…mpress-v2-base (#1613)

## Description

Adds an opt-in flag that routes **all** compressible content through
Kompress (`kompress-v2-base`), bypassing per-type compressor selection
(SmartCrusher / CodeAware / log / diff / html / tabular / search). For
deployments that prefer a single uniform compressor over the per-type
set, at a deliberate cost of per-type structural fidelity.

The mechanism already existed: `ContentRouter` reads a `force_kompress`
runtime kwarg but nothing turned it on. This PR wires it to user-facing
config (CLI + env), defaulting off.

Closes # N/A

## 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 `force_kompress_all` to `ProxyConfig` (`headroom/proxy/models.py`)
and `ContentRouterConfig` (`headroom/transforms/content_router.py`).
- Default the existing `force_kompress` runtime path from config:
`kwargs.get("force_kompress", self.config.force_kompress_all)` — a
per-request kwarg still overrides.
- Expose `--force-kompress-all` CLI flag and
`HEADROOM_FORCE_KOMPRESS_ALL=1` env, mirroring the existing
`--disable-kompress` pattern (both the env factory and the `__main__`
CLI path).
- Add `tests/test_force_kompress_all.py`.

**Safety preserved:** the flag changes *strategy selection only*. The
Read/Glob/Grep exclusion (`excluded_tool_ids`) runs *before* any
compressor, and the tool-output reversibility gate (`#1307`/`#1479`)
runs *after* — neither is reachable from the strategy choice. So tool
ground truth stays verbatim.

## Testing

- [x] Unit tests pass (`pytest`)
- [x] Linting passes (`ruff check`)
- [x] Type checking passes (`mypy`)
- [x] New tests added for new functionality
- [ ] Manual testing performed (see Real Behavior Proof → Not tested)

### Test Output

```text
$ ruff check headroom/proxy/models.py headroom/transforms/content_router.py headroom/proxy/server.py tests/test_force_kompress_all.py
All checks passed!

$ ruff format --check <same files>
4 files already formatted

$ mypy headroom/proxy/models.py headroom/transforms/content_router.py headroom/proxy/server.py tests/test_force_kompress_all.py
Success: no issues found in 4 source files

$ pytest tests/test_force_kompress_all.py tests/test_content_router_exclude_tools.py -q
tests/test_force_kompress_all.py ....                                    [ 44%]
tests/test_content_router_exclude_tools.py .....                         [100%]
============================== 9 passed in 1.31s ===============================
```

## Real Behavior Proof

- **Environment:** macOS (Darwin 25.4.0), Python 3.12.6, project
`.venv`.
- **Exact command / steps:** Constructed
`ContentRouter(ContentRouterConfig(force_kompress_all=True))` and drove
the real `apply()` entry point (see `tests/test_force_kompress_all.py`)
to verify: (1) the config resolves the runtime flag on; (2) an explicit
`force_kompress=False` kwarg overrides it; (3) a `Read` tool_result is
passed through **verbatim** with the flag on (`router:excluded:tool`
marker present). Plus the full ruff/mypy/pytest suite above.
- **Observed result:** 9 tests pass. Read tool output is unchanged
(byte-for-byte) under `force_kompress_all=True`; the per-request kwarg
override works; the existing exclude-tools suite still passes through
`HeadroomProxy` (which now builds
`ContentRouterConfig(force_kompress_all=...)`).
- **Not tested:** Live proxy end-to-end against a real upstream with the
`kompress-v2-base` ONNX model compressing real traffic; aggregate
savings/accuracy deltas on a real workload. The unit tests assert the
**routing decision and the Read/Glob carve-out**, not model output
quality or ratio.

## 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
(documented inline via config docstring + `--help`; see Additional
Notes)
- [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 (Release
Please generates it from the `feat(proxy):` commit)

## Additional Notes

- **Accuracy tradeoff (intentional):** forcing Kompress on all types
trades per-type structural fidelity (and possibly compression ratio,
since SmartCrusher/CodeAware can beat a general model on their native
type) for a single uniform compressor. Off by default; opt-in per
deployment. Correctness is *not* affected — excluded tools and
reversibility-gated tool ground truth are never touched.
- **Docs:** behavior is documented inline (CLI `--help` text +
`ProxyConfig` docstring). Happy to add a README/wiki note if maintainers
want one.

