Claude Code writes one transcript JSONL line per content block, so a
single API response (one message.id) spans multiple assistant lines that
each repeat the same message.usage. sumUsageFromTranscript summed every
line, inflating token totals and estimated_cost_usd roughly 2.5-3x.
Verified on a real session: 704 assistant lines but only 286 unique
message.ids (2.46 lines/response on average); line-summing reported
$866.52 while the deduped total is $332.62. Usage payloads are identical
across lines of the same id (0/286 varied), so counting once per id is
equivalent to taking the last line per id.
Fix: collect usage into a Map keyed by message.id (last line wins) and
sum unique entries. Lines without a message.id (older transcript shapes)
keep the previous per-line behavior via a synthetic key, so existing
tests and old transcripts are unaffected.
Adds a regression test: a response split into 3 content-block lines with
the same message.id is counted exactly once.
Note: rows already written to ~/.claude/metrics/costs.jsonl by the old
code carry inflated token counts and estimates (except rows whose cost
came from the harness-cost cache, where cost is authoritative but token
counts are still inflated). Downstream consumers may want to annotate
history; this change intentionally does not rewrite the raw log.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* fix: harden local data boundaries
Bind the capabilities dashboard exclusively to loopback and reject untrusted Host and Origin values. Constrain project-configured agent data paths to the Cursor data root, and harden lifecycle repair/uninstall operations against state-file traversal, symlink swaps, unsafe sources, and forged install-state destinations.\n\nCloses #2506
* fix: eliminate repair source read race
Read source bytes and mode from one no-follow file descriptor so a path replacement cannot mix metadata from one inode with content from another. Add a regression that rejects separate path-based source metadata lookup.
* fix: close dashboard hardening review gaps
update_version rewrote plugins/ecc/.codex-plugin/plugin.json on disk, but
CODEX_MARKETPLACE_PLUGIN_JSON was missing from the git add list, so the bump
was never committed. The tag then carried a 2.0.0 manifest and
plugin-manifest.test.js failed the release in CI.
Also commits the 2.1.0 value the previous run left uncommitted.
Co-Authored-By: Claude <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0149VwNuynam6rvEfcMmiHHa
The step ran node tests/omp/omp-plugin.test.js, which has never existed in
this repository. It was added by #2382 without the test file, so Verify
Release failed on every tag and no release could publish.
The OpenCode payload is already verified by tests/scripts/build-opencode.test.js
in the preceding step, and the plugin and marketplace manifests by
tests/plugin-manifest.test.js in Verify release metadata stays in sync.
Co-Authored-By: Claude <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0149VwNuynam6rvEfcMmiHHa
Two bumps were being skipped, both caught by plugin-manifest.test.js only
after the version had already been rewritten across twenty files.
.claude-plugin/marketplace.json used sed with GNU's 0,/re/ address form.
BSD sed on macOS ignores it and exits 0, so the substitution silently did
nothing. Replaced with a node first-match rewrite that fails loudly.
docs/zh-CN/README.md had its version row updated but not its release
heading, unlike the other localized READMEs.
Co-Authored-By: Claude <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0149VwNuynam6rvEfcMmiHHa
The banner regex still expected 'Everything Claude Code', but the plugin
banner in .opencode/plugins/ecc-hooks.ts reads 'ECC' since the rename, so
update_opencode_hook_banner_version aborted every bump. Accept both names.
Co-Authored-By: Claude <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0149VwNuynam6rvEfcMmiHHa
Lockfile-only Dependabot Cargo group update for ecc2. Verified PR was clean/mergeable with no failing or pending checks and no unresolved review threads.
Add a local-first, cross-harness memory vault with CLI and MCP surfaces, bounded search and storage, harness-scoped visibility, setup guidance, and comprehensive tests.
Map the ECC Ultra report into ten dependency-ordered execution lanes with explicit security, consent, schema, lifecycle, testing, and distribution gates.
Add a contract-first workflow for consumer/provider collaboration, including shared artifact authority, compatibility review, generated-type and runtime verification, and safe handling of contract-driven tooling.
