t1081: Daily skill auto-update pipeline — 24h freshness gate in auto-update-helper.sh#1591
Merged
marcusquinn merged 1 commit intomainfrom Feb 17, 2026
Merged
t1081: Daily skill auto-update pipeline — 24h freshness gate in auto-update-helper.sh#1591marcusquinn merged 1 commit intomainfrom
marcusquinn merged 1 commit intomainfrom
Conversation
- Add check_skill_freshness() with 24h gate (AIDEVOPS_SKILL_FRESHNESS_HOURS) - Add update_skill_check_timestamp() to persist last_skill_check in state file - Call check_skill_freshness() from all cmd_check() exit paths (runs every 10min, gate throttles to 24h) - Opt-out via AIDEVOPS_SKILL_AUTO_UPDATE=false env var - Update cmd_status() to display last_skill_check timestamp - Update help text with new env vars and how-it-works section - ShellCheck zero violations, bash -n syntax OK Layer 1 of t1081: all users get fresh skill docs locally within 24h. Layer 2 (t1082): maintainer PR pipeline for repo-level updates. Ref #1577
Contributor
WalkthroughIntroduces a daily skill freshness mechanism to Changes
Sequence Diagram(s)sequenceDiagram
participant Client as Client/cmd_check()
participant Helper as auto-update-helper.sh
participant StateFile as State File<br/>(last_skill_check)
participant SkillHelper as skill-update-helper.sh
Client->>Helper: Execute cmd_check()
Helper->>Helper: Perform standard update flows
Helper->>Helper: check_skill_freshness()
Helper->>StateFile: Read last_skill_check timestamp
alt Timestamp missing or >24h old
Helper->>SkillHelper: Invoke --auto-update --quiet
SkillHelper->>SkillHelper: Update skills
SkillHelper-->>Helper: Return status
end
Helper->>Helper: update_skill_check_timestamp()
Helper->>StateFile: Write current timestamp
Helper-->>Client: Complete with status
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related issues
Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Summary of ChangesHello @marcusquinn, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request introduces an automated daily skill update pipeline to the aidevops system. It ensures that all users with imported skills automatically receive fresh skill documentation within a 24-hour window, without requiring manual intervention. The changes integrate a new skill freshness check into the existing auto-update cron job, intelligently managing update frequency to optimize network usage while providing configurable options for users. Highlights
Changelog
Activity
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Tue Feb 17 23:52:26 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
The pull request introduces a daily skill auto-update pipeline with a 24-hour freshness gate, enhancing the auto-update-helper.sh script. The changes include new functions check_skill_freshness() and update_skill_check_timestamp(), updates to cmd_check(), cmd_status(), and cmd_help(), and new configuration options. The implementation is robust, handling opt-out mechanisms, cross-platform date parsing, and ensuring the skill freshness check runs consistently across various update scenarios. The code adheres well to the repository's shell script style guide, including explicit return statements, local variable declarations, and || true guards for commands that might fail. Overall, this is a well-executed and valuable addition to the project.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 3
🧹 Nitpick comments (1)
.agents/scripts/auto-update-helper.sh (1)
170-180:pgrep -f "setup\.sh"may match unrelated processes.The pattern
setup\.shis fairly generic and could match another project'ssetup.shor even agrepof the term in an editor buffer. In practice, the consequence is just a skipped cycle (conservative and safe), so this is low risk. If you ever want to tighten it:- if pgrep -f "setup\.sh" >/dev/null 2>&1; then + if pgrep -f "${INSTALL_DIR}/setup\.sh" >/dev/null 2>&1; then🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.agents/scripts/auto-update-helper.sh around lines 170 - 180, The pgrep usage in is_update_running() is too broad: replace the generic pgrep -f "setup\.sh" with a stricter check (e.g., match the concrete script path or use a safe regex to avoid matching the grep/other projects). Update the first check to either pgrep -f "/full/path/to/setup\.sh" or use pgrep -f "[s]etup\.sh" and/or validate candidate PIDs by inspecting their command line (ps -o args= <pid>) to ensure the process is the intended setup script; leave the existing "aidevops update" pgrep as-is unless you also want to tighten it. Ensure changes are made inside the is_update_running() function replacing the pgrep -f "setup\.sh" line.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.agents/scripts/auto-update-helper.sh:
- Around line 619-623: The help block describing the scheduled run in
.agents/scripts/auto-update-helper.sh currently documents calling
"skill-update-helper.sh --auto-update --quiet" but the script actually invokes
"skill-update-helper.sh check --auto-update --quiet"; update one of them for
consistency: either change the runtime call that uses the "check" subcommand in
the invocation of skill-update-helper.sh to match the documented "--auto-update
--quiet" form, or modify the help text to state "skill-update-helper.sh check
--auto-update --quiet". Locate the help text block (the "Runs daily skill
freshness check (24h gate):" paragraph) and the code that calls
skill-update-helper.sh (the invocation that includes "check --auto-update
--quiet") and make them match exactly so logs and docs align.
