uploaded with sdist/wheel files named gitpython-3.1.46.*. The version field in uv.lock said 3.1.47 but all download URLs reference 3.1.46 files, causing uv >=0.11.19 to refuse to parse the lockfile with a version-mismatch error. Change the version field to 3.1.46 so the entry is internally consistent. Also revert the now-unnecessary UV_SKIP_WHEEL_FILENAME_CHECK workaround from post-create.sh. --------- Co-authored-by: Tejas Chopra <chopratejas@gmail.com> |
||
|
github-actions[bot]
|
f7c2552264
|
chore: release main | ||
|
github-actions[bot]
|
cc71e07d01
|
chore: release main | ||
|
chopratejas
|
8e4ab187e9 |
ci(release): align manifest + pyproject + package.json to 0.22.3
The repo had drifted: pyproject.toml said 0.9.1 but PyPI's latest
published headroom-ai was 0.22.3. release_version.py papered over
this by taking max(canonical, latest_tag) at release time;
release-please does NOT do that — it trusts the manifest verbatim.
Left as-is, release-please would propose 0.9.2 on the next merge
and PyPI would reject it ("400 Cannot publish version lower than
latest"), looping the bot forever.
Fix: align every version-bearing file to 0.22.3 (the truth on
PyPI). Done via `scripts/version-sync.py --version 0.22.3`:
- .release-please-manifest.json
- pyproject.toml
- sdk/typescript/package.json
- plugins/openclaw/package.json (+ headroom-ai dep range -> ^0.22.3)
- .claude-plugin/marketplace.json
- .github/plugin/marketplace.json
- plugins/headroom-agent-hooks/.claude-plugin/plugin.json
- plugins/headroom-agent-hooks/.github/plugin/plugin.json
After this lands, the bot's next release PR will propose 0.22.4
(patch) or 0.23.0 (minor) depending on conventional-commit traffic
since v0.22.3.
|
||
|
chopratejas
|
20dc1f28f3 |
fix(proxy): Strands MCP bundle + backend path fixes + Codex fail-closed protection
Three logically-related sets of proxy changes ship in this branch:
1. Strands integration on the Bedrock path (HeadroomBundle + 4 OpenAI
handler fixes + LiteLLM cache stats + dep pin)
2. /stats MCP aggregation (cross-process events log → proxy summary)
3. Codex compression-failure fail-closed (WS + HTTP /v1/responses)
== 1. Strands integration on the Bedrock path ==
* HeadroomBundle (headroom/integrations/strands/bundle.py): single-helper
MCP wiring for a Strands Agent — Headroom MCP server (headroom_compress
/ headroom_retrieve / headroom_stats) plus optional Serena MCP and
optional in-process compression hook. Constructor builds unstarted
MCPClient instances per server; Strands' Agent owns the subprocess
lifecycle. Default config: MCP enabled, Serena enabled, hook OFF
(proxy is the single source of truth for compression). User-side
integration is two lines in any Strands app.
* headroom/proxy/handlers/openai.py — backend path now:
- calls PrefixCacheTracker.update_from_response (was direct-OpenAI only)
- intercepts CCR headroom_retrieve tool_calls server-side, mirroring
the Anthropic handler pattern; NO silent fallback, re-raises on
CCR errors (per feedback_no_silent_fallbacks)
- works for both non-streaming and streaming paths
* headroom/proxy/handlers/streaming.py: _stream_openai_via_backend now
accepts prefix_tracker + optimized_messages, parses cache stats from
the SSE final-usage frame (cache_creation_input_tokens added to the
state machine), records CCR retrieve feedback via a new
_record_ccr_feedback_from_openai_sse helper. Streaming CCR intercept
is intentionally out of scope (mirrors Anthropic streaming behaviour).
* headroom/backends/litellm.py: send_openai_message response usage block
now carries cache_read_input_tokens / cache_creation_input_tokens
(Anthropic/Bedrock dialect) and prompt_tokens_details.cached_tokens
(OpenAI dialect). Backwards-compatible — cold-start callers see the
same 3-key shape; cache keys appear only when the underlying provider
returns them. Pinned by test_no_cache_fields_means_no_cache_keys.
* headroom/proxy/auth_mode.py: ("strands-agents/", "strands") added to
CLIENT_UA_MAP. Production callers should also set X-Client: strands
since the default openai-python UA carries no Strands signal.
* pyproject.toml: huggingface-hub>=1.5.0,<2.0 pinned in [ml] so a sibling
install (e.g. strands-agents) can't drag the version below the floor
transformers 5.x requires (otherwise Kompress silently goes
"unavailable").