Honor an explicit non-git CLAUDE_PROJECT_DIR as an isolated project scope, canonicalize and hash it consistently in the shell observer and Python CLI, and preserve the global fallback for arbitrary non-git working directories.
Preserve complete Stop-hook stdout through lifecycle wrappers, wait for queued output to flush before exiting, bound child output with a larger explicit buffer, and add end-to-end regressions for large, multibyte, dry-run, and failure cases.
* fix(resolve-ecc-root): require ECC skills, not just scripts, before accepting a root (#2544)
resolveEccRoot() accepted a candidate root on script-only evidence
(scripts/lib/utils.js). A partial install that lands ECC's scripts into
~/.claude but not ECC's skills short-circuited at the standard-install
branch, so skill-resolving callers built skills/... paths against a root
where they do not exist and every command failed three layers away.
For the default probe (skill consumers, reached via INLINE_RESOLVE) a
candidate now qualifies only if it contains both the script tree and a
sentinel ECC skill; the same stricter check guards the plugin-root and
plugin-cache branches. An explicit caller probe is still honored exactly,
so script consumers (e.g. session-start-bootstrap, which probes for the
hook runner) are unaffected. Merely checking that skills/ exists is
insufficient — a user's own ~/.claude/skills/ can be present with none of
ECC's skills.
Adds a regression test for the exact partial-install scenario and updates
the resolver test fixtures to build complete roots.
* test(resolve-ecc-root): cover partial exact-plugin and cache roots; DRY skill sentinel (#2544)
Address CodeRabbit review on PR #2577:
- Extend #2544 regression coverage to the exact-plugin and versioned
plugin-cache branches, asserting the stricter both-sentinels predicate
rejects a scripts-only root there too (not only for ~/.claude).
- Extract the ECC_SKILL_SENTINEL constant in command-plugin-root.test.js
and reuse it at both fixture setup sites instead of duplicating the literal.
Replace the generated Itō SVG wordmark with the supplied transparent monogram assets, keep the exact white-and-gold mark for dark mode, add a same-geometry light-mode variant, and refresh the dependency lock entry flagged by CI.
Merge the official ECC Tools favicon mark, normalized Itō Drive lockup canvas, and equal 16:9 guide cards after full CI and GitHub-render visual verification.
Expose the canonical Itō CLI's pinned sixtytwo node-qualification path through ECC with double opt-in, explicit node/config gates, credential isolation, and no new MCP or execution authority.
Validated across the full Linux, macOS, and Windows Node/package-manager matrix, hosted coverage, CodeQL, security, lint, and focused bridge tests.
* docs: add Itô Markets GPU compute sponsor section to README
Adds a GPU compute sponsor entry under the Sponsors section: Itô Markets
logo linking itomarkets.com plus the compute dashboard at
compute.itomarkets.com, matching the framing from the merged sponsor
routing (4e341183, 8eb43383). Includes a hidden HTML-comment placeholder
for Moonshot AI (Kimi), pending countersign; nothing renders publicly
for Moonshot yet.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0149VwNuynam6rvEfcMmiHHa
* docs(sponsors): consistent sponsor treatment, Moonshot public, real brand assets
- Replace cropped ito.svg with the full Drive lockup; add ito-dark.svg
(white marks) with picture/source theme switching for dark mode
- Add Moonshot AI (Kimi) as a public business sponsor: logo in the top
sponsors table, SPONSORS.md row, placeholder comment removed
- Swap atlascloud.png for the official atlascloud.svg wordmark; add
dark-theme variants for Atlas Cloud and Moonshot
- Rewrite the bottom Sponsors section: one consistent list, no
Ito-only subsection or stray horizontal rule
- Point the self-host/gateway FAQ at the ito-compute skill for
fixed-rate GPU blocks (npm CLI marked coming soon, not yet published)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0149VwNuynam6rvEfcMmiHHa
* docs: drop em dash from sponsor FAQ line
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0149VwNuynam6rvEfcMmiHHa
* docs(sponsors): Itô is a Partner, Moonshot AI (Kimi) are Open Source Friends
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0149VwNuynam6rvEfcMmiHHa
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
The existing OpenAI pattern sk-[a-zA-Z0-9]{20,} never matches real
Anthropic keys: their sk-ant-api03-... format contains hyphens, which
break the character class before reaching the 20-char threshold. Keys
from the fastest-growing Claude Code user base slipped through the scan.