🤖 I have created a release *beep* *boop*
---


<details><summary>0.29.0</summary>

##
[0.29.0](v0.28.0...v0.29.0)
(2026-07-03)


### Features

* **proxy:** add --lossless no-CCR mode with format-native compaction
([#1721](#1721))
([c75ebde](c75ebde))
* **stats:** surface Codex WS compression counters in /stats summary
([#1680](#1680))
([2fe19c3](2fe19c3))
* **transforms:** adaptive Otsu KEEP/DROP threshold (+ land relevance
split on main)
([#1726](#1726))
([eea667a](eea667a))


### Bug Fixes

* **bedrock:** fail fast when session-token auth lacks botocore
([#1553](#1553))
([54cfa36](54cfa36))
* **bedrock:** route ARNs via converse, named AWS profiles, and au. re…
([#1456](#1456))
([7d87aa2](7d87aa2))
* **ccr:** honor workspace dir for sqlite store
([#1564](#1564))
([96e1dfe](96e1dfe))
* **claude:** surface Remote Control proxy incompatibility
([#1610](#1610))
([4bf7f92](4bf7f92))
* **cli:** stop advertising unwired compression tuning env vars in
banner
([#1634](#1634))
([d5bf98d](d5bf98d))
* **codex:** avoid duplicate headroom provider config
([#1431](#1431))
([ddd4adf](ddd4adf))
* **compression:** reject lossy unmarked tool output in unit router path
([#1479](#1479))
([de24cd5](de24cd5))
* **cortex-code:** migrate to current Cortex REST API endpoints + add
e2e benchmarks
([#1474](#1474))
([f00ace6](f00ace6))
* **dashboard:** align token savings headline denominator
([#1653](#1653))
([646e705](646e705))
* **dashboard:** derive per-project setup URL from live origin
([#1511](#1511))
([e035aef](e035aef))
* **detection:** contain unidiff panic on orphaned +++ target line
([#1548](#1548))
([e386c09](e386c09))
* **evals:** CJK-aware F1 tokenization + token estimation
([#1527](#1527))
([99a8540](99a8540))
* **install:** close parent log fd in start_detached_agent
([#1576](#1576))
([816cb85](816cb85))
* **install:** use Windows-safe PID liveness probe in runtime_status
([#1544](#1544))
([#1560](#1560))
([6b227b9](6b227b9))
* **learn:** aggregate verbosity baselines across projects instead of
overwriting
([#1288](#1288))
([27a5468](27a5468))
* **mcp:** show lifetime totals and label rolling session scope in
headroom_stats
([#1428](#1428))
([1c0e152](1c0e152))
* **memory:** cap local embedder CPU thread oversubscription
([#198](#198))
([#1559](#1559))
([b84afbf](b84afbf))
* **memory:** singleflight LocalBackend init to stop cold-start races
([#1691](#1691))
([bec47a1](bec47a1))
* **openclaw:** detect uv-installed headroom binary in ~/.local/bin
([#1459](#1459))
([adaeb88](adaeb88))
* **opencode:** preserve custom OpenAI gateway paths
([#1596](#1596))
([c19347c](c19347c))
* **opencode:** route native providers + load transport plugin, fix
Serena context
([#1573](#1573))
([ad0034f](ad0034f))
* preserve anthropic passthrough tool order
([#1427](#1427))
([a932247](a932247))
* **proxy/auth:** match real Anthropic OAuth token prefix (sk-ant-oat)
([#1672](#1672))
([8cddf9b](8cddf9b))
* **proxy:** expose persistent savings metrics
([#1647](#1647))
([5fe4e7b](5fe4e7b))
* **proxy:** fail open when kompress saturation would exhaust
pre-upstream budget
([#1430](#1430))
([15ac650](15ac650))
* **proxy:** handle streaming CCR retrieval
([#1451](#1451))
([d337e3b](d337e3b))
* **proxy:** include system/tools/sampling in cache key
([#1473](#1473))
([312129a](312129a))
* **proxy:** preserve Responses passthrough bytes
([#1598](#1598))
([2a34a82](2a34a82))
* **proxy:** strip Codex lite header on the HTTP /responses path
([#1663](#1663))
([9fbd47b](9fbd47b))
* **proxy:** wire --compression-max-workers /
HEADROOM_COMPRESSION_MAX_WORKERS
([#1632](#1632))
([814ffa3](814ffa3))
* **savings:** count cache-read tokens in input cost estimate
([#1429](#1429))
([72ade37](72ade37))
* skip Magika backend on x86 CPUs without AVX2
([#1162](#1162))
([64783d8](64783d8))
* **transforms/content-router:** route grep/log output away from HTML
extractor
([#1719](#1719))
([0d18ef2](0d18ef2))
* **transforms:** bound native content detection with a Windows watchdog
([#575](#575))
([#1563](#1563))
([95abca3](95abca3))
* Vertex AI support for Claude Code with ANTHROPIC_VERTEX_BASE_URL
([#1393](#1393))
([cff7247](cff7247))
* **wrap:** detach the shared proxy on Windows so it survives an
ungraceful agent close
([#1464](#1464))
([6cba441](6cba441))
* **wrap:** preserve custom Vertex base URL
([#1477](#1477))
([75427bb](75427bb))
* **wrap:** remove rtk instructions from Codex AGENTS.md on unwrap
([#1604](#1604))
([c9d717c](c9d717c))
</details>