== 2. /stats MCP aggregation ==
* headroom/proxy/cost.py: _aggregate_mcp_events() reads the cross-process
shared events file the Headroom MCP server already writes to and
surfaces summary.mcp with three new keys:
- compressions (count of headroom_compress invocations)
- tokens_removed (sum of input - output across those)
- retrievals (count of headroom_retrieve — the load-bearing
over-compression alarm; if it grows linearly
with turn count, lossy compressors are
dropping info the model actually needs)
Defensive on every axis — missing MCP SDK, missing file, malformed
events, read errors — never blocks /stats.
* examples/strands_bundle_demo.py: stats panel prints the new fields so
the demo shows the full proxy-HTTP + MCP-tool story in one view.
== 3. Codex compression-failure fail-closed protection ==
Reported by Camille (2026-05-21): Codex threads were locking with
"ran out of room in the model's context window" after Headroom's
compression timed out on an oversized response.create frame and
forwarded the original ~1.7 MB frame to the upstream, which then
rejected it. Codex's auto-compact heuristic gates on the upstream-
reported total_usage_tokens (which Headroom had been shrinking on
earlier turns), so its compaction never fired and the thread locked.
Validated against open Codex issues (CLI + Desktop share codex-rs/core):
* #16068 — confirms compaction gates on total_usage_tokens,
estimated_token_count is computed but only logged
* #19806 — confirms image token estimator unbounded, contributes to
the same ContextManager.get_total_token_usage → auto-compaction chain
* headroom/proxy/helpers.py: decide_compression_failure_action() with a
unit-tested decision matrix:
- asyncio.TimeoutError → refuse, always
- non-timeout failure + frame > 256 KiB (configurable) → refuse
- non-timeout failure + small frame → forward (legacy)
Operator escape hatches:
- HEADROOM_WS_FAIL_OPEN_ON_COMPRESSION_FAILURE=1 restores legacy
- HEADROOM_WS_COMPRESSION_FAIL_THRESHOLD_BYTES tunes the threshold
* headroom/proxy/handlers/openai.py (WS /v1/responses): consults the
helper after compression failure. On refuse: close client websocket
code 1009 with "headroom: compression <reason> — please compact
context and retry" reason; set termination_cause for the outer
lifecycle finally; return.
* headroom/proxy/handlers/openai.py (HTTP /v1/responses): same helper.
On refuse: raise HTTPException(413) with a structured error body so
FastAPI's HTTPException handler emits a clean 413. The existing
`except HTTPException: raise` guard in this handler already ensures
the 413 propagates without being swallowed by the 502 catch-all.
Anthropic /v1/messages NOT changed in this branch: no equivalent bug
report on Anthropic-protocol clients, Claude Code (Anthropic-owned)
handles context overflow via its own cache_control/ephemeral
primitives, and Cursor/Aider don't maintain the local-Y estimate the
Codex bug requires. Deferred until a real report lands; the patch is
a one-liner reusing the same helper.
== Tests + verification ==
* tests/test_backends/test_litellm_cache_stats.py — 3 tests pinning
cache-stat surfacing across Anthropic/OpenAI dialects + backwards-
compat for no-cache responses.
* tests/test_proxy/test_openai_backend_path.py — 5 tests (Bedrock cache
fields, OpenAI fallback shape, CCR intercept with provider="openai",
CCR re-raise on exception, streaming signature contract).
* tests/test_proxy/test_mcp_stats_aggregation.py — 5 tests pinning the
aggregator across compress+retrieve mixes, empty events, unknown event
types, missing token fields, and read failures.
* tests/test_proxy/test_compression_failure_action.py — 12 tests pinning
the fail-closed decision matrix (timeout always refuses, small
transient passes through, oversize refuses, env override variants,
custom threshold, invalid threshold falls back, 0/negative ignored).
* examples/strands_bedrock_demo.py — model_id bumped from deprecated
Claude 3 Haiku to Sonnet 4.5 (the deprecated model now errors on
account access).
* examples/strands_via_proxy_demo.py — proxy + Bedrock cache + streaming
smoke test.
* examples/strands_mcp_dispatch_test.py — pure MCP round-trip probe.
* examples/strands_bundle_demo.py — full Strands + HeadroomBundle E2E
demo (this is the shape a real Strands user copies into their app).
Full pytest: 5327 passed, 178 skipped. The previously-failing
test_core_operations.py::TestAddBatch::test_add_batch_basic passes now
that the huggingface-hub pin in pyproject.toml unblocks transformers
imports.
