- 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>
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>
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>
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>
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>
* 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>
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>
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
* 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>
* 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>
Affaan Mustafa ·
Lidang-Jiang ·
Chris Yau ·
to.watanabe ·
Affaan Mustafa ·
ispaydeu ·