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

…th (headroomlabs-ai#1479)

## Description

Closes headroomlabs-ai#1342

Codex shell output currently goes through the unit-router compression
path as a plain `local_shell_call_output` string. When that path picks a
lossy strategy and the compressed text carries no CCR retrieval marker,
the agent gets a summary that can't be reversed back to the original
shell log. That breaks the point of showing command output at all.

This change keeps structured shell output verbatim unless the
replacement stays recoverable. Other tool-output paths stay 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

- `headroom/transforms/compression_units.py`: add a lossy-strategy set
and a structured-shell heuristic, then reject lossy unmarked
replacements for `role="tool"` plus
`item_type="local_shell_call_output"` by returning the original text
with `reason="lossy_unrecoverable_tool_output"`.
- `tests/test_compression_units.py`: add regression coverage for the
failing case, the recoverable-marker case, non-shell tool output, and
assistant text so the guard stays scoped.

## 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
GitHub Actions on head 6790f03:
- PR Governance: green
- CI: green, including lint, build-wheel, docker-native-e2e, test shards 1-4, test-agno, test-dashboard-ui, and test-extras
- Init E2E: green
- Wrap E2E: green
- Evaluation Suite smoke-test: green
```

## Real Behavior Proof

- Environment: current PR head
`6790f034862cb7f6e698c745d729061b4d112aae` in GitHub Actions.
- Exact command / steps: exercise `compress_unit_with_router` with
structured multi-line `local_shell_call_output`, return a lossy unmarked
replacement, and assert the original shell text is kept with
`reason="lossy_unrecoverable_tool_output"`. Paired tests prove that
CCR-marked replacements still compress, non-shell tool output still
compresses, and assistant text still compresses when explicitly allowed.
- Observed result: the new regression coverage passes on the PR head and
the full PR check set is green.
- Not tested: end-to-end live shell sessions through the Responses API;
intentionally unstructured shell output below this heuristic remains
compressible.

## 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
- [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
- [ ] I have updated the CHANGELOG.md if applicable

## Screenshots (if applicable)

N/A, backend compression-path change.

## Additional Notes

`mypy headroom` was not run for this PR body refresh, so the type-check
box stays unchecked here. The changelog and docs boxes are N/A for this
targeted bug fix.

…mpress-v2-base (headroomlabs-ai#1613)

## Description

Adds an opt-in flag that routes **all** compressible content through
Kompress (`kompress-v2-base`), bypassing per-type compressor selection
(SmartCrusher / CodeAware / log / diff / html / tabular / search). For
deployments that prefer a single uniform compressor over the per-type
set, at a deliberate cost of per-type structural fidelity.

The mechanism already existed: `ContentRouter` reads a `force_kompress`
runtime kwarg but nothing turned it on. This PR wires it to user-facing
config (CLI + env), defaulting off.

Closes # N/A

## 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 `force_kompress_all` to `ProxyConfig` (`headroom/proxy/models.py`)
and `ContentRouterConfig` (`headroom/transforms/content_router.py`).
- Default the existing `force_kompress` runtime path from config:
`kwargs.get("force_kompress", self.config.force_kompress_all)` — a
per-request kwarg still overrides.
- Expose `--force-kompress-all` CLI flag and
`HEADROOM_FORCE_KOMPRESS_ALL=1` env, mirroring the existing
`--disable-kompress` pattern (both the env factory and the `__main__`
CLI path).
- Add `tests/test_force_kompress_all.py`.

**Safety preserved:** the flag changes *strategy selection only*. The
Read/Glob/Grep exclusion (`excluded_tool_ids`) runs *before* any
compressor, and the tool-output reversibility gate (`headroomlabs-ai#1307`/`headroomlabs-ai#1479`)
runs *after* — neither is reachable from the strategy choice. So tool
ground truth stays verbatim.

## Testing

- [x] Unit tests pass (`pytest`)
- [x] Linting passes (`ruff check`)
- [x] Type checking passes (`mypy`)
- [x] New tests added for new functionality
- [ ] Manual testing performed (see Real Behavior Proof → Not tested)

### Test Output