E2E verified live against AWS Bedrock (Sonnet 4.5):
* cache_write=10,438 on turn A → cache_read=10,438 on turn B
* streaming SSE final usage frame carries cache_read_input_tokens
* 78.7% reduction on a 50 KB JSON tool_result via SmartCrusher (
dispatched per-content-type by ContentRouter)
* Strands Agent + HeadroomBundle: model autonomously called
headroom_compress + headroom_retrieve via MCP; CompressionStore
round-trip succeeded; final answer correct.
|
||
|
chopratejas
|
c1d2eec588 |
docs: improve discoverability for AI agents and search crawlers
Several signals AI agents and search engines use to discover and install a project were misaligned or missing: * ``docs/app/layout.tsx`` set ``metadataBase`` to ``https://chopratejas.github.io/headroom/`` while the live docs run on Vercel — every page's ``og:url`` and ``twitter:url`` resolved to a URL that returns 404 for ``/llms.txt``. Now points at the live Vercel host (overridable via ``NEXT_PUBLIC_SITE_URL`` for a future custom domain). Adds explicit ``openGraph`` and ``twitter`` metadata so social shares render a card with the project's pitch. * No ``llms.txt`` at the GitHub repo root. AI agents crawling ``github.com/chopratejas/headroom/`` saw only the README. The new ``llms.txt`` follows the llmstxt.org convention: 1-line pitch, canonical docs links, copy-paste install commands (pip / npm / Docker / proxy / ``headroom wrap``), and entry points for the library, proxy, MCP server, and SDK integrations. Points at the Fumadocs-generated ``/llms.txt`` and ``/llms-full.txt`` for the full picture. * ``pyproject.toml`` ``Documentation`` URL pointed at the GitHub README anchor. Updated to point at the docs site so PyPI visitors land on searchable docs, and adds an ``AI / LLM Index`` URL pointing at the Fumadocs ``/llms.txt``. * No explicit AI-bot allow list. Added ``docs/app/robots.ts`` (Next 13+ App Router convention) with explicit allows for GPTBot, ClaudeBot, PerplexityBot, Google-Extended, OAI-SearchBot, ChatGPT-User, Cohere-AI, CCBot, and Applebot-Extended. Wildcard allow as the catch-all. Advertises the sitemap. * No ``sitemap.xml`` route. Added ``docs/app/sitemap.ts`` that pulls every Fumadocs page out of ``source`` (same source backing ``/llms.txt``, search, and OG images) so search and AI crawlers can enumerate doc pages without scraping HTML. * README didn't tell AI agents where to look. Added a 2-line pointer near the top nav row: read ``/llms.txt`` here, or fetch the live index / full docs blob. Also tightened the GitHub repo description and added five topics (``claude-code``, ``cursor``, ``tokens``, ``prompt-engineering``, ``typescript``) via ``gh repo edit`` — that's already live on the repo, not part of this commit. No Python or Rust code changes; ``make ci-precheck`` was run to confirm the test slice still passes. |
||
|
JerrettDavis
|
2fd48260f6 | ci: skip live evals without credentials | ||
|
Tejas Chopra
|
9ff28e9803
|
Merge pull request #422 from chopratejas/fix-user-experience-and-feature-clarity
fix(cli): proxy/perf/wrap UX cleanup + perf --hours correctness |
||
|
chopratejas
|
265554d4ad |
fix(cli): proxy/perf/wrap UX cleanup + perf --hours correctness
Address user-reported UX gaps across the CLI surface: - code-aware: add --code-aware/--no-code-aware (+ HEADROOM_CODE_AWARE_ENABLED env) to the Click CLI. PR #411 had added these only to the orphaned argparse main; the user-facing CLI couldn't reach the flag. Banner status text "remove --no-code-aware to enable" referenced a flag that didn't exist — fix to point at the actual flag/env. Surface code-aware in the click banner and add print_banner=False plumbing to run_server so the click path doesn't print two banners back-to-back. - --mode: hide alias clutter via metavar=[token|cache] and rewrite help to lead with the two real modes. Legacy aliases (token_mode/token_savings/...) still validate. - perf --hours: was documented but