mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
120 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
AxelRay
|
ef7e07e0f5
|
fix(policy): price net-cost mutations with the 1h cache-write tier (#2780)
## Description This fixes the net-cost mutation gate for requests using Anthropic's 1-hour prompt-cache TTL. The gate previously hardcoded the 5-minute cache-write multiplier of 1.25x. A 1-hour cache write costs 2.0x, so the old calculation understated the true write penalty and could incorrectly recommend mutation for 1-hour clients. Closes #2773 ## 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 - Added TTL-aware cache-write multiplier selection for 5-minute and 1-hour tiers. - Threaded the resolved TTL through the content router and compression policy helpers. - Preserved the existing 5-minute behavior as the default. - Added Python and Rust regression coverage for the 1-hour tier. - Retuned the netcost gate fixtures so the 1-hour write tier flips the decision in the full ContentRouter path. - Did not edit CHANGELOG.md. ## Testing - [x] Unit tests pass (pytest) - [x] Linting passes (ruff check .) - [ ] Type checking passes (mypy headroom) - [x] New tests added for new functionality - [ ] Manual testing performed ### Test Output ```text pytest tests/test_compression_policy.py -q 20 passed cargo test -p headroom-core --lib compression_policy -- --nocapture 14 passed pytest tests/test_netcost_gate.py -q 27 passed Ruff checks and formatting passed. git diff --check passed. ``` ## Real Behavior Proof - Environment: Linux x86_64 contributor checkout with Python and Rust test environments. - Exact command / steps: - Ran the Python compression policy test suite. - Ran the Rust compression policy unit tests. - Ran the netcost gate suite, including the 1-hour env and request-marker cases. - Exercised the new 1-hour TTL golden case alongside the existing 5-minute cases. - Observed result: The 1-hour case uses the 2.0x write multiplier and skips the same candidate that still mutates under 5-minute pricing. Existing 5-minute behavior remains covered and passing. - Not tested: A live Anthropic request through the proxy and production traffic. ## 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 - [ ] I have commented my code, particularly in hard-to-understand areas - [ ] I have made corresponding changes to the documentation - [ ] 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 did **not** edit CHANGELOG.md - it is generated by release-please from my Conventional Commit PR title (a CI guard enforces this) ## Screenshots (if applicable) Not applicable for this backend policy fix. ## Additional Notes Ready for review. CI is green on the current tip. |
||
|
dependabot[bot]
|
322425c43b
|
deps: bump sha2 from 0.10.9 to 0.11.0 (#2288)
Bumps [sha2](https://github.com/RustCrypto/hashes) from 0.10.9 to 0.11.0. <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
dependabot[bot]
|
b30f339d69
|
deps: bump criterion from 0.5.1 to 0.8.2 (#2965)
Bumps [criterion](https://github.com/criterion-rs/criterion.rs) from 0.5.1 to 0.8.2. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/criterion-rs/criterion.rs/releases">criterion's releases</a>.</em></p> <blockquote> <h2>criterion-plot-v0.8.2</h2> <h3>Other</h3> <ul> <li>Update Readme</li> </ul> <h2>criterion-v0.8.2</h2> <h3>Fixed</h3> <ul> <li>don't build alloca on unsupported targets</li> </ul> <h3>Other</h3> <ul> <li><em>(deps)</em> bump crate-ci/typos from 1.40.0 to 1.43.0</li> <li>Fix panic with uniform iteration durations in benchmarks</li> <li>Update Readme</li> <li>Exclude development scripts from published package</li> </ul> <h2>criterion-plot-v0.8.1</h2> <h3>Fixed</h3> <ul> <li>Typo</li> </ul> <h2>criterion-v0.8.1</h2> <h3>Fixed</h3> <ul> <li>Homepage link</li> </ul> <h3>Other</h3> <ul> <li><em>(deps)</em> bump crate-ci/typos from 1.23.5 to 1.40.0</li> <li><em>(deps)</em> bump jontze/action-mdbook from 3 to 4</li> <li><em>(deps)</em> bump actions/checkout from 4 to 6</li> </ul> <h2>criterion-plot-v0.8.0</h2> <p>No release notes provided.</p> <h2>criterion-v0.8.0</h2> <h3>BREAKING</h3> <ul> <li>Drop async-std support</li> </ul> <h3>Changed</h3> <ul> <li>Bump MSRV to 1.86, stable to 1.91.1</li> </ul> <h3>Added</h3> <ul> <li>Add ability to plot throughput on summary page.</li> <li>Add support for reporting throughput in elements and bytes - <code>Throughput::ElementsAndBytes</code> allows the text summary to report throughput in both units simultaneously.</li> <li>Add alloca-based memory layout randomisation to mitigate memory effects on measurements.</li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/criterion-rs/criterion.rs/blob/master/CHANGELOG.md">criterion's changelog</a>.</em></p> <blockquote> <h2><a href="https://github.com/criterion-rs/criterion.rs/compare/criterion-v0.8.1...criterion-v0.8.2">0.8.2</a> - 2026-02-04</h2> <h3>Fixed</h3> <ul> <li>don't build alloca on unsupported targets</li> </ul> <h3>Other</h3> <ul> <li><em>(deps)</em> bump crate-ci/typos from 1.40.0 to 1.43.0</li> <li>Fix panic with uniform iteration durations in benchmarks</li> <li>Update Readme</li> <li>Exclude development scripts from published package</li> </ul> <h2><a href="https://github.com/criterion-rs/criterion.rs/compare/criterion-v0.8.0...criterion-v0.8.1">0.8.1</a> - 2025-12-07</h2> <h3>Fixed</h3> <ul> <li>Homepage link</li> </ul> <h3>Other</h3> <ul> <li><em>(deps)</em> bump crate-ci/typos from 1.23.5 to 1.40.0</li> <li><em>(deps)</em> bump jontze/action-mdbook from 3 to 4</li> <li><em>(deps)</em> bump actions/checkout from 4 to 6</li> </ul> <h2><a href="https://github.com/criterion-rs/criterion.rs/compare/criterion-v0.7.0...criterion-v0.8.0">0.8.0</a> - 2025-11-29</h2> <h3>BREAKING</h3> <ul> <li>Drop async-std support</li> </ul> <h3>Changed</h3> <ul> <li>Bump MSRV to 1.86, stable to 1.91.1</li> </ul> <h3>Added</h3> <ul> <li>Add ability to plot throughput on summary page.</li> <li>Add support for reporting throughput in elements and bytes - <code>Throughput::ElementsAndBytes</code> allows the text summary to report throughput in both units simultaneously.</li> <li>Add alloca-based memory layout randomisation to mitigate memory effects on measurements.</li> <li>Add doc comment to benchmark runner in criterion_group macro (removes linter warnings)</li> </ul> <h3>Fixed</h3> <ul> <li>Fix plotting NaN bug</li> </ul> <h3>Other</h3> <ul> <li>Remove Master API Docs links temporarily while we restore the docs publishing.</li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
JD Davis
|
3077ac81e8
|
feat: add deterministic runtime rollout controls (#1490)
## Description Establish one centrally resolved, observable, deterministic, versioned runtime rollout-control mechanism for Headroom. Runtime rollout controls which behaviors an already-built artifact may expose; it does not select or qualify a Headroom release/version. ## Type of Change - [x] New feature (non-breaking change that adds functionality) - [x] Bug fix (non-breaking change that fixes rollout enforcement regressions) - [x] Documentation update - [x] Code refactoring (no functional changes) ## Changes Made - Added `RolloutChannel`, `HEADROOM_ROLLOUT_CHANNEL`, `--rollout-channel`, and a versioned immutable `RolloutSnapshot` shared by Python configuration boundaries. - Added schema/policy versions, canonical registry and snapshot SHA-256 identities, per-feature decision reasons, disable precedence, unsafe qualification poisoning, strict CLI validation, and fail-closed environment handling. - Added `headroom rollout status --json`, Python `/stats.rollout`, and Rust `/rollout/status` runtime provenance. - Added equivalent Rust snapshot semantics and shared Python/Rust policy vectors while retaining language-specific feature registries. - Enforced rollout policy at alternate Python server composition roots so `HEADROOM_READ_MATURATION=1` cannot bypass its beta gate. - Preserved typed rollout snapshots across multi-worker serialization with schema, policy, registry, snapshot-digest, type, and feature-name validation. - Made loopback runtime output-shaper updates replace the immutable snapshot atomically for request readers, retain explicit request/disable provenance, preserve channel and kill-switch precedence, invalidate cached stats, and return the effective rollout decision. - Made `headroom learn --verbosity --apply` report a channel-blocked update instead of claiming the shaper is live. - Made explicit CLI feature flags fail loudly when their current channel blocks them. - Made persistent interceptor installation select canary automatically, or reject an explicitly insufficient channel unless the break-glass override is set. - Updated architecture, proxy, rollout, learn, and output-shaper documentation with required channels and hot-reload semantics. ## Testing - [x] Unit tests pass - [x] Linting passes (`ruff check .` and `ruff format --check .`) - [x] Type checking passes (`mypy headroom --ignore-missing-imports`) - [x] New regression tests added for every corrected behavior - [x] Rust tests and production-target Clippy pass - [x] Documentation build passes ### Test Output ```text Focused rollout coverage suite 57 passed; headroom.rollout + rollout CLI: 98% coverage Affected proxy/rollout/transform/governance suites 222 passed; 0 failed Final changed regression suites 100 passed; 0 failed Cross-module hot-reload isolation regression 6 passed; 0 failed cargo test -p headroom-core -p headroom-proxy --quiet headroom-core: 924 passed; 1 ignored headroom-proxy and integration suites: all passed cargo clippy -p headroom-core -p headroom-proxy --lib --bins -- -D warnings cargo fmt --all -- --check ruff check . ruff format --check . mypy headroom --ignore-missing-imports git diff --check All passed cd docs && npm run build Compiled successfully; 164 static pages generated ``` The unsharded Windows-only CI selection exposed unrelated baseline failures, principally the existing `sqlite:///C:\\...` URL parser producing an invalid `\\C:\\...` path. At commit ` |
||
|
Zhenjia ZHOU
|
6840153473
|
fix(tokenizer): price CJK in the Rust fixed-ratio estimator (Python parity) (#2260)
## Description The Rust `EstimatingCounter` priced every character at the Latin `chars_per_token` (default 4.0), but the Python `EstimatingTokenCounter` it explicitly mirrors already prices dense scripts (CJK / Kana / Hangul / full-width) at `CHARS_PER_TOKEN_CJK = 1.5` — so Rust under-counted CJK by ~2.5× and the two implementations diverged. #2080 fixed only the Python path; the Rust module doc still says "Mirrors …EstimatingTokenCounter" while it no longer did. This is the live count path for every provider-calibrated fixed-ratio counter (Anthropic 3.5, Google / Cohere 4.0, Moonshot 3.1), so CJK traffic was mis-budgeted (savings/estimates skewed). This counts dense-script codepoints — the same 8 `CJK_PATTERN` Unicode ranges Python uses — and prices them separately: `int(other / ratio + cjk / 1.5 + 0.5)`. Non-CJK output is byte-identical. ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) ## Changes Made - `crates/headroom-core/src/tokenizer/estimator.rs`: add `is_dense_script(c)` (8 ranges byte-mirroring Python `CJK_PATTERN`) and `CHARS_PER_TOKEN_CJK = 1.5`; `count_text` prices dense-script chars separately from Latin. - Reference tests for CJK / kana / full-width / mixed — values cross-checked against Python. ## Testing - [x] Unit tests pass (`cargo test`) - [x] Linting passes (`cargo clippy` / `cargo fmt`) - [x] New tests added - [x] Verified against Python (see Real Behavior Proof) ### Test Output ```text $ cargo test -p headroom-core --lib tokenizer test result: ok. 45 passed; 0 failed $ cargo clippy / fmt # clean ``` ## Real Behavior Proof - Environment: macOS (Darwin), Rust via cargo + Python in a uv venv, branch `feat/tokenizer-estimator-cjk` off `main`. - Exact command / steps: ran the same inputs through Python `EstimatingTokenCounter(4.0).count_text` and the Rust `EstimatingCounter::default().count_text`, comparing outputs. - Observed result: identical on every input — `数据库` → 2, `数据库连接失败` → 5 (was 2 under the old flat 7/4), `ひらが` → 2, full-width `ＡＰＩ` → 2 vs plain `API` → 1, mixed `api数据` → 2. The existing non-CJK reference tests (`a`×40 → 10, Claude-3.5 densities, `héllo`/emoji char-count) are unchanged, confirming no ASCII regression. - Not tested: nothing further — parity is verified directly against the Python reference (same values on both sides). ## 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 — N/A (internal estimator) - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective - [x] New and existing unit tests pass locally with my changes - [ ] I have updated the CHANGELOG.md — happy to add an entry if preferred. ## Additional Notes - Completes #2080 (which priced CJK in the Python fixed-ratio estimator) on the Rust side, restoring Rust↔Python parity for the density estimator. Co-authored-by: JerrettDavis <mxjerrett@gmail.com> |
||
|
dependabot[bot]
|
4925bf6a82
|
deps: bump hf-hub from 0.4.3 to 0.5.0 (#2285)
Bumps [hf-hub](https://github.com/huggingface/hf-hub) from 0.4.3 to 0.5.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/huggingface/hf-hub/releases">hf-hub's releases</a>.</em></p> <blockquote> <h2>v0.5.0</h2> <h2>What's Changed</h2> <ul> <li>Upgrade ureq by <a href="https://github.com/Narsil"><code>@Narsil</code></a> in <a href="https://redirect.github.com/huggingface/hf-hub/pull/114">huggingface/hf-hub#114</a></li> <li>Update indicatif to current version in Cargo.toml by <a href="https://github.com/gordonmessmer"><code>@gordonmessmer</code></a> in <a href="https://redirect.github.com/huggingface/hf-hub/pull/126">huggingface/hf-hub#126</a></li> <li>Fix failing API tests due to outdated model metadata expectations by <a href="https://github.com/bmqube"><code>@bmqube</code></a> in <a href="https://redirect.github.com/huggingface/hf-hub/pull/124">huggingface/hf-hub#124</a></li> <li>fix: fix typo by <a href="https://github.com/AndyDai-nv"><code>@AndyDai-nv</code></a> in <a href="https://redirect.github.com/huggingface/hf-hub/pull/121">huggingface/hf-hub#121</a></li> <li>Updating tests and dependencies. by <a href="https://github.com/Narsil"><code>@Narsil</code></a> in <a href="https://redirect.github.com/huggingface/hf-hub/pull/127">huggingface/hf-hub#127</a></li> <li>Remove markdown from Cargo.toml by <a href="https://github.com/gordonmessmer"><code>@gordonmessmer</code></a> in <a href="https://redirect.github.com/huggingface/hf-hub/pull/128">huggingface/hf-hub#128</a></li> <li>Fixup the docstrings for download function (which always downloads). by <a href="https://github.com/Narsil"><code>@Narsil</code></a> in <a href="https://redirect.github.com/huggingface/hf-hub/pull/130">huggingface/hf-hub#130</a></li> <li>Expose <code>metadata</code> and <code>pointer_path</code> methods by <a href="https://github.com/danieldk"><code>@danieldk</code></a> in <a href="https://redirect.github.com/huggingface/hf-hub/pull/136">huggingface/hf-hub#136</a></li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/gordonmessmer"><code>@gordonmessmer</code></a> made their first contribution in <a href="https://redirect.github.com/huggingface/hf-hub/pull/126">huggingface/hf-hub#126</a></li> <li><a href="https://github.com/bmqube"><code>@bmqube</code></a> made their first contribution in <a href="https://redirect.github.com/huggingface/hf-hub/pull/124">huggingface/hf-hub#124</a></li> <li><a href="https://github.com/AndyDai-nv"><code>@AndyDai-nv</code></a> made their first contribution in <a href="https://redirect.github.com/huggingface/hf-hub/pull/121">huggingface/hf-hub#121</a></li> <li><a href="https://github.com/danieldk"><code>@danieldk</code></a> made their first contribution in <a href="https://redirect.github.com/huggingface/hf-hub/pull/136">huggingface/hf-hub#136</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/huggingface/hf-hub/compare/v0.4.3...v0.5.0">https://github.com/huggingface/hf-hub/compare/v0.4.3...v0.5.0</a></p> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/huggingface/hf-hub/blob/main/RELEASE.md">hf-hub's changelog</a>.</em></p> <blockquote> <h1>Releasing hf-hub</h1> <p>This document covers the full release process for the <code>hf-hub</code> crate. If anything here is unclear or out of date, please open a PR.</p> <h2>What gets released</h2> <p>A single tag push releases one artifact:</p> <ul> <li><strong><code>hf-hub</code> Rust crate</strong> on <a href="https://crates.io/crates/hf-hub">crates.io</a>, via <code>.github/workflows/rust-release.yml</code>.</li> </ul> <p>The workflow triggers on tags matching <code>v*</code> (e.g., <code>v1.0.0</code>, <code>v1.0.0-rc.0</code>).</p> <p>There are no Python components in this repo. The other workspace members are not published:</p> <ul> <li><code>hfrs/</code> — CLI binary, distributed via <code>cargo install --git</code>.</li> <li><code>examples/</code>, <code>benches/</code>, <code>integration-tests/</code> — internal-only, version <code>0.0.0</code>, never published.</li> </ul> <h2>Pre-release checklist</h2> <ol> <li><strong>CI is green on <code>main</code>.</strong> The <code>Rust</code> workflow must be passing on every platform in the matrix (Ubuntu, Windows, macOS) with both feature configurations (<code>""</code> and <code>--all-features</code>).</li> <li><strong>Review the diff since the last release.</strong> <pre lang="bash"><code>git log --oneline v0.5.0..main git diff v0.5.0..main --stat -- hf-hub/ </code></pre> Pay particular attention to changes under <code>hf-hub/src/</code> — those are the only changes that actually ship to crates.io.</li> <li><strong>Identify breaking changes.</strong> Anything that changes the public Rust API (types, function signatures, removed re-exports, builder fields) needs to be reflected in the version bump per <a href="https://semver.org">semver</a> and called out in the release notes.</li> <li><strong>Run the full pre-release test sweep</strong> (see next section).</li> </ol> <h2>Pre-release test sweep</h2> <p>Run all of these from the repo root before tagging. They mirror what CI runs, plus a publish dry-run that CI does not currently do.</p> <h3>Format and lint</h3> <pre lang="bash"><code>cargo +nightly fmt --all -- --check cargo clippy --workspace --all-targets -- -D warnings cargo clippy --workspace --all-targets --all-features -- -D warnings </code></pre> <h3>Unit tests (<code>hf-hub</code>)</h3> <pre lang="bash"><code>cargo test -p hf-hub cargo test -p hf-hub --features blocking </code></pre> <h3>Integration tests (<code>integration-tests</code>)</h3> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
dependabot[bot]
|
522faa1a59
|
deps: bump rusqlite from 0.32.1 to 0.40.1 (#2287)
Bumps [rusqlite](https://github.com/rusqlite/rusqlite) from 0.32.1 to 0.40.1. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/rusqlite/rusqlite/releases">rusqlite's releases</a>.</em></p> <blockquote> <h2>0.40.1</h2> <h2>What's Changed</h2> <ul> <li>Fix clippy warnings <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1852">#1852</a></li> <li>Bump bundled SQLite version to 3.53.2 <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1853">#1853</a></li> <li>Bump hashlink version <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1855">#1855</a></li> <li>Fix SQL injection when SAVEPOINT name is tainted <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1854">#1854</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/rusqlite/rusqlite/compare/v0.40.0...v0.40.1">https://github.com/rusqlite/rusqlite/compare/v0.40.0...v0.40.1</a></p> <h2>0.40.0</h2> <h2>What's Changed</h2> <ul> <li>Breaking changes: Replace VTab macros by constructors <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1823">#1823</a></li> <li>Breaking changes: Fix VTab::best_index <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1824">#1824</a></li> <li>Asserts on VTab::connect aux and args <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1825">#1825</a></li> <li>Breaking changes: Fix VTab::connect / create <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1826">#1826</a></li> <li>Breaking changes: Allow opting out of using sqlite-wasm-rs on wasm32-unknown-unknown <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1828">#1828</a>, <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1829">#1829</a></li> <li>Derive Default for SeriesTabCursor/ArrayTabCursor <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1830">#1830</a></li> <li>Update link to pre-update hook <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1831">#1831</a></li> <li>Breaking changes: Fix VTab::connect <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1832">#1832</a></li> <li>impl From<!-- raw HTML omitted --> for FromSqlError <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1833">#1833</a></li> <li>Breaking changes: Fix vtab::dequote <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1835">#1835</a></li> <li>Bump bundled SQLCipher to version 4.14.0 <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1837">#1837</a></li> <li>sqlite3_set_errmsg <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1752">#1752</a></li> <li>Bump sqlite3-parser version <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1838">#1838</a></li> <li>Fix UB in ToSqlOutput::from_rc <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1839">#1839</a></li> <li>Ensure miri doesn't complain <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1840">#1840</a></li> <li>Bump to actions/checkout@v6 <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1842">#1842</a></li> <li>Add support to UtcDateTime <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1843">#1843</a>, <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1844">#1844</a></li> <li>Bump bundled SQLite version to 3.53.1 <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1848">#1848</a></li> <li>Replace some cfg(not by cfg_select <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1850">#1850</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/rusqlite/rusqlite/compare/v0.39.0...v0.40.0">https://github.com/rusqlite/rusqlite/compare/v0.39.0...v0.40.0</a></p> <h2>0.39.0</h2> <h2>What's Changed</h2> <ul> <li>Fix constraints on VTab Aux data <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1778">#1778</a>, <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1771">#1771</a></li> <li>Fix docs.rs generation <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1779">#1779</a></li> <li>Fix a small typo in <code>rollback_hook</code> docstring <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1780">#1780</a></li> <li>Fix some warnings from Intellij <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1781">#1781</a></li> <li>Minimal doc for features <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1783">#1783</a></li> <li>Clear hooks only for owning connections <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1785">#1785</a>, <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1784">#1784</a></li> <li>Fix link to SQLite C Interface, Prepare Flags <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1787">#1787</a></li> <li>Comment functions which are not usable from a loadable extension <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1789">#1789</a></li> <li>Factorize code <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1792">#1792</a></li> <li>Update getrandom to 0.4 <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1798">#1798</a></li> <li>Update Cargo.toml <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1800">#1800</a></li> <li>Fix appveyor <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1807">#1807</a></li> <li>Add support to unix timestamp for chrono, jiff and time <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1808">#1808</a>, <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1803">#1803</a></li> <li>fix(trace): check that the sql string pointer is not NULL <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1805">#1805</a></li> <li>Bump bundled SQLite version to 3.51.3 <a href="https://redirect.github.com/rusqlite/rusqlite/issues/1818">#1818</a></li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
JD Davis
|
f236ef2e31
|
test(ccr): cross SQLite max lifetime boundary (#2794)
## Description
Fixes the failing Rust test on `main` after #2669 made SQLite CCR
entries valid at the exact TTL boundary. The integration test waited
only 3.3 seconds for a three-second ceiling; unix-second truncation can
represent that as exactly three seconds, so the entry is correctly still
valid. The test now crosses a guaranteed four-second elapsed boundary.
