everything-claude-code

fix: port continuous-learning observer fixes

Ports continuous-learning observer signal, storage, remote normalization, and v1 deprecation fixes onto current main.

Affaan Mustafa · 2026-05-11 03:35:42 -04:00

12e1bc424d

fix: retry observer wait after signal

Affaan Mustafa · 2026-04-28 22:11:47 -04:00

fd95cf6b29

fix: harden windows observer prompt handling

Affaan Mustafa · 2026-04-06 14:05:38 -07:00

df96abe74c

fix: raise observer turn budget

Affaan Mustafa · 2026-04-05 14:23:06 -07:00

908116d736

fix: clean up observer sessions on lifecycle end

Affaan Mustafa · 2026-04-02 18:02:29 -07:00

16e9b17ad7

fix(clv2): honor CLV2_CONFIG in start-observer

Affaan Mustafa · 2026-03-29 00:21:55 -04:00

be76918850

fix(observer): clean up prompt_file early and fix test for analysis_relpath

- Remove prompt_file immediately after shell expansion into -p arg,
  avoiding stale temp files during long analysis windows (greptile feedback)
- Update test assertion to check analysis_relpath instead of analysis_file,
  matching the cross-platform relative path change from earlier commits

Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>

Lidang-Jiang · 2026-03-28 23:32:44 +08:00

7a4cb8c570

fix(observer): clean up temp files on cd failure early return

The cd "$PROJECT_DIR" failure path returned without removing prompt_file
and analysis_file, leaving stale temp files in .observer-tmp/.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>

Lidang-Jiang · 2026-03-28 11:38:10 +08:00

451732164f

fix(observer): guard cd failure with early return and log message

Address reviewer feedback: under set +e, a failing cd would silently
leave CWD unchanged, causing the relative analysis path to break.
Add || return with a diagnostic log entry.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>

Lidang-Jiang · 2026-03-28 10:45:41 +08:00

194bc0000b

fix(observer): anchor CWD to PROJECT_DIR before Claude invocation

Reviewers correctly identified that the relative analysis_relpath
(.observer-tmp/<file>) only resolves when CWD equals PROJECT_DIR.
Without an explicit cd, non-Windows users launching the observer from
a different directory would fail to read the analysis file.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>

Lidang-Jiang · 2026-03-28 10:34:40 +08:00

31af1adcc8

fix(observer): improve Windows compatibility for temp files and Haiku prompt

Address remaining issues from #842 after PR #903 moved temp files to
PROJECT_DIR/.observer-tmp:

Bug A (path resolution): Use relative paths (.observer-tmp/filename)
in the prompt instead of absolute paths from mktemp. On Windows
Git Bash/MSYS2, absolute paths use MSYS-style prefixes (/c/Users/...)
that the spawned Claude subprocess may fail to resolve.

Bug B (asks for permission): Add explicit IMPORTANT instruction block
at the prompt start telling the Haiku agent it is in non-interactive
--print mode and must use the Write tool directly without asking for
confirmation.

Additional improvements:
- Pass prompt via -p flag instead of stdin redirect for Windows compat
- Add .observer-tmp/ to .gitignore to prevent accidental commits

Fixes #842

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>

Lidang-Jiang · 2026-03-28 09:54:35 +08:00

c80631fc1d

fix: fold session manager blockers into one candidate

Affaan Mustafa · 2026-03-24 23:08:27 -04:00

1d0aa5ac2a

feat: pending instinct TTL pruning and /prune command (#725 )

* feat: add pending instinct TTL pruning and /prune command

Pending instincts generated by the observer accumulate indefinitely
with no cleanup mechanism. This adds lifecycle management:

- `instinct-cli.py prune` — delete pending instincts older than 30 days
  (configurable via --max-age). Supports --dry-run and --quiet flags.
- Enhanced `status` command — shows pending count, warns at 5+,
  highlights instincts expiring within 7 days.
- `observer-loop.sh` — runs prune before each analysis cycle.
- `/prune` slash command — user-facing command for manual pruning.