ignored. Records are now actually filtered, the report shows the actual time-range covered, and the count of records filtered out (so users can tell when raising --hours helps). - perf TOIN: replace the hash-keyed pattern dump with a strategy-distribution view + recommendation-eligibility from the live store — actionable signal rather than opaque rows. - code-graph: clarify in --help that it indexes cwd / project root. - wrap: spell out supported tools, wrap-vs-proxy distinction, and that `headroom wrap opencode` isn't a thing (use `proxy` directly for opencode; openclaw is not opencode). - mcp: note that mcp__headroom__headroom_retrieve is correct MCP namespacing, not a doubled-prefix bug. Renaming would break the proxy's tool injection. - LLMLingua cleanup: remove [llmlingua] extra from pyproject (no live code uses it). Delete wiki/llmlingua.md and clean retired flag/class references in 6 other wiki pages. Point at [ml] (Kompress) where ML compression is documented. - init -g openclaw: strip mcpServers from existing plugin entries before re-writing — newer openclaw schemas reject it, leaving stale entries from older installs unhealable. Pinned with regression test. Tests: mock_run_server signatures in two existing tests accept **kwargs (needed for the new print_banner plumbing). New test for the openclaw mcpServers strip. Full suite: 4847 passed, 262 skipped, 0 failed. |
||
|
chopratejas
|
183d51c8a8 |
fix(ci): include NOTICE in sdist + assert License-File metadata matches tarball
Every release since v0.20.16 has uploaded 12 wheels but no sdist. The
underlying failure is a 400 from PyPI:
400 License-File NOTICE does not exist in distribution file
headroom_ai-X.Y.Z.tar.gz at headroom_ai-X.Y.Z/NOTICE
Two-part regression:
1. The hatch -> maturin migration in
|
||
|
Daniel Munoz
|
9492386398 | fix: harden release gating and clarify pipx compatibility | ||
|
chopratejas
|
b154e17853 |
fix: PR #372 — restore [image] extra on Python 3.13 via rapidocr 3.x adapter
Root cause: `headroom-ai[all]==0.20.16` fails to install on Python 3.13
because `rapidocr-onnxruntime` 1.4.0–1.4.4 wheels declare
`requires-python: <3.13,>=3.6`. After 1.4.x the rapidocr ecosystem
split: `rapidocr-onnxruntime` (bundled-ORT, capped at <3.13) vs
`rapidocr` 3.x (engine-agnostic core, supports 3.13+, returns
RapidOCROutput dataclass instead of v1's tuple).
Fix:
1. pyproject.toml — environment-marker hybrid in [image]:
- rapidocr-onnxruntime>=1.4.0,<2; python_version<'3.13'
- rapidocr>=3.0,<4; python_version>='3.13'
- onnxruntime>=1.7,<2; python_version>='3.13'
ORT remains the engine on every Python version; bundle and speed
unchanged, just split into two packages on 3.13+.
2. headroom/image/compressor.py — runtime adapter:
_resolve_rapidocr() tries v1 first, falls back to v3 when v1 is
missing, returns (None, None) when neither installed. Cached at
module scope. Detection at runtime (not Python-version-based) so
users can install either package on any Python version.
_ocr_extract branches on resolved api_version:
- v1: (list[(box, text, score)], elapsed) tuple — unchanged
- v3: RapidOCROutput dataclass with .txts / .scores / .boxes
attrs (each may be None when nothing detected)
Defensive None-handling, length-mismatch detection, structured
log events for both branches.
Smoke test (real install verified before commit):
pip install rapidocr onnxruntime pillow
→ result type: RapidOCROutput
→ fields: txts (None when empty), scores (None when empty), boxes
Confirms the v3 None-coercion is necessary.
Tests: 11 new unit tests in tests/test_image_ocr_api_compat.py covering:
- Resolver: v1 preferred, v3 fallback, both missing
- v1 path: tuple parses, low-confidence None, empty result None
- v3 path: dataclass parses, low-confidence None, None attrs handled,
mismatched lengths logged + None
- Backend missing: returns None gracefully
All 11 pass; `make ci-precheck` PASSED.
Closes #372.