## 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
- Extend the max-lifetime test's access loop from four to five 700 ms
gaps.
- Document why four gaps can land on the valid equality boundary and why
five are deterministic.
- Leave production SQLite TTL behavior and defaults unchanged.
## Testing
- [x] Unit tests pass (`cargo test -p headroom-core --test
ccr_backends`)
- [x] Formatting passes (`cargo fmt --all -- --check`)
- [ ] Type checking passes (`mypy headroom`)
- [ ] New tests added for new functionality
- [x] Manual testing performed
### Test Output
```text
cargo test -p headroom-core --test ccr_backends
test result: ok. 12 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out
5 consecutive repetitions of the previously failing test:
test result: ok. 1 passed; 0 failed; 0 ignored; 0 measured; 11 filtered out
```
## Real Behavior Proof
- Environment: macOS, Rust workspace at
`
|
||
|
Agistaris
|
d0a86d409f
|
fix(ccr): preserve exact SQLite TTL boundary (#2669)
## Description SQLite CCR timestamps have whole-second resolution. Expiring a row when `last_accessed + ttl == now` or `created_at + max_lifetime == now` can shorten the configured lifetime by almost one second. This change keeps entries valid at the exact boundary and expires them one second later. ## 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 - Use strict expiration predicates for idle TTL and maximum lifetime. - Keep lookup predicates valid at the exact boundary. - Add deterministic fixed-time tests for both boundaries. ## Testing - [ ] Unit tests pass (`pytest`) - [ ] Linting passes (`ruff check .`) - [ ] Type checking passes (`mypy headroom`) - [x] New tests added for new functionality - [x] Manual testing performed ### Test Output ```text running 3 tests test ccr::backends::sqlite::tests::exact_max_lifetime_boundary_is_still_valid ... ok test ccr::backends::sqlite::tests::exact_idle_ttl_boundary_is_still_valid ... ok test transforms::code_compressor::tests::english_exact_token_match_unchanged ... ok test result: ok. 3 passed; 0 failed; 0 ignored; 0 measured; 911 filtered out ``` ## Real Behavior Proof - Environment: Linux x86_64, repository Rust toolchain. - Exact command / steps: `cargo test -p headroom-core exact_` - Observed result: Both SQLite boundary tests returned the stored payload at the exact configured boundary and removed it one second later. The focused command passed 3/3 selected tests, including one unrelated existing exact-token test. - Not tested: Live provider or model traffic; the change is isolated to the deterministic Rust SQLite backend. ## Review Readiness - [x] I have performed a self-review - [x] This PR is ready for human review ## Checklist - [x] My code follows the project style guidelines - [x] I have performed a self-review of my code - [x] I have commented the boundary behavior - [ ] I have made corresponding documentation changes (not applicable; behavior and tests are local to the backend) - [x] My changes generate no new warnings - [x] I have added tests that prove the fix is effective - [x] New and existing relevant tests pass locally with my changes - [x] I did not edit `CHANGELOG.md` ## Screenshots (if applicable) Not applicable. ## Additional Notes Rust formatting and `headroom-core` Clippy pass. A broader package run passed 994 tests with three ignored; two unrelated ONNX parity tests were excluded after reproducing their pre-existing futex stall. |
||
|
Tejas Chopra
|
3e348f327f
|
fix(ccr): stop persisting retrieval markers as original content (#2694) (#2703)
## Description CCR entries could end up holding a `<<ccr:...>>` marker — or nothing at all — where the original bytes belonged, so `headroom_retrieve(hash)` answered with the very placeholder the caller was trying to resolve. For a base64/credential field that is permanent, silent data loss: the inner marker's hash is the only handle on the real payload, and it disappears from anywhere the model can see. Four sites, one root cause — **a compressed intermediate (or nothing) was stored in place of the source**, the same defect class as #1209 (tag placeholders persisted as originals). Closes #2694 ## 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 - **`compaction/walker.rs`** — `walk_array` compacted through the store-LESS `compact()`. Opaque cells inside a compacted table got a marker whose payload was **never written**, so retrieval 404'd forever. Now uses `compact_with_store` so the emitted hash resolves. - **`compaction/classifier.rs`** — nothing stopped an already-marked string from being offloaded a second time, which stashed the MARKER as the new entry's "original". Marker-bearing text is our own output, not source content, so it is never classified opaque. One guard at the choke point both the walker and the table compactor share. - **`smart_crusher/crusher.rs`** — on the prose-hook path the row-drop marker hashed and stored rows whose leaves were **already** rewritten (prose compressed, blobs marker-substituted), so retrieving dropped rows returned compressed output. Now hashes and stashes the pre-processing array via `crush_array_with_source`. - **`content_router.py`** — compression pinning matched only `Retrieve more: hash=` / `Retrieve original: hash=`, **not** `<<ccr:`, so opaque-blob output was readmitted to the compressor on a later turn — the path that feeds the corruption above. Consolidated into `_is_already_compressed()` and applied at all three pinning sites. - **`cache/compression_store.py`** — store-level guard: refuse to persist a *bare* marker as `original_content` and log at ERROR, so a future producer regression surfaces loudly instead of silently converting "retrievable" into "gone". Deliberately narrow — originals may legally *contain* markers (nested offloads); only a bare marker is rejected. - **Regression tests** — `test_nested_table_markers_resolve_to_source_bytes` (asserts payloads are verbatim-retrievable, not merely that a marker was emitted) and `test_already_marked_content_is_not_re_offloaded`. ## Testing - [x] Unit tests pass (`pytest`) - [x] Linting passes (`ruff check`) - [x] Type checking passes (`mypy`) - [x] New tests added for new functionality - [x] Manual testing performed ### Test Output ```text $ cargo build -p headroom-core Finished `dev` profile [unoptimized + debuginfo] target(s) in 2m 37s $ cargo test -p headroom-core --lib smart_crusher test result: ok. 329 passed; 0 failed; 0 ignored; 0 measured; 583 filtered out; finished in 0.19s $ python -m pytest tests/test_transforms/test_smart_crusher_ccr_roundtrip.py -q 16 passed in 0.68s $ python -m pytest tests/test_ccr_row_drop_store_bridge.py tests/test_ccr_tool_injection.py -q 50 passed in 12.52s $ python -m pytest tests/test_compression_store.py tests/test_lossless_mode.py -q 100 passed in 13.14s $ ruff check headroom/transforms/content_router.py headroom/cache/compression_store.py \ tests/test_transforms/test_smart_crusher_ccr_roundtrip.py All checks passed! $ mypy headroom/transforms/content_router.py headroom/cache/compression_store.py Success: no issues found in 2 source files ``` ## Real Behavior Proof - **Environment:** macOS (Darwin 25.4.0), Python 3.12.6, headroom-ai 0.33.0 editable, `HEADROOM_CCR_BACKEND=memory`, Rust extension rebuilt via `maturin develop --release`. - **Exact command / steps:** compact a nested document — 5 rows whose `detail` field is a stringified sub-array of 6 base64 blobs (1600 B each) — then, for every `<<ccr:HASH>>` marker in the output, call `ccr_get(HASH)` and check the payload is the verbatim source rather than a marker. ```python inner = [{"k": f"key{i}", "v": i, "tok": blob(1200)} for i in range(6)] doc = {"rows": [{"id": i, "detail": json.dumps(inner), "note": "x"} for i in range(5)]} out = SmartCrusher().compact_document_json(json.dumps(doc)) for h in re.findall(r"<<ccr:([0-9a-f]+)", out): payload = crusher.ccr_get(h) # must be real bytes, not a marker ``` - **Observed result — BEFORE (on `main`):** all six payloads collapsed into a single dead marker. The rendered sub-table was re-classified opaque (`html`, because `<<` reads as a tag), offloaded again, and its payload never stored — so the six inner hashes were erased from the visible text *and* the outer hash resolved to nothing. ```text {"rows":"[5]{detail:string,id:int,note:string} <<ccr:3fb1d44933da,html,289B>>,0,x <<ccr:3fb1d44933da,html,289B>>,1,x ..."} 3fb1d44933da -> RUST MISS # unrecoverable — 6 × 1600 B gone ``` - **Observed result — AFTER (this branch):** the sub-table stays inline, each blob keeps its own marker, and every marker resolves to verbatim source. ```text {"rows":"[5]{detail:string,id:int,note:string} \"[6]{k:string,tok:string,v:int} key0,\"\"<<ccr:955b1fed2ef7,base64,1.6KB>>\"\",0 ..."} 6ad5846997f4: resolves, len=1600, is-verbatim-source=True 78a0bd9364a7: resolves, len=1600, is-verbatim-source=True 955b1fed2ef7: resolves, len=1600, is-verbatim-source=True a0cef69da7f0: resolves, len=1600, is-verbatim-source=True dfcde5e940c0: resolves, len=1600, is-verbatim-source=True e57c4e0a3ce8: resolves, len=1600, is-verbatim-source=True RESULT: PASS — every marker resolves to real source bytes ``` ## Notes for reviewers - The issue also reports **function words dropped from retained prose** (`is`, `a`, `the`) and **interleaved log output corrupting `headroom doctor`'s table borders**. Those are separate defects on different paths (extractive prose compression and log-handler buffering respectively) and are **not** addressed here — this PR is scoped to the CCR store/retrieve corruption. They should be tracked separately; the prose one overlaps #2586. - The `crusher.rs` prose-hook fix is on the Rust pipeline (`json_offload`) rather than the Python proxy path, but it is the same store-the-intermediate bug and was cheap to close while in the file. |
||
|
Zhenjia ZHOU
|
e825588bfb
|
fix(ccr): sliding idle-window TTL with max-lifetime ceiling in the Rust core backends (#2604) (#2631)
## Description
Rust-core counterpart of the CCR mid-session expiry fix. #2604 (and its
duplicate #2616) report that the 30-minute wall-clock TTL kills entries
in the middle of a normal multi-agent burst: the clock starts at
compression time and never refreshes, so an entry the session keeps
touching still dies.
#2607 fixes this on the Python side by turning the TTL into an idle
window that restarts on every successful retrieval, bounded by an
absolute max lifetime (8x the idle TTL) — but it explicitly notes the
caveat that the Rust core still measures TTL from insertion. This PR
closes that gap: all three Rust CCR backends (`InMemoryCcrStore`,
`SqliteCcrStore`, `RedisCcrStore`) now use the same sliding idle-window
+ max-lifetime-ceiling semantics as the Python `CompressionStore`.
Scoped to the Rust core only; it deliberately does not touch
`DEFAULT_TTL`'s value (1800), which #2607 bumps to 3600 — happy to
rebase in lockstep whichever lands first.
Refs #2604, #2616. Complements #2607.
## 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
- `crates/headroom-core/src/ccr/mod.rs`:
`DEFAULT_MAX_LIFETIME_MULTIPLIER = 8` + `max_lifetime_for()` helper;
documents the idle-window semantics.
- `in_memory.rs`: entries track `last_accessed`; a hit refreshes it
under the shard write lock (`get_mut`), expiry checks idle window OR max
lifetime, and the existing `remove_if` TOCTOU protection now uses the
same predicate. New `with_capacity_and_ttls` constructor for independent
control of window and ceiling.
- `sqlite.rs`: new `last_accessed` column (legacy DBs migrated in place
via `ALTER TABLE`, backfilled from `created_at` so old rows keep their
original expiry baseline); lazy purge and the lookup honour both bounds;
a hit touches the row under the same connection mutex as the read. New
`open_with_ttls` constructor.
- `redis.rs`: a hit re-arms the key's expiry, capped by a companion
`{prefix}:{hash}:born` key whose remaining TTL marks the absolute
ceiling; entries written by pre-sliding builds (no born key) are
backfilled rather than dropped.
- `tests/ccr_backends.rs`: 6 new tests — sliding-window survival and
max-lifetime cap for in-memory and SQLite, legacy-schema migration, and
a gated Redis sliding test.
No public API is broken: existing constructors keep their signatures and
derive the ceiling as 8x the idle TTL.
## Testing
- [x] Unit tests pass (`cargo test -p headroom-core`)
- [x] Linting passes (`cargo clippy -p headroom-core --all-features`,
`cargo fmt --check`)
- [ ] Type checking passes (`mypy headroom`) — N/A, no Python files
touched
- [x] New tests added for new functionality
- [x] Manual testing performed
### Test Output
```text
$ cargo test -p headroom-core --test ccr_backends
test result: ok. 12 passed; 0 failed; 0 ignored (8.12s)
$ cargo test -p headroom-core ccr # all ccr-named tests across suites
38 passed, 949 filtered out (13 suites)
$ cargo test -p headroom-core --test ccr_roundtrip --test live_zone_ccr
18 passed (2 suites)
$ cargo check -p headroom-core --features redis # cfg-gated backend compiles
Finished `dev` profile in 25.09s
$ cargo clippy -p headroom-core --all-features
No issues found
```
## Real Behavior Proof
- Environment: macOS (Darwin 25.5), local checkout at upstream `main`
(
|
||
|
Zhenjia ZHOU
|
e86c6390ce
|
fix(rust): port CJK-aware relevance-query matching to CodeCompressor (#2634)
## Description The Rust port of `CodeCompressor` (#1154, parity-only) did not carry over the CJK-aware relevance-query matching from `headroom/transforms/code_compressor.py` (`_CONTEXT_DELIMS` / `_CJK_CHARS` / `_query_context_tokens()` / `_symbol_in_context()`, lines 2353-2387, called from lines 987/1009): - Rust tokenized the context with an ASCII-only delimiter class `[\s,;:.()\[\]{}"']+`, so a CJK query (no spaces, CJK punctuation) collapses into a single blob and never isolates an ASCII symbol name. - The substring-fallback guard `chars().count() > 3` had no CJK relaxation, so a short ASCII name glued to CJK text (e.g. `run` in `修复run函数的报错`, `db` in `请保留db相关的逻辑`) could never receive the +3.0 context boost — while Python does boost it. Same `(code, context)` input, different `symbol_scores`. This PR ports the two Python helpers with identical semantics: - `query_context_tokens()` — delimiter class extended with the CJK/full-width punctuation and ideographic space from Python's `_CONTEXT_DELIMS`; returns `(words, lowered, has_cjk)` with CJK detection over U+3000-U+9FFF, U+AC00-U+D7AF, U+FF00-U+FFEF (Python's `_CJK_CHARS`). - `symbol_in_context()` — exact token match, plus the substring fallback gated by `> 3` **characters** (Python `len()`, not bytes), relaxed when the query contains CJK. The call site in `analyze_symbols` now uses these helpers; no other behavior changed. Pure-ASCII query behavior is identical to before (exact token match, `>3`-gated substring fallback), which the tests pin down. Closes #2630 ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) ## Changes Made - `crates/headroom-core/src/transforms/code_compressor.rs`: extract `query_context_tokens()` / `symbol_in_context()` free functions mirroring the Python helpers (CJK/full-width delimiter class, CJK detection, CJK-relaxed `>3`-character guard); replace the inline ASCII-only tokenization + guard in `analyze_symbols` with calls to them. - Unit tests mirroring `tests/test_transforms/test_code_compressor_cjk.py` case-for-case, plus a character-vs-byte guard test and an end-to-end `compress_with` test asserting `symbol_scores`. ## Testing - [x] Unit tests pass (`cargo test -p headroom-core` — Rust-only change; Python untouched) - [x] Linting passes (`cargo fmt --check`, `cargo clippy -p headroom-core --all-targets` — no new warnings) - [ ] Type checking passes (`mypy headroom`) — N/A, no Python changes - [x] New tests added for new functionality - [x] Manual testing performed New tests (all in `code_compressor.rs` `mod tests`): - `cjk_query_isolates_wrapped_ascii_symbol` — full-width parens isolate `parse_config` - `cjk_query_matches_short_ascii_name_glued_to_cjk` — `db` (len 2) glued to CJK matches via the relaxed guard - `english_short_name_substring_still_gated` — `db` vs "keep the database helper" must NOT match (ASCII guard unchanged) - `english_exact_token_match_unchanged`, `english_long_name_substring_fallback_unchanged`, `empty_context_matches_nothing` - `guard_counts_chars_not_bytes` — the guard is a character count, matching Python `len()` - `cjk_context_boosts_named_symbol_end_to_end` — full `compress_with` run asserting `symbol_scores` (red on main, green here — see proof) ### Test Output ```text $ cargo test -p headroom-core --lib -- code_compressor::tests test transforms::code_compressor::tests::empty_and_short_passthrough ... ok test transforms::code_compressor::tests::empty_context_matches_nothing ... ok test transforms::code_compressor::tests::estimate_tokens_uses_chars_div_4_min_1 ... ok test transforms::code_compressor::tests::py_round3_matches_cpython ... ok test transforms::code_compressor::tests::py_round_int_is_half_to_even ... ok test transforms::code_compressor::tests::cjk_query_isolates_wrapped_ascii_symbol ... ok test transforms::code_compressor::tests::english_short_name_substring_still_gated ... ok test transforms::code_compressor::tests::cjk_query_matches_short_ascii_name_glued_to_cjk ... ok test transforms::code_compressor::tests::english_exact_token_match_unchanged ... ok test transforms::code_compressor::tests::english_long_name_substring_fallback_unchanged ... ok test transforms::code_compressor::tests::guard_counts_chars_not_bytes ... ok test transforms::code_compressor::tests::cjk_context_boosts_named_symbol_end_to_end ... ok test transforms::code_compressor::tests::detect_language_basic ... ok test result: ok. 13 passed; 0 failed; 0 ignored; 0 measured; 899 filtered out; finished in 0.05s $ cargo test -p headroom-core # per-binary summaries lib .......................... ok. 911 passed; 0 failed; 1 ignored auth_mode .................... ok. 16 passed; 0 failed cache_control ................ ok. 14 passed; 0 failed ccr_backends ................. ok. 7 passed; 0 failed ccr_roundtrip ................ ok. 15 passed; 0 failed code_compressor_parity ....... ok. 1 passed; 0 failed (recorded byte-parity fixtures) live_zone_ccr ................ ok. 3 passed; 0 failed live_zone_dispatch ........... ok. 6 passed; 0 failed live_zone_thresholds ......... ok. 2 passed; 0 failed live_zone_token_validation ... ok. 3 passed; 0 failed recommendations_loader ....... ok. 4 passed; 0 failed tokenizer_proptest ........... ok. 5 passed; 0 failed doc-tests .................... ok. 1 passed; 0 failed; 2 ignored $ cargo fmt --check # clean $ cargo clippy -p headroom-core --all-targets # no new warnings ``` ## Real Behavior Proof - Environment: macOS (Darwin 25.5.0), repo-pinned Rust toolchain (`rust-toolchain.toml`), branch based on current `main`. - Exact command / steps: the end-to-end test was written first and run against unmodified `main` (red), then after the fix (green). Input: Python source with two signal-symmetric functions `run` and `keep`; context `修复run函数的报错`. The Python reference gives `run` the boost (`_symbol_in_context('run', ...) == True`, `_symbol_in_context('keep', ...) == False`, verified against the live Python implementation), so expected normalized scores are `run = 1.0`, `keep = 0.0`. - Observed result: on unmodified main the end-to-end test fails (`left: 0.5, right: 1.0` — the CJK query `修复run函数的报错` gives `run` no boost, both symbols collapse to 0.5, while Python scores `run=1.0, keep=0.0`); on this branch all 8 new tests pass and the same query boosts `run` to 1.0, matching Python. Full output: Before (unmodified `main` + new test only — Rust gives no boost, both symbols collapse to 0.5): ```text ---- transforms::code_compressor::tests::cjk_context_boosts_named_symbol_end_to_end stdout ---- thread '...cjk_context_boosts_named_symbol_end_to_end' panicked at crates/headroom-core/src/transforms/code_compressor.rs:1890:9: assertion `left == right` failed: run must get the context boost left: 0.5 right: 1.0 test result: FAILED. 0 passed; 1 failed; 0 ignored; 0 measured; 904 filtered out ``` After (this branch): the same test passes, including its ASCII control case (`fix the runner` must NOT boost `run` — scores stay 0.5/0.5), proving pure-ASCII behavior is unchanged. The recorded byte-parity fixture suite (`code_compressor_parity`) also still passes. - Not tested: real proxy traffic end-to-end (change is confined to the symbol-scoring context boost inside the Rust compressor; the Python implementation is the behavioral reference and is untouched). `kompress_parity` was not run locally — it is model-gated and my sandbox blocks the model fetch; it is unrelated to this change and CI covers its skip path. ## 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 — N/A (internal behavior fix) - [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 did **not** edit `CHANGELOG.md` — it is generated by release-please from my Conventional Commit PR title (a CI guard enforces this) ## Additional Notes For background, the Python-side CJK handling comes from the merged CJK sweep work (#2220 and follow-ups); #1154 predates part of it, which is likely how the port missed it. Longer names wrapped in full-width punctuation happened to still match in Rust via the substring fallback, but the token set itself was wrong; this PR restores exact-token semantics for those too. |
||
|
Ruben A.