```text
$ ruff check headroom/proxy/models.py headroom/transforms/content_router.py headroom/proxy/server.py tests/test_force_kompress_all.py
All checks passed!

$ ruff format --check <same files>
4 files already formatted

$ mypy headroom/proxy/models.py headroom/transforms/content_router.py headroom/proxy/server.py tests/test_force_kompress_all.py
Success: no issues found in 4 source files

$ pytest tests/test_force_kompress_all.py tests/test_content_router_exclude_tools.py -q
tests/test_force_kompress_all.py ....                                    [ 44%]
tests/test_content_router_exclude_tools.py .....                         [100%]
============================== 9 passed in 1.31s ===============================
```

## Real Behavior Proof

- **Environment:** macOS (Darwin 25.4.0), Python 3.12.6, project
`.venv`.
- **Exact command / steps:** Constructed
`ContentRouter(ContentRouterConfig(force_kompress_all=True))` and drove
the real `apply()` entry point (see `tests/test_force_kompress_all.py`)
to verify: (1) the config resolves the runtime flag on; (2) an explicit
`force_kompress=False` kwarg overrides it; (3) a `Read` tool_result is
passed through **verbatim** with the flag on (`router:excluded:tool`
marker present). Plus the full ruff/mypy/pytest suite above.
- **Observed result:** 9 tests pass. Read tool output is unchanged
(byte-for-byte) under `force_kompress_all=True`; the per-request kwarg
override works; the existing exclude-tools suite still passes through
`HeadroomProxy` (which now builds
`ContentRouterConfig(force_kompress_all=...)`).
- **Not tested:** Live proxy end-to-end against a real upstream with the
`kompress-v2-base` ONNX model compressing real traffic; aggregate
savings/accuracy deltas on a real workload. The unit tests assert the
**routing decision and the Read/Glob carve-out**, not model output
quality or ratio.

## 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
(documented inline via config docstring + `--help`; see Additional
Notes)
- [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 (Release
Please generates it from the `feat(proxy):` commit)

## Additional Notes

- **Accuracy tradeoff (intentional):** forcing Kompress on all types
trades per-type structural fidelity (and possibly compression ratio,
since SmartCrusher/CodeAware can beat a general model on their native
type) for a single uniform compressor. Off by default; opt-in per
deployment. Correctness is *not* affected — excluded tools and
reversibility-gated tool ground truth are never touched.
- **Docs:** behavior is documented inline (CLI `--help` text +
`ProxyConfig` docstring). Happy to add a README/wiki note if maintainers
want one.

🤖 I have created a release *beep* *boop*
---


<details><summary>0.29.0</summary>

##
[0.29.0](headroomlabs-ai/headroom@v0.28.0...v0.29.0)
(2026-07-03)


### Features

* **proxy:** add --lossless no-CCR mode with format-native compaction
([headroomlabs-ai#1721](headroomlabs-ai#1721))
([c75ebde](headroomlabs-ai@c75ebde))
* **stats:** surface Codex WS compression counters in /stats summary