Design rationale: council consensus (4/4) rejected auto-promote in
favor of TTL-based garbage collection. Frequency of observation does
not establish correctness. Unreviewed pending instincts auto-delete
after 30 days; if the pattern is real, the observer will regenerate it.

Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

* fix: remove duplicate functions, broaden extension filter, fix prune output

- Remove duplicate _collect_pending_dirs and _parse_created_date defs
- Use ALLOWED_INSTINCT_EXTENSIONS (.md/.yaml/.yml) instead of .md-only
- Track actually-deleted items separately from expired for accurate output
- Update README.md and AGENTS.md command counts: 59 → 60

Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

* fix: address Copilot and CodeRabbit review findings

- Use is_dir() instead of exists() for pending path checks
- Change > to >= for --max-age boundary (--max-age 0 now prunes all)
- Use CLV2_PYTHON_CMD env var in observer-loop.sh prune call
- Remove unused source_dupes variable
- Remove extraneous f-string prefix on static string

Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

* fix: update AGENTS.md project structure command count 59 → 60

Co-Authored-By: Claude <noreply@anthropic.com>

* fix: address cubic and coderabbit review findings

- Fix status early return skipping pending instinct warnings (cubic #1)
- Exclude already-expired items from expiring-soon filter (cubic #2)
- Warn on unparseable pending instinct age instead of silent skip (cubic #4)
- Log prune failures to observer.log instead of silencing (cubic #5)

Co-Authored-By: Claude <noreply@anthropic.com>

* fix: YAML single-quote unescaping, f-string cleanup, add /prune to README

- Fix single-quoted YAML unescaping: use '' doubling (YAML spec) not
  backslash escaping which only applies to double-quoted strings (greptile P1)
- Remove extraneous f-string prefix on static string (coderabbit)
- Add /prune to README command catalog and file tree (cubic)

Co-Authored-By: Claude <noreply@anthropic.com>

---------

Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Happy <yesreply@happy.engineering>

Chris Yau · 2026-03-22 15:40:58 -07:00

0e733753e0

fix(clv2): add --allowedTools to observer Haiku invocation (#661 )

The observer's Haiku subprocess cannot access files outside the project
sandbox (/tmp/ for observations, ~/.claude/homunculus/ for instincts).
Adding --allowedTools "Read,Write" grants the necessary file access
while keeping the subprocess constrained by --max-turns and timeout.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

to.watanabe · 2026-03-20 16:00:17 +09:00

f37c92cfe2

fix: observer memory explosion with throttling, re-entrancy guard, and tail sampling (#536 )

Three fixes for the positive feedback loop causing runaway memory usage:

1. SIGUSR1 throttling in observe.sh: Signal observer only every 20
   observations (configurable via ECC_OBSERVER_SIGNAL_EVERY_N) instead
   of on every tool call. Uses a counter file to track invocations.

2. Re-entrancy guard in observer-loop.sh on_usr1(): ANALYZING flag
   prevents parallel Claude analysis processes from spawning when
   signals arrive while analysis is already running.

3. Cooldown + tail-based sampling in observer-loop.sh:
   - 60s cooldown between analyses (ECC_OBSERVER_ANALYSIS_COOLDOWN)
   - Only last 500 lines sent to LLM (ECC_OBSERVER_MAX_ANALYSIS_LINES)
     instead of the entire observations file

Closes #521

Affaan Mustafa · 2026-03-16 13:47:25 -07:00

f9e8287346

Merge branch 'main' into main

Affaan Mustafa · 2026-03-13 00:00:34 -07:00

1c1a9ef73e

fix: harden observer prompt guard handling

Affaan Mustafa · 2026-03-12 23:59:01 -07:00

e043a2824a

feat: active hours + idle detection gates for session-guardian (#413 )

* feat: add project cooldown log to prevent rapid observer re-spawn

Adds session-guardian.sh, called by observer-loop.sh before each Haiku
spawn. It reads ~/.claude/observer-last-run.log and blocks the cycle if
the same project was observed within OBSERVER_INTERVAL_SECONDS (default
300s).