|
e530de5ad2
|
feat(rust): port CodeCompressor AST compressor to Rust (parity-only) (#1154)
Adds crates/headroom-core/src/transforms/code_compressor.rs (1,882 lines): the AST-aware CodeCompressor ported to Rust on tree-sitter, with grammars for Python, JavaScript, TypeScript, Go, Rust, Java, C and C++. Parity-only, like #1153. Nothing calls it: the only references outside the module are the pub mod / pub use declarations in transforms/mod.rs, and live_zone.rs still routes SourceCode to a no-op. The pyo3 bridge is untouched and no Python source changes, so the engine is unreachable from the shipped package. #1155 wires it into live-zone dispatch. Every grammar is pinned with '=' to the exact version of the corresponding Python tree-sitter-<lang> PyPI wheel. Same version on crates.io and PyPI means the same grammar.js, hence the same generated parser.c, hence node-for-node identical ASTs — the precondition for byte-parity. A canary over 9 samples x 8 languages confirmed identical node-type and line-span trees at these pins; bumping any pin requires re-running it and re-recording the fixtures. Ships 30 recorded parity fixtures, a CodeCompressorComparator in headroom-parity, and scripts/record_code_compressor_fixtures.py. Verified byte-identical to the recorded Python output: [code_aware_compressor] total=30 matched=30 skipped=0 diffed=0 Full harness on the merge result: 227 fixtures, 182 matched, 45 skipped (cache_aligner + ccr stubs), 0 diffed, exit 0 — with kompress at 21/21 under ONNX Runtime 1.24.4 (see #2591). Also verified cargo check -p headroom-core --no-default-features passes, so the static-musl path stays intact. |
||
|
Ruben A.
|
83e27e5036
|
feat(rust): port Kompress ML prose compressor to Rust (parity-only) (#1153)
Adds crates/headroom-core/src/transforms/kompress.rs (672 lines): the Kompress ML prose compressor ported to Rust, running the ModernBERT tokenizer plus the kompress-v2-base ONNX model through ort with a cache-only loader that never touches the network. Parity-only. Nothing calls it: the only references outside the module are the pub mod / pub use declarations in transforms/mod.rs. live_zone.rs still carries TODO(PR-B4), so PlainText dispatch remains a no-op and Python continues to serve prose compression. The pyo3 bridge is untouched and no Python source changes, so the new engine is unreachable from the shipped package. #1155 wires it up. Ships 21 recorded parity fixtures, a KompressComparator in headroom-parity, and scripts/record_kompress_fixtures.py. Verified byte-identical to the recorded Python output: [kompress] total=21 matched=21 skipped=0 diffed=0 That required ONNX Runtime >= 1.24 (see #2591) — below it ort deadlocks instead of erroring, which is why these fixtures had never been run. In CI the model is absent from the HF cache, so the comparator errors and the fixtures report Skipped rather than hanging. Also gates the module behind the ml feature, matching magika_detector: kompress.rs uses ort, which is optional = true, so an unconditional pub mod broke cargo check --no-default-features (the static-musl path). CI does not catch that class of break because cargo test --workspace only builds default features. |
||
|
Rod Boev
|
9e0778553f
|
feat(rust): add structured prose offload plumbing (#334) (#2378)
## Description Structured payloads still leave long prose leaves without a dedicated prose compressor. The Rust pipeline already handles top-level log, diff, search, and JSON-array shapes, and the existing structured recursion rewrites stringified JSON and opaque blobs, but a plain prose string leaf inside structured content still falls back to generic opaque long-string handling instead of query-aware extractive compression. That wastes prompt budget on fields like `summary`, `description`, and `analysis` even though `headroom-core` already ships the deterministic, query-aware `TextCrusher`. This PR adds a bounded prose-field path for structured leaves. It introduces a reusable `ProseFieldOffload` backed by `TextCrusher`, then wires that offload into `JsonOffload`'s structured recursion with conservative byte and segment thresholds. Only detector-confirmed `PlainText` leaves are eligible. When a leaf clears those gates and the marker-inclusive output still saves bytes, the exact original leaf is written to CCR and the inline output carries a prose marker keyed to that store entry. Short prose, low-segment prose, diff-shaped strings, stringified JSON, and opaque base64 or HTML keep their existing behavior. This stays inside the Rust transform stack. It does not add a PyO3 shim, ONNX runtime, live-zone prose handling, or any new Python dependency. It also keeps the existing wrapper-level `JsonOffload` CCR entry, so the full structured payload remains recoverable as before. ## 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 - Add `ProseFieldOffload` as a `ContentType::PlainText` pipeline offload backed by `TextCrusher`, with conservative byte, segment, and target-ratio thresholds. - Thread the prose offload into the structured `JsonOffload` recursion so nested prose leaves can compress and recover through the orchestrator store. - Add a pipeline-aware `JsonOffload::from_pipeline` constructor so `offload.prose_field` overrides actually reach the live prose hook instead of falling back to embedded defaults. - Preserve current behavior for short prose, low-segment prose, diff-shaped leaves, stringified JSON containers, and opaque base64 or HTML leaves. - Add focused config, routing, determinism, and CCR roundtrip coverage for the new prose path. - Leave changelog generation to the repo's conventional-commit release flow rather than editing `CHANGELOG.md` directly. ## Testing - [x] Unit tests pass (`cargo test -p headroom-core --lib transforms::pipeline::offloads::prose_field::tests`) - [x] Linting passes (`cargo clippy -p headroom-core -- -D warnings`) - [ ] Type checking passes (`uv run mypy headroom`) - [x] New tests added for new functionality when applicable - [ ] Manual testing performed ### Test Output ```text cargo fmt --all -- --check cargo clippy -p headroom-core -- -D warnings cargo test -p headroom-core --lib transforms::pipeline::offloads::prose_field::tests test result: ok. 6 passed; 0 failed cargo test -p headroom-core --lib transforms::pipeline::offloads::json_offload::tests test result: ok. 17 passed; 0 failed cargo test -p headroom-core --lib transforms::smart_crusher::crusher::tests::default_crush_ignores_opt_in_prose_hook -- --exact test result: ok. 1 passed; 0 failed cargo test -p headroom-core --lib transforms::smart_crusher::crusher::tests::prose_hook_preserves_html_opaque_routing -- --exact test result: ok. 1 passed; 0 failed cargo test -p headroom-core --lib transforms::smart_crusher::crusher::tests::prose_hook_runs_for_dict_array_rows -- --exact test result: ok. 1 passed; 0 failed cargo test -p headroom-core --lib transforms::smart_crusher::crusher::tests::unchanged_stringified_json_container_skips_prose_hook -- --exact test result: ok. 1 passed; 0 failed cargo test -p headroom-core --test ccr_roundtrip nested_structured_prose_leaf_uses_ccr -- --exact test result: ok. 1 passed; 0 failed git diff --check ``` ## Real Behavior Proof - Environment: Windows 11, stable Rust toolchain, in-memory CCR store, no live provider - Exact command / steps: run the focused nested CCR roundtrip test through `CompressionPipeline::run` on a five-row structured payload containing a long prose leaf, then resolve the emitted prose marker key from the same orchestrator store - Observed result: the generic `CompressionPipeline` plus `JsonOffload` path applies, the nested prose leaf becomes shorter on the wire, and that prose key retrieves the byte-identical original leaf from the orchestrator store while HTML-shaped and diff-shaped leaves stay on their opaque marker routes - Not tested: live provider run ## 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 - [ ] 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 feature works - [x] New and existing unit tests pass locally with my changes - [ ] I have updated the CHANGELOG.md if applicable ## Additional Notes - The upstream issue body originally parked PR3b behind a PyO3 shim or a later ONNX port. This PR takes the narrower Rust-native path instead by reusing the existing `TextCrusher` already in `headroom-core`. - This PR advances the pipeline-side PR3b slice from #334. It does not close #334, and it does not wire live-zone or PyO3 SmartCrusher callers to this path. - `CHANGELOG.md` is intentionally untouched because this repo's release pipeline generates changelog entries from conventional commits, and `repos/headroom/config.md` marks manual changelog edits as out of policy. - Python lint, type checking, and pytest are not part of the focused local proof for this slice because the change stays inside `crates/headroom-core`. |
||
|
Zhenjia ZHOU
|
844d9caaa1
|
feat(text-crusher): fold full-width ASCII to half-width in CJK token keys (#2259)
## Description Real CJK content routinely mixes full-width and half-width forms (`ＡＰＩ` vs `API`, `０` vs `0`, the ideographic space ` ` vs a normal space). After #1504's ICU tokenization, these width variants produced *different* token keys, so `ＡＰＩ` and `API` didn't dedup or match as the same term on the CJK relevance and near-duplicate paths. This folds full-width ASCII (U+FF01–U+FF5E, via the U+FEE0 offset) and the ideographic space (U+3000 → space) to their half-width forms **when building the internal token key** inside `tokens_icu`. Only the token key is normalized — the kept output stays byte-verbatim, so TextCrusher's extractive / byte-faithful contract is preserved. CJK-gated (`tokens_icu` is the CJK path); the ASCII path is untouched. ## Type of Change - [x] Bug fix / enhancement (non-breaking) ## Changes Made - `crates/headroom-core/src/transforms/text_crusher/crusher.rs`: a `width_fold(c)` helper applied when building token keys in `tokens_icu`. - Rust unit tests: full-width ASCII folds to half-width in token keys; CJK segments split on full-width terminators. ## Testing - [x] Unit tests pass (`cargo test`) - [x] Linting passes (`cargo clippy` / `cargo fmt`) - [x] New tests added ### Test Output ```text $ cargo test -p headroom-core --lib text_crusher test result: ok. 13 passed; 0 failed $ cargo clippy / fmt # clean ``` ## Real Behavior Proof - Environment: macOS (Darwin), Rust via cargo, branch `feat/text-crusher-fullwidth-fold` off `main` (rebased after #1504 merged). - Exact command / steps: `cargo test -p headroom-core --lib text_crusher`. - Observed result: `fullwidth_ascii_folds_to_halfwidth` confirms `ＡＰＩ` and `API` now produce the same token key (so they dedup/relevance-match as one term); `cjk_splits_on_full_width_terminators` confirms full-width `！`/`？` terminate segments. All 13 text_crusher tests pass; the kept output is byte-verbatim (only the internal key is folded). - Not tested: no Python side — TextCrusher is Rust-only, and output stays byte-verbatim, so no parity fixtures change. ## 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 — N/A - [x] My changes generate no new warnings - [x] I have added tests that prove my change is effective - [x] New and existing unit tests pass locally with my changes - [ ] I have updated the CHANGELOG.md — happy to add an entry if preferred. ## Additional Notes - Follow-up to #1504 (CJK-aware TextCrusher); it only touches the CJK-gated `tokens_icu` path, so English tokenization is unchanged. |
||
|
Zhenjia ZHOU
|
4035c04187
|
feat(text-crusher): CJK-aware segmentation + relevance via ICU (#1504)
## Description `TextCrusher` (the native extractive prose compressor added in #1171) only handled ASCII: `split_segments` split on `.!?`+whitespace and `tokens` split on whitespace/alphanumeric runs. CJK (Chinese/Japanese/Korean) has neither spaces nor ASCII terminators, so a whole CJK paragraph collapsed into **one segment / one token** — it passed through at ~0% compression, and BM25 relevance + salience scored zero terms. This makes `TextCrusher` CJK-aware. CJK-bearing content takes an ICU (`icu_segmenter`, UAX#29 sentence + dictionary word) segmentation path, with a length fallback for terminator-sparse runs, a local BM25 over the ICU word tokens, and ICU-token salience. Dispatch is on **content only**, so pure-ASCII text is byte-identical to before — the shared `BM25Scorer` and the ASCII path are untouched. It also adds a committed, reproducible answer-retention eval (`benchmarks/i18n_compression_eval.py`) with a deterministic zh/ja/ko CI regression gate, so the improvement below is permanently verifiable rather than a one-off measurement. Extends #1171. ## Type of Change - [x] Bug fix (CJK passed through near-uncompressed) - [x] New feature (CJK segmentation / relevance support) - [x] Performance improvement (CJK now compresses; ICU segmenters cached, not rebuilt per call) ## Changes Made - `is_cjk` predicate gates a CJK path (ideographs, kana, Hangul, CJK punctuation, full/half-width forms). - `split_segments` → ICU `SentenceSegmenter` for CJK + a mandatory length fallback (whitespace / CJK punctuation / hard cap) for terminator-sparse runs; ASCII path unchanged. - `tokens` → ICU `WordSegmenter` (dictionary) for CJK; ASCII path unchanged. - `relevance_cjk`: a local BM25 over ICU word tokens — the shared ASCII `BM25Scorer` scores zero terms for CJK and is parity-locked, so this is an intentional separate scorer (documented in code). - CJK salience uses ICU tokens (whitespace-split gave one giant "word" → zero salience). - `count_tokens`: CJK-aware so `compression_ratio` isn't nonsense for space-free text. - ICU segmenters resolved once in `static LazyLock` (compiled_data is static) instead of rebuilt per call. - New dep `icu_segmenter` 2.2, `compiled_data` only (see Dependency below). - `benchmarks/i18n_compression_eval.py` + `tests/test_transforms/test_text_crusher_cjk_eval.py`: a zh/ja/ko answer-retention eval — a deterministic needle CI gate (always-runs, no external data), real-transcript fidelity with CJK-aware salient, and optional `multi-wiki-qa` natural-data retention (loaded via the `[evals]` `datasets` extra, skipped if absent; data never vendored — CC-BY-NC-SA). ## Testing - [x] Unit tests pass (`pytest` + `cargo test`) - [x] Linting passes (`ruff check`/`format` on the new eval + test — clean) - [ ] Type checking passes (`mypy headroom`) — N/A, the only Python added is a benchmark + test, not `headroom/` source - [x] New tests added for new functionality - [x] Manual testing performed (see Real Behavior Proof) ### Test Output ```text $ cargo test -p headroom-core --lib text_crusher running 12 tests test result: ok. 12 passed; 0 failed; 0 ignored; 0 measured; 841 filtered out $ .venv/bin/python -m pytest tests/test_transforms/test_text_crusher*.py 15 passed $ .venv/bin/python -m pytest tests/test_transforms/test_text_crusher_cjk_eval.py 6 passed # deterministic zh/ja/ko needle CI gate $ cargo clippy -p headroom-core && ruff check benchmarks/i18n_compression_eval.py # both clean ``` ## Real Behavior Proof - Environment: macOS (Darwin 25.3.0), Python in a uv venv, `headroom-core` built via `uv pip install -e .` (maturin), branch `feat/cjk-text-compression`. - Exact command / steps: built `_core`, then ran a mixed Chinese+Japanese doc (no spaces, `。` terminators) through `TextCrusher().compress(doc, "认证令牌缓存策略", 0.3)`; separately evaluated answer-retention on the public CMRC2018 Chinese QA dev set (bury the gold-answer paragraph among 25 distractors, query = the question, compress to 30%, check the gold answer survives), and end-to-end through `ContentRouter`. - Observed result: a mixed Chinese+Japanese doc compressed 189 → 78 tokens (ratio 0.41, kept 3/8 segments) with the query-relevant sentence surviving — before this change the same doc was a single segment → 100% passthrough. On the public CMRC2018 Chinese QA dev set, answer-retention under 30% compression rose 34% → 93% (multiple seeds). End-to-end through `ContentRouter` on real CJK content, aggregate savings rose 16% → 40%. Pure-ASCII (English) output stayed byte-identical (the English parity fixtures did not move). Demo terminal output: ```text ORIGINAL tokens= 189 chars=189 COMPRESS tokens= 78 ratio=0.41 segments kept 3/8 QUERY-RELEVANT sentence survived: True --- compressed output (verbatim kept CJK sentences) --- 认证令牌的缓存策略采用最近最少使用淘汰算法来管理过期条目。 请求重试使用指数退避并设置最大次数上限。 数据备份每天凌晨执行并保留最近三十天的快照。 ``` The committed eval now demonstrates this across all three CJK languages. The deterministic needle gate (in CI via `tests/test_transforms/test_text_crusher_cjk_eval.py`, 6 passed) has TextCrusher keep the query-relevant needle while truncate/random drop it in zh, ja, and ko. On real `multi-wiki-qa` natural data (n=80/lang), query-aware answer-retention is **zh 74% / ja 70% / ko 50%** vs **25–41%** for the truncate/random baselines: ```text === Part A: multi-wiki-qa answer-retention (n=80/lang, target_ratio=0.3) === lang text_crusher truncate random zh-cn 74% 25% 38% ja 70% 31% 39% ko 50% 26% 41% ``` Korean is measurably weaker (ICU has no Korean dictionary and falls back to UAX#29 word-breaking) — still well above baselines, and scoped as a follow-up. - Not tested: the live proxy HTTP path (validated at the `ContentRouter` / `TextCrusher` layer, not via a running proxy); no-space Korean (standard Korean is space-delimited and is covered); non-CJK SE-Asian scripts (out of scope). ## Dependency (per CONTRIBUTING supply-chain policy) `icu_segmenter` 2.2 (ICU4X), `features = ["compiled_data"]`: - **Why this package (vs. ourselves / existing deps):** CJK needs dictionary/UAX#29 segmentation. A hand-rolled char-bigram scored slightly worse on real data (CMRC2018 answer-retention: 92.5% ICU vs 91% bigram, 4 seeds); jieba/lindera are ZH-only or 13–207 MB dicts. ICU4X covers zh/ja/ko in one crate. The existing `unicode-segmentation` does UAX#29 only (no CJK dictionary), so it can't word-segment space-free CJK. - **Who maintains it:** the official `unicode-org` ICU4X project; active release cadence (2.2 in 2025); no known CVEs. - **Install surface:** ~13 new pure-Rust crates, no build scripts, no native code, no build/runtime network. `compiled_data` bundles locale data at compile time (hermetic). `auto`/`lstm` deliberately NOT enabled — LSTM covers SE-Asian scripts (Thai/Lao), not CJK, and would pull in `libm` for nothing. - **Why this version:** 2.x is the stabilized ICU4X API (1.x used a different data-provider model); floored at 2.2 (Cargo.lock pins the patch) since segmenter boundaries are observable in output and bumps should be deliberate. ## 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 (CHANGELOG) - [x] My changes generate no new warnings (clippy + fmt clean) - [x] I have added tests that prove my feature works - [x] New and existing unit tests pass locally with my changes - [x] I have updated the CHANGELOG.md ## Additional Notes - **Parity:** the shared `BM25Scorer` (byte-exact parity-locked with `headroom/relevance/bm25.py`) is untouched. `relevance_cjk` is a separate local scorer because the shared one's tokenizer is ASCII-only. The whole CJK path lives in Rust (`text_crusher.py` is a thin wrapper over `_core`), so there is no Python mirror to keep in sync; the parity fixtures stay green (only the CJK `unicode` fixture was re-recorded, intentionally; English fixtures unchanged). - **Known by-design gap (not a bug):** CJK content + a pure-ASCII query yields no token overlap, so relevance falls back to recency + salience (cross-script query matching is unsupported). - The Python added is a benchmark (`benchmarks/i18n_compression_eval.py`) plus its test, not `headroom/` runtime source — both are `ruff`-clean; `mypy headroom` is unaffected. - **License:** the optional Part A pulls `alexandrainst/multi-wiki-qa` (CC-BY-NC-SA-4.0) at run time via the `[evals]` extra and is skipped if absent — the dataset is never vendored into the repo, and the always-run CI gate (Part C) uses only our own deterministic data. 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
mstattma
|
3757a7cef3
|
fix(core): avoid unidiff panic on bash xtrace (#1506)
## Summary
- preflight unified diff inputs before calling the Rust unidiff parser
- catch parser panics so malformed-but-diff-looking input falls back to
non-diff
- add regressions for Bash xtrace lines like `+++ test.sh` and `+++
dirname test.sh`
## Repro
`detect_content_type("+++ test.sh")` could panic through the Rust
detector because unidiff treated the lone `+++` line as a target header
without a preceding source header.
## Tests
- `cargo fmt --all --check`
- `cargo test -p headroom-core --lib
transforms::unidiff_detector::tests`
- `cargo test -p headroom-core --lib`
Co-authored-by: Michael Stattmann <mstattma@users.noreply.github.com>
Co-authored-by: JerrettDavis <mxjerrett@gmail.com>
|
||
|
Ashish
|
6469fcd018
|
feat(transforms): language-aware stack-trace collapse for Go/Rust/.NET/Java/Node (#1791)
## Description
Stack-trace handling covered only Python tracebacks and a generic ` at
symbol(` pattern. Go panics and Rust panics flowed to prose compression;
.NET traces were unrecognized; Java chained exceptions split into
separate traces at every `Caused by:` (so later chain heads fell off the
`max_stack_traces` cliff); and oversized traces were blindly
head-truncated — keeping runtime scheduler noise while dropping the app
frames and chain heads an agent actually needs.
This PR adds language-aware trace flavors (Go, Rust, .NET, Java chains,
Node async) to the Rust core and both Python mirrors, and replaces blind
truncation with a runtime-frame collapse: message lines, chain heads,
the trace head, and app-code frames survive; contiguous runtime/stdlib
frames fold into `[... N frames collapsed]` markers. A 147-line Go panic
dump compresses to 19 lines with the panic message, signal line, and app
frame intact.
Note one intentional behavior change: now that Go/Rust panics are
*detected*, panics ≤8KB in tool outputs gain the existing error-output
protection (`protect_error_outputs`) they previously missed — small
panics stay verbatim, exactly like small Python tracebacks already do.
