* feat(session-start): rank injected instincts by project/stack relevance
Instinct selection at SessionStart ranked purely by confidence, so a
high-confidence instinct about an unrelated stack could take an injection
slot from a lower-confidence instinct that is actually relevant to the
current project.
Rank by confidence + location/stack relevance instead: project-scoped
instincts, and instincts whose domain/trigger matches the detected stack
(languages/frameworks via detectProjectType, plus terraform/dbt markers),
get a small additive boost. The confidence>=threshold floor and the
injection cap are unchanged, and ranking degrades to confidence-only when
nothing matches or when ECC_INSTINCT_RELEVANCE_RANKING is set to off.
The ranking helpers live in scripts/lib/instinct-relevance.js with unit
coverage in tests/lib/, plus an end-to-end ordering test in tests/hooks/.
Completes part (b) of #2371; part (a) (configurable count + threshold)
shipped in #2413.
Fixes#2371
* refactor(session-start): drop redundant confidence tiebreaker in instinct sort
Greptile flagged that the secondary `right.confidence` comparison in
summarizeActiveInstincts' sort was dead code when relevance ranking is
disabled and, when enabled, was reached only on a floating-point tie of the
combined score — where it skipped the intended scope-label tiebreaker.
Remove it: the primary combined-score comparison already reduces to
confidence-only ordering when relevance is off, so behavior there is
unchanged; a genuine combined-score tie now falls through to the documented
scope-first, then id, order.
* test: isolate instinct relevance environment
---------
Co-authored-by: haelyra <49814733+haelyra@users.noreply.github.com>
* feat(session-start): make instinct injection count and confidence threshold configurable
Expose ECC_MAX_INJECTED_INSTINCTS and ECC_INSTINCT_CONFIDENCE_THRESHOLD so
operators can tune SessionStart instinct injection without editing source.
Defaults are unchanged (6 instincts, 0.7 confidence floor).
The two previously hardcoded constants become DEFAULT_-prefixed fallbacks,
resolved through getMaxInjectedInstincts() and getInstinctConfidenceThreshold(),
mirroring the existing getSessionRetentionDays() /
getSessionStartMaxContextChars() env-override pattern already in this file.
Invalid or out-of-range values fall back to the defaults.
Adds subprocess coverage in tests/hooks/hooks.test.js and documents both
variables in the README Hook Runtime Controls section.
Implements part (a) of #2371.
* fix(session-start): reject partial env values for instinct injection knobs
Parse ECC_MAX_INJECTED_INSTINCTS and ECC_INSTINCT_CONFIDENCE_THRESHOLD with
Number() (after trim) instead of parseInt/parseFloat, so malformed values
like "3.9", "6abc", or "0.7x" fall back to the default rather than silently
accepting the numeric prefix (parseInt("3.9")=3, parseFloat("0.7x")=0.7).
Adds a regression assertion that a non-integer count falls back to 6.
* fix(session-start): validate decimal grammar for instinct injection env vars
Number() still accepts non-decimal numeric syntax, so
ECC_INSTINCT_CONFIDENCE_THRESHOLD=0x1 resolved to 1 and
ECC_MAX_INJECTED_INSTINCTS=1e2 to 100. Gate each value on a strict format
(/^\d+(\.\d+)?$/ for the 0-1 threshold, /^\d+$/ for the positive-integer
count) before converting, so hex/exponent/partial values fall back to the
default. Adds regression assertions for 1e2 and 0x1.
* fix(session-start): support ECC_SESSION_RETENTION_DAYS opt-out + document env var
The retention pass for *-session.tmp files (issue #2151) landed previously,
but the env var that controls it was undocumented in the README and rejected
falsy values (0, off, disabled), silently falling back to the 30-day default.
Users who want to keep all sessions for forensic or research workflows had no
way to opt out.
This patch:
- Extends getSessionRetentionDays() so 0|off|false|disabled|never|none disables
pruning entirely (returns null sentinel; default behavior unchanged).
