Skip to content

feat(content-router): accept any real compression (remove min-savings floor) - #1771

Merged
chopratejas merged 1 commit into
mainfrom
tejas/accept-any-compression
Jul 3, 2026
Merged

feat(content-router): accept any real compression (remove min-savings floor)#1771
chopratejas merged 1 commit into
mainfrom
tejas/accept-any-compression

Conversation

@chopratejas

@chopratejas chopratejas commented Jul 3, 2026

Copy link
Copy Markdown
Collaborator

Description

The compression acceptance gate rejected any compression that saved less than ~15% (min_ratio interpolated 0.85 at low context pressure → 0.65 under pressure). That floor was a crude proxy for "big enough to justify busting the prefix cache," but it dropped genuine token savings — notably lossless code/log folds that shrink <15% (the ratio_too_high rejections).

This makes the gate accept any real shrink (ratio < 1.0): any token saved is worth taking. The two guards that actually protect correctness are untouched:

Lowering the two values back to 0.85/0.65 restores the savings floor.

Closes #

Type of Change

  • New feature (non-breaking change that adds functionality)
  • Performance improvement

Changes Made

  • ContentRouterConfig.min_ratio_relaxed: 0.85 → 1.0
  • ContentRouterConfig.min_ratio_aggressive: 0.65 → 1.0
  • Gate now accepts any compression_ratio < 1.0 at every context pressure; reversibility + net-cost guards unchanged.

Testing

  • Unit tests pass (pytest)
  • Linting passes (ruff check)
  • Type checking passes (mypy headroom)
  • New tests added for new functionality (existing gate-mechanism tests cover it; they pass explicit min_ratio values and are unaffected)
  • Manual testing performed

Test Output

# content-router + compression suites (default-config paths):
tests/test_transforms/test_content_router.py ......... 139 passed
# broad compression sweep (-k compress/router/crush/kompress/lossless/ccr/savings/...):
1 failed, 1940 passed, 54 skipped in 181.25s
#   the 1 failure = test_lossless_mode::test_router_lossless_search_no_marker_and_recoverable
#   — a local fastembed-cache state-leak flake; passes in isolation (1 passed in 3.15s),
#   and is in lossless mode which bypasses this gate entirely.
ruff check headroom/transforms/content_router.py  -> All checks passed!
mypy headroom/transforms/content_router.py         -> Success: no issues found

Real Behavior Proof

  • Environment: local worktree, Python 3.12, PYTHONPATH pinned to the branch checkout.
  • Exact command / steps: ran the content-router acceptance-gate suites and a compression-adjacent sweep against the branch; verified the flaky test passes in isolation.
  • Observed result: gate-mechanism tests (explicit min_ratio) unaffected; no default-floor test regressed; blocks that previously produced ratio_too_high at ratios in [0.85, 1.0) are now accepted.
  • Not tested: no live end-to-end proxy run was performed for this specific change; the behavioral effect (more router:* acceptances, fewer ratio_too_high) is inferred from the gate logic + suite.

Review Readiness

  • I have performed a self-review
  • This PR is ready for human review

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 (existing gate tests cover the mechanism)
  • New and existing unit tests pass locally with my changes
  • I have updated the CHANGELOG.md if applicable (handled at release time)

Additional Notes

Deliberate tradeoff (discussed and chosen): without the net-cost policy enabled, accepting sub-15% wins can be net-negative on prompt-cached sessions, because compressing a block invalidates the cached suffix (a one-time re-write, at 1.25× on Anthropic). If that shows up in practice, enable HEADROOM_NET_COST_POLICY=1 (the precise economics guard) or restore a floor by lowering the two min_ratio_* values.

@chopratejas
feat(content-router): accept any real compression (remove min-savings…
db260ee 
… floor)

The acceptance gate rejected compressions saving <15% (min_ratio 0.85 at low
context pressure, 0.65 under pressure) — a crude proxy for "big enough to
justify busting the prefix cache." It dropped genuine token savings, including
lossless code/log folds that shrink <15% (the ratio_too_high rejects).

Set min_ratio to 1.0 at every pressure: accept ANY real shrink (ratio < 1.0);
any token saved is worth taking. The two guards that actually matter are
untouched — the reversibility gate keeps lossy-unmarked tool output verbatim
(accuracy), and the opt-in net-cost policy (HEADROOM_NET_COST_POLICY=1)
precisely accounts for cache-bust economics when enabled. Lower the values to
restore a savings floor.
@github-actions

github-actions Bot commented Jul 3, 2026

Copy link
Copy Markdown
Contributor

PR governance

This PR follows the template and is marked ready for human review.