## Type of Change
- [x] New feature (non-breaking change which adds functionality)
- [ ] Bug fix (non-breaking change which fixes an issue)
- [ ] Breaking change (fix or feature that would cause existing
functionality to not work as expected)
- [ ] Documentation update
- [ ] Performance improvement
- [ ] Code refactoring
## Changes Made
- `crates/headroom-core/src/transforms/log_compressor.rs`:
- New `TraceFlavor::GoPanic` (`panic:` / `fatal error:` / `goroutine N
[state]:` openers, tab-indented `.go:` frame lines, `created by` /
call-line continuation, blank-separated goroutine blocks) and
`TraceFlavor::DotNet` (`Unhandled exception.`, `at … ) in file:line N`
frames — checked before Java since those frames also satisfy the Java
shape — plus `--->` inner-exception heads and `--- End of` separators).
- Renamed the misnamed `Go` flavor to `RustBacktrace` (its `is_go_frame`
matched `N: 0x<hex>` — the Rust backtrace shape) and gave it real
openers (`thread '…' panicked at`, `stack backtrace:`); the free-text
panic-message line after the opener stays in the trace (`terminates` now
receives `lines_so_far`).
- Java: continues across `Caused by:` / `Suppressed:` / `... N more`,
and `is_java_at_frame` admits `/` so JPMS module frames (`at
java.base/…`) pass the opener re-check — without this, modern JDK traces
fragmented at the parse cap into ≤20-line groups.
- Frame collapse (`collapse_trace_frames`): for traces over
`stack_trace_max_lines`, keeps message/chain-head lines, first
`trace_head_frames` frames, up to `trace_app_frames` app frames; runtime
frames (prefix + path marker tables per language) fold into `[... N
frames collapsed]` markers that occupy the run's first line slot and
carry score 0.8 so the global cap doesn't drop them first. Collapsed
frame indices are excluded from the context-line pass (otherwise ±3
context re-added them), and the parse cap re-opens on continuation lines
so selection sees one contiguous trace. New config:
`collapse_runtime_frames=true`, `trace_head_frames=3`,
`trace_app_frames=5`; new sidecar stat `runtime_frames_collapsed`.
- `crates/headroom-py/src/lib.rs`: the three new knobs on the
`LogCompressorConfig` PyO3 signature.
- `headroom/transforms/log_compressor.py`: dataclass fields +
constructor pass-through; `_parse_lines` opener patterns mirrored per
the documented contract.
- `headroom/transforms/content_detector.py`: `_LOG_PATTERNS` additions
(Go panic/goroutine/frame lines, Rust panic/backtrace/numbered frames,
.NET, Java chain heads, Node `at async`); JS/Java `at` pattern admits
JPMS module paths.
- `tests/test_transforms_stack_traces.py` (new, 10 tests) + 7 new Rust
unit tests (flavor open/continue/terminate, chain grouping, collapse
keeps chain heads/app frames, collapse-off comparison, small traces
untouched).
## Testing
- [x] Added new tests for the changes
- [x] All existing tests pass
### Test Output
```
$ cargo test -p headroom-core
928 passed; 3 ignored
$ python -m pytest tests/test_transforms_stack_traces.py tests/test_log_compressor.py \
tests/test_transforms_log_compressor.py tests/test_transforms_content_detection.py \
tests/test_transforms_content_router.py tests/test_transforms/test_content_router.py \
tests/test_lossless_mode.py tests/test_compression_fidelity_regression.py -q
191 passed
```
## Real Behavior Proof
- Environment: macOS arm64, Python 3.13, repo main @
|
||
|
Matthew Jackson
|
cdba2eccdd
|
feat(core): gate ONNX transforms behind a default-on ml feature (static/lexical builds) (#2165)
## Description `TextCrusher` and the BM25 relevance path can run without the ONNX-backed ML stack, but `headroom-core` previously compiled `ort`, `fastembed`, and `magika` unconditionally. This made lexical-only downstream consumers carry the ONNX Runtime dependency even when they never used embedding relevance or Magika detection. This PR makes those ML crates optional behind a new default-on `ml` Cargo feature. Default builds keep the existing ML-backed behavior. Consumers that only need lexical compression can opt out with `default-features = false`; in that mode the ML modules are compiled out and the relevance path falls back to BM25. ## 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 - `crates/headroom-core/Cargo.toml`: marks `ort`, `fastembed`, and `magika` optional; adds default-on `ml = ["dep:ort", "dep:fastembed", "dep:magika"]`. - `crates/headroom-core/src/lib.rs`: gates the shared ONNX CPU helper behind `ml`. - `crates/headroom-core/src/relevance/embedding.rs`: gates the fastembed implementation behind `ml` and provides a no-ml stub with the same scorer surface so `HybridScorer` naturally falls back to BM25. - `crates/headroom-core/src/transforms/detection.rs`: gates the Magika tier behind `ml`; no-ml builds start at the existing unidiff/plain-text fallback tiers. - `crates/headroom-core/src/transforms/mod.rs`: gates the Magika module and re-exports behind `ml`. ## Testing - [x] Default build compiles (`cargo build -p headroom-core`) - [x] Lexical-only build compiles (`cargo build -p headroom-core --no-default-features`) - [x] Default tests pass (`cargo test -p headroom-core`) - [x] Lexical-only tests pass (`cargo test -p headroom-core --no-default-features`) - [x] Dependency tree checked for no-ml build (`cargo tree -p headroom-core --no-default-features` contains no `fastembed`, `magika`, or `ort` packages) - [ ] Manual testing performed ## Real Behavior Proof - Environment: Windows 11 review worktree, Rust/Cargo workspace. - Exact command / steps: - `cargo build -p headroom-core` - `cargo build -p headroom-core --no-default-features` - `cargo test -p headroom-core` - `cargo test -p headroom-core --no-default-features` - `cargo tree -p headroom-core --no-default-features` - Observed result: both feature configurations build and test cleanly. The no-default dependency tree does not include `fastembed`, `magika`, or `ort`, while the default build still compiles the ML path. - Not tested: model-backed `RUN_FASTEMBED_TESTS=1` cases that require downloading the embedding model; those remain env-gated as before. ## 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 - [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 The no-ml build intentionally degrades embedding relevance to the existing unavailable-model behavior, so `HybridScorer` takes its BM25 fallback path. Magika detection is skipped when `ml` is disabled; detection then proceeds through unidiff and plain-text fallback tiers. --------- Co-authored-by: Matthew Jackson <mattjackson86@gmail.com> Co-authored-by: JerrettDavis <mxjerrett@gmail.com> |
||
|
Zhenjia ZHOU
|
528517cff8
|
fix(diff-compressor): CJK-aware relevance scoring for hunk selection (#2220)
## Description `score_hunks` boosts diff hunks whose content overlaps the query/context (+`SCORE_CONTEXT_WORD_WEIGHT` per match); the resulting score decides which hunks survive when `max_hunks_per_file` fires. It split the context on whitespace, so a spaceless CJK query became one blob that only matched a hunk containing the whole query verbatim — relevant hunks weren't boosted and got dropped. This adds CJK character bigrams to the query match set so a CJK query boosts the hunks it overlaps. Rust-only (`diff_compressor.py` is a thin shim over Rust; hunk scoring lives only in Rust). CJK-gated: for a pure-ASCII query `cjk_bigrams` returns an empty set and the new loop is a no-op, so non-CJK scoring is byte-identical and the 20 diff parity fixtures stay green. ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) ## Changes Made - `crates/headroom-core/src/transforms/diff_compressor.rs`: add `is_cjk_char` + `cjk_bigrams`, and a separate loop in `score_hunks` that boosts hunks containing each CJK query bigram. The existing ASCII word loop is untouched. - Rust unit test (`cjk_bigrams` extraction) + an end-to-end test (a CJK query promotes the overlapping hunk into the kept set; the no-query baseline drops it). ## Testing - [x] Unit tests pass (`cargo test`) - [x] Linting passes (`cargo clippy` / `cargo fmt`) - [x] New tests added for new functionality - [x] Manual testing performed (see Real Behavior Proof) ### Test Output ```text $ cargo test -p headroom-core --lib diff_compressor test result: ok. 23 passed; 0 failed $ cargo clippy -p headroom-core # clean ``` ## Real Behavior Proof - Environment: macOS (Darwin), Rust via cargo, branch `feat/diff-compressor-cjk` off `main`. - Exact command / steps: `cargo test -p headroom-core --lib diff_compressor` — the `cjk_query_boosts_matching_hunk_into_kept_set` test builds a diff with 4 hunks (first / plain / cjk / last), `max_hunks_per_file = 3` (one contested middle slot between the plain hunk at change-density `0.12` and the CJK hunk at `0.06`), and compresses it once with the CJK context `数据库连接超时排查` and once with no query. - Observed result: with no query the higher-density plain hunk takes the slot (the CJK hunk `数据库连接失败重试` is dropped); with the CJK context its bigrams (`数据` / `据库` / `库连` / `连接`) match → score `0.06 + 4×0.2 = 0.86` beats the plain hunk's `0.12` → the CJK hunk survives. Both directions are asserted; before this change the spaceless CJK query matched neither hunk and the CJK hunk was always dropped. - Not tested: the Python side — `diff_compressor.py` is a thin shim that delegates `compress()` straight to Rust, so hunk scoring has no Python twin; and no new parity fixtures were recorded, since the 20 existing diff fixtures contain no CJK and therefore stay byte-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 - [ ] I have made corresponding changes to the documentation — N/A (internal scoring) - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective - [x] New and existing unit tests pass locally with my changes - [ ] I have updated the CHANGELOG.md — N/A: internal relevance-scoring fix, no user-facing surface change ## Additional Notes - Completes the relevance-scorer CJK sweep across the compressors (search, adaptive sizer, the shared BM25 tokenizer, and now diff). Rust-only — no Python parity mirror is needed because diff hunk scoring has no Python twin (the shim delegates `compress()` straight to Rust). |
||
|
Zhenjia ZHOU
|
5de12f75e3
|
docs(ccr): correct stale 5-minute TTL hints to 30 minutes (#2224)
## Description The CCR store default TTL is `DEFAULT_TTL = 1800s` (30 minutes — see `crates/headroom-core/src/ccr/mod.rs` and `config.py store_ttl_seconds=1800`), but several user-facing hints and docstrings still said "5 minutes", the old default. The opencode/openclaw retrieve tools surfaced `(default TTL: 5 minutes)` in their expiry hint — exactly the misleading message reported in #1023. (The CCR cache itself works; the row-drop store bridge that populates the retrieve store landed for #389.) This corrects the two plugin hints, the `InMemoryCcrStore` docstrings, the SQLite/backend default TTL comments, and the `smart_crusher` mirror comment. The `mod.rs` comment that references "the *old* 5-minute default" is intentionally left unchanged — it correctly describes history. ## Type of Change - [x] Documentation update ## Changes Made - `plugins/openclaw/src/tools/headroom-retrieve.ts` + `plugins/opencode/src/retrieve.ts`: retrieve-failure hint `5 minutes` → `30 minutes`. - `crates/headroom-core/src/ccr/backends/in_memory.rs`: two docstrings (`5 minutes by default`, `5-minute TTL`) → `30 minutes` / `30-minute`. - `crates/headroom-core/src/ccr/backends/mod.rs` + `sqlite.rs`: SQLite/default backend TTL comments `5-minute` → `30-minute`. - `headroom/transforms/smart_crusher.py`: mirror comment `defaults to 5 minutes` → `30 minutes`. ## Testing - [x] Linting passes (`ruff` / `cargo check`) - [x] Manual verification (see Real Behavior Proof) ### Test Output ```text $ ruff format --check headroom/transforms/smart_crusher.py # clean $ cargo check -p headroom-core # Finished, no errors ``` ## Real Behavior Proof - Environment: macOS (Darwin), branch `feat/ccr-ttl-hint-fix` off `main`. - Exact command / steps: grepped every `5 minutes` / `5-minute` TTL reference across the repo; confirmed the real default is `DEFAULT_TTL = Duration::from_secs(1800)` (`ccr/mod.rs:66`), that `InMemoryCcrStore::new()` uses `DEFAULT_TTL` (not a local 300s), and that `config.py` sets `store_ttl_seconds = 1800 # 30 minutes`. - Observed result: all stale CCR default-TTL "5 minutes" references now read "30 minutes"; the one historical reference (`mod.rs`: "the old 5-minute default") is left as-is because it is accurate. - Not tested: nothing runtime changed — these are docstring/comment/hint string edits only, so there is no behavior to exercise. ## 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 - [ ] I have commented my code — N/A (this PR is comments/strings) - [x] I have made corresponding changes to the documentation (this *is* the doc change) - [x] My changes generate no new warnings - [ ] I have added tests — N/A (no behavior change) - [x] New and existing unit tests pass locally with my changes - [ ] I have updated the CHANGELOG.md — N/A: user-facing hint/docstring correction, no functional change ## Additional Notes - Surfaced while root-causing #1023: the "cache permanently empty / TTL: 5 minutes" report is resolved on `main` (the store-bridge for #389 populates the retrieve store), but the stale "5 minutes" strings the reporter actually saw were still in the tree. This PR fixes those. --------- Co-authored-by: JerrettDavis <mxjerrett@gmail.com> |
||
|
Doyeon Baek
|
36577d9547
|
fix(search_compressor): don't let a date in a path hijack the line-number parse (#2084)
## Description
`SearchCompressor::parse_match_line` splits a grep/ripgrep line into
`(file, line_number, content)` by finding the **leftmost**
`<sep><digits><sep>` triplet, where `<sep>` is `:` or `-`. A path
segment that itself contains such a triplet hijacks the parse — and that
shape is everyday, not exotic:
| real ripgrep line | parsed as |
|---|---|
| `logs/2026-05-03/app.log:12:ERROR boom` | `("logs/2026", 5,
"03/app.log:12:ERROR boom")` |
| `advisories/CVE-2021-44228.md:8:Log4Shell` | `("advisories/CVE", 2021,
"44228.md:8:Log4Shell")` |
| `src/v1-2-beta/mod.rs:3:fn x()` | `("src/v1", 2, "beta/mod.rs:3:fn
x()")` |
| `migrations/20240101-002-add_users.sql-9-…` | `("migrations/20240101",
2, "add_users.sql-9-…")` |
**This is silent corruption, not a drop.** The parse *succeeds*, so the
line is never counted in `stats.lines_unparsed` and never falls back to
passthrough. The bogus path becomes the **grouping key** in
`parse_search_results`, so unrelated files collapse into one bucket, and
the bogus path + line number + mangled body are what get scored, capped,
and rendered into the compressed output handed to the model. **The LLM
is shown a file and a line that do not exist.**
## Type of Change
- [x] Bug fix (non-breaking change that fixes an issue)
## Changes Made
One file, one function:
`crates/headroom-core/src/transforms/search_compressor.rs`.
`parse_match_line` becomes a 3-tier scan:
- **Colon tier** — leftmost `:\d+:` whose path part contains no
whitespace. `:` is grep's *match* separator and a path practically never
contains one (the Windows drive colon is already skipped by the existing
`scan_start` logic), so leftmost is right. The whitespace bound stops a
`foo.rs:12:` reference *inside the body* of a `-` context line from
hijacking the parse.
- **Dash tier** — **last** `-\d+-` whose path part contains no
whitespace. `-` is grep's *context* separator, and unlike `:` it
genuinely appears inside real paths (`2026-05-03`, `CVE-2021-44228`,
`20240101-002-…`), so the marker is the *last* triplet in the path
token, not the first.
- **Permissive tier** — the original leftmost-any rule, byte-for-byte
unchanged. Only reached when neither typed tier matched (e.g. a path
containing a space), so those lines behave exactly as before.
- Also tightened in the typed tiers: the closing separator must equal
the opening one — grep emits `file:12:body` or `file-12-body`, never a
mix.
- Added 4 tests: 2 reproducing the bug, 2 regression guards against the
naive fixes.
**Safety argument (verified by execution):** with `parse_match_line`
temporarily forced to the Permissive tier alone, all 18 pre-existing
`search_compressor` tests still pass — i.e. the fallback is a faithful
reproduction of today's rule, so the change can only *add* correct
parses on lines a typed tier claims, never remove one.
This is the next bug in a family the module already tracks: the doc has
a "Bug fixes vs Python" section and three `fixed_in_3e2_*` tests
hardening this same parser against Windows drive colons and dashes in
filenames. `pre-commit-config.yaml-42-…` (dash before a *non*-digit) is
covered; `2026-05-03` (dash before a digit run followed by another dash)
was not.
## Testing
- [x] Unit tests pass
- [x] Linting passes (`cargo clippy -p headroom-core --all-targets` → 0
warnings)
- [x] Formatting passes (`cargo fmt --all -- --check`)
- [x] New tests added (4: 2 reproducing the bug, 2 regression guards
against naive fixes)
- [x] Manual testing performed (see Real Behavior Proof)
### Test Output
**Before the fix** (new tests run against the unmodified scan rule):
```text
$ cargo test -p headroom-core --lib search_compressor
---- transforms::search_compressor::tests::date_stamped_path_is_not_misread_as_line_number_marker stdout ----
assertion `left == right` failed
left: Some(("logs/2026", 5, "03/app.log:12:ERROR boom"))
right: Some(("logs/2026-05-03/app.log", 12, "ERROR boom"))
---- transforms::search_compressor::tests::date_stamped_paths_are_not_collapsed_into_one_bogus_file stdout ----
assertion `left == right` failed
left: ["logs/2026"]
right: ["logs/2026-05-03/app.log", "logs/2026-05-04/app.log"]
test result: FAILED. 18 passed; 2 failed; 0 ignored
```
**After the fix:**
```text
$ cargo test -p headroom-core --lib search_compressor
test result: ok. 20 passed; 0 failed; 0 ignored; 835 filtered out
$ cargo test -p headroom-core --lib # whole crate — no regressions
test result: ok. 854 passed; 0 failed; 1 ignored
$ cargo test -p headroom-parity
test result: ok. 4 passed; 0 failed
$ cargo fmt --all -- --check -> OK
$ cargo clippy -p headroom-core --all-targets -> 0 warnings, 0 errors
```
Regression guards added for the two ways a naive fix breaks:
- `digit_terminated_path_still_parses_ripgrep_context_line` —
`logs/app.log.1-42-rotated line` (path ends in a digit, so the context
separator is digit-preceded).
- `body_line_reference_does_not_hijack_a_context_line` —
`src/main.py-44-see foo.rs:12:bar` (body quotes a `file:line:`
reference).
## Real Behavior Proof
Per CONTRIBUTING — unit tests alone don't prove user-visible behavior,
so this was reproduced against the **released build** (`headroom-ai`
0.26.0 from PyPI, the compiled `_core.abi3.so`), driving the **public
`SearchCompressor.compress()` API** on **real `rg` output over real
files on disk** — not fixtures or mocks.
- Environment: macOS (Darwin 25.5.0, arm64), Python 3.13, released
`headroom-ai` 0.26.0 (`site-packages/headroom/_core.abi3.so`); patched
build = this branch compiled with `cargo build --release -p
headroom-py`, rustc 1.96.0.
- Exact command / steps: created 20 real log files at
`logs/2026-05-01/app.log` … `logs/2026-05-20/app.log` (12 real `ERROR`
lines each); ran `rg -n ERROR logs > rg_big.txt` (240 real match lines);
then called
`SearchCompressor(SearchCompressorConfig()).compress(open("rg_big.txt").read())`
on the shipped 0.26.0 build and on the patched build, comparing
`files_affected`, the rendered output, and whether each referenced path
exists on disk.
- Observed result: on shipped 0.26.0, the 20 distinct real files
collapse into **1 bogus bucket** `logs/2026` (a path that does **not**
exist on disk), per-line paths are mangled to
`logs/2026:5:01/app.log:10:`, 19 of 20 files effectively vanish from the
output, and `lines_unparsed: 0` means **nothing signals the
corruption**. On the patched build, same input and same API:
`files_affected: 20` (matches reality), every path in the compressed
output exists on disk (`all_exist=True`), and per-file match counts and
line numbers are correct.
- Not tested: the end-to-end proxy path (`headroom-proxy` against a live
LLM provider) — I exercised the `SearchCompressor` public API directly,
which is the surface `SearchOffload` and the MCP `headroom_compress`
tool wrap. I also did not test Windows path behavior on an actual
Windows host (the existing `scan_start` drive-letter logic is untouched,
and its tests still pass).
**Observed on the SHIPPED 0.26.0 build (the bug, in the released
product):**
```text
SHIPPED headroom 0.26.0 | real `rg -n ERROR logs` output, 240 lines
lines_unparsed : 0 <-- corruption is SILENT: nothing reported as unparsed
original_match_count: 240
files_affected : 1 <-- 20 distinct real files collapsed into ONE bucket
=== compressed output actually handed to the model ===
logs/2026:5:01/app.log:10:ERROR failure 1 connection refused upstream timeout on 2026-05-01 ...
logs/2026:5:20/app.log:21:ERROR failure 12 connection refused upstream timeout on 2026-05-20 ...
logs/2026:5:01/app.log:11:ERROR failure 2 connection refused upstream timeout on 2026-05-01 ...
[... and 235 more matches in logs/2026]
[240 matches compressed to 5. Retrieve more: hash=39c894009014d42b856ddd8a]
=== do the file paths in that output exist on disk? ===
logs/2026 exists_on_disk=False
```
**Observed on the PATCHED build (same input, same API, only the patch
differs):**
```text
PATCHED headroom-core | same real `rg` output, 240 lines
lines_unparsed : 0
original_match_count: 240
files_affected : 20 <-- was 1 (bogus) on the shipped build
=== compressed output handed to the model ===
logs/2026-05-01/app.log:10:ERROR failure 1 connection refused upstream timeout on 2026-05-01 ...
logs/2026-05-01/app.log:11:ERROR failure 2 connection refused upstream timeout on 2026-05-01 ...
[... and 7 more matches in logs/2026-05-01/app.log]
logs/2026-05-02/app.log:10:ERROR failure 1 connection refused upstream timeout on 2026-05-02 ...
=== do the file paths in that output exist on disk? ===
logs/2026-05-01/app.log exists_on_disk=True
logs/2026-05-02/app.log exists_on_disk=True
...all distinct paths referenced, all_exist=True
```
## 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] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective
- [x] New and existing unit tests pass locally with my changes
## Additional Notes
**Known residual ambiguity (stating it rather than hiding it).** grep
output is inherently ambiguous — `logs/2026-05-03/x:12:y` *could*
legitimately be a file literally named `logs/2026` with context line 5.
