renderToolDoc pretty-printed every input_schema with 2-space indent,
putting each property on its own line. At cols=100 this wasted ~70% of
horizontal space — schemas rendered to many short rows instead of a few
dense ones.
Live measurement on 2026-05-19: 150 KB of pretty-printed tool docs in a
177 KB combined slab → 31 static-slab images per request at 40% fill.
With the new row-aware break-even gate (f0176c1), those rejected as
not_profitable — no savings on the user's typical workload.
Synthetic measurement on 30 realistic tool schemas:
- pretty: 320,843 chars / 14,074 lines → 100 images
- compact: 124,720 chars / 179 lines → 10 images
- 2.57× char shrink, 78× row shrink, 10× image cost reduction
Compact JSON is unambiguous: descriptions are already stripped under
compressSchemas, so only structural keys (type/properties/required/
enum/items) remain — those read fluently on one wrapped row. Frontier
models handle compact JSON natively; it's the default wire format for
tool_use blocks anyway.
Test pins the density gain on a representative schema.
isCompressionProfitable previously estimated image count as
ceil(chars / charsPerImage), which assumes uniform full-width line-fill.
renderTextToPngs actually budgets by wrapped visual rows (141 per image),
so newline-heavy code/logs and short-line content render to many more
images than the chars-based estimate predicts.
Live impact: dashboard reported -69% reduction (net loss). 33 compressions
averaged 5494 chars/image (39% fill ratio) — gate under-counted cost by
~9× on sparse content and let net-losing compressions through.
Fix:
- isCompressionProfitable now accepts the full text string; uses
estimateImageCount (the same row-aware math renderTextToPngs uses).
- Adds an optional imageCountCap for paths that truncate before rendering
(tool_results). Cost bounded by cap; savings still measured against
the full pre-truncation length, so 500KB logs still profit.
- All 4 production call sites in transform.ts pass the string. The
tool_result sites also pass maxImagesPerToolResult as the cap.
- Number-arg form retained for back-compat with the existing
isCompressionProfitable(N) unit tests.
Tests:
- 3 new unit tests pin the row-aware regression: sparse content rejected,
dense content accepted, capped content (paging) accepted.
- 7 integration tests previously used 'claude.md\n'.repeat(5000) — sparse
fixtures the new gate correctly rejects. Updated to dense fixtures
('x'.repeat(40000) or single-line repeats without embedded newlines)
so they still exercise the cache_control / determinism / reminder /
tool_result code paths they're meant to.
The dashboard headline was showing 0% saved because the math was
apples-to-oranges:
- orig_chars = static slab + tool docs ONLY (~135 KB)
- image_count = ALL images including reminders + tool_results (~33)
- txtReplaced = 135k/4 = 33.7k tokens
- imgTokensEst = 33 × 2500 = 82.5k tokens
- extraText = max(0, 33.7k - 82.5k) = 0 ← clamped negative
- baseline == paid → 'saved 0%' headline despite real savings happening
Two fixes:
1. Track 'compressedChars' separately from 'origChars'. It accumulates
only when a block actually image-renders (passes the break-even gate
AND any per-block min thresholds). Includes the static slab + all
compressed reminders + all compressed tool_results.
2. Remove the Math.max(0,...) clamp in baselineCost(). Negative savings
surface honestly — they're the signal that small-block compressions
are cost-bleeding, which the break-even gate is supposed to prevent.
Wires:
- TransformInfo.compressedChars (new field, mandatory).
- All 4 image-render success paths accumulate (static slab + reminder
+ tool_result string branch + tool_result array branch).
- TrackEvent.compressed_chars (new optional field, emitted when > 0).
- dashboard.baselineCost() takes compressedChars now; clamp removed.
- sessions.aggregateSessions() also uses compressed_chars + honest math.
229/229 tests passing. Bundle stays at 496 KB gzipped.
Post-restart, the dashboard 'tokens saved' will show real numbers
including negatives. Empirically expect ~1-5% net positive in
steady-state cache-hit traffic.