@github-actions github-actions Bot added the status: ready for review Pull request body is complete and the author marked it ready for human review label Jul 3, 2026
@chopratejas
chopratejas merged commit 6c31db9 into main Jul 3, 2026
29 checks passed
@chopratejas chopratejas mentioned this pull request Jul 3, 2026
Merged
13 of 16 tasks
chopratejas added a commit that referenced this pull request Jul 3, 2026
@chopratejas
fix(content-router): token-measure lossless folds at the acceptance gate
3e6cb34 
Unit mismatch: the apply() acceptance gate computes compression_ratio from
len(text.split()) (word count), but a lossless search/log fold cuts TOKENS by
collapsing a repeated path prefix into one heading — word count stays flat or
rises (the heading adds a word). So the gate saw ratio >= 1.0 and discarded
every free, recoverable win as ratio_too_high. Raising the floor to 1.0 (#1771)
didn't help; the word-ratio was already >= 1.0.

Measure lossless results (strategy_chain has a lossless_* entry) by REAL TOKEN
count via the tokenizer already in scope — not words, not bytes — so a fold is
accepted iff it genuinely reduces tokens. Gate + result cache use this ratio.
Lossy strategies are unchanged (word count tracks their savings) and the
reversibility gate is untouched (LOG/SEARCH/DIFF aren't lossy-unmarked). The
excluded and bash-search paths already bypass this gate; this fixes the main
strategy dispatch.

Regression test drives the full router.apply() path and asserts fewer TOKENS
(compress()/_apply_strategy_to_content bypass the gate, which is why prior unit
tests missed it).
chopratejas added a commit that referenced this pull request Jul 3, 2026
@chopratejas
fix(content-router): token-measure lossless folds at the acceptance g…
c5493ea 
…ate (#1772)

## Description

Unit-mismatch bug in the compression acceptance gate. `router.apply()`
computes `compression_ratio` from `len(text.split())` (word count), but
a **lossless** search/log fold (`compact_lossless`) saves **bytes** by
collapsing a repeated path prefix into a single heading — word count
stays flat or even *rises* (the heading adds a word). So the gate saw
`ratio ≥ 1.0` and discarded every free, byte-recoverable win as
`ratio_too_high`. (Raising the floor to 1.0 in #1771 did **not** fix
this — the word-ratio was already ≥ 1.0.)

Measure lossless results (those whose `strategy_chain` carries a
`lossless_*` entry) by **byte ratio** at the gate and in the result
cache — the real saving. Lossy strategies are unchanged (word count
tracks their token savings), and the reversibility gate is untouched
(`LOG`/`SEARCH`/`DIFF` aren't in `LOSSY_UNMARKED_STRATEGIES`). The
excluded-tool and bash-search paths already bypass this gate via
`continue`; this fixes the **main strategy dispatch** (the lossless-mode
`LOG`/`SEARCH`/`DIFF` path).

Follow-up to #1771.

Closes #

## Type of Change

- [x] Bug fix (non-breaking change that fixes an issue)

## Changes Made

- At the `apply()` acceptance gate: compute `accept_ratio` = byte ratio
for lossless results (`strategy_chain` has `lossless_*`), else the
existing word ratio. Gate + result-cache entry now use `accept_ratio`.
- Added an end-to-end regression test that drives the full
`router.apply()` path.