The tiers pick the overwhelmingly more likely reading. Two contrived
cases still parse the old way, both preserved deliberately:
1. a path containing a whitespace character;
2. a `-`-context line whose body is a whitespace-free token containing
its own `-N-` triplet.
If you'd prefer a different disambiguation policy (e.g. only trusting
`:` and treating all `-` context lines as unparseable, or gating on
filesystem existence), I'm happy to rework — the tiering is deliberately
isolated to one function so the policy is easy to swap.
N/A checklist items: no documentation or CHANGELOG change (internal
parser fix, no public API or behavior contract change); no screenshots
(no UI surface).
---------
Signed-off-by: dosthcpp <drakedog19@gmail.com>
Co-authored-by: JerrettDavis <mxjerrett@gmail.com>
Co-authored-by: Tejas Chopra <chopratejas@gmail.com>
|
||
|
Parideboy
|
c46cd8f950
|
fix(core): load ONNX Runtime dynamically so headroom._core imports on non-AVX2 x86-64 (#1715)
## Description
`import headroom._core` dies with SIGILL (`Illegal instruction`) on
x86-64 CPUs without AVX2 (Pentium N4200, Celeron N4500, AMD FX 8350 —
all reported on the issue). The repo sets no `RUSTFLAGS`/`target-cpu`
anywhere, so first-party Rust code is baseline x86-64; the AVX2 code
comes from Microsoft's prebuilt ONNX Runtime, statically linked into the
extension by fastembed's `ort-download-binaries-rustls-tls` feature on
non-Windows targets. Because it is statically linked, its code is mapped
and initialized when the extension module loads — **before** the runtime
AVX2 guard from #1162 can run, which is why that fix helped Magika init
but not the import-time crash.
Fix, mirroring what Windows already does for its own reasons (DirectML
link libs): build with `ort-load-dynamic` on every platform, so ONNX
Runtime is only `dlopen`'d at first use, where the #1162 AVX2 guard
falls back to the non-ONNX detection tiers on unsupported CPUs. Since
both target blocks became identical, they are collapsed into one
platform-independent `fastembed` dependency.
To keep Magika/fastembed working out of the box on Linux/macOS, the
existing `ORT_DYLIB_PATH` auto-pin (`headroom/_ort.py`, previously
Windows-only) now resolves the pip `onnxruntime` package's shared
library on all platforms (`onnxruntime.dll` / `libonnxruntime.so*` /
`libonnxruntime*.dylib`). The pip `onnxruntime` CPU wheels use runtime
CPU dispatch, so they also work on pre-AVX2 machines — non-AVX2 users
get working ML detection instead of a crash. Without the `onnxruntime`
package, ML detection degrades gracefully to the non-ONNX tiers exactly
as it already does on Windows.
Fixes #1278
## 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
- `crates/headroom-core/Cargo.toml`: replaced the per-target `fastembed`
blocks (`ort-download-binaries-rustls-tls` on non-Windows,
`ort-load-dynamic` on Windows) with a single platform-independent
dependency on `ort-load-dynamic`, with a comment documenting both the
DirectML and the AVX2/#1278 rationale.
- `Cargo.lock`: regenerated — `ort-sys` drops its static-download
dependencies (`hmac-sha256`, `lzma-rust2`, `ureq`); no version bumps.
- `headroom/_ort.py`: `ORT_DYLIB_PATH` auto-pin extended from
Windows-only to all platforms via a small `_find_dylib` helper that
resolves the platform's shared-library name inside the pip `onnxruntime`
package.
- `tests/test_transforms/test_ort_dylib.py`: replaced the obsolete
`test_noop_on_non_windows` with Linux (versioned `.so`) and macOS
(`.dylib`) pin tests; module docstring updated.
- `docs/content/docs/configuration.mdx`: `ORT_DYLIB_PATH` row updated
from Windows-only wording to the cross-platform behavior.
## 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
$ cargo fmt --all -- --check && cargo clippy --workspace -- -D warnings && cargo test -p headroom-core --lib
clean
test result: 844 passed; 0 failed; 1 ignored
$ python -m pytest tests/test_transforms/test_ort_dylib.py -q
8 passed
$ ruff check headroom/_ort.py tests/test_transforms/test_ort_dylib.py
All checks passed!
```
## Real Behavior Proof
- Environment: Windows 11 (AVX2-capable — the SIGILL itself is not
reproducible on this machine), Python 3.13, Rust 1.95.0, local checkout
branched from `upstream/main` (
|
||
|
JD Davis
|
2c9eb7c5f1
|
feat(simulators): add provider simulator service (#2014)
## Description
Adds a Rust-only `headroom-simulators` workspace crate: a deterministic
local upstream simulator service for Headroom proxy and pipeline
validation. It supplies configurable stubs plus bottled provider-shaped
responses for supported provider/path surfaces without calling real
LLMs.
## Type of Change
- [x] 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)
- [x] Documentation update
- [ ] Performance improvement
- [ ] Code refactoring (no functional changes)
## Changes Made
- Added `crates/headroom-simulators` Rust crate with library and
`headroom-simulators` binary.
- Added clean domain classification for supported surfaces: Anthropic
`/v1/messages`, OpenAI chat/responses/conversations, Bedrock
invoke/stream routes, Vertex raw/stream predict, health, and generic
fallback.
- Added JSON-configured stub matching by method, path, body substring,
and JSON pointer.
- Added bottled provider-shaped JSON, SSE, and Bedrock EventStream
responses for unconfigured requests.
- Added a container `Dockerfile` and README for local/GitHub Actions
usage.
- Added unit and HTTP integration tests for defaults, configured stubs,
SSE, Vertex, and Bedrock EventStream behavior.
- Added proxy-level simulator-backed E2E tests that run Headroom against
the simulator across Anthropic, OpenAI Chat, OpenAI Responses, OpenAI
Conversations, Bedrock invoke/converse/streaming, Vertex raw/stream
predict, and upstream health.
- Added simulator-backed provider error-path E2E coverage for OpenAI
429, Anthropic 529, Bedrock 502, and Vertex 503 responses flowing
through Headroom unchanged.
- Added Headroom-owned preflight error E2E coverage proving Bedrock
missing credentials and invalid Vertex envelopes stop inside the proxy
instead of silently falling through to the simulator/provider.
- Fixed direct Rust `headroom-core` binaries/tests on Windows so Magika
initializes ONNX Runtime via `ort::init_from` from an explicit pip
`onnxruntime` library path, with fail-fast fallback only when no safe
runtime is discoverable.
- Added a Rust CI `simulator-e2e` matrix for `ubuntu-latest`,
`macos-latest`, and `windows-latest` that runs `cargo test -p
headroom-proxy --test e2e_simulators`.
- Gated dynamic Magika `Path`/`PathBuf` imports to Windows and x86_64
macOS so Linux clippy does not see unused dynamic-ORT-only imports.
## Testing
- [ ] Unit tests pass (`pytest`)
- [ ] Linting passes (`ruff check .`)
- [ ] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed
### Test Output
cargo fmt --all -- --check
# passed
cargo clippy --workspace -- -D warnings
# passed
$env:ORT_DYLIB_PATH=$null
cargo test -p headroom-core transforms::magika_detector::tests:: --lib
# 17 passed, 0 failed; Magika initialized from discovered pip
onnxruntime DLL
$env:ORT_DYLIB_PATH=$null
cargo test --workspace
# passed
gitleaks protect --staged --no-banner --redact
# no leaks found
gitleaks git --log-opts="headroomlabs/main..HEAD" --no-banner --redact
# 5 commits scanned; no leaks found
## Real Behavior Proof
- **Environment:** Windows PowerShell, Rust toolchain `1.95.0`, clean
worktree from `headroomlabs/main` at `
|
||
|
dependabot[bot]
|
6c705b4066
|
deps: bump toml from 0.8.23 to 1.1.2+spec-1.1.0 (#1517)
Bumps [toml](https://github.com/toml-rs/toml) from 0.8.23 to 1.1.2+spec-1.1.0. <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
Zhenjia ZHOU
|
8879c50dbe
|
fix(adaptive-sizer): char bigrams for spaceless CJK items (#1748)
## Description `compute_unique_bigram_curve` — the adaptive sizer's coverage-curve builder, mirrored in Rust and Python — word-splits each item on whitespace to form word bigrams. A spaceless CJK item has no whitespace, so it collapsed into one `(whole_string, "")` pseudo-bigram: the coverage curve then grew ~1 per item, the kneedle knee detector found no knee, and CJK lists under-compressed. Spaceless CJK items now use character bigrams, producing a real coverage curve. Mirrored byte-exactly in Rust and Python (identical reference-test curve values). Non-CJK items — anything whitespace-bearing or spaceless-ASCII — are byte-identical to before, so the `smart_crusher` parity fixtures are unchanged. ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) ## Changes Made - `crates/headroom-core/src/transforms/adaptive_sizer.rs` + `headroom/transforms/adaptive_sizer.py`: add `is_cjk_char`/`_is_cjk_char` (identical code-point ranges) and a spaceless-CJK character-bigram branch in `compute_unique_bigram_curve`. - Rust unit tests + `tests/test_adaptive_sizer.py`: CJK curve, single-char CJK, ASCII-unchanged, empty-item — the Rust and Python reference values are identical. ## Testing - [x] Unit tests pass (`cargo test` + `pytest`) - [x] Linting passes (`cargo clippy` / `cargo fmt` / `ruff` / `mypy`) - [x] New tests added for new functionality - [x] Manual testing performed (see Real Behavior Proof) ### Test Output ```text $ cargo test -p headroom-core --lib adaptive_sizer test result: ok. 35 passed; 0 failed $ .venv/bin/python -m pytest tests/test_adaptive_sizer.py 20 passed $ .venv/bin/python -m pytest -k "smart_crusher and parity" 18 passed, 6 skipped # non-CJK fixtures unchanged ``` ## Real Behavior Proof - Environment: macOS (Darwin), Rust via cargo, Python in a uv venv, branch `feat/adaptive-sizer-cjk` off `main`. - Exact command / steps: called `compute_unique_bigram_curve` on a CJK list and on ASCII lists, in both implementations. - Observed result: `compute_unique_bigram_curve(["数据库连接失败", "数据库连接成功"])` returns `[6, 8]` in **both** Rust and Python (before: ~`[1, 2]` — one pseudo-bigram per item, no coverage signal). ASCII curves are unchanged: `["the cat", "the dog", "a fish"]` → `[1, 2, 3]`. The `smart_crusher` parity suite (all-ASCII fixtures) stays green, confirming non-CJK output is byte-identical. - Byte-exact parity: the Rust reference test (`vec![6, 8]`) and the Python test (`[6, 8]`) use the same inputs and the same expected values, so the two implementations are pinned to agree. ## 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 — N/A (internal sizing heuristic) - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective - [x] New and existing unit tests pass locally with my changes - [ ] I have updated the CHANGELOG.md — N/A: internal sizing-heuristic fix, no user-facing surface change ## Additional Notes - This is a parity-locked function (Rust and Python must agree byte-for-byte). The fix is CJK-gated, so non-CJK output is byte-identical and the `smart_crusher` parity fixtures need no re-recording. |
||
|
Zhenjia ZHOU
|
985621d60e
|
fix(search-compressor): CJK-aware relevance + harden Rust/Python parity (#1749)
## Description
The search compressor's relevance scorer (`score_matches`, present in
both the Rust runtime path and the Python legacy mirror) split the query
on whitespace. A spaceless CJK query therefore matched a result line
only when the WHOLE query was a literal substring of that line — partial
overlaps never boosted relevant lines, so correct matches got dropped
when the result set was over budget.
This adds CJK character bigrams to the query match set, so a longer CJK
query boosts lines that share a substring. It also fixes two latent
Rust/Python parity divergences the ASCII-only fixtures had masked:
- **Length filter**: Rust counted word length in BYTES (`w.len()`),
Python in codepoints (`len(w)`), so a CJK word crossed the `> 2`
threshold differently. Rust now uses `chars().count()`.
- **Dedup**: Rust collected words into a `Vec` (no dedup), Python into a
`set`, so a repeated query word double-counted in Rust. Rust now uses a
`BTreeSet`.
Both scorers are byte-exact now; non-CJK output is unchanged (the 53
existing tests and the parity fixtures stay green).
## Type of Change
- [x] Bug fix (non-breaking change that fixes an issue)
## Changes Made
- `crates/headroom-core/src/transforms/search_compressor.rs` +
`headroom/transforms/search_compressor.py`: add
`is_cjk_char`/`_is_cjk_char` and `cjk_bigrams`/`_cjk_bigrams` (identical
ranges + logic), union CJK bigrams into the query match set, and align
the Rust word set to Python (`chars().count()` length, `BTreeSet`
dedup).
- `tests/test_search_compressor_cjk.py` + a Rust unit test: CJK bigram
extraction (same input/expected in both languages) and a CJK query
boosting a partially-overlapping line.
- Corrected a stale `_score_matches` docstring that referenced a
non-existent parity assertion; it now states honestly how the two sides
are pinned (test-equal for word-overlap + CJK bigrams; a few error-boost
keywords still diverge, fixed only Rust-side).
## Testing
- [x] Unit tests pass (`cargo test` + `pytest`)
- [x] Linting passes (`cargo clippy` / `cargo fmt` / `ruff` / `mypy`)
- [x] New tests added for new functionality
- [x] Manual testing performed (see Real Behavior Proof)
### Test Output
```text
$ cargo test -p headroom-core --lib search_compressor
test result: ok. 16 passed; 0 failed
$ .venv/bin/python -m pytest tests/test_search_compressor_cjk.py \
tests/test_transforms_search_compressor.py tests/test_search_compressor.py
55 passed # 2 new CJK tests + 53 existing (no regression)
```
## Real Behavior Proof
- Environment: macOS (Darwin), Rust via cargo, Python in a uv venv
(`_core` rebuilt on this branch), branch `feat/search-compressor-cjk`
off `main`.
- Exact command / steps: scored a CJK content line against a longer CJK
query whose whole form is not a substring of the line.
- Observed result: for content `src/a.py:10:认证令牌已过期需要重新登录` and query
`认证令牌缓存淘汰策略` (the whole query is NOT a substring of the line, but its
bigrams are), the line now scores `> 0` (bigrams 认证 / 证令 / 令牌 match);
before, it scored `0`. An ASCII-only line still scores `0`. All 53
existing search-compressor tests are unchanged. `cjk_bigrams("认证令牌")`
returns `{认证, 证令, 令牌}` in **both** Rust and Python.
## 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 — N/A
(internal relevance scoring)
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective
- [x] New and existing unit tests pass locally with my changes
- [ ] I have updated the CHANGELOG.md — N/A: internal relevance-scoring
fix, no user-facing surface change
## Additional Notes
- The two parity divergences (byte-vs-codepoint length, `Vec`-vs-`set`
dedup) were pre-existing and only reachable with non-ASCII or
repeated-word queries — the all-ASCII fixtures never exercised them.
This PR brings both sides back to byte-exact for the word-overlap +
CJK-bigram scoring. The remaining error-boost keyword divergence is
pre-existing (fixed only Rust-side in the 3e.1 port) and is now
documented in the code rather than glossed over.
|
||
|
Rod Boev
|
be51008c70
|
fix(toin): publish skip compression recommendations (#1782)
## Description TOIN already learns when a tool-output slice should skip compression, but the published recommendation artifact drops that signal. A high full-retrieval row can therefore still publish an ordinary compressor strategy even though TOIN marked it as skip-worthy. This change carries `skip_compression_recommended` into `recommendations.toml`, keeps Rust parsing backward compatible for older files, and makes skip rows publish a skip-oriented strategy hint instead of misleading compressor guidance. Refs #1775 ## 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 - Publishes `skip_compression_recommended` in generated recommendation rows. - Uses retrieval-aware strategy output for rows TOIN already marked as skip-worthy. - Extends the Rust recommendation schema with a backward-compatible default for older TOML files. - Adds focused publish and schema coverage for skip and non-skip rows. ## Testing - [x] Unit tests pass (`uv run pytest tests/test_toin_publish.py -q`) - [x] Linting passes (`uv run ruff check headroom/cli/toin_publish.py headroom/telemetry/toin.py tests/test_toin_publish.py`) - [ ] Type checking passes (`uv run mypy headroom`) - [x] New tests added for new functionality - [ ] Manual testing performed - [ ] I have made corresponding changes to the documentation ### Test Output ```text uv run pytest tests/test_toin_publish.py -q: 8 passed uv run ruff check headroom/cli/toin_publish.py headroom/telemetry/toin.py tests/test_toin_publish.py: passed cargo fmt --all -- --check: passed cargo check -p headroom-core: passed cargo test -p headroom-core --lib transforms::recommendations: 6 passed cargo clippy --workspace -- -D warnings: passed ``` ## Real Behavior Proof - Environment: Windows for Python validation through the headless runner; Rust validation via focused local cargo commands where available. - Exact command / steps: `uv run pytest tests/test_toin_publish.py -q`, `uv run ruff check headroom/cli/toin_publish.py headroom/telemetry/toin.py tests/test_toin_publish.py`, `cargo fmt --all -- --check`, `cargo check -p headroom-core`, `cargo test -p headroom-core --lib transforms::recommendations`, and `cargo clippy --workspace -- -D warnings`. - Observed result: Skip-worthy rows carry `skip_compression_recommended = true` and a skip strategy hint; normal rows carry `false` and preserve their ordinary strategy. - Not tested: Live runtime dispatcher skip behavior and full Rust workspace tests. ## 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 - [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 This PR fixes the published recommendation artifact. Runtime dispatcher enforcement remains a separate follow-up because it needs a dedicated consumer proof matrix. Documentation and changelog are left unchecked because this changes generated recommendation data and Headroom's changelog is generated from conventional commits. |
||
|
Rob Francis
|
32ce99e4b4
|
fix(build): enable Intel macOS pip installs via ort-load-dynamic (#1538)
## Description
Fix `pip install headroom-ai` on Intel Mac (`x86_64-apple-darwin`).
Source installs failed because `ort-sys 2.0.0-rc.12` (transitive via
`fastembed`) does not ship prebuilt ONNX Runtime binaries for that
target, causing maturin/cargo to exit during the wheel build.
This PR mirrors the existing Windows fix: build the Rust core with
`ort-load-dynamic`, pin `ORT_DYLIB_PATH` to the pip `onnxruntime` native
library at import time, and publish Intel macOS wheels from CI.
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
- `crates/headroom-core/Cargo.toml`: use `ort-load-dynamic` for
`x86_64-apple-darwin` instead of `ort-download-binaries-rustls-tls`.
- `headroom/_ort.py`: extend the ORT dylib pin hook to Intel macOS
(`darwin` + `x86_64`), resolving `libonnxruntime*.dylib` from the pip
`onnxruntime` package.
- `.github/workflows/release.yml` and `.github/workflows/rust.yml`: add
`macos-15-intel` / `x86_64-apple-darwin` wheel matrix entries.
- `tests/test_release_workflows.py` and
`tests/test_transforms/test_ort_dylib.py`: update/add coverage for the
new target and dylib pin behavior.
- `README.md`: note that prebuilt wheels are published for Intel macOS.
## Testing
- [x] Unit tests pass (`pytest`)
- [ ] Linting passes (`ruff check .`)
- [ ] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed
### Test Output
```text
$ pytest tests/test_transforms/test_ort_dylib.py \
tests/test_release_workflows.py::test_fastembed_uses_dynamic_ort_on_windows \
tests/test_release_workflows.py::test_build_wheels_matrix_includes_intel_macos_with_dynamic_ort -q
.......................... [100%]
10 passed in 0.18s
$ maturin build --release -o /tmp/headroom-dist
📦 Built wheel for abi3 Python ≥ 3.10 to /tmp/headroom-dist/headroom_ai-0.27.0-cp310-abi3-macosx_10_12_x86_64.whl
$ python3.11 -m venv /tmp/hr-venv && /tmp/hr-venv/bin/pip install .
Successfully built headroom-ai
Successfully installed headroom-ai-0.27.0
$ cd /tmp && /tmp/hr-venv/bin/python -c "import headroom; import headroom._core; print('ok')"
version 0.27.0
_core ok
```
## Real Behavior Proof
- Environment: macOS `x86_64-apple-darwin`, Python 3.11.5, Rust 1.95.0
- Exact command / steps: Reproduced the reported failure with `pip
install headroom-ai` (sdist build dies in `ort-sys` for
`x86_64-apple-darwin`); after this patch ran `maturin build --release`,
then `pip install .` in a clean venv, then `python -c "import
headroom._core"`.
- Observed result: Before fix, cargo/maturin exit 101 on missing ORT
prebuilts; after fix, wheel build succeeds and `headroom._core` imports
cleanly (`version 0.27.0`, `_core ok`).
- Not tested: `macos-15-intel` GitHub Actions wheel matrix row (will be
validated by CI after merge).
## 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
- [ ] 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
- ML features (magika detection, fastembed embeddings) still require
`onnxruntime` at runtime on Intel Mac. Users should install
`headroom-ai[proxy]` or `pip install onnxruntime`; `_ort.py` auto-pins
`ORT_DYLIB_PATH` when that package is present.
- Apple Silicon (`aarch64-apple-darwin`) behavior is unchanged: it
continues to bundle ORT via `ort-download-binaries-rustls-tls`.
- Lint/mypy not re-run locally in this pass; targeted pytest +
maturin/pip install proof covers the changed surface.