Two distinct improvements in one slice:
1. History-image compression (Variant C — opt-in, default OFF).
New src/core/history.ts module:
- findClosedPrefixBoundary(): walks tool_use_id openSet, returns largest
fully-closed prefix index. Mid-flight tool_use blocks bail the collapse.
- blocksToText(): linearises content blocks for the history image. Drops
thinking blocks (per Opus 4.7+ docs: only most-recent must be bit-perfect),
renders tool_use args + tool_result inner text, emits [image] placeholder
for nested images.
- collapseHistory(): orchestrates. Applies isCompressionProfitable() gate.
Returns a synthesized {role:'user', content:[text,image,text]} prepended
message + the elided turns dropped from messages[].
New TransformOptions: compressHistory (default false), historyKeepTail (4),
historyMinPrefix (10). Wired through src/node.ts + src/worker.ts as
COMPRESS_HISTORY / HISTORY_KEEP_TAIL / HISTORY_MIN_PREFIX env vars.
Cache_control: history-image carries NO cache_control on this first cut.
Static slab keeps its 1 breakpoint. Conservative — telemetry will reveal
whether the cache-miss rate on history images warrants the round-3
rebalance in a follow-up slice.
29 new tests in tests/history.test.ts: closed-prefix detection (parallel
tool calls, mid-flight, openSet straddling), block linearisation, full
collapse flow, isCompressionProfitable gate firing on small histories.
2. Per-session savings: honest formula (fixes task #63).
Previous src/sessions.ts computed saved = orig_chars - image_bytes — a
nonsense comparison of chars to PNG bytes, then clamped via Math.max(0,...).
Result: charsSaved/tokensSavedEst was 0 for every session including ones
with hundreds of MB of compressed traffic.
New formula mirrors src/dashboard.ts:
textTokens = orig_chars / 4
imageTokens = image_count × 2500
tokensSaved = textTokens − imageTokens (CAN be negative)
Negatives are NOT clamped — they surface the cost-bleed on small-block
compressions that the per-block break-even check is supposed to prevent.
2 new tests: positive-net case, all-negative case (must report negative).
229/229 tests passing. Bundle ~500 KB gzipped.
Two related improvements:
1. Per-tool_result paging / truncation. When a single tool_result would
render to more than maxImagesPerToolResult images (default 10), the
source text is truncated head+marker+tail BEFORE rendering. Classifier
picks the truncation strategy:
- structured (JSON/YAML/diff): head-only, tail is repeating elements
- log (timestamps / [LEVEL] prefixes): 60% head + 40% tail
- other (prose, dumps): same head/tail split
The marker tells the model what was elided so it can reason about the
gap: '[ pixelpipe paging: omitted N lines (K chars) ... ]'. Keeps
requests under Anthropic's 100-image-per-request cap even when a single
tool dumps a multi-megabyte log.
2. Adaptive CHARS_PER_IMAGE. Previously hardcoded at 14_100 (Unifont 10px
@ cell 5×11). Now derived at module load from ATLAS_CELL_H + render.ts
constants. When gen-atlas regenerates with a different font/size, the
break-even threshold automatically updates: at Cozette 4×7 the chars/
image jumps from 14.1k → 22.2k and the break-even drops from ~10k → ~3k.
Single source of truth in src/core/.
Wires:
- TransformOptions.maxImagesPerToolResult (default 10)
- TransformInfo.truncatedToolResults + omittedChars
- TrackEvent.truncated_tool_results + omitted_chars (emit when > 0)
- Two new exported helpers: estimateImageCount, classifyContent, truncateForBudget
- Paging fires before image-encoding at both tool_result branches
(string content and array-of-text-blocks content)
Tests: +28 paging-specific (paging.test.ts), 199/199 total green.
Bundle delta: negligible (~3 KB raw, ~1 KB gzipped). 488 KB dist gzipped.
Closes the paging-implementer worktree merge that was deferred earlier.
Pivot from prior CLI subcommands (stats, sessions) to dashboard-based UI.
bin/cli.js becomes a minimal proxy starter; all functionality lives at
http://127.0.0.1:47821/.