([headroomlabs-ai#1680](headroomlabs-ai#1680))
([2fe19c3](headroomlabs-ai@2fe19c3))
* **transforms:** adaptive Otsu KEEP/DROP threshold (+ land relevance
split on main)
([headroomlabs-ai#1726](headroomlabs-ai#1726))
([eea667a](headroomlabs-ai@eea667a))


### Bug Fixes

* **bedrock:** fail fast when session-token auth lacks botocore
([headroomlabs-ai#1553](headroomlabs-ai#1553))
([54cfa36](headroomlabs-ai@54cfa36))
* **bedrock:** route ARNs via converse, named AWS profiles, and au. re…
([headroomlabs-ai#1456](headroomlabs-ai#1456))
([7d87aa2](headroomlabs-ai@7d87aa2))
* **ccr:** honor workspace dir for sqlite store
([headroomlabs-ai#1564](headroomlabs-ai#1564))
([96e1dfe](headroomlabs-ai@96e1dfe))
* **claude:** surface Remote Control proxy incompatibility
([headroomlabs-ai#1610](headroomlabs-ai#1610))
([4bf7f92](headroomlabs-ai@4bf7f92))
* **cli:** stop advertising unwired compression tuning env vars in
banner
([headroomlabs-ai#1634](headroomlabs-ai#1634))
([d5bf98d](headroomlabs-ai@d5bf98d))
* **codex:** avoid duplicate headroom provider config
([headroomlabs-ai#1431](headroomlabs-ai#1431))
([ddd4adf](headroomlabs-ai@ddd4adf))
* **compression:** reject lossy unmarked tool output in unit router path
([headroomlabs-ai#1479](headroomlabs-ai#1479))
([de24cd5](headroomlabs-ai@de24cd5))
* **cortex-code:** migrate to current Cortex REST API endpoints + add
e2e benchmarks
([headroomlabs-ai#1474](headroomlabs-ai#1474))
([f00ace6](headroomlabs-ai@f00ace6))
* **dashboard:** align token savings headline denominator
([headroomlabs-ai#1653](headroomlabs-ai#1653))
([646e705](headroomlabs-ai@646e705))
* **dashboard:** derive per-project setup URL from live origin
([headroomlabs-ai#1511](headroomlabs-ai#1511))
([e035aef](headroomlabs-ai@e035aef))
* **detection:** contain unidiff panic on orphaned +++ target line
([headroomlabs-ai#1548](headroomlabs-ai#1548))
([e386c09](headroomlabs-ai@e386c09))
* **evals:** CJK-aware F1 tokenization + token estimation
([headroomlabs-ai#1527](headroomlabs-ai#1527))
([99a8540](headroomlabs-ai@99a8540))
* **install:** close parent log fd in start_detached_agent
([headroomlabs-ai#1576](headroomlabs-ai#1576))
([816cb85](headroomlabs-ai@816cb85))
* **install:** use Windows-safe PID liveness probe in runtime_status
([headroomlabs-ai#1544](headroomlabs-ai#1544))
([headroomlabs-ai#1560](headroomlabs-ai#1560))
([6b227b9](headroomlabs-ai@6b227b9))
* **learn:** aggregate verbosity baselines across projects instead of
overwriting
([headroomlabs-ai#1288](headroomlabs-ai#1288))
([27a5468](headroomlabs-ai@27a5468))
* **mcp:** show lifetime totals and label rolling session scope in
headroom_stats
([headroomlabs-ai#1428](headroomlabs-ai#1428))
([1c0e152](headroomlabs-ai@1c0e152))
* **memory:** cap local embedder CPU thread oversubscription
([headroomlabs-ai#198](headroomlabs-ai#198))
([headroomlabs-ai#1559](headroomlabs-ai#1559))
([b84afbf](headroomlabs-ai@b84afbf))
* **memory:** singleflight LocalBackend init to stop cold-start races
([headroomlabs-ai#1691](headroomlabs-ai#1691))
([bec47a1](headroomlabs-ai@bec47a1))