Adds a dedicated sk-ant-[a-zA-Z0-9_-]{20,} pattern (checked before the
OpenAI one) and extends the staged-secrets test with a realistic
Anthropic key fixture.
Two continuous-learning-v2 observer regressions reported in #2452:
- start-observer.sh still called _ecc_resolve_homunculus_dir, but the
shared lib was renamed to _clv2_resolve_homunculus_dir (with observe.sh
and detect-project.sh updated, start-observer.sh missed). Under set -e
every launch dies with exit 127 at line 40 - daemon boot is broken on
all platforms, not just Windows.
- observer-loop.sh backgrounds the analysis claude call with stdin left
open; on Git Bash/MSYS2 the child inherits it, waits, warns 'no stdin
data received', and exits 1 before reading the analysis file. Close
stdin with </dev/null while keeping the -p prompt flag, preserving the
Windows-compat decision from #842 instead of reverting to a stdin
redirect.
Adds two source invariant guards to tests/hooks/hooks.test.js: every
*_resolve_homunculus_dir call site must match a function the shared lib
defines, and the backgrounded claude call must close stdin.
Fixes#2452
* fix(suggest-compact): recognize large-window model families without a [1m] marker
resolveContextWindowTokens() only detected a 1M window via the env
override, the [1m] model-id marker, or observed tokens already above
200k. Large-window models whose ids carry none of these (e.g.
claude-fable-5) were misclassified as 200k windows, overstating
context usage ~5x in the compact suggestion.
Add a known-model-family substring table (claude-fable-5,
claude-mythos-5) checked after the env override and [1m] marker and
before the token-count heuristic. Env overrides still win, and unknown
model ids still fall back to the 200k default.
Closes#2461
* fix(suggest-compact): anchor known-model-family match at a token boundary
Unanchored substring matching would misclassify a hypothetical smaller
tier sharing a known family prefix (e.g. claude-fable-5-mini) as a 1M
window. Require the family id to end at a token boundary: end of id, a
delimiter, or a dated/versioned suffix (-20260115). Alphanumeric
continuations and letter suffixes no longer match.
Addresses CodeRabbit/Greptile review on #2468
On a case-insensitive filesystem (macOS APFS/HFS+, Windows NTFS) a write to
`.ESLINTRC.JS` lands on the exact same inode as `.eslintrc.js`, but the guard
looked the basename up in PROTECTED_FILES with a case-sensitive `Set.has`.
Every entry in that Set is lowercase, so any case-variant path missed the
branch entirely and returned exit 0 — a single Write silently overwrote a
live config while the hook reported success.
Reproduced on macOS APFS: `.eslintrc.js` and `.ESLINTRC.JS` share one inode,
yet the hook returned exit 2 for the former and exit 0 for the latter, and the
uppercase write replaced the real config's contents.
This is a one-step bypass of the whole guard and needs no shell access, unlike
the known delete-then-recreate route.
Fix: also test `basename.toLowerCase()`. All 32 PROTECTED_FILES entries are
already lowercase, so the fallback is exact. On a genuinely case-sensitive
filesystem this costs at most a false positive on a distinct file whose name
differs from a protected one by case alone.
Behaviour deliberately unchanged: first-time creation is still allowed (the
bootstrap affordance), non-config paths still pass through, and the existing
lstat/ENOENT fail-closed semantics are untouched.
Test: adds a case-variant case that asserts exit 2. It guards itself with an
inode comparison and skips on case-sensitive filesystems rather than asserting
something untrue there. Verified in both directions — it FAILS against the
unpatched hook (`Got 0; 0 !== 2`) and passes with the fix. Suite: 9/9.