New endpoints:
GET /api/sessions.json — session list + Claude Code mapping
GET /api/sessions/:id.json — session detail (bodies redacted by default)
POST /api/sessions/prune — dry-run-first cleanup with atomic rewrite
GET /api/disk.json — events.jsonl + 4xx-bodies disk usage
GET /api/stats.json — full-history aggregate (replaces CLI 'stats')
GET /sessions/:id — HTML detail page
Dashboard HTML extended with sessions panel + stats panel + cleanup panel.
Smooth-poll: 2s tick for legacy live counters, 5s tick for sessions/stats/disk.
Session rows diff-rendered (no full-table flash). Destructive actions show
window.confirm() with dry-run preview of impact.
Session mapping: synthetic ID from first_user_sha8 (already on every event)
+ opportunistic enrichment by fingerprinting against ~/.claude/projects/*.jsonl.
Falls back gracefully if Claude Code's session dir is missing.
Atomic events.jsonl rewrite (write to .tmp, fsync, rename) preserved from
the prior CLI design — trigger is now HTTP POST.
+51 new tests (33 sessions + 18 dashboard-api). 149/149 total.
URGENT production-cost fix. Empirical data (orig_chars=169779, image_count=88)
showed we were paying ~220k image tokens to replace ~42k text tokens — a
net LOSS of ~178k tokens per request. Dashboard hid this via Math.max(0,...).
Two changes ship together:
1. isCompressionProfitable(textLen) gate in transform.ts. Before any
per-block image encode (static slab, reminder, tool_result), compute:
estImages × TOKENS_PER_IMAGE vs textLen / CHARS_PER_TOKEN
Compress only when the image side wins. Constants:
CHARS_PER_IMAGE = 14100 (Unifont 10px, cell 5×11, 100 cols)
CHARS_PER_TOKEN = 4
TOKENS_PER_IMAGE = 2500 (empirical, history-researcher round 3)
Result: blocks under ~10k chars stay as text. Static slab still
compresses (always above break-even).
2. Coarse thresholds bumped as fast-path:
minReminderChars 1000 → 5000
minToolResultChars 5000 → 10000
(Cover the obvious-no cases without invoking the precise check.)
3. Dashboard honesty: removed Math.max(0,...) clamp in baselineCost().
Negative savings now display as negative (no more hidden cost-bleed).
4. Telemetry: passthrough_reasons.below_threshold + .not_profitable
counters surface how often each gate fires.
After restart, dashboard 'saved' should jump from clamped-0 to a real
positive number (~1-3% on aggregate; static slab compression is the
only block consistently profitable at our current cell).
Unifont glyphs are inherently 1-bit (every pixel is 0 or 255). Storing as
8-bit bytes wasted 7 bits per pixel.
Changes:
- scripts/gen-atlas.ts: emit ATLAS_PIXELS as bit-packed MSB-first. OFFSETS
now indexes bits not bytes. Per-cell paint thresholds R-channel at 128
defensively (Unifont is already 0/255).
- src/core/render.ts:blitGlyph: byte read replaced with bit extraction
(~3 extra ops per pixel; negligible). max() blending removed since bit
data is binary, no AA edges, no glyph overlap.
- src/core/atlas.ts: regenerated with the new format. Header comment
documents the bit-extraction formula.
- tests/render.test.ts: +1 structural assertion that ATLAS_PIXELS.byteLength
matches the bit-packed total.
Bundle size:
atlas.ts raw: 5.47 MB → 1.06 MB (5.2× shrink)
atlas.ts gzip: 1.55 MB → 479 KB (3.2× shrink)
dist gzipped: 1.57 MB → 488 KB (3.15× shrink, well under Workers
free-tier 1 MB cap)
Pre-deflate shrink is 8× (theoretical max). The 3.15× post-deflate
result reflects that deflate was already exploiting long runs of 0/255
in the 8-bit data; the bit-packed bytes are denser and less compressible.