|
||
|
chopratejas
|
e325d1b866 |
fix(ci): pin public PyPI in pyproject.toml + scrub Netflix URLs from uv.lock
Devcontainer validate jobs were failing on PR #360 with: × Failed to fetch: https://pypi.netflix.net/packages/.../nvidia_nvshmem_cu12-3.4.5-...whl ├─▶ Request failed after 3 retries ╰─▶ operation timed out `pypi.netflix.net` is Netflix's internal PyPI mirror. It got into the lockfile because my local `~/.config/uv/uv.toml` had: index-url = "https://pypi.netflix.net/simple" Running `uv lock` from that machine baked Netflix-internal URLs into uv.lock for every package. Public CI runners (and any external contributor) can't resolve them. Two fixes: 1. Add `[[tool.uv.index]]` block to pyproject.toml pinning public PyPI as the project's default index. uv now ignores user-level config when resolving for this project, regardless of who runs `uv lock`. This prevents the same contamination from any developer in the future. 2. Regenerate uv.lock against public PyPI. All package URLs now point at `https://files.pythonhosted.org/...` and `https://pypi.org/simple/`. Zero references to `pypi.netflix.net` remain in the lockfile. Verified: `grep -c "pypi.netflix" uv.lock` returns 0. |
||
|
chopratejas
|
2a91cbb4b4 |
refactor: single-wheel maturin build backend (fixes #355)
Eliminates the dual-package architecture that was the root cause of #355. `pip install headroom-ai` now produces ONE wheel containing both the Python source (headroom/*.py) and the compiled Rust extension (headroom/_core.so). No more separate `headroom-core-py` package, no more chicken-and-egg with PyPI publication, no more wheelhouse / PIP_FIND_LINKS / composite-action plumbing in CI. This is the canonical pattern used by cryptography, polars, ruff, pydantic-core, and other Rust-as-core Python packages. Honors the "Rust as core engine" direction. ## What changed - pyproject.toml: `[build-system]` swapped from hatchling to maturin. `[tool.hatch.*]` deleted; `[tool.maturin]` added pointing at `crates/headroom-py/Cargo.toml` for the cdylib. `python-source = "."` picks up the root `headroom/` package directly (dashboard HTML templates and other non-Python files included automatically). - crates/headroom-py/pyproject.toml: deleted. The crate is no longer a separate published package; its Cargo.toml stays as the cdylib build target invoked via `[tool.maturin] manifest-path`. - crates/headroom-py/python/: deleted (placeholder layout for the old separate package). ## CI updates - ci.yml: `test` / `test-extras` / `test-agno` jobs simplified — Rust toolchain set up before `pip install -e .` (which now invokes maturin via build-system). Removed the "build wheel + symlink .so" dance. `build` job swapped from `python -m build` (hatch) to `maturin build` + `maturin sdist`. - release.yml: collapsed dual-package matrix into one. New `build-wheels` matrix produces cross-platform wheels for cp310/11/12/13 × {linux x86_64, linux aarch64, macos x86_64, macos aarch64}. New `collect-dist` aggregator merges artifacts. publish-pypi consumes the merged dist. - init-native-e2e.yml: dropped windows-latest from the matrix — upstream `esaxx-rs` (/MT) and `ort-sys` (/MD) link with conflicting MSVC C runtime libraries, so the Rust extension cannot build for win_amd64 today. Tracked as a follow-up; not a blocker for Linux+macOS. - headroom-e2e-setup: composite action now sets up Rust toolchain + Swatinem/rust-cache before `pip install -e .[proxy]`. - eval.yml, publish.yml, rust.yml: same pattern — rust toolchain before install. rust.yml's wheels job builds from root pyproject.toml (no more `-m crates/headroom-py/Cargo.toml`). - e2e/init/Dockerfile, e2e/wrap/Dockerfile: install rust + maturin in the build stage; copy `crates/` + workspace `Cargo.toml/lock` so the install can build the extension. Dropped `HEADROOM_REQUIRE_RUST_CORE=false` from wrap-e2e — the image now ships the full Rust core. - Dockerfile (main): simplified — no more Layer 2/3 dance with `headroom-core-py` install + symlink. Single `uv pip install` builds + installs everything. - .devcontainer/Dockerfile: rust toolchain + libssl-dev + maturin added so `uv sync` builds the extension inside the devcontainer. ## Lockfile + script - uv.lock: regenerated. No `headroom-core-py` entries remain. - scripts/build_rust_extension.sh: simplified from a symlink-into-tree workaround to a thin wrapper around `pip install -e .`. The maturin build-backend handles placement automatically. ## Local validation (all green on macOS aarch64) 1. Clean venv `pip install -e .` → `from headroom._core import …` works. 2. `maturin build --release` → 13.8 MB wheel, 336 files including `headroom/_core.cpython-311-darwin.so` (32 MB cdylib) and `headroom/dashboard/templates/dashboard.html`. 3. `pip install <wheel>` in fresh venv → import works. 4. Wheel contents verified via `unzip -l`. 5. `pytest tests/test_transforms/test_diff_compressor.py` — 29 passed. 6. `pytest tests/test_relevance.py` — 30 passed. 7. `cargo build --workspace` + `cargo test --workspace` — all green. 8. `make ci-precheck` — 176 Python tests + Rust + commitlint green. ## Migration notes Users on `pip install headroom-ai` get the Rust core automatically (linux + macos wheels). sdist installs require rust toolchain available locally — pip will build via maturin. Closes #355 Supersedes #357 (workarounds-based fix abandoned in favor of architectural fix) |
||
|
chopratejas
|
dcbc921d63 |
fix: Wave 3 — multi-turn live integration tests for A+B realignment
Adds tests/test_realignment_live_multi_turn.py with 9 OPT-IN live tests
that validate the load-bearing claims of the Phase A+B megamerge against
real upstream APIs (Anthropic, OpenAI, Gemini). Each test maps to one or
more realignment PRs:
1. test_anthropic_cache_hit_across_two_turns — A2/A6/E
Identical cache_control'd system+messages on two turns must
eventually produce cache_read_input_tokens > 0. Guards the cache
hot zone invariant (I2): proxy must not mutate frozen prefix bytes.