* **openclaw:** detect uv-installed headroom binary in ~/.local/bin
([headroomlabs-ai#1459](headroomlabs-ai#1459))
([adaeb88](headroomlabs-ai@adaeb88))
* **opencode:** preserve custom OpenAI gateway paths
([headroomlabs-ai#1596](headroomlabs-ai#1596))
([c19347c](headroomlabs-ai@c19347c))
* **opencode:** route native providers + load transport plugin, fix
Serena context
([headroomlabs-ai#1573](headroomlabs-ai#1573))
([ad0034f](headroomlabs-ai@ad0034f))
* preserve anthropic passthrough tool order
([headroomlabs-ai#1427](headroomlabs-ai#1427))
([a932247](headroomlabs-ai@a932247))
* **proxy/auth:** match real Anthropic OAuth token prefix (sk-ant-oat)
([headroomlabs-ai#1672](headroomlabs-ai#1672))
([8cddf9b](headroomlabs-ai@8cddf9b))
* **proxy:** expose persistent savings metrics
([headroomlabs-ai#1647](headroomlabs-ai#1647))
([5fe4e7b](headroomlabs-ai@5fe4e7b))
* **proxy:** fail open when kompress saturation would exhaust
pre-upstream budget
([headroomlabs-ai#1430](headroomlabs-ai#1430))
([15ac650](headroomlabs-ai@15ac650))
* **proxy:** handle streaming CCR retrieval
([headroomlabs-ai#1451](headroomlabs-ai#1451))
([d337e3b](headroomlabs-ai@d337e3b))
* **proxy:** include system/tools/sampling in cache key
([headroomlabs-ai#1473](headroomlabs-ai#1473))
([312129a](headroomlabs-ai@312129a))
* **proxy:** preserve Responses passthrough bytes
([headroomlabs-ai#1598](headroomlabs-ai#1598))
([2a34a82](headroomlabs-ai@2a34a82))
* **proxy:** strip Codex lite header on the HTTP /responses path
([headroomlabs-ai#1663](headroomlabs-ai#1663))
([9fbd47b](headroomlabs-ai@9fbd47b))
* **proxy:** wire --compression-max-workers /
HEADROOM_COMPRESSION_MAX_WORKERS
([headroomlabs-ai#1632](headroomlabs-ai#1632))
([814ffa3](headroomlabs-ai@814ffa3))
* **savings:** count cache-read tokens in input cost estimate
([headroomlabs-ai#1429](headroomlabs-ai#1429))
([72ade37](headroomlabs-ai@72ade37))
* skip Magika backend on x86 CPUs without AVX2
([headroomlabs-ai#1162](headroomlabs-ai#1162))
([64783d8](headroomlabs-ai@64783d8))
* **transforms/content-router:** route grep/log output away from HTML
extractor
([headroomlabs-ai#1719](headroomlabs-ai#1719))
([0d18ef2](headroomlabs-ai@0d18ef2))
* **transforms:** bound native content detection with a Windows watchdog
([headroomlabs-ai#575](headroomlabs-ai#575))
([headroomlabs-ai#1563](headroomlabs-ai#1563))
([95abca3](headroomlabs-ai@95abca3))
* Vertex AI support for Claude Code with ANTHROPIC_VERTEX_BASE_URL
([headroomlabs-ai#1393](headroomlabs-ai#1393))
([cff7247](headroomlabs-ai@cff7247))
* **wrap:** detach the shared proxy on Windows so it survives an
ungraceful agent close
([headroomlabs-ai#1464](headroomlabs-ai#1464))
([6cba441](headroomlabs-ai@6cba441))
* **wrap:** preserve custom Vertex base URL
([headroomlabs-ai#1477](headroomlabs-ai#1477))
([75427bb](headroomlabs-ai@75427bb))
* **wrap:** remove rtk instructions from Codex AGENTS.md on unwrap
([headroomlabs-ai#1604](headroomlabs-ai#1604))
([c9d717c](headroomlabs-ai@c9d717c))
</details>

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>