## Testing

- [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
tests/test_lossless_mode.py::test_router_apply_accepts_lossless_search_byte_measured PASSED
tests/test_content_router_tool_role_reversibility.py .......... (10 passed)
# broader (pre-move) sweep on the same change:
tests/test_lossless_mode.py / test_transforms/test_content_router.py /
test_lossless_excluded_compaction.py / test_bash_search_lossless_fold.py — 121 passed
ruff check headroom/transforms/content_router.py  -> All checks passed!
mypy headroom/transforms/content_router.py         -> Success: no issues found
```

## Real Behavior Proof

- Environment: local worktree, Python 3.12, `PYTHONPATH` pinned to the
branch.
- Exact command / steps: new regression test constructs a single-file
grep result, runs it through `ContentRouter(lossless=True).apply(...)`,
and asserts the tool output is byte-smaller and recovers exactly
(`search_unheading(out) == original`).
- Observed result: before this fix the fold was rejected (`out ==
original`, counted `ratio_too_high`); after, it's applied (`len(out) <
len(original)`, marker-free, byte-exact recovery). The test also asserts
the fold's word count is ≥ the original's, so the test is meaningless if
"fixed" by word count.
- Not tested: no live end-to-end proxy run; validated via the full
`apply()` path in unit 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
- [x] New and existing unit tests pass locally with my changes
- [ ] I have updated the CHANGELOG.md if applicable (handled at release
time)

## Additional Notes

Why prior tests missed it: `compress()` and `_apply_strategy_to_content`
return the folded result directly and never touch the `apply()`
acceptance gate, so the existing lossless-mode unit tests (which call
those) passed while the real proxy path silently discarded the fold. The
new test exercises `apply()` end-to-end.
@github-actions github-actions Bot mentioned this pull request Jul 9, 2026
Merged
chopratejas pushed a commit that referenced this pull request Jul 9, 2026
@github-actions
chore: release main (#1918)
a951515 
🤖 I have created a release *beep* *boop*
---


<details><summary>0.31.0</summary>

##
[0.31.0](v0.30.0...v0.31.0)
(2026-07-09)


### Features

* **cache:** provider-agnostic cache-mode delta + cc-agnostic prefix
comparison
([#1868](#1868))
([7c2f0ea](7c2f0ea))
* **ccr:** wire retrieve-tool interception into OpenAI Responses handler
([#1898](#1898))
([62cd307](62cd307))
* **compression:** add audit-safe mode with protected pattern matching
([#1899](#1899))
([bb112dd](bb112dd))
* **content-router:** accept any real compression (remove min-savings
floor)
([#1771](#1771))
([6c31db9](6c31db9))
* **content-router:** lossless-first dispatch, cross-turn dedup, and A7
lossy-after-fold
([#1818](#1818))
([60af15f](60af15f))
* **proxy:** add provider-only HTTP proxy
([#1807](#1807))
([ebe0a3b](ebe0a3b))
* **proxy:** add turn-hook extension point for buffered model turns
([#1891](#1891))
([ec950f7](ec950f7))


### Bug Fixes

* **build:** enable Intel macOS pip installs via ort-load-dynamic
([#1538](#1538))
([32ce99e](32ce99e))
* **cache:** avoid fallback session collisions
([#1827](#1827))
([0f606b6](0f606b6))
* **ccr:** make expired retrieve misses terminal
([#1781](#1781))
([9cbdba4](9cbdba4))
* **ccr:** preserve Anthropic re-stream shape
([#1854](#1854))
([f663894](f663894))
* **ccr:** preserve thinking blocks in buffered stream re-synthesis
([#1897](#1897))
([ede085c](ede085c))
* **cli/proxy:** preserve explicit HEADROOM_MIN_TOKENS=0 / MAX_ITEMS=0
([#1886](#1886))
([3a33af1](3a33af1))
* **code-compressor:** CJK-aware relevance-query symbol matching
([#1747](#1747))
([b38315c](b38315c))
* **codex:** discover updated Codex state stores
([#1889](#1889))
([9d42eba](9d42eba))
* **codex:** OpenCode Zen telemetry attribution
([#1648](#1648))
([f18c6bd](f18c6bd))
* **content-detector:** detect and compress space-separated JSON objects
([#1742](#1742))
([5194bdc](5194bdc))
* **content-router:** token-measure lossless folds at the acceptance
gate ([#1772](#1772))
([c5493ea](c5493ea))
* **copilot:** normalize subscription routing host
([#1836](#1836))
([afd9cbd](afd9cbd))
* **copilot:** route mixed-model requests per model
([#1785](#1785))
([5af5e22](5af5e22))
* **dashboard:** deduplicate repeated savings metrics
([#1804](#1804))
([88f935a](88f935a))
* **dashboard:** distinguish unavailable RTK from zero stats in Docker
([#1900](#1900))
([87f6e93](87f6e93))
* **dashboard:** distinguish unavailable RTK from zero stats in Docker
([#1901](#1901))
([361adcd](361adcd))
* **dashboard:** price proxy savings without litellm
([#1728](#1728))
([188e382](188e382))
* detect and clear stale ANTHROPIC_BASE_URL from crashed wrap sessions
([#1768](#1768))
([#1837](#1837))
([84509a4](84509a4))
* **docker:** persist headroom workspace in compose
([#1839](#1839))
([5e29c06](5e29c06))
* **docker:** report source build version
([#1862](#1862))
([3807488](3807488))
* **evals:** default unparseable judge scores below pass threshold
([#1892](#1892))
([42ebbc6](42ebbc6))
* **install:** pass sc.exe create as raw command line so binPath=
quoting survives
([#1654](#1654))
([#1702](#1702))
([d6e0710](d6e0710))
* **install:** persist --no-http2 override through install apply
([#1676](#1676))
([6fb5f3b](6fb5f3b))
* **mcp:** isolate ClaudeRegistrar CLI config env
([#1888](#1888))
([1c947b1](1c947b1))
* **mcp:** surface dead proxy state