Prevents self-referential loops where a spawned session triggers
observe.sh, which signals the observer before the cooldown has elapsed.

Uses a mkdir-based lock for safe concurrent access across multiple
simultaneously-observed projects. Log entries use tab-delimited format
to handle paths containing spaces. Fails open on lock contention.

Config:
  OBSERVER_INTERVAL_SECONDS   default: 300
  OBSERVER_LAST_RUN_LOG       default: ~/.claude/observer-last-run.log

No external dependencies. Works on macOS, Linux, Windows (Git Bash/MSYS2).

* feat: extend session-guardian with time window and idle detection gates

Adds Gate 1 (active hours check) and Gate 3 (system idle detection) to
session-guardian.sh, building on the per-project cooldown log from PR 1.

Gate 1 — Time Window:
- OBSERVER_ACTIVE_HOURS_START/END (default 800–2300 local time)
- Uses date +%k%M with 10# prefix to avoid octal crash at midnight
- Toolless on all platforms; set both vars to 0 to disable

Gate 3 — Idle Detection:
- macOS: ioreg + awk (built-in, no deps)
- Linux: xprintidle if available, else fail open
- Windows (Git Bash/MSYS2): PowerShell GetLastInputInfo via Add-Type
- Unknown/headless: always returns 0 (fail open)
- OBSERVER_MAX_IDLE_SECONDS=0 disables gate

Fixes in this commit:
- 10# base-10 prefix prevents octal arithmetic crash on midnight minutes
  containing digits 8 or 9 (e.g. 00:08 = "008" is invalid octal)
- PowerShell output piped through tr -d '\r' to strip Windows CRLF;
  also uses [long] cast to avoid TickCount 32-bit overflow after 24 days
- mktemp now uses log file directory instead of TMPDIR to ensure
  same-filesystem mv on Linux (atomic rename instead of copy+unlink)
- mkdir -p failure exits 0 (fail open) rather than crashing under set -e
- Numeric validation on last_spawn prevents arithmetic error on corrupt log

Gate execution order: 1 (time, ~0ms) → 2 (cooldown, ~1ms) → 3 (idle, ~50ms)

* fix: harden session guardian gates

---------

Co-authored-by: Affaan Mustafa <affaan@dcube.ai>

ispaydeu · 2026-03-12 23:44:34 -07:00

a6f380fde0

fix(observe): 5-layer automated session guard to prevent self-loop observations (#399 )

* fix(observe): add 5-layer automated session guard to prevent self-loop observations

observe.sh currently fires for ALL hook events including automated/programmatic
sessions: the ECC observer's own Haiku analysis runs, claude-mem observer
sessions, CI pipelines, and any other tool that spawns `claude --print`.

This causes an infinite feedback loop where automated sessions generate
observations that trigger more automated analysis, burning Haiku tokens with
no human activity.

Add a 5-layer guard block after the `disabled` check:

Layer 1: agent_id payload field — only present in subagent hooks; skip any
         subagent-scoped session (always automated by definition).

Layer 2: CLAUDE_CODE_ENTRYPOINT env var — Claude Code sets this to sdk-ts,
         sdk-py, sdk-cli, mcp, or remote for programmatic/SDK invocations.
         Skip if any non-cli entrypoint is detected. This is universal: catches
         any tool using the Anthropic SDK without requiring tool cooperation.

Layer 3: ECC_HOOK_PROFILE=minimal — existing ECC mechanism; respect it here
         to suppress non-essential hooks in observer contexts.

Layer 4: ECC_SKIP_OBSERVE=1 — cooperative env var any external tool can set
         before spawning automated sessions (explicit opt-out contract).