Uses a bounded retry loop (max 4 attempts) to absorb Anthropic's
eventually-consistent prompt-cache write latency without masking
a real "proxy broke cache stability" regression.
2. test_anthropic_cache_stable_when_live_zone_compresses — B2/B3
Turn 2 mutates only the LATEST user content (8KB+ JSON tail);
cache_read on turn 2 must still be > 0 AND the proxy must emit
compression headers — proving the live-zone block dispatcher
ran on the new tail without disturbing the cached prefix.
3. test_anthropic_cache_control_passthrough_byte_faithful — A3/A4
Wraps proxy._retry_request to snapshot the upstream-bound body
and assert cache_control on system blocks survives verbatim,
and user content is not flattened from list to string form.
4. test_openai_chat_completions_multi_turn_through_proxy — A8/B
Three-turn conversation through /v1/chat/completions; each
turn returns valid content, prior assistant turns survive in
the messages list (proxy doesn't drop them).
5. test_openai_streaming_sse_chunks_arrive_in_order — A8 (SSE wire)
Streams /v1/chat/completions; asserts each event is
'data: ...\\n\\n', terminator is 'data: [DONE]\\n\\n',
reassembled content non-empty, no malformed events.
6. test_gemini_multi_turn_through_proxy — Gemini reach
Two-turn conversation through native
/v1beta/models/{model}:generateContent. Proves Gemini handler
wiring stayed intact through the megamerge.
7. test_ccr_marker_round_trip_live — B7 (CCR)
Pre-populates compression_store with a fixture entry, embeds
a CCR marker on a tool_result, verifies (a) headroom_retrieve
tool is injected into the upstream tools array (PR-B7
always-on), and (b) /v1/retrieve returns the original bytes
by hash with all rows intact. Pre-populating the Python store
(vs. driving SmartCrusher's internal Rust store) matches the
established pattern in tests/test_proxy_ccr.py and exercises
the surface served by /v1/retrieve.
8. test_memory_tail_injection_does_not_modify_system_prompt_live — B6/A2
Spins up a memory-enabled proxy with MemoryMode.AUTO_TAIL,
seeds LocalBackend, captures upstream-bound body. Asserts:
(a) system prompt byte-identical to input; (b) memory text
lands on latest user message tail; (c) earlier messages
untouched. Guards the live-zone-only injection contract.
9. test_classify_auth_mode_routes_payg_vs_oauth — Phase F-prep / B5
NOT a live API call. Sends three header shapes through the
proxy (x-api-key=..., Bearer sk-ant-oat01-..., Bearer
sk-ant-api03-...), captures dispatcher headers via a wrap on
_retry_request, and asserts the canonical auth-mode classifier
maps each correctly. Codifies the Phase F contract.
Conventions:
* file-level pytestmark = pytest.mark.live → excluded by default
via 'pytest -m "not live"'. Adds a 'live' marker registration in
pyproject.toml's [tool.pytest.ini_options].markers.
* each test skipif's on the relevant API key — no silent fallbacks,
no real-API runs against fake keys.
* uses tests/_dotenv.py helpers (load_env_overrides + autouse_apply_env)
rather than re-implementing env loading.
* model IDs and thresholds live in a top-of-file LIVE_CONFIG dict
(no hardcodes); Anthropic primary/fallback resolves at runtime per
key entitlement.
* assertions are direction-only (cache_read > 0, tokens_after <=
tokens_before) — never tied to upstream pricing/tokenizer drift.
* shared module-scoped TestClient fixture for performance; CCR and
memory tests build dedicated proxies for their config-specific paths.