([#1786](#1786))
([931eed8](931eed8))
* **memory:** resolve Trae cwd metadata from user reminders
([#1737](#1737))
([#1887](#1887))
([3e85eb1](3e85eb1))
* **opencode:** use local MCP config
([#1383](#1383))
([4bd3ddf](4bd3ddf))
* **proxy/openai:** thread savings-profile kwargs into chat completions
([#1606](#1606))
([7ff842d](7ff842d))
* **proxy/openai:** translate max_tokens -&gt; max_completion_tokens on
chat path
([#1774](#1774))
([285808b](285808b))
* **proxy:** bound Codex WS compression fallback latency
([#1802](#1802))
([d24a3f8](d24a3f8))
* **proxy:** bound HF tokenizer load and offload token counting off
event loop
([#1738](#1738))
([46d5d68](46d5d68))
* **proxy:** cancel retry backoff on shutdown
([#1834](#1834))
([da2d8dc](da2d8dc))
* **proxy:** compress Anthropic user text blocks when enabled
([#1875](#1875))
([e36439a](e36439a))
* **proxy:** freeze must forward cached (compressed) prefix
byte-identical — stop token-mode cache busting
([#1850](#1850))
([248ae0f](248ae0f))
* **proxy:** fsync savings dir after atomic rename
([#1764](#1764))
([7de2c1e](7de2c1e))
* **proxy:** keep cache_control bounded + stable so the freeze overlay
stops busting
([#1852](#1852))
([4820134](4820134))
* **proxy:** persist lifetime cache-read savings across restarts
([#1665](#1665))
([908997e](908997e))
* **proxy:** preserve streaming passthrough beta headers
([#1783](#1783))
([0f553a8](0f553a8))
* **proxy:** release _active_streams session lock on setup-phase errors
([#1864](#1864))
([2ccd831](2ccd831))
* **proxy:** retry HTTP/2 stream resets instead of 502ing
([#1645](#1645))
([2ce19c2](2ce19c2))
* **proxy:** retry passthrough on transient upstream connection close
([#1513](#1513))
([5d14080](5d14080))
* **proxy:** route Foundry Anthropic messages
([#1878](#1878))
([739f654](739f654))
* **proxy:** serve /favicon.ico locally instead of tunneling upstream
([#1787](#1787))
([#1847](#1847))
([3076e32](3076e32))
* **proxy:** stop rtk stat failures from corrupting session baseline
([#1693](#1693))
([681b9a8](681b9a8))
* **proxy:** strip 1m model suffix before upstream forwarding
([#1840](#1840))
([e22d745](e22d745))
* **proxy:** subtract cache write premiums from net savings
([#1800](#1800))
([53a465b](53a465b))
* **router:** honor MCP aliases in excluded tools
([#1822](#1822))
([#1863](#1863))
([140d6e4](140d6e4))
* **rtk:** link managed rtk onto PATH instead of mutating the hook
([#1698](#1698))
([140cb05](140cb05))
* **streaming:** preserve server_tool_use sse blocks
([#1826](#1826))
([4ac5493](4ac5493))
* **toin:** publish skip compression recommendations
([#1782](#1782))
([be51008](be51008))
* **transforms:** normalize diff compressor context
([#1801](#1801))
([838c523](838c523))
* **transforms:** pass through ragged tables instead of misaligning
columns
([#1713](#1713))
([c7665ca](c7665ca))
* use rtk native Cursor hook instead of injecting .cursorrules
([#756](#756))
([#1846](#1846))
([1573f1f](1573f1f))
* **wrap:** replace stale-proxy detection with Vite-style port fallback
([#1406](#1406))
([b4205c6](b4205c6))


### Performance Improvements

* **proxy:** cap compression workers to CPU count
([#1803](#1803))
([0a3851b](0a3851b))
* **savings:** batch tracker persistence off the request hot path
([#1817](#1817))
([451b9f0](451b9f0))


### Dependencies

* bump the cargo-minor-patch group across 1 directory with 7 updates
([#1909](#1909))
([45601d9](45601d9))
* bump the npm-minor-patch group across 4 directories with 18 updates
([#1907](#1907))
([8872bbc](8872bbc))
</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>
JerrettDavis pushed a commit to peterlodri-sec/headroom that referenced this pull request Jul 14, 2026
@chopratejas
feat(content-router): accept any real compression (remove min-savings…
bdc9495 
… floor) (headroomlabs-ai#1771)

## Description

The compression acceptance gate rejected any compression that saved less
than ~15% (`min_ratio` interpolated 0.85 at low context pressure → 0.65
under pressure). That floor was a crude proxy for "big enough to justify
busting the prefix cache," but it dropped genuine token savings —
notably lossless code/log folds that shrink <15% (the `ratio_too_high`
rejections).

This makes the gate accept **any real shrink** (`ratio < 1.0`): any
token saved is worth taking. The two guards that actually protect
correctness are untouched:
- **Reversibility gate** — lossy, unmarked tool output still stays
verbatim (accuracy; headroomlabs-ai#1307).
- **Net-cost policy** (`HEADROOM_NET_COST_POLICY=1`, opt-in) — precisely
accounts for the prefix-cache-bust economics (savings × expected-reads
vs one-time suffix re-write) when a session wants that protection.

Lowering the two values back to `0.85`/`0.65` restores the savings
floor.

Closes #

## Type of Change

- [x] New feature (non-breaking change that adds functionality)
- [x] Performance improvement

## Changes Made

- `ContentRouterConfig.min_ratio_relaxed`: `0.85 → 1.0`
- `ContentRouterConfig.min_ratio_aggressive`: `0.65 → 1.0`
- Gate now accepts any `compression_ratio < 1.0` at every context
pressure; reversibility + net-cost guards unchanged.

## Testing

- [x] Unit tests pass (`pytest`)
- [x] Linting passes (`ruff check`)
- [x] Type checking passes (`mypy headroom`)
- [ ] New tests added for new functionality (existing gate-mechanism
tests cover it; they pass explicit `min_ratio` values and are
unaffected)
- [ ] Manual testing performed

### Test Output