---------
Co-authored-by: Bor <you@example.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
||
|
Parideboy
|
728b33088b
|
fix(relevance): gate ONNX embedding backend behind AVX2 to avoid SIGILL (#1723) (#1765)
## Description Fixes the `SIGILL` / Illegal instruction crash in `headroom.compress` on CPUs without AVX2 (Docker / QEMU / older cloud VMs). The precompiled ONNX Runtime binary shipped by `ort-sys` (via fastembed's `ort-download-binaries*` feature) contains AVX2-family instructions on x86; running it on a non-AVX2 CPU traps with SIGILL — an uncatchable native fault that kills the whole host process. Magika detection was already guarded (#1162, landed after `v0.28.0`); the embedding relevance scorer shared the same `ort-sys` binary with no guard. This PR closes that remaining entry point and documents the requirement. Closes #1723 ## 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 - Add shared `onnx_cpu::onnx_runtime_supported_by_cpu()` helper (AVX2 check on x86/x86_64, `true` on other arches) as the single source of truth. - Route `magika_detector` through the shared helper (no behavior change). - Gate `EmbeddingScorer::try_new*` on the helper: unsupported CPU returns `Err` before touching ONNX, so callers fall back to BM25/stub instead of crashing. - Document the x86 AVX2 requirement + auto-fallback in the README. - Add offline tests (no network / no `RUN_FASTEMBED_TESTS`). ## Testing - [x] Unit tests pass (Rust: `cargo test -p headroom-core`) - [x] Linting passes (`cargo clippy -p headroom-core --all-targets`, `cargo fmt --check`) - [ ] Type checking passes (`mypy headroom`) — N/A, Rust-only change - [x] New tests added for new functionality - [x] Manual testing performed ### Test Output ```text $ cargo test -p headroom-core --lib relevance::embedding cargo test: 13 passed, 834 filtered out (1 suite, 0.00s) $ cargo test -p headroom-core --lib magika cargo test: 16 passed, 831 filtered out (1 suite, 0.16s) $ cargo clippy -p headroom-core --all-targets (no warnings, no errors) $ cargo fmt --check -p headroom-core (clean) $ cargo build --workspace cargo build (225 crates compiled) Finished `dev` profile [unoptimized + debuginfo] target(s) in 6m 57s ``` ## Real Behavior Proof - Environment: `headroom-core` workspace, Rust stable, x86_64 (AVX2-capable dev host). - Exact command / steps: added `onnx_guard_matches_cpu_features` and `try_new_errors_on_unsupported_cpu_instead_of_sigill` tests; ran the suites above. On a no-AVX2 host the guard makes `EmbeddingScorer::try_new()` return `Err(... "AVX2" ...)` instead of executing the AVX2 ONNX binary; callers fall back to BM25 relevance rather than crashing. - Observed result: guard returns `false` only when the CPU lacks AVX2; embedding + magika ONNX paths both short-circuit to non-ONNX fallbacks; no SIGILL. All suites green. - Not tested: end-to-end `pip install` run on a physically AVX2-less machine (dev host has AVX2); guard behavior is unit-tested via the shared `onnx_cpu` helper and mirrors the already-shipped magika guard (#1162). ## 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 — N/A (release-please generates the changelog) ## Additional Notes Rust-only change, so the Python `pytest`/`ruff`/`mypy` items are N/A; equivalent Rust `cargo test`/`clippy`/`fmt` were run and pasted above. The fix is defense-in-depth parity with the existing magika AVX2 guard (#1162), applied to the second ONNX entry point (embedding relevance). Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
Abhay Singh
|
8cddf9b58e
|
fix(proxy/auth): match real Anthropic OAuth token prefix (sk-ant-oat) (#1672)
## Description
`classify_auth_mode` (in `headroom/proxy/auth_mode.py`) checks for
Anthropic
OAuth tokens with:
```python
if token.startswith("sk-ant-oat-"):
return AuthMode.OAUTH
if token.startswith("sk-ant-api") or token.startswith("sk-"):
return AuthMode.PAYG
```
But real Anthropic OAuth access tokens are **`sk-ant-oat01-...`** — a
version
number right after `oat`, **no dash**. So the `sk-ant-oat-` check never
matches a
real token; it falls through to the broad `sk-` rule and gets classified
**`PAYG`**.
That's exactly the misclassification the module is built to prevent: a
subscription/OAuth-bound request tagged `PAYG` gets the
aggressive-compression
policy — lossy compression, auto `cache_control`, `prompt_cache_key`
injection —
instead of the passthrough-prefer path OAuth is meant to get.
The existing tests didn't catch it because they use a synthetic
`sk-ant-oat-01-`
fixture (dashed) that happens to match the buggy prefix. Corroboration
that the
real shape is dash-less:
- `.gitguardian.yaml` fixture: `sk-ant-oat01-oauth-fixture`
- `tests/test_oauth_bearer_routing.py`: `sk-ant-oat01-xxx`
- the sibling helper `headroom/proxy/helpers.py` matches on `sk-ant-`
(no `oat-`)
## Fix
Match the dash-less `sk-ant-oat` prefix. It still matches the legacy
dashed
shape, and ordering relative to `sk-ant-api` / `sk-` is unchanged (OAuth
is
still checked first).
```python
if token.startswith("sk-ant-oat"):
return AuthMode.OAUTH
```
## Type of Change
- [x] Bug fix (non-breaking change that fixes an issue)
## Changes Made
- `headroom/proxy/auth_mode.py`: match OAuth tokens on the dash-less
`sk-ant-oat` prefix.
- `tests/test_auth_mode.py`: add a regression test using the real
`sk-ant-oat01-...` format (the existing test keeps the legacy dashed
fixture, which still classifies correctly).
- `CHANGELOG.md`: Bug Fixes entry under Unreleased.
## Testing
- [x] New regression test added (`tests/test_auth_mode.py`)
- [x] Linting passes (`ruff check`) and formatting is clean (`ruff
format --check`)
- [ ] Full `pytest` deferred to CI (local-OOM reason below).
```text
$ uv run ruff check headroom/proxy/auth_mode.py tests/test_auth_mode.py
All checks passed!
```
## Real Behavior Proof
- Environment: Windows 11, Python 3.12.11, headroom from this branch.
Importing `headroom` loads the torch/transformers stack and a full
`pytest` gets OOM-killed on this box, so I verified the classification
logic with a dependency-free script and left the full pytest to CI.
- Exact command / steps: replicated the Bearer-token branch of
`classify_auth_mode` in a standalone script (only stdlib, no `headroom`
import) and ran the real and legacy token shapes plus PAYG keys through
it.
- Observed result: the real `sk-ant-oat01-...` now classifies OAUTH (was
PAYG before the change); the legacy dashed fixture still classifies
OAUTH; `sk-ant-api*` / `sk-*` keys still classify PAYG:
```text
OK: sk-ant-oat01-... -> OAUTH (was PAYG before fix)
OK: sk-ant-oat-01-... -> OAUTH (legacy fixture still matches)
OK: sk-ant-api* / sk-* -> PAYG (unchanged)
AUTH LOGIC VERIFIED
```
- Not tested: a live proxied Anthropic OAuth request end-to-end (needs a
real subscription token); the classification is pure and covered by the
regression test. Full local `pytest` deferred to CI (OOM, per above).
## 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
- [x] 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 — ran
lint + a standalone logic check; full pytest deferred to CI (local OOM,
disclosed above)
- [x] I have updated the CHANGELOG.md if applicable
## Additional Notes
- `crates/headroom-core/src/auth_mode.rs` carries the identical dashed
prefix (its Rust test matrix uses the same synthetic dashed fixture). I
scoped this PR to the Python runtime classifier since that's the
request-time path; happy to mirror the one-line fix in Rust in the same
PR or a follow-up — I just couldn't `cargo build` locally to verify, so
I left it out rather than push an unverified Rust edit.
- @JerrettDavis tagging you since you've been triaging these — small,
contained fix with a regression test if you have a moment.
Co-authored-by: JerrettDavis <mxjerrett@gmail.com>
|
||
|
Manmit Singh
|
e386c097d6
|
fix(detection): contain unidiff panic on orphaned +++ target line (#1548)
## Description `headroom._core.detect_content_type()` panics with `pyo3_runtime.PanicException: called Option::unwrap() on a None value` on any text containing a `+++ ` target line with no preceding `--- ` source line — e.g. `set -x` xtrace output or a partial `git diff` quoted out of context. The panic originates in the bundled `unidiff` 0.4.0 parser (`lib.rs:665`): on a target-file header it does `source_file.clone().unwrap()`, but `source_file` is still `None` when no source header was seen. The crate's only guard there checks `current_file`, not `source_file`, so it falls through and unwraps `None` instead of returning `Err`. Because detection runs inside a `ThreadPoolExecutor` worker on the Python side, the native panic surfaces as an uncaught `PanicException`, bypasses the compression error handling, and returns **HTTP 500** for the whole request. The failure is deterministic on payload content, so client retries fail until the offending text leaves the context window. `is_diff()` in `unidiff_detector.rs` is the single entry point that drives `PatchSet::parse`, so the fix is contained there: wrap the parse in `catch_unwind` and treat an unparseable fragment as "not a diff". This matches the workspace's deliberate no-`panic = "abort"` policy (Cargo.toml) of surviving bad input rather than taking the long-lived proxy down. Closes #1547 ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) ## Changes Made - `crates/headroom-core/src/transforms/unidiff_detector.rs`: contain any `unidiff` parser panic inside `is_diff()` via `catch_unwind`, returning `false` (not a diff) on panic. Added regression test `orphaned_target_line_does_not_panic`. - `CHANGELOG.md`: note under Unreleased → Fixed. ## Testing - [x] Unit tests pass (`cargo test -p headroom-core`) - [x] Linting passes (`cargo fmt --check`, `cargo clippy`) - [x] New tests added for new functionality - [x] Manual testing performed ### Test Output Before the fix (regression test reproduces the exact panic): ```text running 1 test test transforms::unidiff_detector::tests::orphaned_target_line_does_not_panic ... FAILED ---- transforms::unidiff_detector::tests::orphaned_target_line_does_not_panic stdout ---- thread '...' panicked at unidiff-0.4.0/src/lib.rs:665:54: called `Option::unwrap()` on a `None` value test result: FAILED. 0 passed; 1 failed; ... ``` After the fix: ```text running 15 tests test transforms::unidiff_detector::tests::orphaned_target_line_does_not_panic ... ok test transforms::unidiff_detector::tests::standard_git_diff_detected ... ok ... test result: ok. 15 passed; 0 failed; 0 ignored # whole transforms suite test result: ok. 700 passed; 0 failed; 0 ignored ``` ## Real Behavior Proof - Environment: macOS (arm64), Rust stable, `cargo test -p headroom-core`. - Exact command / steps: `cargo test -p headroom-core --lib unidiff_detector` then `cargo test -p headroom-core`. (1) Added a test calling `is_diff("+++ x")` / `detect_diff("+++ x")` and ran it → reproduced the panic at `unidiff-0.4.0/src/lib.rs:665:54` (output above), confirming the same crash path as the report. (2) Applied the `catch_unwind` containment in `is_diff()`. (3) Re-ran the test and the full transforms suite → all green (output above). - Observed result: the orphaned-`+++ ` input is now classified as "not a diff" (plain text) and returns normally instead of panicking. Real diffs (`standard_git_diff_detected`, `naked_hunk_without_git_header_detected`, multi-file, added/removed-only) still detect correctly, so the containment does not weaken detection. - Not tested: I exercised the Rust layer directly (the sole `unidiff` caller, which the `headroom._core.detect_content_type` binding routes through) rather than rebuilding the Python wheel; I did not run the live proxy against a real provider. ## 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] My changes generate no new warnings - [x] I have added tests that prove my fix is effective - [x] New and existing unit tests pass locally with my changes - [x] I have updated the CHANGELOG.md |
||
|
DM
|
64783d8824
|
fix: skip Magika backend on x86 CPUs without AVX2 (#1162)
## Description Adds a narrow runtime AVX2 guard before initializing the Magika/ONNX Runtime detector on x86/x86_64. On x86/x86_64 CPUs without AVX2, Headroom falls back to existing non-Magika detection tiers instead of crashing during ONNX Runtime initialization. AVX2-capable systems retain existing behavior. Refs #1005 ## 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 - Adds a Magika/ONNX Runtime CPU support guard before `Session::new()`. - Returns a normal Magika init error on x86/x86_64 hosts without AVX2, allowing the existing detection chain to fall through to non-Magika tiers. - Keeps AVX2-capable x86/x86_64 behavior unchanged. - Does not apply the x86-specific AVX2 gate on non-x86 targets. - Adds CPU-aware Rust tests and a short troubleshooting note. ## Testing - [ ] Unit tests pass (`pytest`) - [ ] Linting passes (`ruff check .`) - [ ] Type checking passes (`mypy headroom`) - [x] New tests added for new functionality - [x] Manual testing performed ### Test Output ```text $ cargo test -p headroom-core --lib --locked 833 passed; 0 failed; 1 ignored $ cargo test --workspace --locked passed $ cargo clippy -p headroom-core --locked -- -D warnings clean ``` ## Real Behavior Proof - Environment: x86_64 Linux host with AVX but no AVX2 (Intel Xeon E5-2697 v2 on Proxmox), local build from this branch. - Exact command / steps: `python -X faulthandler -c 'from headroom._core import detect_content_type; print(detect_content_type("hello world"))'` - Observed result: before — process exited with `Fatal Python error: Illegal instruction`; after — command completed successfully returning `DetectionResult(content_type="text", ...)`, and full `cargo test -p headroom-core --lib --locked` passed with 833/0/1. - Not tested: generic no-AVX CPUs, alternate ONNX Runtime builds, non-x86 platforms. ## 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 ## Screenshots (if applicable) N/A ## Additional Notes This partially addresses #1005 by handling one concrete native crash class: the Magika detector initializes ONNX Runtime through ort/ort-sys, whose precompiled runtime can contain AVX2-family instructions. On AVX-only x86_64 hosts, that initialization can SIGILL before Headroom can fall back. Scope: - This does not introduce generic no-AVX wheels. - This does not redesign Rust-core packaging. - This does not disable the Rust core globally. - This only prevents the Magika/ONNX detector tier from loading on x86/x86_64 CPUs where AVX2 is unavailable. - Non-Magika detection tiers continue to run. - On non-x86 targets, this x86-specific AVX2 gate is not applied. Changelog omitted: small native detector fallback fix with no public API change. Co-authored-by: AI Agent <ai-agent@homelab.internal> |
||
|
Nadia Ujovich
|
7c93c50c2c
|
Marker-free lossless_only mode + gate opaque-blob CCR markers behind enable_ccr_marker (#1129)
## Description `enable_ccr_marker` only gated the **row-drop sentinel** path. The **opaque-blob** path still emitted `<<ccr:HASH,kind,size>>` markers unconditionally whenever a string cell exceeded `opaque_min_bytes` (256), so **no configuration could produce a fully marker-free prompt**. Any `<<ccr:>>` marker is a promise that the full payload lives in the CCR store and must be fetched back via a retrieval tool call — there was no way to get compression without that round-trip dependency. **Rebased on #1130 (merged).** That PR fixed the opaque-blob gate at the classifier (`ClassifyConfig.emit_opaque_markers`, driven by `enable_ccr_marker`) and closed #1091. This branch originally carried its own equivalent gating commit; that commit is now **redundant and has been dropped** — `classifier.rs` here is identical to upstream. What remains is the **net-new** work that is **not** in #1130: - **Strict `lossless_only` mode** — keeps lossless tabular compaction, but routes every path that would need a CCR marker (row-drop sentinel **and** opaque-blob offload) to leave content uncompacted instead, so output is always marker-free **and** byte-recoverable. - **Python parity** — `lossless_only` exposed across both config dataclasses, a `SmartCrusher` kwarg, and a per-call `crush(..., lossless_only=)` override. - **`HEADROOM_LOSSLESS_ONLY` env var** — wires the mode through to the proxy runtime so real agents can use it. The #1130 opaque gate is consumed here through a single centralized helper (`opaque_markers_enabled() = enable_ccr_marker && !lossless_only`) used by **all four** `ClassifyConfig` construction sites. ## Type of Change - [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 - [x] Code refactoring (no functional changes) ## Changes Made - **`feat(smart_crusher)`** — Add `lossless_only` (default `false`): keeps lossless tabular compaction but routes every marker-requiring path (row-drop sentinel + opaque-blob offload) to leave content uncompacted instead. Exposed across the Rust core, PyO3 bridge, both Python config dataclasses, a `SmartCrusher` kwarg, a per-call `crush(..., lossless_only=)` override, and `smart_crush_tool_output`. Includes a `debug_assert` documenting the load-bearing invariant (a `lossless_only` crusher must never reach the CCR store write). - **`refactor(smart_crusher)`** — Extract `SmartCrusherConfig::opaque_markers_enabled()` as the single source of truth for `enable_ccr_marker && !lossless_only`, consumed by **all four** `ClassifyConfig` sites: the compaction-stage builder, `with_compaction_format`, the top-level `process_string` path (Rust core), and the PyO3 `compact_document_json` document-compactor path. No site derives the gate inline anymore, so they cannot drift. - **`feat(proxy)`** — Expose the mode via `HEADROOM_LOSSLESS_ONLY`: `ContentRouterConfig.smart_crusher_lossless_only` → `_get_smart_crusher`; the proxy reads the env var and sets it on the live router config. Previously reachable only via the Python API, never through the proxy. ## Testing - [x] Unit tests pass (`pytest`) - [x] Linting passes (`ruff check` on changed files) - [ ] Type checking passes (`mypy headroom`) — not run (see Additional Notes) - [x] New tests added for new functionality - [x] Manual testing performed (proxy env-var seam, end-to-end — see Real Behavior Proof) ### Test Output ```text ### RUST (cargo test -p headroom-core --lib smart_crusher) test result: ok. 323 passed; 0 failed; 0 ignored; 0 measured; 516 filtered out ### PYTEST (test_smart_crusher_bugs.py + test_agent_savings.py + test_smart_crusher_toin_attachment.py) 45 passed ### RUFF (changed files) All checks passed! ### FMT + CLIPPY (cargo fmt --check && cargo clippy --workspace --lib) clean — no warnings ``` New/affected tests: `enable_ccr_marker_false_suppresses_opaque_markers`, `lossless_only_leaves_array_uncompacted_instead_of_dropping`, `lossless_only_inlines_opaque_blobs_when_table_ships`, `lossless_only_never_writes_to_ccr_store` (Rust); `TestLosslessOnlyMode`, `test_router_lossless_only_flag_reaches_crusher`, `test_router_lossless_only_defaults_off` (Python). Coexists green with #1130's `long_string_stays_scalar_when_opaque_markers_disabled` (Rust) and `test_smart_crusher_toin_attachment.py` (Python). The Python `TestOpaqueMarkerGate` from the dropped gating commit was removed as redundant with #1130's coverage. ## Real Behavior Proof ### Proxy env-var seam — end-to-end (this revision) The one path with no automated coverage was `server.py` reading `HEADROOM_LOSSLESS_ONLY` from the environment and threading it into the live router config. Verified end-to-end by instantiating the **real** `HeadroomProxy`, pulling the `ContentRouter` out of its pipeline, and crushing a 50-row array with >256B opaque cells through the real Rust crusher: | | `HEADROOM_LOSSLESS_ONLY=1` | env unset (default) | |---|---|---| | `crusher._lossless_only` | **True** | **False** | | output contains `<<ccr:` | **No** (marker-free) | Yes (normal lossy) | | byte-recoverable (round-trips to original JSON) | **Yes** | No (rows offloaded) | This confirms the full chain `os.environ["HEADROOM_LOSSLESS_ONLY"]` → `server.py` → `ContentRouterConfig.smart_crusher_lossless_only` → `content_router.py` → `crusher_config.lossless_only` → Rust crusher. The default column proves strict mode genuinely changes behavior (not a no-op) and that the default path is unchanged. ### Prior live-traffic run - Environment: Headroom proxy in front of a real agent (Hermes) routed to NVIDIA NIM (OpenAI-compatible upstream). Isolated config dir; `OPENAI_TARGET_API_URL=https://integrate.api.nvidia.com/v1`, `HEADROOM_LOSSLESS_ONLY=1`. Confirmed with `ss` that all LLM traffic flowed agent → proxy → upstream with no direct bypass. - Exact command / steps: Start the proxy with `python -m headroom.proxy.server --host 127.0.0.1 --port 8787`; point the agent's LLM base_url at `http://127.0.0.1:8787/v1`; run a real chat plus a `search_files`-style task; read `/stats` and `/v1/retrieve/stats`; then toggle `HEADROOM_LOSSLESS_ONLY` and repeat for the comparison. - Observed result: With 150K+ tokens of real traffic processed, `lossless_only` kept the CCR store empty (`entry_count: 0`) and emitted zero markers. A synthetic before/after with opaque (>256B) cells produced 12 `<<ccr:>>` markers in default mode and 0 under `lossless_only`, with output round-tripping to the original JSON structure. - Not tested: A live `lossless_only`-vs-markers contrast on real agent traffic. The SmartCrusher offload path never engaged on this agent's tool outputs (`total_compressions: 0`; CCR store stayed at `entry_count: 0` even after a broad codebase search), and compression stayed marginal (~0.2–0.4%) in both modes. The agent's tool results don't match the crushable-array profile the offload paths target, so the marker path is never exercised in that integration. Why SmartCrusher barely engages with this agent's outputs is a separate integration question (output format / routing / size thresholds), out of scope for this change. ## 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 — N/A (config docstrings updated in-tree; no separate docs) - [x] My changes generate no new warnings - [x] I have added tests that prove my feature works - [x] New and existing unit tests pass locally with my changes - [ ] I have updated the CHANGELOG.md if applicable — N/A ## Additional Notes - Rebased on top of merged #1130; the now-redundant opaque-blob gating commit was dropped, so this PR is purely the `lossless_only` feature + proxy wiring on top of #1130's gate. - `mypy headroom` was not run in this environment; happy to add the result if CI requires it. - Default behavior is fully preserved: `enable_ccr_marker` defaults to `true`, `lossless_only` defaults to `false`, and `HEADROOM_LOSSLESS_ONLY` unset is a no-op. |
||