Verification:
* pytest tests/test_realignment_live_multi_turn.py -v
→ 9 passed, 0 skipped, 0 failed in ~25s (with all keys set)
* pytest -m "not live" --tb=short -q
→ 4694 passed, 265 skipped, 9 deselected — same baseline as today
* make ci-precheck → green (rust + python + commitlint)
Per-realignment-plan: REALIGNMENT/04-phase-B-live-zone.md.
|
||
|
chopratejas
|
fb9be139a5 |
feat(python): switch relevance scorer to fastembed (BAAI/bge-small-en-v1.5)
Replace `sentence-transformers` (PyTorch-backed) with `fastembed` (ONNX-
backed) so Python and Rust call into the same library + same model for
relevance scoring. Both sides run BAAI/bge-small-en-v1.5 (33M params,
384 dims, ~30 MB int8-quantized ONNX) auto-downloaded from HF Hub.
Cross-language verification on ('authentication failed for user',
'login error'): Python=0.7505, Rust=0.7507, delta ~0.0002 — well below
the relevance_threshold (0.3) buffer SmartCrusher uses for keep/drop
decisions, so the two implementations agree on every observable
SmartCrusher output. (True byte-equal would require both to load the
identical ONNX weights file — Rust's `fastembed` crate and Python's
`fastembed` package can pick different upstream artifacts; deferred.)
Why fastembed:
- removes torch from the relevance/ path (Phase 6: drop torch from
Python).
- ~2-3x faster than sentence-transformers' all-MiniLM-L6-v2 for the
same input shape.
- bge-small-en-v1.5 outranks all-MiniLM-L6-v2 on MTEB by ~6 points.
- self-contained: no longer reads ML_MODEL_DEFAULTS.sentence_transformer
from utils config.
|
||
|
chopratejas
|
7ed2b0ba34 | Sync plugins to 0.9.2, pyproject canonical at 0.9.1 [skip ci] | ||
|
JerrettDavis
|
56f6307665 |
fix: support py310 version sync scripts
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
chopratejas
|
7cd67ef06d |
fix: bundle ast-grep/difftastic/scc + generic tool_result interceptor framework
What this does, in plain terms: Headroom's proxy now ships with three CLI tools (ast-grep, difftastic, scc) that it can use to shrink tool_result payloads before they reach the model. The goal is simple: when Claude Code (or Codex, Aider, etc.) asks the model to reason about a big file or diff, we swap the verbose output for a compact, same-meaning version. Fewer tokens per turn, same answers, lower bill. Today a single interceptor is wired: ast-grep on Read. When an agent reads a large code file, the proxy replaces the file body with an outline of its top-level functions/classes plus docstrings. In live tests that cut prompt tokens 74–76% on both OpenAI and Anthropic, same answer either way. How it works: - `pip install headroom-ai` now installs ast-grep via a PyPI wheel (core dep). difftastic and scc are fetched once at proxy startup from pinned upstream GitHub releases and cached per-user. - A generic registry (`headroom/proxy/interceptors/`) lets us add more tool-aware rewrites in one file each: declare `matches()` and `transform()`, call `register()`, done. No proxy or metrics plumbing per tool. - Safety rails built in: pass-through when a Read specifies a line range; second Read of the same file in a conversation returns full content (progressive disclosure); any failing interceptor logs and skips, never crashes a request. Opt-in for now: - Off by default while this ships. Turn on with `headroom proxy --intercept-tool-results` or `HEADROOM_INTERCEPT_ENABLED=1`, so we can measure before flipping defaults. What users see after turning it on: - First `headroom wrap claude` boot is ~5s longer (binaries fetched). Every subsequent run is cache-only. - Existing `transforms_applied` field in metrics gets entries like `interceptor:ast-grep`, so savings show up in current dashboards and HTML reports with no UI change. Other housekeeping in this PR: - uv.lock moved to .gitignore — regenerated locally per environment. - 35 unit + integration tests, ruff + mypy clean. - Dead-code audit done: removed `binaries.run()`, `needs_filesystem` plumbing, unused `_kind` tuple elements, unused `tool_output` parameter, and the never-set HEADROOM_SKIP_TOOLS_BOOTSTRAP env. |
||
|
Adryan Eka Vandra
|
b71b659e1b
|
fix(ci): restore repro harness test in dev installs
Add websockets to the dev extra so the repro harness smoke test can import its websocket client dependency in the CI test matrix. Also apply ruff formatting to the files the formatter check was rejecting so the 3.12 lint job passes. |
||
|
chopratejas
|
3373dabce0 |
chore(proxy): add third-party extension point
Adds `headroom/proxy/extensions.py` — a generic entry-point hook under
the `headroom.proxy_extension` group. External packages register an
`install(app, config)` callable that runs once at proxy startup and is
free to add ASGI middleware, routes, mutate config, or raise to
fail-closed (e.g., license check failure aborts startup).