```text
# content-router + compression suites (default-config paths):
tests/test_transforms/test_content_router.py ......... 139 passed
# broad compression sweep (-k compress/router/crush/kompress/lossless/ccr/savings/...):
1 failed, 1940 passed, 54 skipped in 181.25s
#   the 1 failure = test_lossless_mode::test_router_lossless_search_no_marker_and_recoverable
#   — a local fastembed-cache state-leak flake; passes in isolation (1 passed in 3.15s),
#   and is in lossless mode which bypasses this gate entirely.
ruff check headroom/transforms/content_router.py  -> All checks passed!
mypy headroom/transforms/content_router.py         -> Success: no issues found
```

## Real Behavior Proof

- Environment: local worktree, Python 3.12, `PYTHONPATH` pinned to the
branch checkout.
- Exact command / steps: ran the content-router acceptance-gate suites
and a compression-adjacent sweep against the branch; verified the flaky
test passes in isolation.
- Observed result: gate-mechanism tests (explicit `min_ratio`)
unaffected; no default-floor test regressed; blocks that previously
produced `ratio_too_high` at ratios in `[0.85, 1.0)` are now accepted.
- Not tested: no live end-to-end proxy run was performed for this
specific change; the behavioral effect (more `router:*` acceptances,
fewer `ratio_too_high`) is inferred from the gate logic + suite.

## Review Readiness

- [x] I have performed a self-review
- [x] This PR is ready for human review

## Checklist

- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective (existing gate
tests cover the mechanism)
- [x] New and existing unit tests pass locally with my changes
- [ ] I have updated the CHANGELOG.md if applicable (handled at release
time)

## Additional Notes

Deliberate tradeoff (discussed and chosen): without the net-cost policy
enabled, accepting sub-15% wins can be net-negative on prompt-cached
sessions, because compressing a block invalidates the cached suffix (a
one-time re-write, at 1.25× on Anthropic). If that shows up in practice,
enable `HEADROOM_NET_COST_POLICY=1` (the precise economics guard) or
restore a floor by lowering the two `min_ratio_*` values.
JerrettDavis pushed a commit to peterlodri-sec/headroom that referenced this pull request Jul 14, 2026
@chopratejas
fix(content-router): token-measure lossless folds at the acceptance g…
4efebdf 
…ate (headroomlabs-ai#1772)

## Description

Unit-mismatch bug in the compression acceptance gate. `router.apply()`
computes `compression_ratio` from `len(text.split())` (word count), but
a **lossless** search/log fold (`compact_lossless`) saves **bytes** by
collapsing a repeated path prefix into a single heading — word count
stays flat or even *rises* (the heading adds a word). So the gate saw
`ratio ≥ 1.0` and discarded every free, byte-recoverable win as
`ratio_too_high`. (Raising the floor to 1.0 in headroomlabs-ai#1771 did **not** fix
this — the word-ratio was already ≥ 1.0.)

Measure lossless results (those whose `strategy_chain` carries a
`lossless_*` entry) by **byte ratio** at the gate and in the result
cache — the real saving. Lossy strategies are unchanged (word count
tracks their token savings), and the reversibility gate is untouched
(`LOG`/`SEARCH`/`DIFF` aren't in `LOSSY_UNMARKED_STRATEGIES`). The
excluded-tool and bash-search paths already bypass this gate via
`continue`; this fixes the **main strategy dispatch** (the lossless-mode
`LOG`/`SEARCH`/`DIFF` path).

Follow-up to headroomlabs-ai#1771.

Closes #

## Type of Change

- [x] Bug fix (non-breaking change that fixes an issue)

## Changes Made

- At the `apply()` acceptance gate: compute `accept_ratio` = byte ratio
for lossless results (`strategy_chain` has `lossless_*`), else the
existing word ratio. Gate + result-cache entry now use `accept_ratio`.
- Added an end-to-end regression test that drives the full
`router.apply()` path.

## Testing

- [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
tests/test_lossless_mode.py::test_router_apply_accepts_lossless_search_byte_measured PASSED
tests/test_content_router_tool_role_reversibility.py .......... (10 passed)
# broader (pre-move) sweep on the same change:
tests/test_lossless_mode.py / test_transforms/test_content_router.py /
test_lossless_excluded_compaction.py / test_bash_search_lossless_fold.py — 121 passed
ruff check headroom/transforms/content_router.py  -> All checks passed!
mypy headroom/transforms/content_router.py         -> Success: no issues found
```