- Updates the call site in main() to skip pruneExpiredSessions when retention
is null and emits a clear "[SessionStart] Pruning disabled via
ECC_SESSION_RETENTION_DAYS" log line so the operator can tell pruning is off.
- Documents ECC_SESSION_RETENTION_DAYS in the README "Hook Runtime Controls"
section alongside the other ECC_SESSION_* knobs.
- Adds three regression tests in tests/hooks/hooks.test.js covering opt-out
via 0, opt-out via off, and garbage-value fallback to default 30.
Verification:
- node tests/hooks/hooks.test.js — 240/240 green (incl. 3 new retention tests)
- node tests/run-all.js — 2622/2622 green
- npx eslint scripts/hooks/session-start.js tests/hooks/hooks.test.js — clean
- node scripts/ci/validate-no-personal-paths.js — clean
- node scripts/ci/check-unicode-safety.js — clean
- node scripts/ci/validate-hooks.js — 28 matchers validated
- node scripts/ci/validate-rules.js — 115 files validated
Fixes#2151
* docs(readme): list all ECC_SESSION_RETENTION_DAYS opt-out values + add Windows example
Address reviewer feedback on PR #2163:
- CodeRabbit and cubic both flagged that the README docs only listed 3 of 6
opt-out values accepted by getSessionRetentionDays() (0, off, disabled),
while the implementation also accepts false, never, none.
- cubic also flagged the missing Windows PowerShell example for the new
variable, breaking the parallel structure of the existing
ECC_CONTEXT_MONITOR_COST_WARNINGS example block.
Updated the README to:
- Spell out all six opt-out values (0, off, false, disabled, never, none)
and clarify they "keep all sessions (disable pruning)".
- Add an ECC_SESSION_RETENTION_DAYS line to the Windows PowerShell example.
No behavior change. README only.
Verification:
- npx markdownlint README.md — clean
- npx eslint scripts/hooks/session-start.js tests/hooks/hooks.test.js — clean
The SessionStart hook injects the most recent *-session.tmp as
additionalContext labelled only with 'Previous session summary:'.
After a /compact boundary, the model frequently re-executes stale
slash-skill invocations it finds inside that summary, re-running
ARGUMENTS-bearing skills (e.g. /fw-task-new, /fw-raise-pr) with the
last ARGUMENTS they saw.
Observed on claude-opus-4-7 with ECC v1.9.0 on a firmware project:
after compaction resume, the model spontaneously re-enters the prior
skill with stale ARGUMENTS, duplicating GitHub issues, Notion tasks,
and branches for work that is already merged.
ECC cannot fix Claude Code's skill-state replay across compactions,
but it can stop amplifying it. Wrap the injected summary in an
explicit HISTORICAL REFERENCE ONLY preamble with a STALE-BY-DEFAULT
contract and delimit the block with BEGIN/END markers so the model
treats everything inside as frozen reference material.
Tests: update the two hooks.test.js cases that asserted on the old
'Previous session summary' literal to assert on the new guard
preamble, the STALE-BY-DEFAULT contract, and both delimiters. 219/219
tests pass locally.
Tracked at: #1534
* fix: filter session-start injection by cwd/project to prevent cross-project contamination
The SessionStart hook previously selected the most recent session file
purely by timestamp, ignoring the current working directory. This caused
Claude to receive a previous project's session context when switching
between projects, leading to incorrect file reads and project analysis.
session-end.js already writes **Project:** and **Worktree:** header
fields into each session file. This commit adds selectMatchingSession()
which uses those fields with the following priority:
1. Exact worktree (cwd) match — most recent
2. Same project name match — most recent
3. Fallback to overall most recent (preserves backward compatibility)
No new dependencies. Gracefully falls back to original behavior when
no matching session exists.