Render output is byte-identical to pre-bit-pack (storage format change
only). 108/108 vitest, 4/4 shell tests, typecheck + build clean.
Adds minifyForRender() as step 1 of wrapLines() pipeline. Strips trailing
whitespace per line and collapses 4+ consecutive newlines to 3 (= 2 blank
lines). Leading whitespace + mid-line spaces preserved (structural).
HANDOFF item R1 predicted ~1.5-2× chars per image. Empirical measurement
on real corpora (v3 corpus, all .md docs, all .ts source, 2.3 MB live
conversation jsonl) showed 0% reduction — modern editors strip trailing
whitespace on save by default. R1 is shipped as defensive infrastructure
that fires when log-dump-heavy / unminified content arrives.
+9 tests covering trailing-strip, blank-line collapse, structural-space
preservation, and combined-with-tab-expansion pipeline. 107/107 vitest.
Previous test expectations had been written against an older silent-space
tab expansion. The arrow form (\t → "→" + padding to tab stop) was already
in src/core/render.ts; this just brings the tests into agreement.
Includes 7 expandTabsInLine tests covering col 0/1/2/3 tab boundaries, the
fast-path for tab-free lines, and EAW-aware width counting for tabs after
CJK glyphs. Total: 98/98 vitest passing.
- Switch font: JetBrains Mono @ 15px → Unifont 16.0.04 @ 10px. Sparse
atlas with double-width EAW dispatch for CJK. Full BMP profile
(35,501 glyphs) covers Latin/Cyrillic/Greek/Hebrew/Arabic/CJK/Hangul
plus Letterlike, Misc Technical, Block Elements, Geometric Shapes,
Misc Symbols, Dingbats, Enclosed Alphanumerics, all box-drawing.
- Fix cell-height bug (was hardcoded 9; now probed from font metrics
via Math.ceil(maxAscent+maxDescent)). Previously clipped the top
2 rows off every CJK glyph since the original Unifont ship.
- Expand tabs to spaces with 4-column tab stops, EAW-aware. Was the
silent-drop source for 99.6% of dropped chars in production.
- Add dropped_codepoints_top telemetry (top 20 per event, only emitted
when drops > 0) so future coverage gaps surface in events.jsonl.
- Raise minToolResultChars 2000→5000 and minReminderChars 1000→2000
to stop net-losing tokens on small compressions, per ~2,500 tok/img
empirical measurement (N=33 cold-miss events).
- Fix dashboard per-image-cost formula: was pngBytes/375 (~190 tok),
now imageCount * 2500 (the measured empirical rate). Reduces the
inflated "tokens saved" headline to honest numbers.
- Schema-stub fix in compressSchemas path: preserveSchemaShell()
retains type / properties / required / enum / oneOf / anyOf / $ref /
numeric constraints recursively (depth 20), strips only descriptions
and metadata. Prevents 400 errors on first-tool-call requests.
- Capture full gzipped 4xx body + per-event req_body_sha8 for upstream
error diagnosis. Sidecar to ~/.pixelpipe/4xx-bodies/ when over 32 KB
inline cap. Workers-safe via CompressionStream + Web Crypto.
- scripts/restart.sh: pnpm-aware one-command kill+rebuild+start with
graceful SIGTERM→SIGKILL escalation, build-failure abort, port-in-use
precheck, --no-build flag for fast iteration. Shell-tested.
- Bundle 1.58 MB gzipped on Node. 91/91 vitest + 4/4 shell tests.
The canary in splitStaticDynamic flags tag-shaped blocks in the static
slab that aren't in DYNAMIC_BLOCK_TAGS — designed to catch a new
Claude Code release that ships a per-turn tag we'd accidentally bake
into the cached image. In production it has been firing on `<types>`
for 93% of real requests (125 of 134 in the user's events log), which
is noise: `<types>` is part of Claude Code's built-in tool
documentation, not a per-turn rotation.
Add a second list, KNOWN_STATIC_TAGS, that mirrors DYNAMIC_BLOCK_TAGS
in shape. The unknown-tag computation now subtracts BOTH lists, so a
tag is only "unknown" when it's in neither the per-turn set nor the
known-static set. Seed KNOWN_STATIC_TAGS with ['types'].