## Real Behavior Proof

- Environment: local worktree, Python 3.12, `PYTHONPATH` pinned to the
branch.
- Exact command / steps: new regression test constructs a single-file
grep result, runs it through `ContentRouter(lossless=True).apply(...)`,
and asserts the tool output is byte-smaller and recovers exactly
(`search_unheading(out) == original`).
- Observed result: before this fix the fold was rejected (`out ==
original`, counted `ratio_too_high`); after, it's applied (`len(out) <
len(original)`, marker-free, byte-exact recovery). The test also asserts
the fold's word count is ≥ the original's, so the test is meaningless if
"fixed" by word count.
- Not tested: no live end-to-end proxy run; validated via the full
`apply()` path in unit 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
- [x] New and existing unit tests pass locally with my changes
- [ ] I have updated the CHANGELOG.md if applicable (handled at release
time)

## Additional Notes

Why prior tests missed it: `compress()` and `_apply_strategy_to_content`
return the folded result directly and never touch the `apply()`
acceptance gate, so the existing lossless-mode unit tests (which call
those) passed while the real proxy path silently discarded the fold. The
new test exercises `apply()` end-to-end.
JerrettDavis pushed a commit to peterlodri-sec/headroom that referenced this pull request Jul 14, 2026
@github-actions
chore: release main (headroomlabs-ai#1918)
1a2cf60 
🤖 I have created a release *beep* *boop*
---


<details><summary>0.31.0</summary>

##
[0.31.0](headroomlabs-ai/headroom@v0.30.0...v0.31.0)
(2026-07-09)


### Features

* **cache:** provider-agnostic cache-mode delta + cc-agnostic prefix
comparison
([headroomlabs-ai#1868](headroomlabs-ai#1868))
([7c2f0ea](headroomlabs-ai@7c2f0ea))
* **ccr:** wire retrieve-tool interception into OpenAI Responses handler
([headroomlabs-ai#1898](headroomlabs-ai#1898))
([62cd307](headroomlabs-ai@62cd307))
* **compression:** add audit-safe mode with protected pattern matching
([headroomlabs-ai#1899](headroomlabs-ai#1899))
([bb112dd](headroomlabs-ai@bb112dd))
* **content-router:** accept any real compression (remove min-savings
floor)
([headroomlabs-ai#1771](headroomlabs-ai#1771))
([6c31db9](headroomlabs-ai@6c31db9))
* **content-router:** lossless-first dispatch, cross-turn dedup, and A7
lossy-after-fold
([headroomlabs-ai#1818](headroomlabs-ai#1818))
([60af15f](headroomlabs-ai@60af15f))
* **proxy:** add provider-only HTTP proxy
([headroomlabs-ai#1807](headroomlabs-ai#1807))
([ebe0a3b](headroomlabs-ai@ebe0a3b))
* **proxy:** add turn-hook extension point for buffered model turns
([headroomlabs-ai#1891](headroomlabs-ai#1891))
([ec950f7](headroomlabs-ai@ec950f7))