Layer 5: CWD path exclusions — skip sessions whose working directory matches
         known observer-session path patterns. Configurable via
         ECC_OBSERVE_SKIP_PATHS (comma-separated substrings, default:
         "observer-sessions,.claude-mem").

Also fix observer-loop.sh to set ECC_SKIP_OBSERVE=1 and ECC_HOOK_PROFILE=minimal
before spawning the Haiku analysis subprocess, making the observer loop
self-aware and closing the ECC→ECC self-observation loop without needing
external coordination.

Fixes: observe.sh fires unconditionally on automated sessions (#398)

* fix(observe): address review feedback — reorder guards cheapest-first, fix empty pattern bug

Two issues flagged by Copilot and CodeRabbit in PR #399:

1. Layer ordering: the agent_id check spawns a Python subprocess but ran
   before the cheap env-var checks (CLAUDE_CODE_ENTRYPOINT, ECC_HOOK_PROFILE,
   ECC_SKIP_OBSERVE). Reorder to put all env-var checks first (Layers 1-3),
   then the subprocess-requiring agent_id check (Layer 4). Automated sessions
   that set env vars — the common case — now exit without spawning Python.

2. Empty pattern bug in Layer 5: if ECC_OBSERVE_SKIP_PATHS contains a trailing
   comma or spaces after commas (e.g. "path1, path2" or "path1,"), _pattern
   becomes empty or whitespace-only, and the glob *""* matches every CWD,
   silently disabling all observations. Fix: trim leading/trailing whitespace
   from each pattern and skip empty patterns with `continue`.

* fix: fail closed for non-cli entrypoints

---------

Co-authored-by: Affaan Mustafa <affaan@dcube.ai>

ispaydeu · 2026-03-12 23:40:03 -07:00

c52a28ace9

fix: add confirmation-prompt guard to start-observer.sh (issue #400 )

- Redirect observer output to temp log before appending to main log
- Check temp log for confirmation/permission language immediately after start
- Fail closed with exit 2 if detected, preventing retry loops

swarnika-cmd · 2026-03-12 06:52:54 +05:30

96708e5d45

fix: raise observer analysis turn budget

Affaan Mustafa · 2026-03-10 20:52:53 -07:00

16bc7436c5

fix: harden hook portability and plugin docs

Affaan Mustafa · 2026-03-09 22:49:43 -07:00

440178d697

feat: deliver v1.8.0 harness reliability and parity updates

Affaan Mustafa · 2026-03-04 14:48:06 -08:00

48b883d741

fix(continuous-learning-v2): observer background process crashes immediately (#312 )

* fix(continuous-learning-v2): observer background process crashes immediately

Three bugs prevent the observer from running:

1. Nested session detection: When launched from a Claude Code session,
   the child process inherits CLAUDECODE env var, causing `claude` CLI
   to refuse with "cannot be launched inside another session". Fix: unset
   CLAUDECODE in the background process.

2. set -e kills the loop: The parent script's `set -e` is inherited by
   the subshell. When `claude` exits non-zero (e.g. max turns reached),
   the entire observer loop dies. Fix: `set +e` in the background process.

3. Subshell dies when parent exits: `( ... ) & disown` loses IO handles
   when the parent shell exits, killing the background process. Fix: use
   `nohup /bin/bash -c '...'` for full detachment, and `sleep & wait`
   to allow SIGUSR1 to interrupt sleep without killing the process.

Additionally, the prompt for Haiku now includes the exact instinct file
format inline (YAML frontmatter with id/trigger/confidence/domain/source
fields), since the previous prompt referenced "the observer agent spec"
which Haiku could not actually read, resulting in instinct files that
the CLI parser could not parse.