Updates the warn log in src/node.ts to mention both options so a
reviewer of a NEW unknown tag knows which list to extend.
Adds a regression test pinning that <types> in the static slab no
longer produces info.unknownStaticTags.
Tool results (Bash output, Read file contents, etc.) accumulate as the
session grows. Once produced they're static — same bytes turn after turn
— but the model gets billed for them on every call until they fall out
of cache. Image-rendering them at the source compounds the savings
across the whole conversation.
Walks ALL user messages (not just the first — that's the reminder-
compression scope) and rewrites tool_result blocks whose content is at
or above minToolResultChars (default 2000, matching legacy/python/proxy.py):
- content: string → replace with image block(s) (whole content goes)
- content: array → walk inner blocks, replace each TextBlock ≥ threshold
with image blocks; leave ImageBlocks and short text
alone
- is_error: true → leave the whole block alone. Anthropic rejects
images inside is_error tool_results
(`tool_result with is_error=true cannot contain images`).
Like reminder compression these images carry NO cache_control — the
system+tools image is our only breakpoint. The savings are 65-73% of
input tokens per compressed block on Opus 4.7.
Wire-up:
- src/core/transform.ts: TransformOptions.compressToolResults (default
true) + minToolResultChars (default 2000). TransformInfo.toolResultImgs
counter. Reuses textToImageBlocks / approxBlockBytes from commit 3.
- src/core/tracker.ts: TrackEvent.tool_result_imgs flows from the
transform info.
- src/worker.ts: COMPRESS_TOOL_RESULTS + MIN_TOOL_RESULT_CHARS env vars.
- src/node.ts: CliOpts fields, parseCli cases (--no-tool-results,
--min-tool-result-chars), help text, env-var summary, `tr+N` in the
per-request console line when tool_result_imgs > 0, and tool_results=
in the startup config summary.
Tests:
- "compresses large tool_result text content across user messages"
confirms info.toolResultImgs ≥ 1, the tool_result block's content
becomes an array of image blocks, and those images carry no
cache_control.
- "leaves is_error tool_results untouched (Anthropic forbids images
there)" confirms info.toolResultImgs is 0 and the content stays a
plain string when is_error: true.
Claude Code re-injects the same long <system-reminder> blocks (CLAUDE.md
hints, task-tools reminders, the dynamic skills list, etc.) into the
FIRST user message on every turn. They're text, so they're not part of
the system+tools image we already cache — they hit the wire fresh every
turn. This rewrite renders any reminder block ≥ minReminderChars (1000
by default, matching legacy/python/proxy.py) to PNG images placed inside
the user message content array, just like the static slab.
Why: the system+tools image is the only cache_control breakpoint we're
allowed (Anthropic caps at 4 and Claude Code uses the others). Per-block
reminder images therefore carry NO cache_control — they're per-turn
content that the model OCRs without prefix-cache benefit. The win is
token cost, not cache: reminders are 65-73% cheaper as PNG than as text,
and a typical turn has 1-3 of them.
Layout inside the first user message after compression:
[intro text] ← static (helps OCR framing)
[image block(s)] ← static; LAST has cache_control
↑ cache breakpoint (the only one)
[End of rendered context.] ← static text closer for the image
[processed existing content] ← per-turn (incl. reminder images)
Wire-up:
- src/core/transform.ts: new TransformOptions.compressReminders (default
true) + minReminderChars (default 1000). Two new helpers,
textToImageBlocks() (wraps renderTextToPngs + makeImageBlock with
no cache_control) and approxBlockBytes() (b64 → byte-count for the
imageBytes telemetry, no second base64 round-trip). The placement
='user' branch now walks `existing` and rewrites long reminders.
- src/core/tracker.ts: TrackEvent.reminder_imgs flows from
TransformInfo.reminderImgs through toTrackEvent so `pixelpipe stats`
and the dashboard can attribute compression contributions.