* fix: address review feedback — eliminate duplicate I/O, add null guards, improve docstrings
- Return { session, content, matchReason } from selectMatchingSession()
to avoid reading the same file twice (coderabbitai, greptile P2)
- Add empty array guard: return null when sessions.length === 0 (coderabbitai)
- Stop mutating input objects — no more session._matchReason (coderabbitai)
- Add null check on result before accessing properties (coderabbitai)
- Only log "selected" after confirming content is readable (cubic-dev-ai P3)
- Add full JSDoc with @param/@returns (docstring coverage)
* fix: track fallback session object to prevent session/content mismatch
When sessions[0] is unreadable, fallbackContent came from a later
session (e.g. sessions[1]) while the returned session object still
pointed to sessions[0]. This caused misleading logs and injected
content from the wrong session — the exact problem this PR fixes.
Now tracks fallbackSession alongside fallbackContent so the returned
pair is always consistent.
Addresses greptile-apps P1 review feedback.
* fix: normalize worktree paths to handle symlinks and case differences
On macOS /var is a symlink to /private/var, and on Windows paths may
differ in casing (C:\repo vs c:\repo). Use fs.realpathSync() to
resolve both sides before comparison so worktree matching is reliable
across symlinked and case-insensitive filesystems.
cwd is normalized once outside the loop to avoid repeated syscalls.
Addresses coderabbitai Major review feedback.
---------
Co-authored-by: kuqili <kuqili@tencent.com>
Windows terminals emit control sequences (cursor movement, screen
clearing) that leaked into session.tmp files and were injected
verbatim into Claude's context on the next session start.
Add a comprehensive stripAnsi() to utils.js that handles CSI, OSC,
charset selection, and bare ESC sequences. Apply it in session-end.js
(when extracting user messages from the transcript) and in
session-start.js (safety net before injecting session content).
getAvailablePackageManagers() spawned where.exe/which for each package
manager (npm, pnpm, yarn, bun). During SessionStart hooks, these 4+
child processes combined with Bun's own initialization exceeded the
spawn limit on Windows, freezing the terminal.
Fix: Remove process spawning from the hot path. Steps 1-5 of detection
(env var, project config, package.json, lock file, global config) already
cover all file-based detection. If none match, default to npm without
spawning. Also fix getSelectionPrompt() to list supported PMs without
checking availability.
session-end.js: Extract meaningful summaries from CLAUDE_TRANSCRIPT_PATH
instead of writing blank template files. Pulls user messages, tools used,
and files modified from the session transcript JSONL.
session-start.js: Output the latest session summary to stdout (via the
output() helper) so it gets injected into Claude's conversation context,
instead of only logging to stderr which just shows briefly in the terminal.
Add a new /sessions command to manage Claude Code session history with
alias support for quick access to previous sessions.
Features:
- List sessions with pagination and filtering (by date, ID)
- Load and view session content and metadata
- Create memorable aliases for sessions
- Remove aliases
- Display session statistics (lines, items, size)
- List all aliases
New libraries:
- scripts/lib/session-manager.js - Core session CRUD operations
- scripts/lib/session-aliases.js - Alias management with atomic saves
New command:
- commands/sessions.md - Complete command with embedded scripts
Modified:
- scripts/lib/utils.js - Add getAliasesPath() export
- scripts/hooks/session-start.js - Show available aliases on session start
Session format support:
- Old: YYYY-MM-DD-session.tmp
- New: YYYY-MM-DD-<short-id>-session.tmp
Aliases are stored in ~/.claude/session-aliases.json with Windows-
compatible atomic writes and backup support.
Co-authored-by: 王志坚 <wangzhijian10@bgyfw.com>
Co-authored-by: Claude <noreply@anthropic.com>
- Fix 16 ESLint no-unused-vars errors across hook scripts and tests
- Add eslint-disable comment for intentional control-regex in ANSI stripper
- Update session file test to use getSessionIdShort() instead of hardcoded 'default'
(reflects PR #110's project-name fallback behavior)
- Add marketing/ to .gitignore (local drafts)
- Add skill-create-output.js (terminal output formatter)
All 69 tests now pass. CI should be green.