Why: Headroom OSS keeps a deliberately minimal surface, but several
high-value capabilities — PII redaction + tool-call vaulting, data-
residency routing, multi-tenant RBAC, compliance audit, vision/voice
privacy — only make sense as separately-distributed packages. A small,
stable plugin contract lets those live outside this repo without
requiring the OSS to know about them.
Contract:
[project.entry-points."headroom.proxy_extension"]
my_extension = "my_pkg.extension:install"
def install(app: FastAPI, config: ProxyConfig) -> None: ...
An extension that raises from install() is a deliberate fail-closed
signal and aborts startup. Entry-point load failures are logged and
skipped so one broken third-party package cannot take the proxy down.
Changes:
* New: headroom/proxy/extensions.py (~55 LOC)
* headroom/proxy/server.py: invoke install_all(app, config) in
create_app() immediately after CORS middleware registration
* pyproject.toml: register slow and real_llm pytest markers
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
chopratejas
|
e306d6b338 |
Bump version to 0.5.25 for PyPI release
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
chopratejas
|
b3a73641a0 | Bump to 0.5.24 | ||
|
chopratejas
|
af3cd7f07f |
Fix #149: memory crash in Docker — missing vector index + pthread error
Three fixes for Docker-native install with --memory: 1. Add sqlite-vec to proxy extras — memory's vector index now installs with pip install headroom-ai[proxy]. No separate pip install needed. 2. Fix AUTO vector backend fallback — was: SQLITE_VEC → HNSW → crash. Now: SQLITE_VEC → HNSW → clear error message listing install options. 3. Fix ONNX pthread_setaffinity_np error in Docker containers — set intra/inter thread count to 1 in SessionOptions. Prevents the "Invalid argument" error on containers with limited CPU affinity. |
||
|
chopratejas
|
ccc763a7b0 | Bump version to 0.5.23 | ||
|
chopratejas
|
00a6ab2dee | Bump version to 0.5.22 | ||
|
chopratejas
|
3c0c540e1b |
Auto-download codebase-memory-mcp binary, add watchdog to proxy deps
No manual install needed. headroom wrap claude --code-graph: 1. Checks if binary exists (PATH or ~/.local/bin/) 2. Downloads from GitHub releases if not found (~15MB, one-time) 3. Indexes project + starts file watcher Same pattern as rtk auto-download. Platform-aware: darwin-arm64, darwin-amd64, linux-arm64, linux-amd64, windows-amd64. Also: add watchdog>=4.0.0 to proxy extras. |
||
|
chopratejas
|
1fee4ac8fd | Revert version to 0.5.21, fix changelog header to 0.5.22 | ||
|
chopratejas
|
0f7f7b0f69 | Release v0.6.0: cross-agent memory, plugin learn, code graph | ||
|
JerrettDavis
|
a1beb08d53 |
feat: add reproducible devcontainers
Add a default devcontainer and a compose-backed memory-stack profile, validate them in CI, and document the contributor workflow. Also lock the memory-stack dependencies, pin related container tooling, and sync the latest healthcheck shutdown fix for stubbed memory handlers. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
JerrettDavis
|
ebd482c0a0 |
feat: add OTEL observability core
Add a shared observability layer for OTEL metrics and Langfuse tracing. Instrument the shared compression pipeline once so SDK and proxy paths can reuse the same metrics and spans without scattering telemetry concerns. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
chopratejas
|
65e4a35546 |
Add OCR routing via RapidOCR + measure actual tokens after compression
Transcode technique now runs RapidOCR to extract text from images. Falls back to full_low if OCR confidence < 70% or no text detected. Token counting is now done AFTER compression by measuring the actual output — no hardcoded estimates. OCR text counted by char length, resized images re-estimated from new dimensions. RapidOCR added to headroom-ai[image] extra (~15MB ONNX models, ~180ms CPU). 4 new OCR tests (extraction, blank image, confidence threshold, full pipeline). 29 total image compression tests passing. |
||
|
chopratejas
|
c52b0f1e57 |
Add sentencepiece to image extra — required by SigLIP tokenizer (#103)
SiglipTokenizer from transformers hard-requires sentencepiece at runtime. Without it, the image router silently falls back to PRESERVE (no compression). Users on pip install headroom-ai[image] or [all] were missing this dependency. |
||
|
chopratejas
|
9c51f63c48 | Bump to v0.5.21 |