### Bug Fixes

* **build:** enable Intel macOS pip installs via ort-load-dynamic
([headroomlabs-ai#1538](headroomlabs-ai#1538))
([32ce99e](headroomlabs-ai@32ce99e))
* **cache:** avoid fallback session collisions
([headroomlabs-ai#1827](headroomlabs-ai#1827))
([0f606b6](headroomlabs-ai@0f606b6))
* **ccr:** make expired retrieve misses terminal
([headroomlabs-ai#1781](headroomlabs-ai#1781))
([9cbdba4](headroomlabs-ai@9cbdba4))
* **ccr:** preserve Anthropic re-stream shape
([headroomlabs-ai#1854](headroomlabs-ai#1854))
([f663894](headroomlabs-ai@f663894))
* **ccr:** preserve thinking blocks in buffered stream re-synthesis
([headroomlabs-ai#1897](headroomlabs-ai#1897))
([ede085c](headroomlabs-ai@ede085c))
* **cli/proxy:** preserve explicit HEADROOM_MIN_TOKENS=0 / MAX_ITEMS=0
([headroomlabs-ai#1886](headroomlabs-ai#1886))
([3a33af1](headroomlabs-ai@3a33af1))
* **code-compressor:** CJK-aware relevance-query symbol matching
([headroomlabs-ai#1747](headroomlabs-ai#1747))
([b38315c](headroomlabs-ai@b38315c))
* **codex:** discover updated Codex state stores
([headroomlabs-ai#1889](headroomlabs-ai#1889))
([9d42eba](headroomlabs-ai@9d42eba))
* **codex:** OpenCode Zen telemetry attribution
([headroomlabs-ai#1648](headroomlabs-ai#1648))
([f18c6bd](headroomlabs-ai@f18c6bd))
* **content-detector:** detect and compress space-separated JSON objects
([headroomlabs-ai#1742](headroomlabs-ai#1742))
([5194bdc](headroomlabs-ai@5194bdc))
* **content-router:** token-measure lossless folds at the acceptance
gate ([headroomlabs-ai#1772](headroomlabs-ai#1772))
([c5493ea](headroomlabs-ai@c5493ea))
* **copilot:** normalize subscription routing host
([headroomlabs-ai#1836](headroomlabs-ai#1836))
([afd9cbd](headroomlabs-ai@afd9cbd))
* **copilot:** route mixed-model requests per model
([headroomlabs-ai#1785](headroomlabs-ai#1785))
([5af5e22](headroomlabs-ai@5af5e22))
* **dashboard:** deduplicate repeated savings metrics
([headroomlabs-ai#1804](headroomlabs-ai#1804))
([88f935a](headroomlabs-ai@88f935a))
* **dashboard:** distinguish unavailable RTK from zero stats in Docker
([headroomlabs-ai#1900](headroomlabs-ai#1900))
([87f6e93](headroomlabs-ai@87f6e93))
* **dashboard:** distinguish unavailable RTK from zero stats in Docker
([headroomlabs-ai#1901](headroomlabs-ai#1901))
([361adcd](headroomlabs-ai@361adcd))
* **dashboard:** price proxy savings without litellm
([headroomlabs-ai#1728](headroomlabs-ai#1728))
([188e382](headroomlabs-ai@188e382))
* detect and clear stale ANTHROPIC_BASE_URL from crashed wrap sessions
([headroomlabs-ai#1768](headroomlabs-ai#1768))
([headroomlabs-ai#1837](headroomlabs-ai#1837))
([84509a4](headroomlabs-ai@84509a4))
* **docker:** persist headroom workspace in compose
([headroomlabs-ai#1839](headroomlabs-ai#1839))
([5e29c06](headroomlabs-ai@5e29c06))
* **docker:** report source build version
([headroomlabs-ai#1862](headroomlabs-ai#1862))
([3807488](headroomlabs-ai@3807488))
* **evals:** default unparseable judge scores below pass threshold
([headroomlabs-ai#1892](headroomlabs-ai#1892))
([42ebbc6](headroomlabs-ai@42ebbc6))
* **install:** pass sc.exe create as raw command line so binPath=
quoting survives
([headroomlabs-ai#1654](headroomlabs-ai#1654))
([headroomlabs-ai#1702](headroomlabs-ai#1702))
([d6e0710](headroomlabs-ai@d6e0710))
* **install:** persist --no-http2 override through install apply
([headroomlabs-ai#1676](headroomlabs-ai#1676))
([6fb5f3b](headroomlabs-ai@6fb5f3b))
* **mcp:** isolate ClaudeRegistrar CLI config env
([headroomlabs-ai#1888](headroomlabs-ai#1888))
([1c947b1](headroomlabs-ai@1c947b1))
* **mcp:** surface dead proxy state
([headroomlabs-ai#1786](headroomlabs-ai#1786))
([931eed8](headroomlabs-ai@931eed8))
* **memory:** resolve Trae cwd metadata from user reminders
([headroomlabs-ai#1737](headroomlabs-ai#1737))
([headroomlabs-ai#1887](headroomlabs-ai#1887))
([3e85eb1](headroomlabs-ai@3e85eb1))
* **opencode:** use local MCP config
([headroomlabs-ai#1383](headroomlabs-ai#1383))
([4bd3ddf](headroomlabs-ai@4bd3ddf))
* **proxy/openai:** thread savings-profile kwargs into chat completions
([headroomlabs-ai#1606](headroomlabs-ai#1606))
([7ff842d](headroomlabs-ai@7ff842d))
* **proxy/openai:** translate max_tokens -&gt; max_completion_tokens on
chat path
([headroomlabs-ai#1774](headroomlabs-ai#1774))
([285808b](headroomlabs-ai@285808b))
* **proxy:** bound Codex WS compression fallback latency
([headroomlabs-ai#1802](headroomlabs-ai#1802))
([d24a3f8](headroomlabs-ai@d24a3f8))
* **proxy:** bound HF tokenizer load and offload token counting off
event loop
([headroomlabs-ai#1738](headroomlabs-ai#1738))
([46d5d68](headroomlabs-ai@46d5d68))
* **proxy:** cancel retry backoff on shutdown