|
Zhenjia ZHOU
|
6c68ff4e9f
|
perf(compression): take large cold-start contexts off the synchronous kompress path (#1171) (#1298)
## Description On a cold-start large context, kompress (ModernBERT ONNX) runs **synchronously on the request thread** — ~200–300s for ~1M tokens. It blows the 30s compression budget, leaks a non-preemptible worker, and cascades (executor saturation → queue timeouts on healthy requests); on timeout the request is forwarded **uncompressed** after eating 30s. This adds four layered, **default-off, fail-open** mitigations so the request path is never blocked on ML compression. Closes #1171 ## 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 - **Phase 0 — size gate** (`HEADROOM_KOMPRESS_MAX_TOKENS`, default 50000): route oversized text away from ModernBERT (→ LogCompressor / TextCrusher / passthrough) at the single `_try_ml_compressor` boundary. - **Phase 1 — cooperative deadline** (`HEADROOM_COMPRESSION_DEADLINE_MS`, default 20000): any kompress run self-terminates at the next chunk boundary past the budget, keeping the unprocessed tail verbatim. - **Phase 2 — TextCrusher** (`HEADROOM_TEXT_CRUSHER`): a new **native Rust** extractive prose compressor in `crates/headroom-core/src/transforms/text_crusher/`, exposed via PyO3 as `headroom._core.TextCrusher` with a thin Python wrapper. It **reuses the shared `crate::relevance::BM25Scorer`** rather than reimplementing BM25, and ships record/replay parity fixtures (mirroring the SmartCrusher Rust-core + Python-shim pattern). - **Phase 3 — off-path compression** (`HEADROOM_BACKGROUND_COMPRESSION`): forward uncompressed immediately and compress in a per-process background drain; a byte-identical cache hit on a later turn means the request never blocks on ML. - Benchmark (`benchmarks/text_crusher_quality_eval.py`), CHANGELOG entry, and docstrings documenting the fail-open limits. ## Testing - [x] Unit tests pass (`pytest`) - [x] Linting passes (`ruff check`) - [x] Type checking passes (`mypy`, new modules) - [x] New tests added for new functionality - [ ] Manual testing performed (Phase 0/1 gate-fire + deadline observed on real traffic in earlier iterations; Phase 3 off-path is unit- + byte-identity-tested, not yet live-validated) ### Test Output ```text $ pytest tests/test_transforms/ tests/test_cache/ \ tests/test_proxy/test_background_compression.py tests/test_proxy/test_phase3_byte_identity.py -q 501 passed, 37 skipped in 40.33s $ cargo test -p headroom-core --lib text_crusher test result: ok. 3 passed; 0 failed; 0 ignored; 0 measured; 834 filtered out $ ruff check <changed files> All checks passed! $ mypy headroom/proxy/background_compression.py headroom/transforms/text_crusher.py Success: no issues found in 2 source files ``` New coverage: size-gate incl. the strategy-dispatch funnel (KOMPRESS + TEXT); partial-run deadline (chunk-0 compressed + chunk-1 verbatim tail); BackgroundCompressor (dedup / queue-full / fail-open); Phase 3 byte-identity round-trip; TextCrusher unit + parity. ## Real Behavior Proof - Environment: macOS, local dev — `uv` venv, Rust `_core` built via `uv pip install -e .`. - Exact command / steps: the `pytest` / `cargo test` / `ruff` / `mypy` commands shown under Test Output; quality eval `python benchmarks/text_crusher_quality_eval.py /tmp/squad_dev.json`. - Observed result: 501 Python + 3 Rust tests pass; ruff + mypy clean on changed/new modules. Quality eval: TextCrusher keeps ~94% of buried SQuAD answers at 30% size vs ~36% truncate/random; self-contained speed run ~333k words in ~76ms (one O(n) pass) — sub-second where ModernBERT takes minutes (fast-vs-slow contrast, not a same-input run). - Not tested: Phase 3 off-path on live traffic; multi-worker (per-process by design — see Additional Notes). ## 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 - [x] I have updated the CHANGELOG.md if applicable ## Additional Notes - **All four features are off by default and fail-open** — with the env flags unset the paths are no-ops for realistic inputs; on any error the request is forwarded (compressed if possible, else verbatim), never dropped. A full background queue / duplicate key surfaces as `deferred:dropped`. - **Known limits (documented in `background_compression.py`):** Phase 3 is per-process, in-memory, and token-mode-only — these are **lost-savings, never lost-correctness**, and consistent with the project's existing per-process compression cache + sticky-session multi-worker model. The startup multi-worker warning now names off-path background compression. - Phase 2 reuses the existing BM25 scorer; reuse did not improve answer-retention over a Python prototype (query-awareness dominates) — its value is the Rust speed + repo-conventional Rust-core/Python-shim shape. --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Parideboy
|
3ccdad6c67
|
Pin ORT dylib on Windows; init Python logging (#1010)
## Description On Windows, headroom's Rust core resolves `onnxruntime.dll` at runtime via `ort-load-dynamic`. Without an explicit `ORT_DYLIB_PATH`, the bare DLL search can land on `C:\Windows\System32\onnxruntime.dll`, the Windows ML OS component, and `Session::new()` can deadlock instead of returning an error. Since a hang is not an `Err`, the tiered fallback cannot engage until the proxy-level timeout fires. This PR pins `ORT_DYLIB_PATH` to the pip-installed `onnxruntime` DLL at import time, and wires Rust `tracing` events into Python logging so the proxy log surfaces these failures when they occur. Closes #928 ## 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 - Added `headroom/_ort.py` with a Windows-only, idempotent `ensure_ort_dylib_pinned()` resolver that respects an existing `ORT_DYLIB_PATH`. - Call the pin from `headroom/__init__.py` before importing `_core` consumers. - Log the effective ORT dylib path from the content router startup path on Windows. - Enable Rust tracing-to-log compatibility and initialize `pyo3-log` in the `_core` module. - Add timeout diagnostics in the Magika detector with the effective `ORT_DYLIB_PATH`. - Document `ORT_DYLIB_PATH` and `HEADROOM_MAGIKA_INIT_TIMEOUT_SECS`. - Add unit coverage for the resolver behavior. ## Testing - [x] Unit tests pass (`python -m pytest tests/test_transforms/test_ort_dylib.py -q`) - [x] Linting passes (`ruff check headroom/_ort.py headroom/__init__.py headroom/transforms/content_router.py tests/test_transforms/test_ort_dylib.py`) - [x] Formatting passes (`ruff format --check headroom/_ort.py headroom/__init__.py headroom/transforms/content_router.py tests/test_transforms/test_ort_dylib.py`) - [x] New tests added for new functionality - [x] Manual testing performed ### Test Output ```text $ python -m pytest tests/test_transforms/test_ort_dylib.py -q 7 passed in 0.19s $ ruff check headroom/_ort.py headroom/__init__.py headroom/transforms/content_router.py tests/test_transforms/test_ort_dylib.py All checks passed! $ ruff format --check headroom/_ort.py headroom/__init__.py headroom/transforms/content_router.py tests/test_transforms/test_ort_dylib.py 4 files already formatted $ cargo check -p headroom-py cargo: The term 'cargo' is not recognized as a name of a cmdlet, function, script file, or executable program. ``` ## Real Behavior Proof - Environment: Windows 11 24H2, Python 3.13, RTX 4080 - Exact command / steps: `python -c "import headroom; from headroom._core import detect_content_type as d; print(d(open('headroom/compress.py').read()).content_type)"` - Observed result: `source_code` in 301ms, clean exit, `Magika: ENABLED` in proxy log - Not tested: macOS/Linux manual runtime behavior; `_ort.py` is a no-op outside Windows, and CI covers cross-platform build/test behavior. ## 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 (N/A: repo uses release-please) ## Additional Notes The branch was rebased onto current `main` and the commit subject was updated to satisfy commitlint. Local Rust verification could not be run on this Windows machine because `cargo` is not installed; GitHub CI should be treated as the Rust build verification for the `pyo3-log` dependency and workspace lockfile changes. --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
jichaowang02-lang
|
c7295cad1d
|
fix(ccr): store opaque blobs from lossless:table compaction (#1083) (#1182)
## Description
SmartCrusher's `lossless:table` compaction path emits opaque-blob CCR
markers
(`<<ccr:HASH,KIND,SIZE>>`) but never wrote the original payload to the
CCR
store. As a result `GET /v1/retrieve/{hash}` and the `headroom_retrieve`
tool
return **404** for those hashes. The opaque-*string* path
(`walker::emit_opaque_ccr_marker`) already stores its payload; the table
compactor diverged simply because no store was threaded into it.
Closes #1083
## 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
- `compaction/compactor.rs`: add `compact_with_store(items, cfg, store)`
and a
private `compact_inner`; thread `Option<&Arc<dyn CcrStore>>` through
`build_homogeneous_table` → `build_row` → `cell_from_value` and the
recursive
bucket/nested calls. In the `Opaque` branch, `store.put(&hash, payload)`
under
the **same** `hash_opaque` value that becomes the marker hash (mirrors
`walker::emit_opaque_ccr_marker`). Public `compact` is unchanged — it
delegates
with `None`.
- `compaction/mod.rs`: add `CompactionStage::run_with_store`; `run` is
unchanged.
- `crusher.rs`: the lossless branch now calls
`stage.run_with_store(items, self.ccr_store.as_ref())` instead of
`stage.run(items)`.
- Two new unit tests in `compactor.rs` (see below).
The IR (and therefore the rendered marker text) is identical whether or
not a
store is supplied — the store only gains the write that should already
have
happened, so existing output stays byte-for-byte the same.
## 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`)
- [x] New tests added for new functionality
- [x] Manual testing performed
> Note: this change is in the Rust core (`crates/headroom-core`), so the
> Python-specific checks above are N/A. The Rust equivalents were run:
### Test Output
```text
$ cargo test -p headroom-core --lib compaction
test result: ok. 70 passed; 0 failed; 0 ignored; 0 measured; 766 filtered out; finished in 0.01s
$ cargo fmt -p headroom-core -- --check
# clean (exit 0)
```
New tests:
- `opaque_payload_is_stored_under_marker_hash` — after
`compact_with_store`, the
original blob is retrievable via `store.get(marker_hash)`, and the
stored key
equals `hash_opaque(payload)` (locks the key↔marker contract).
- `store_presence_does_not_change_the_ir` — `compact` and
`compact_with_store`
produce identical IR; only the store write is added.
(The full `cargo test -p headroom-core --lib` run has 18 pre-existing
failures,
all in `transforms::magika_detector` — they require the ONNX
runtime/model and
are unrelated to this change. All 70 compaction + crusher tests pass.)
## Real Behavior Proof
- Environment: Windows, Rust 1.95.0, `cargo test -p headroom-core` (no
live proxy).
- Exact command / steps: build a 2-item array with a long opaque-blob
field →
`compact_with_store(&items, &cfg, Some(&InMemoryCcrStore))` → read the
`OpaqueRef.ccr_hash` from the IR → `store.get(ccr_hash)`.
- Observed result: before the fix the store is empty (retrieval would
404);
after the fix `store.get(ccr_hash) == Some(original_payload)` and the
marker
hash is unchanged.
- Not tested: end-to-end through a running proxy / a real `GET
/v1/retrieve/{hash}`
HTTP round-trip. Verified at the unit level that the store now receives
the
payload under the exact marker hash, which is the write that was
missing.
## 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
- [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
- Docs/CHANGELOG checklist items are N/A — this is an internal
correctness fix
with no user-facing API change.
- Scope is intentionally minimal: public `compact`/`run` signatures are
preserved (delegating with `None`), so all existing callers and the 68
in-crate compaction tests are unaffected. Only the lossless
`crush_array`
branch opts into the store-threading via `run_with_store`.
|
||
|
Zhenjia ZHOU
|
27d6f8e2a7
|
fix(smart-crusher): honor enable_ccr_marker on the opaque-blob path (#1130)
## Description Closes #1091. SmartCrusher's array compaction is lossless-first, but the **opaque-blob** substitution path emitted `<<ccr:HASH,string,KB>>` markers **unconditionally** — it did not honor `enable_ccr_marker` / `inject_retrieval_marker`, which gate only the lossy **row-drop** path. As the issue notes, the consequence was that *no configuration produced guaranteed-lossless, marker-free output*: any array with a single string cell over `opaque_min_bytes` (256B default) still emitted a CCR marker, forcing a retrieval round-trip for consumers that need verbatim output. **Root cause:** the row-drop path is gated (`crusher.rs` — `if dropped_count > 0 && self.config.enable_ccr_marker`), but opaque classification in `compaction/classifier.rs` keyed purely on byte length, with no reference to the flag, and both emit sites (`walker.rs`, `crusher.rs`) then produced a marker. **Fix:** thread the gate into classification. `ClassifyConfig` gains an `emit_opaque_markers` field (default `true`); when `false`, a long string is classified `Scalar` (kept verbatim) instead of `Opaque`, so no marker is emitted and nothing is written to the CCR store anywhere downstream. The flag is set from `enable_ccr_marker` at both `ClassifyConfig` construction sites in `crusher.rs`. > Design note: gating at the classifier (rather than at marker-emit time) is the single complete fix — it covers all three emit paths (walker inline-substitution, the crusher string path, and the compactor `OpaqueRef`→formatter path, which no longer has the original string by the time it formats). One consequence: with markers **off**, an array dominated by unique long-string cells now falls through to a conservative passthrough (`skip:unique_entities_no_signal`) instead of a lossy opaque table — still lossless and marker-free, which is the point of disabling markers. If you'd rather preserve structural table compaction with the blob inlined verbatim, that's a larger change at the emit + compactor layers; happy to take it that direction if preferred. Default behavior (`enable_ccr_marker=true`) is unchanged. ## 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 - `crates/headroom-core/src/transforms/smart_crusher/compaction/classifier.rs`: add `emit_opaque_markers: bool` (default `true`) to `ClassifyConfig`; in `classify_cell`, keep long strings `Scalar` when it is `false`. New unit test `long_string_stays_scalar_when_opaque_markers_disabled`. - `crates/headroom-core/src/transforms/smart_crusher/crusher.rs`: set `classify.emit_opaque_markers = config.enable_ccr_marker` at both `ClassifyConfig` construction sites (the `CompactConfig` builder and the standalone string path). - `tests/test_smart_crusher_toin_attachment.py`: regression test pinning both directions — markers ON ⇒ opaque marker present (input really triggers the path); markers OFF ⇒ no marker, blob verbatim. ## Testing - [x] Unit tests pass (`pytest`) - [x] Rust tests pass (`cargo test`) - [x] Linting passes (`ruff check .`, `cargo fmt --check`, `cargo clippy -- -D warnings`) - [ ] Type checking (`mypy headroom`) — N/A (no headroom/ Python source changed) - [x] New tests added ### Test Output ```text # Rust $ cargo test -p headroom-core --lib smart_crusher test result: ok. 319 passed; 0 failed (incl. new: ...classifier::tests::long_string_stays_scalar_when_opaque_markers_disabled ... ok) $ cargo fmt --check && cargo clippy --workspace -- -D warnings ok # Python (after `uv pip install -e .` to rebuild the Rust core) $ pytest tests/test_smart_crusher_toin_attachment.py tests/test_transforms/ tests/test_ccr_row_drop_store_bridge.py 289 passed, 35 skipped # Full suite is green except the 5 pre-existing caplog logging-isolation # flakes that are unrelated to this change and fixed separately in #1117. ``` ## Real Behavior Proof - Environment: macOS, Python 3.13.3, Rust core rebuilt via `uv pip install -e .`. - Exact command / steps: crush a 60-row array whose rows carry a distinct >256B `blob` string, with `inject_retrieval_marker` ON then OFF. - Observed result: with `inject_retrieval_marker` OFF (after this fix) the crushed output contains NO `<<ccr:` marker and the original `sentinel5_…` blob survives verbatim; before the fix the same input still emitted `<<ccr:…,string,407B>>` (the bug); with markers ON behavior is unchanged. Concretely: - markers ON → `strategy=lossless:table`, output contains `<<ccr:…,string,407B>>` (blob replaced). - markers OFF (before fix) → `lossless:table` **still emitted `<<ccr:…>>`** (the bug). - markers OFF (after fix) → no `<<ccr:` marker, the original `sentinel5_…` blob present verbatim. - Not tested: behavior under CI's sharded jobs specifically; fix is deterministic and config-gated. ## 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 — N/A - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective - [x] New and existing unit tests pass locally with my changes - [ ] I have updated the CHANGELOG.md — N/A 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Tejas Chopra
|
b7be3814f1
|
feat: compression extraction — Rust knob exposure, CCR hardening, traffic audits (#818)
## Description
A data-driven push for better compression savings without accuracy loss,
in four parts: expose and tune the Rust compressor knobs, harden the CCR
retrieval store, add traffic-audit tooling that sizes opportunities from
real transcripts, and introduce **read maturation** — a new,
live-validated mechanism that compresses Read outputs *before* they ever
enter the provider prefix cache.
## Type of Change
- [x] 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
### 1. Rust compressor extraction
- Expose `lossless_min_savings_ratio` end-to-end and lower the default
0.30 → 0.15 (lockstep across Rust, PyO3, and both Python config classes)
so the lossless Table/CSV compaction path wins more often.
- Expose the `CompactConfig` heuristics (core-field fraction,
heterogeneity ratio, flatten cap, bucket bounds) through PyO3 + Python.
- `SearchCompressor` grouped-by-file output (`rg --heading` style — path
once per file instead of per match). Library default off; the proxy
enables it in token mode.
- Complete `factor_out_constants`: constant fields now emit once in a
`_constant_fields` sentinel with slim rows (defensive per-item value
match; default off).
- `ContentRouter` accepts a SmartCrusher config override and the
search-grouping knob.
### 2. CCR store hardening
- Session-scale TTL: 300s → 1800s (CCRConfig, CompressionEntry,
CompressionStore, Rust `DEFAULT_TTL` — lockstep).
- **SQLite is the default CCR backend** (`~/.headroom/ccr_store.db`,
WAL): survives proxy restarts and is shared across workers.
`HEADROOM_CCR_BACKEND=memory` opts out.
- Multi-worker safety: `busy_timeout`, and corruption detection narrowed
so transient `SQLITE_BUSY` errors can never trigger database deletion.
- Data-at-rest hygiene: `chmod 600` on db + sidecars, expired rows swept
at open.
- Retrieval-miss messages are actionable (re-read the file / re-run the
command).
### 3. Traffic audit tooling (measure before tuning)
- `headroom audit-reads`: sizes Read opportunities from local Claude
Code transcripts (read share, stale %, line-number overhead, context
residency, cache-death windows).
- `--simulate-maturation`: Mechanism B risk sizing (re-read rates,
never-touched-again share, quiesce coverage, at-risk edits).
- `--codex`: shell-read classifier for Codex transcripts (rtk-wrapper
aware, workdir resolution).
- Findings that shaped this PR (81 sessions): Reads are 67% of tool
bytes; median Read lingers 118 turns (~13x lifetime cost); a prototyped
repeat-Read dedup measured 0.1% and was **removed** rather than shipped
as dead code.
### 4. Read maturation (Mechanism B) — experimental, default OFF
- Activity-based: a fresh large Read is held **out** of the provider
cache (trailing breakpoint relocated before it), stays verbatim while
its file is active, and matures into a CCR-backed marker once the file
is quiet for `quiesce_turns` (default 5; `max_hold_turns` bounds busy
files).
- Only the final compressed form ever enters the cache — **no cached
byte is ever mutated**; matured markers replay byte-identically.
- Wired into the Anthropic handler behind `--read-maturation` /
`HEADROOM_READ_MATURATION=1`; session state rides on the prefix tracker;
advisory (can never fail a request).
- Live-validated against the Anthropic API: held content excluded from
cache_creation; after maturation the prior cached prefix still served —
the no-bust invariant holds end-to-end.
### 5. Rebase / CI fixups (this update)
- Rebased onto latest `main` (was 28 commits behind): picks up `ci: pass
CODECOV_TOKEN to coverage uploads (#968)`, which is what was turning the
4 test shards red — the tests themselves passed (1528) but the post-test
codecov upload exited non-zero on a protected branch.
- Resolved the duplicate `lossless_min_savings_ratio` that two
independent main/branch additions left in `SmartCrusherConfig` and the
Rust-config kwarg (import-time `SyntaxError` + mypy `no-redef`).
- Aligned CCR tests with the new defaults (SQLite backend, 1800s TTL)
across `test_ccr`, `test_adapter_hooks`, `test_compression_store`,
`test_proxy_ccr`, and the lossy row-drop bridge test.