- src/worker.ts: COMPRESS_REMINDERS + MIN_REMINDER_CHARS env vars.
- src/node.ts: matching CliOpts, parseCli cases (--no-reminders,
--min-reminder-chars), help text, env-var summary, and `rem+N` in
the per-request console line when reminder_imgs > 0.
Tests:
- "compresses long <system-reminder> blocks in the first user message"
confirms info.reminderImgs ≥ 1, the reminder text is gone from
user-content text blocks, the user's actual prompt survives, and the
new reminder image blocks carry NO cache_control.
- "leaves short <system-reminder> blocks alone (below minReminderChars)"
confirms info.reminderImgs is 0 and the reminder text passes through
as text.
Two protocol-correctness fixes that have to ship together.
1. **Default placement: 'system' → 'user'.** Anthropic's `system` field is
typed as `string | TextBlock[]` — image blocks there come back as
`400 system.N.type: Input should be 'text'`. Images must go into a
user-message content array.
2. **ttl='1h' on the image's cache_control.** Anthropic enforces the rule
"ttl='1h' must not come after ttl='5m'" in processing order
(tools → system → messages). Claude Code marks its own user-message
content with ttl='1h'; if we leave ttl unset it defaults to '5m', our
block lands first in processing order, and the request 400s the moment
Claude Code's own 1h breakpoint shows up later in the conversation.
The existing image-placement tests now look in messages[0].content instead
of out.system, and a new test pins the ttl='1h' invariant directly.
Reads ~/.pixelpipe/events.jsonl (or --file / PIXELPIPE_LOG) and prints
a one-screen summary of how the proxy is doing:
- request counts by status bucket (2xx/4xx/5xx)
- compression rate (compressed vs passthrough)
- latency p50/p95/p99 (duration + first-byte separately)
- aggregate Anthropic token usage (input/output/cache_create/cache_read)
- cache hit rate computed two ways (by tokens, by events)
- top skip reasons (so we see WHY a request wasn't compressed)
- top cwds with per-project compression ratio
- system_sha8 distribution → 'reuse rate' = how often the cached
payload is being re-sent. High reuse + low cache_read means
something is breaking cache_control.
- unknown_static_tags warning section if Claude Code shipped a new
dynamic tag that we're silently baking into the image.
--json mode dumps the raw Summary as JSON for downstream pipelines.
Streaming reader so a 100 MB log file doesn't OOM. Pure aggregator
(fold/newSummary/renderTextReport) is unit-tested; only the file IO
shell is untested.
Dispatched from src/node.ts BEFORE parseCli so its flags don't collide
with the proxy's flags. The CLI shim in bin/cli.js stays unchanged.
Tests: +6 (status bucketing, compressed/passthrough split, token agg,
cwd & sha histogram, unknown-tag collection, text report rendering).
Node host now appends one JSONL event per request to
~/.pixelpipe/events.jsonl (override with --events-file or PIXELPIPE_LOG).
- Size-based rotation at 100 MB (old file → events.jsonl.1).
- Sync writes — overhead is ~1ms, dwarfed by upstream latency.
- Failures degrade silently: a broken disk disables the tracker but
never breaks a request.
- Flushed and fsync'd on SIGINT/SIGTERM so the last batch isn't lost.
- Opt out via --no-track or PIXELPIPE_TRACK=0.
Worker host uses JsonLogTracker with console.log; Cloudflare ingests
this as Workers Logs, and Logpush can ship it to R2/S3 as JSONL —
same shape Node writes locally, so analysis tooling works on either.
Console log line on both hosts now also includes tokens/cache_read
inline (e.g. 'compressed 4799ch → 2img/12343B tokens=1234+56
cache_read=800') so cache effectiveness is visible at a glance even
without parsing the JSONL.
Unknown-tag canary fires a stderr warning when info.unknownStaticTags
is non-empty — surfaces Claude Code releases that introduce new
dynamic tags before they tank the cache hit rate.
Help text and HANDOFF will be updated in the next commit; for now the
new flag drops the need for --exclude-dynamic-system-prompt-sections.