* fix: address review feedback on observer process management

- Use `env` to pass variables to child process instead of quote-splicing,
  avoiding shell injection risk from special chars in paths
- Add USR1_FIRED flag to prevent double analysis when SIGUSR1 interrupts
  the sleep/wait cycle
- Track SLEEP_PID and kill it in both TERM trap and USR1 handler to
  prevent orphaned sleep processes from accumulating
- Consolidate cleanup logic into a dedicated cleanup() function

* fix: guard PID file cleanup against race condition on restart

Only remove PID file in cleanup trap if it still belongs to the
current process, preventing a restarted observer from losing its
PID file when the old process exits.

zzzhizhi · 2026-03-02 22:23:01 -08:00

adc0f67008

fix: resolve CI failures on main — lint, hooks validator, and test alignment

- Fix MD012 trailing blank lines in commands/projects.md and commands/promote.md
- Fix MD050 strong-style in continuous-learning-v2 (escape __tests__ as inline code)
- Extract doc-file-warning hook to standalone script to fix hooks validator regex parsing
- Update session-end test to match #317 behavior (always update summary content)
- Allow shell script hooks in integration test format validation

All 992 tests passing.

Affaan Mustafa · 2026-03-02 22:15:46 -08:00

1df0a53f22

feat: project-scoped instinct isolation

* feat: add project-scoped instinct isolation

* fix(continuous-learning-v2): harden instinct loading and promotion safety; sync v2.1 command docs

* fix(ci): make copilot-setup-steps a valid GitHub Actions workflow

* fix(hooks): stabilize docs warning inline JS regex parsing

Harry Kwok · 2026-03-01 12:07:13 -08:00

5818e8adc7

fix: harden CI validators, shell scripts, and expand test suite

- Add try-catch around readFileSync in validate-agents, validate-commands,
  validate-skills to handle TOCTOU races and file read errors
- Add validate-hooks.js and all test suites to package.json test script
  (was only running 4/5 validators and 0/4 test files)
- Fix shell variable injection in observe.sh: use os.environ instead of
  interpolating $timestamp/$OBSERVATIONS_FILE into Python string literals
- Fix $? always being 0 in start-observer.sh: capture exit code before
  conditional since `if !` inverts the status
- Add OLD_VERSION validation in release.sh and use pipe delimiter in sed
  to avoid issues with slash-containing values
- Add jq dependency check in evaluate-session.sh before parsing config
- Sync .cursor/ copies of all modified shell scripts

Affaan Mustafa · 2026-02-12 14:11:33 -08:00

f3a4b33d41

fix: harden error handling, fix TOCTOU races, and improve test accuracy

Core library fixes:
- session-manager.js: wrap all statSync calls in try-catch to prevent
  TOCTOU crashes when files are deleted between readdir and stat
- session-manager.js: use birthtime||ctime fallback for Linux compat
- session-manager.js: remove redundant existsSync before readFile
- utils.js: fix findFiles TOCTOU race on statSync inside readdir loop

Hook improvements:
- Add 1MB stdin buffer limits to all PostToolUse hooks to prevent
  unbounded memory growth from large payloads
- suggest-compact.js: use fd-based atomic read+write for counter file
  to reduce race window between concurrent invocations
- session-end.js: log when transcript file is missing, check
  replaceInFile return value for failed timestamp updates
- start-observer.sh: log claude CLI failures instead of silently
  swallowing them, check observations file exists before analysis

Test fixes:
- Fix blocking hook tests to send matching input (dev server command)
  and expect correct exit code 2 instead of 1

Affaan Mustafa · 2026-02-12 13:40:14 -08:00

36864ea11a

feat: v1.1.0 release - session ID tracking, async hooks, new skills

- Add session ID to session filenames (Issue #62)
- Add getSessionIdShort() helper for unique per-session tracking
- Add async hooks documentation with example
- Create iterative-retrieval skill for progressive context refinement
- Add continuous-learning-v2 skill with instinct-based learning
- Add ecc.tools ecosystem section to README
- Update skills list in README

All 67 tests passing.

Affaan Mustafa · 2026-01-25 18:21:27 -08:00

5c63fa9006

29 Commits