## Testing
<!-- Check what you actually ran, then paste the real command output
below. -->
- [x] Unit tests pass (`pytest`)
- [x] Linting passes (`ruff check .`)
- [x] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [ ] Manual testing performed
### Test Output
```text
$ python -m pytest tests/test_proxy_ccr.py tests/test_ccr.py tests/test_compression_store.py tests/test_adapter_hooks.py tests/test_ccr_row_drop_store_bridge.py -q
170 passed, 4 warnings in 42.49s
$ python -m pytest tests/test_audit_reads.py tests/test_audit_codex.py tests/test_read_maturation.py tests/test_transforms_content_router.py tests/test_smart_crusher_toin_attachment.py -q
83 passed
$ mypy headroom/
Success: no issues found in 365 source files
$ python -m compileall headroom/ -q
COMPILE-OK
# CI (run 27488990477, pre-rebase head): all 4 shards ran to completion —
# "1528 passed, 120 skipped, 4922 deselected"
# The red shards were the codecov upload step, not test failures; fixed by
# the #968 rebase above.
```
## Real Behavior Proof
- Environment: macOS (darwin), Python 3.12 venv; branch
`feat/compression-extraction` rebased onto `origin/main` (head
|
||
|
Yasser Sheikh
|
0dc2e1cb3f
|
feat(bedrock): cross-region + Converse compression; bundle proxy binary in images (#999)
## Description The native Bedrock path (Phase D) compresses + signs Anthropic-on-Bedrock requests, but two real-world cases slipped through, and the native binary that powers it was never shipped. This PR closes those gaps as a focused set of give-backs. Aligns with the Rust migration plan (see below). ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) - [x] New feature (non-breaking change that adds functionality) - [ ] Breaking change - [ ] Documentation update - [ ] Performance improvement - [ ] Code refactoring (no functional changes) ## Changes Made - **Cross-region inference-profile detection** via a new `bedrock::vendor` module (`canonical_vendor()`), following the design proposed in #953: strip a known geo prefix (`eu.`/`us.`/`apac.`/`global.`) then match the canonical vendor. Geo-prefixed Anthropic profiles (`eu.anthropic.…`) now get live-zone compression instead of being silently skipped; geo-prefixed non-Anthropic vendors stay correctly excluded. - **Converse-body compression (two parts)**: 1. `run_anthropic_compression` no longer bails to passthrough when the body lacks an InvokeModel `anthropic_version` envelope; envelope re-emit stays gated on successful parse. 2. The **live-zone dispatcher now recognizes Bedrock Converse content blocks**. Converse blocks carry no `type` discriminator (the variant is the key: `{"text": …}` vs Anthropic's `{"type":"text","text":…}`), so real Converse user-message text was still passing through uncompressed. A typeless block whose `text` is a JSON string now routes through the same surgical text path. Anthropic blocks always carry `type`, so the Anthropic path is byte-for-byte unchanged; non-text Converse blocks (`{"image":…}`, `{"toolUse":…}`) stay unrecognized and no-op. - **Correct `/converse` upstream routing**: the non-streaming handler resolved the upstream action from a hard-coded `"invoke"`, so `/converse` requests were forwarded to Bedrock's `/invoke` endpoint. It now resolves the action from the inbound path (`extract_invoke_action`), mirroring the streaming handler's `extract_streaming_action`. SigV4 signs the same URL it forwards, so the signature stays consistent. - **`aws-config` `sso` feature**: SSO profiles now resolve through the default credential chain for SigV4 — the credential chain in `docs/bedrock.md` already promised SSO; this makes the code match. - **Ship the `headroom-proxy` binary in published images** (`Dockerfile`): built in the builder stage (`--locked`, with the cargo registry cache mounted at `CARGO_HOME`) and copied into both the debian and distroless runtime images. - **Docs** (`docs/bedrock.md`): document cross-region inference profiles and a "Running the proxy" section. AWS credentials mount at `/home/nonroot/.aws` (the default nonroot image home) where the SDK looks for `~/.aws`, with a note on the root-image alternative. ## Related issues - Closes #976 — ship the `headroom-proxy` binary in published images (this PR implements the exact fix proposed there). - Addresses the **cross-region inference-profile** half of #953 via its proposed `canonical_vendor()` design. Non-Anthropic vendor compression parity (Nova/GLM/MiniMax/ Kimi) is the natural follow-up — `bedrock::vendor` is the shared resolver it can build on. - Extends the native Bedrock InvokeModel compression requested in #734 (the Bedrock slice of #510) to cross-region profiles and Converse bodies. - Partially enables #181 (native, Python-free packaging): the native binary now ships in the images, though full Python-free distribution remains out of scope. ## Alignment with the Rust migration plan Per `docs/spec/022-rust-migration.md`, the migration is **proxy-first**: `headroom-proxy` is the deployable Rust artifact, native routes replace Python passthroughs one at a time (Stage 4 = provider expansion, Bedrock included), and the binary is meant to be "built, tested, and **released together with the Python package**." Two ways this PR advances that: - The binary-in-images change makes the codebase do what the spec already states (ship the artifact) — closing the gap that forced downstreams to build from source. - Hardening the native Bedrock route (cross-region, Converse routing + body compression) is exactly the Stage-4 provider-expansion work, keeping the native path at parity with real traffic so it can be the default rather than a passthrough. ## Testing - [x] Unit tests pass (`cargo test -p headroom-core -p headroom-proxy` — full suites, 0 failures) - [x] Linting passes (`cargo clippy -p headroom-core -p headroom-proxy --all-targets -- -D warnings`) - [x] Formatting passes (`cargo fmt -- --check`) - [x] New tests added — `bedrock::vendor` (foundation + inference-profile matching), `extract_invoke_action` + converse upstream URL, and live-zone Converse text-block routing (`block_has_string_text_field`, converse-vs-anthropic dispatch equivalence). - [x] Manual testing performed ### Test Output ```text $ cargo test -p headroom-core -p headroom-proxy # all suites: ok, 0 failed $ cargo clippy -p headroom-core -p headroom-proxy --all-targets -- -D warnings # Finished, no warnings $ cargo fmt -- --check # clean # image validation (local, proxy/code extras): $ docker build --target runtime ... # debian: /usr/local/bin/headroom-proxy, --help OK $ docker build --target runtime-slim ... # distroless: binary links + --help OK ``` ## Real Behavior Proof - Environment: native Bedrock proxy against `bedrock-runtime.eu-west-2`, SSO profile, model `eu.anthropic.claude-haiku-4-5-20251001-v1:0`. - Exact command / steps: POST a large multi-turn Converse body to `/model/eu.anthropic.claude-haiku-4-5-20251001-v1:0/converse`; separately build the `runtime` + `runtime-slim` targets and run `/usr/local/bin/headroom-proxy --help`. - Observed result: before — `bedrock_compression_skipped` (geo-prefixed id not recognized), forwarded uncompressed to the wrong `/invoke` upstream; after — geo-prefixed id recognized, `/converse` forwarded to the `/converse` upstream, live-zone dispatcher compresses the Converse user-message text, measurable token savings. Images contain a runnable `headroom-proxy` in both variants. - Not tested: non-Anthropic vendor compression parity (#953 follow-up); Converse `toolResult` nested-text compression (follow-up — only top-level Converse text blocks compress today). ## 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 - [x] New and existing unit tests pass locally with my changes - [x] I have updated the CHANGELOG.md if applicable ## Additional Notes - An earlier revision flipped the EventStream `Accept` default (`*/*`/absent → passthrough); **dropped** — `*/*` is what most clients (incl. reqwest and the proxy's own metrics tests) send while expecting SSE, so forcing passthrough breaks the standard SSE path. - The binary build adds the native-proxy compile to the image build; happy to gate it behind a build arg if maintainers prefer it opt-in. - Addressed a Copilot review round: corrected the `/converse` upstream routing, the stale `run_anthropic_compression` comment, the Dockerfile cargo cache mount + `--locked`, and the nonroot AWS-credentials docs example. |
||
|
Serge ARADJ
|
60d952e857
|
Fix/magika new session hangs on windows (#928)
## Description Brief description of changes and motivation. Fixes #(issue number) ## Type of Change - [ ] 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 - Change 1 - Change 2 - Change 3 ## 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 - [ ] Manual testing performed ## Test Output ``` # Paste relevant test output here pytest -v tests/test_your_feature.py ``` ## Checklist - [ ] My code follows the project's style guidelines - [ ] 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 - [ ] 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) Add screenshots to help explain your changes. ## Additional Notes Any additional information that reviewers should know. <!-- headroom-maintainer-template-completion:start --> ## Description This PR prepares `Fix/magika new session hangs on windows` for review by documenting the intended change, validation evidence, and remaining merge-readiness context. Linked issues: None declared. ## Type of Change - [x] Bug fix - [ ] New feature - [ ] Documentation - [ ] Refactor - [ ] Tests only ## Changes Made - Commit: fix(magika): bound ONNX session init with configurable timeout to pre… - Commit: Merge branch 'main' into fix/magika-new-session-hangs-on-windows - Touches `crates/headroom-core/src/transforms/magika_detector.rs` - Touches `headroom/proxy/handlers/openai.py` ## Testing - [x] GitHub checks reviewed - [x] Metadata/template validation - [ ] Local functional testing ### Test Output ```text gh pr view 928 --repo chopratejas/headroom --json statusCheckRollup - CI / changes: SUCCESS - Init E2E / docker-init-e2e: SUCCESS - PR Governance / label: SUCCESS - Wrap E2E / docker-wrap-e2e: SUCCESS - rust / test (ubuntu): SUCCESS - CI / commitlint: SUCCESS - rust / wheels (x86_64-unknown-linux-gnu): SUCCESS - rust / wheels (aarch64-apple-darwin): SUCCESS - CI / lint: SUCCESS - rust / audit: SUCCESS - rust / parity (nightly, allowed to fail during Phase 0): SKIPPED - CI / build-wheel: SUCCESS ``` ## Real Behavior Proof - Environment: GitHub PR metadata and checks for `chopratejas/headroom` PR #928. - Exact command / steps: Reviewed PR title, commits, changed files, linked issues, labels, and check rollup; appended this maintainer template completion block without replacing the author's original description. - Observed result: PR body now contains all required governance sections, checked readiness fields, and a non-placeholder validation evidence block. - Not tested: This pass updated PR metadata only; code validation remains represented by the linked GitHub checks and any author-provided evidence above. ## Review Readiness - [x] I have performed a self-review - [x] This PR is ready for human review <!-- headroom-maintainer-template-completion:end --> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|
Focused Instability
|
0632eba6c3
|
fix(policy): correct warm-cache penalty in net_mutation_gain to (S + dT) (#903)
Fixes #906. ## What Part of #904 (net-cost policy completion tracking). Follows up #856 / #857 with the corrected gain term raised in [this #856 comment](https://github.com/chopratejas/headroom/issues/856#issuecomment-4679706939) — prerequisite for P2 (pipeline consumption), which would otherwise wire in a formula that is always-pro-mutation by exactly `P_alive·(w−r)·ΔT`. ## Why the corrected form is right With a live cache, the ΔT tokens a mutation removes are **already cache-written** — keeping them costs only reads (`ΔT·r·R`), so a mutation cannot avoid a fresh write of them. Blending alive (`ΔT·r·R − (w−r)·S`) and dead (`ΔT·(w + r·(R−1))`, no suffix penalty) cases over `P_alive`: ``` gain = ΔT·(w + r·(R−1)) − P_alive·(w−r)·(S + ΔT) ``` Three independent confirmations: 1. **Direct cost check** (w=1.25, r=0.1, warm, ΔT=50K, S=10K, R=2): keeping costs 60K·0.1·2 = 12,000 in reads; mutating costs 10K·1.25 (suffix rewrite, the first of the R touches) + 10K·0.1 (remaining read) = 13,500 — mutation loses 1,500, matching the corrected gain of −1,500. The old form said +56,000. 2. **The issue's own anchors**: corrected break-even is exactly `R = 11.5·S/ΔT` → 2K/50K = 287.5 (~290, as the issue says) and 50K/10K = 2.3 — the spec text's anchor numbers can only be derived from the corrected penalty. The implemented form gave 276 and *negative*. 3. **Internal consistency**: `break_even_reads` already shipped with the ~11.5·S/ΔT shape; this PR reconciles `net_mutation_gain` with it (and drops break_even's stray −1 term). ## Behavior changes (formula is still dead code — nothing consumes it yet) - 50K-shave/10K-suffix/R=3 golden: +61,000 → **+3,500** (tight win, consistent with 2.3-read break-even). - 2K-shave/50K-suffix/R=10 golden: −53,200 → **−55,500**. - S=0 boundary: an edit of already-cached content with no suffix is profitable whenever ≥1 read remains (`gain = ΔT·r·R`), and exactly 0 at R=0 warm. Not-yet-cached (live-zone) content should bypass the formula — now documented on both implementations. Rust + Python goldens updated in lockstep: 13 Rust + 19 Python tests green. ## Next (separate PRs) - **P2**: flag-gated consumption (`HEADROOM_NET_COST_POLICY=1`) with decision telemetry. - **P3**: batch deep edits (reclaim threshold), idle-timer compaction near TTL lapse. Co-authored-by: integration-check <integration@local> |
||
|
Focused Instability
|
d5f58026e2
|
feat: net-cost cache mutation formula on CompressionPolicy (#856 P1) (#857)
Closes #856 **P1 of the #856 phased plan** — pure functions, zero behavior change. (Closing keyword links the issue; if P2 hasn't started when this merges, reopen #856 or it remains the design record for the P2/P3 follow-up PRs.) ## What Adds the break-even decision rule for deep (pre-cache-marker) edits to `CompressionPolicy`: ``` gain = ΔT · (w + r·(R−1)) − P_alive · (w − r) · S ``` - `net_mutation_gain()`, `should_mutate_deep()` (gain > 0), `break_even_reads()` (R = ((w−r)/r)·(S/ΔT−1) ≈ 11.5·S/ΔT) on the Rust struct (source of truth) and the Python hand-mirror, following the existing F2.1/F2.2 parity pattern. - `CACHE_WRITE_MULTIPLIER = 1.25` / `CACHE_READ_MULTIPLIER = 0.1` public constants (Anthropic 5-minute tier). - Inputs clamped (`expected_reads ≥ 0`, `p_alive ∈ [0,1]`); methods take `&self`/`self` so a follow-up can add per-mode margins. - The formula derives the existing Subscription live-zone policy as its S=0 special case rather than contradicting it. **No callers yet.** P2 (consuming this in `TransformPipeline` behind `HEADROOM_NET_COST_POLICY`, replacing the binary `live_zone_only` gate, with decision telemetry) is specified in #856 and awaits maintainer direction — this PR just lands the audited arithmetic both dispatchers will share. ## Tests Golden-value parity: 6 new Rust unit tests and 7 new Python tests assert the **identical scenario numbers** (loss −53 200 for a 2K shave under a 50K warm suffix at R=10; win +61 000 for a 50K shave under a 10K suffix at R=3; S=0 always profitable; P_alive=0 always profitable — the idle-timer window; clamping; break-even 276 reads for the 2K/50K anchor). A drift on either side trips the pair loudly, same contract as the existing field-map parity test. - `cargo test -p headroom-core --lib compression_policy`: 12 passed (6 existing + 6 new) - `pytest tests/test_compression_policy.py`: 17 passed (10 existing + 7 new) - `cargo fmt --check`, `cargo clippy -p headroom-core` clean; `ruff check` + `ruff format --check` clean ## Real behavior proof Not applicable in the runtime sense — this PR intentionally adds **no runtime behavior** (pure functions, no call sites). The arithmetic is validated against the research anchors above in both languages' test suites; live decision telemetry arrives with P2 where the formula first gates real traffic. ## Out of scope P2 (flag-gated pipeline consumption + telemetry), P3 (deep-edit batching, idle-timer compaction near TTL lapse), retiring the deprecated `volatile_token_threshold`/`max_lossy_ratio` fields — all tracked in #856. --------- Co-authored-by: Ash Rhodes <ashley.rhodes@king.com> |
||
|
Focused Instability
|
06b2625b17
|
feat: gated Markdown-KV compaction formatter (serialization-aware output) (#859)
Closes #858. ## What Adds an opt-in **Markdown-KV** renderer to the lossless-first compaction stage, plus the plumbing to pick a compaction formatter by name. Default behavior is unchanged (`csv-schema`). Format-comprehension benchmarks show models retrieve values from Markdown-KV substantially more reliably than from CSV (~60.7% vs ~44.3%) — token-cheapest is not the same as most comprehensible. This makes the trade-off selectable per workload. ## How - **`MarkdownKvFormatter`** (`compaction/formatter.rs`): keeps the `[N]{cols}` declaration line, renders each row as a Markdown list item with `key: value` lines. - Missing cells omitted entirely (the KV advantage over positional CSV). - Strings ambiguous on a line (newlines, leading/trailing whitespace, empty) render JSON-quoted; everything else raw — commas and quotes need no escaping. - Nested cells inline compact JSON; opaque cells keep the fixed `<<ccr:HASH,KIND,SIZE>>` marker contract shared by all formatters. - **`CompactionStage::from_format_name`** maps `"csv-schema" | "json" | "markdown-kv"` to presets. - **Core**: `SmartCrusher::with_compaction_format(config, name)` — standard OSS composition with the named formatter. - **PyO3 bridge**: `SmartCrusher.with_compaction_format(config, format_name)` staticmethod; `ValueError` on unknown names (loud, no silent fallback). - **Python**: `SmartCrusher(compaction_format=...)` kwarg, falling back to the `HEADROOM_COMPACTION_FORMAT` env var, default `"csv-schema"`. ## Safety - **Default-off**: the default constructor path still calls the Rust `new()` constructor, so byte-parity coverage stays on the exact production codepath. A test asserts default output is byte-identical to an explicit `csv-schema` opt-in. - The existing `lossless_min_savings_ratio` gate (0.30) still applies. Markdown-KV repeats field names per row, so it clears the gate less often than CSV and falls through to the lossy path — we never inline a "lossless" rendering that isn't actually smaller. - CCR marker format unchanged across formatters; downstream retrieval pattern-matching keeps working. - No user/assistant content dropped — the formatter is a pure rendering of the same Compaction IR. ## Tests - Rust: 10 new unit tests in `compaction/formatter.rs` (table/buckets rendering, missing-cell omission, string quoting, CCR markers, drop summary, byte-size sanity vs raw JSON). `cargo test -p headroom-core`: 894 passed. Clippy + fmt clean. - Python: `tests/test_compaction_markdown_kv.py` (10 tests) — bridge rendering end-to-end, name→preset parity with the default constructor, kwarg/env knob precedence, loud failure on unknown names, default-output-unchanged guarantee. Existing smart_crusher suite: 38 passed. --------- Co-authored-by: Ash Rhodes <ashley.rhodes@king.com> |
||
|
Tejas Chopra
|
294df2b894
|
Merge pull request #403 from chopratejas/realign-F2_2-policy-tuning
fix(proxy): F2.2 — per-mode CompressionPolicy tuning fields |
||
|
Tejas Chopra
|
c83687798b | Fix Windows ORT builds and Docker signing retries | ||
|
Tejas Chopra
|
17ffae0cd8 |
fix: clear CI mypy + rust test failures introduced in eaf5980
compression_units.py:
- Replace dict-unpacking pattern with dataclasses.replace() so mypy can
type-check fields. The `**base` form forced mypy to infer
`dict[str, object]`, which doesn't satisfy the per-field types of
UnitCompressionResult (46 arg-type errors).
- Use `isinstance(candidates, Iterable)` for the transform-iteration
guard. The previous `iter()` call had a `# type: ignore[arg-type]`
that was misclassified — mypy actually emits `call-overload` here.
live_zone_thresholds.rs:
- Update the JsonArray threshold assertion from 1024 to 512 to match
the new constant.
|
||
|
Tejas Chopra
|
eaf5980b4a | fix: stabilize codex compression, stats, and proxy lifecycle | ||
|
chopratejas
|
89f7b6c2dd |
fix: complete /v1/responses compression telemetry, multi-frame WS, frozen-count cap
Builds on PR #406 (HTTP /v1/responses PyO3) and PR #410 (WS first-frame PyO3) which landed the binding for `compress_openai_responses_live_zone`. This change closes the remaining gaps so every (provider × endpoint × auth-mode × streaming) combination compresses AND surfaces in the dashboard. Telemetry: extend the PyO3 binding return tuple from `(bytes, modified)` to `(bytes, modified, tokens_saved, transforms_applied)` by adding `CompressionManifest::tokens_saved()` and `transforms_applied()` accessors on the existing manifest. The Python proxy populates request-log telemetry from the binding output instead of recounting tokens. Updates the existing 2-tuple call sites in HTTP and WS first-frame, plus the unpacks in tests. WebSocket multi-frame compression: subscription Codex users keep a long-lived WS open and send multiple `response.create` events per session. PR #410 only compressed the first frame; subsequent frames went raw. Added `_maybe_compress_response_create_frame` closure inside `_client_to_upstream` that runs the same Rust dispatcher on every client→upstream `response.create` text frame, passes other event types (response.cancel, session.update, etc.) through unchanged, and accumulates `tokens_saved` / `transforms_applied` / `ws_frames_compressed` counters across the session. Pre-existing dashboard gap: `streaming.py` and `anthropic.py` write `RequestLog` entries; the non-streaming OpenAI HTTP and WS handlers did not. Result: /transformations/feed was invisible for every Codex turn and every Cline / OpenClaude / Aider turn. Added the same wiring in `handle_openai_chat` (non-streaming), `handle_openai_responses` (non-streaming HTTP), and `handle_openai_responses_ws` (session-end). All three populate `auth_mode` + `endpoint` tags so the dashboard can break compression activity down by client class (PAYG / OAuth / Subscription) and surface (`chat_completions` / `responses_http` / `responses_ws`). The WS metric record is now unconditional — was previously gated on `tokens_saved > 0`, so first-frame no-changes never registered. compute_frozen_count over-freeze for prose-format clients: `compute_frozen_count` walked until it found an unstable `tool_result` / `role: "tool"` block. Cline / OpenClaude / Aider — clients that embed tool calls as XML inside plain text — never produce such a boundary, so the function returned `len(messages)` and the pipeline froze 100% of messages including the brand-new user turn. Live zone empty → `Transform content_router: 16414 → 16414 tokens (saved 0)`. Reported on Discord 2026-05-07 with Cline+DeepSeek. Fix: cap at `max(0, len(messages) - 1)`. Updates 3 existing test assertions whose expected values encoded the old over-freeze. Adds 6 new prose-format invariant tests. CodeQL "clear-text logging of sensitive information" fix: `tests/e2e_real_compression.py` previously stored API keys in local variables in the same scope as diagnostic prints, which CodeQL flagged via data-flow analysis. Refactored to read keys from `os.environ` inside the request helper — the credentials never enter the runner's main scope, so the taint flow never reaches the print. End-to-end verification with real keys (.env): /v1/messages (PAYG, non-stream) tok 14109 → 969 saved 13140 /v1/messages (PAYG, stream) tok 14109 → 969 saved 13140 /v1/chat/completions (PAYG, non-stream) tok 18460 → 1374 saved 17086 /v1/chat/completions (PAYG, stream) tok 18460 → 1374 saved 17086 (cache_hit=100%) /v1/responses HTTP (PAYG, non-stream) bytes 50138 → 597 saved 18391 /v1/responses WS (frame 1) bytes 46429 → 488 saved 16791 /v1/responses WS (frame 2 multi) bytes 46429 → 488 saved 16791 /v1/responses WS (response.cancel) passthrough untouched Tests: cargo workspace + pytest (4846 pass, 0 fail), make ci-precheck passed, two E2E scripts (multi-turn HTTP, WS fake-upstream) all green. |