([headroomlabs-ai#1834](headroomlabs-ai#1834))
([da2d8dc](headroomlabs-ai@da2d8dc))
* **proxy:** compress Anthropic user text blocks when enabled
([headroomlabs-ai#1875](headroomlabs-ai#1875))
([e36439a](headroomlabs-ai@e36439a))
* **proxy:** freeze must forward cached (compressed) prefix
byte-identical — stop token-mode cache busting
([headroomlabs-ai#1850](headroomlabs-ai#1850))
([248ae0f](headroomlabs-ai@248ae0f))
* **proxy:** fsync savings dir after atomic rename
([headroomlabs-ai#1764](headroomlabs-ai#1764))
([7de2c1e](headroomlabs-ai@7de2c1e))
* **proxy:** keep cache_control bounded + stable so the freeze overlay
stops busting
([headroomlabs-ai#1852](headroomlabs-ai#1852))
([4820134](headroomlabs-ai@4820134))
* **proxy:** persist lifetime cache-read savings across restarts
([headroomlabs-ai#1665](headroomlabs-ai#1665))
([908997e](headroomlabs-ai@908997e))
* **proxy:** preserve streaming passthrough beta headers
([headroomlabs-ai#1783](headroomlabs-ai#1783))
([0f553a8](headroomlabs-ai@0f553a8))
* **proxy:** release _active_streams session lock on setup-phase errors
([headroomlabs-ai#1864](headroomlabs-ai#1864))
([2ccd831](headroomlabs-ai@2ccd831))
* **proxy:** retry HTTP/2 stream resets instead of 502ing
([headroomlabs-ai#1645](headroomlabs-ai#1645))
([2ce19c2](headroomlabs-ai@2ce19c2))
* **proxy:** retry passthrough on transient upstream connection close
([headroomlabs-ai#1513](headroomlabs-ai#1513))
([5d14080](headroomlabs-ai@5d14080))
* **proxy:** route Foundry Anthropic messages
([headroomlabs-ai#1878](headroomlabs-ai#1878))
([739f654](headroomlabs-ai@739f654))
* **proxy:** serve /favicon.ico locally instead of tunneling upstream
([headroomlabs-ai#1787](headroomlabs-ai#1787))
([headroomlabs-ai#1847](headroomlabs-ai#1847))
([3076e32](headroomlabs-ai@3076e32))
* **proxy:** stop rtk stat failures from corrupting session baseline
([headroomlabs-ai#1693](headroomlabs-ai#1693))
([681b9a8](headroomlabs-ai@681b9a8))
* **proxy:** strip 1m model suffix before upstream forwarding
([headroomlabs-ai#1840](headroomlabs-ai#1840))
([e22d745](headroomlabs-ai@e22d745))
* **proxy:** subtract cache write premiums from net savings
([headroomlabs-ai#1800](headroomlabs-ai#1800))
([53a465b](headroomlabs-ai@53a465b))
* **router:** honor MCP aliases in excluded tools
([headroomlabs-ai#1822](headroomlabs-ai#1822))
([headroomlabs-ai#1863](headroomlabs-ai#1863))
([140d6e4](headroomlabs-ai@140d6e4))
* **rtk:** link managed rtk onto PATH instead of mutating the hook
([headroomlabs-ai#1698](headroomlabs-ai#1698))
([140cb05](headroomlabs-ai@140cb05))
* **streaming:** preserve server_tool_use sse blocks
([headroomlabs-ai#1826](headroomlabs-ai#1826))
([4ac5493](headroomlabs-ai@4ac5493))
* **toin:** publish skip compression recommendations
([headroomlabs-ai#1782](headroomlabs-ai#1782))
([be51008](headroomlabs-ai@be51008))
* **transforms:** normalize diff compressor context
([headroomlabs-ai#1801](headroomlabs-ai#1801))
([838c523](headroomlabs-ai@838c523))
* **transforms:** pass through ragged tables instead of misaligning
columns
([headroomlabs-ai#1713](headroomlabs-ai#1713))
([c7665ca](headroomlabs-ai@c7665ca))
* use rtk native Cursor hook instead of injecting .cursorrules
([headroomlabs-ai#756](headroomlabs-ai#756))
([headroomlabs-ai#1846](headroomlabs-ai#1846))
([1573f1f](headroomlabs-ai@1573f1f))
* **wrap:** replace stale-proxy detection with Vite-style port fallback
([headroomlabs-ai#1406](headroomlabs-ai#1406))
([b4205c6](headroomlabs-ai@b4205c6))


### Performance Improvements

* **proxy:** cap compression workers to CPU count
([headroomlabs-ai#1803](headroomlabs-ai#1803))
([0a3851b](headroomlabs-ai@0a3851b))
* **savings:** batch tracker persistence off the request hot path
([headroomlabs-ai#1817](headroomlabs-ai#1817))
([451b9f0](headroomlabs-ai@451b9f0))


### Dependencies

* bump the cargo-minor-patch group across 1 directory with 7 updates
([headroomlabs-ai#1909](headroomlabs-ai#1909))
([45601d9](headroomlabs-ai@45601d9))
* bump the npm-minor-patch group across 4 directories with 18 updates
([headroomlabs-ai#1907](headroomlabs-ai#1907))
([8872bbc](headroomlabs-ai@8872bbc))
</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>
@eilhamv eilhamv mentioned this pull request Jul 23, 2026
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@JerrettDavis JerrettDavis Awaiting requested review from JerrettDavis JerrettDavis is a code owner
@DevanshiVyas DevanshiVyas Awaiting requested review from DevanshiVyas DevanshiVyas is a code owner

Assignees

No one assigned

Labels

status: ready for review Pull request body is complete and the author marked it ready for human review

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@chopratejas