Tests: +5 (toTrackEvent flattening, JsonLogTracker sink behavior, error
swallowing, minimal-event handling, noop).
Two cheap guardrails based on architectural review:
1. Determinism test: renders the same input twice and asserts byte
equality of the produced PNGs. Without this guarantee, identical
system prompts on consecutive turns would yield different image
bytes, silently destroying the cache hit rate that justifies the
whole proxy. The test currently passes — locking it in so a future
refactor can't regress it without noticing.
2. Unknown-tag canary: splitStaticDynamic now sniffs the *static* slab
for any <tag>...</tag>-shaped block whose name isn't in
DYNAMIC_BLOCK_TAGS. Surfaced via info.unknownStaticTags and emitted
on the tracker event as unknown_static_tags. If Claude Code ships a
new per-turn tag in a future release, it'll show up in logs within
hours instead of being silently baked into the cached image (where
it would tank cache hit rate with no error).
Also adds tracker.ts (Tracker interface, TrackEvent shape,
JsonLogTracker, noopTracker, toTrackEvent normalizer). Hosts will wire
these in the next commit.
ProxyEvent gains two new fields:
- usage: Anthropic's input/output/cache_creation/cache_read tokens.
- firstByteMs: ms to upstream response headers (durationMs now measures
end-to-end since the event fires after usage is extracted).
Implementation (teeForUsage):
- Tee the response body. Client gets one side immediately; we read the
other in the background.
- SSE: scan up to 64 KiB for 'event: message_start' + the data: payload.
Usage is always in the first event so this terminates within ms of
upstream first byte.
- JSON: buffer up to 4 MiB and parse.
- Error responses (status >= 400) and bodyless responses skip extraction.
- Drains the tee fully in the background to avoid backpressure.
Without this, the proxy had no way to validate its own value
proposition. Now we can compute cache hit rate, real input-token
savings, etc. directly from log events.
Tests: +3 (JSON usage, SSE message_start usage, error skips extraction).
Three short hashes carried in TransformInfo:
- systemSha8: sha256[0..8] of the actual image-bound text. Stable
across turns proves cache_control is doing its job. If it drifts
unexpectedly, that's a cache leak to investigate.
- claudeMdSha8: hash of just the CLAUDE.md slab (heuristic header
detection). Lets us bucket requests by project even when cwd is
absent or anonymized.
- firstUserSha8: hash of first user message (4 KiB cap). Rough
thread id since the wire protocol has none.
All async via Web Crypto so Node + Workers share one impl. Hashing is
in parallel via Promise.all; ~0.1ms overhead.
+2 tests (systemSha8 invariant under dynamic-block change,
firstUserSha8 format).
New EnvFields type and extractEnvFields() helper. Parses the <env>
block Claude Code injects, plus 'On branch' / 'Branch:' lines that
appear in <git_status> or context blocks. Read-only — telemetry signal
only, never mutates the request.
Per-project compression ratios, repeat-CWD detection, today's-date
drift checks all become possible from logs now.
+2 tests (full env block extraction, no-env-no-info).
Claude Code injects per-turn blocks (<env>, <context>, <git_status>,
<directoryStructure>, <system-reminder>) into the system prompt.
Previously those got rendered into the image alongside the static
slab (CLAUDE.md, agent defs, tool docs), which kills Anthropic's
prompt cache: image bytes drift turn-to-turn → 0% cache hits.
Now we split:
- static (cacheable) → image with cache_control: ephemeral
- dynamic (per-turn) → plain text block AFTER the image
- billing line → also AFTER the image (was BEFORE, also a
cache-killer — bug fix as a side effect)
Net effect: stable cache key on the big slab, model still sees cwd /
branch / today's date. Removes the need for users to pass
--exclude-dynamic-system-prompt-sections to claude.
TransformInfo now carries staticChars / dynamicChars / dynamicBlockCount
for downstream telemetry.
Tests: 8 existing pass unchanged + 3 new (env survives as text after
image, cache_control on image only, all-dynamic input is pass-through).
teamchong