- Around line 239-241: The script multiplies freshness_hours into
freshness_seconds without validating AIDEVOPS_SKILL_FRESHNESS_HOURS, so
non-numeric input will cause a bash arithmetic error under set -e; before
computing freshness_seconds, validate freshness_hours (the local
AIDEVOPS_SKILL_FRESHNESS_HOURS fallback assigned to freshness_hours) is an
integer (e.g., regex ^[0-9]+$ or use a numeric test) and if invalid or empty,
reset freshness_hours to DEFAULT_SKILL_FRESHNESS_HOURS and optionally log a
warning; then compute freshness_seconds from the validated freshness_hours.
- Around line 289-298: Make the CLI invocation and timestamp logic explicit:
either remove the redundant "check" subcommand from the invocation of
"$skill_update_script" so it matches the documented usage, or update the doc to
include "check" — pick one and make it consistent. Capture the command exit code
(e.g., rc=$?) after running "$skill_update_script" --auto-update --quiet, and
only call update_skill_check_timestamp when rc==0 (success) or when rc==1 AND
AUTO_UPDATE is set/true (meaning updates were found and applied); otherwise do
not update the timestamp so transient failures are retried. Also add a log line
that includes the captured rc to aid debugging.
---
Nitpick comments:
In @.agents/scripts/auto-update-helper.sh:
- Around line 170-180: The pgrep usage in is_update_running() is too broad:
replace the generic pgrep -f "setup\.sh" with a stricter check (e.g., match the
concrete script path or use a safe regex to avoid matching the grep/other
projects). Update the first check to either pgrep -f "/full/path/to/setup\.sh"
or use pgrep -f "[s]etup\.sh" and/or validate candidate PIDs by inspecting their
command line (ps -o args= <pid>) to ensure the process is the intended setup
script; leave the existing "aidevops update" pgrep as-is unless you also want to
tighten it. Ensure changes are made inside the is_update_running() function
replacing the pgrep -f "setup\.sh" line.
Comment on lines
+239
to
+241
| local freshness_hours="${AIDEVOPS_SKILL_FRESHNESS_HOURS:-$DEFAULT_SKILL_FRESHNESS_HOURS}" | ||
| local freshness_seconds=$((freshness_hours * 3600)) | ||
|
|
Contributor
There was a problem hiding this comment.
Non-numeric AIDEVOPS_SKILL_FRESHNESS_HOURS will crash the script under set -e.
Since this value comes from a user-controlled environment variable, a non-numeric input (e.g., "24h" or "") will cause a bash arithmetic evaluation error and abort the entire cron run, skipping both the update check and skill refresh.
Consider validating before arithmetic:
🛡️ Proposed defensive guard
local freshness_hours="${AIDEVOPS_SKILL_FRESHNESS_HOURS:-$DEFAULT_SKILL_FRESHNESS_HOURS}"
+ if ! [[ "$freshness_hours" =~ ^[0-9]+$ ]]; then
+ log_warn "Invalid AIDEVOPS_SKILL_FRESHNESS_HOURS='$freshness_hours' — using default ${DEFAULT_SKILL_FRESHNESS_HOURS}"
+ freshness_hours="$DEFAULT_SKILL_FRESHNESS_HOURS"
+ fi
local freshness_seconds=$((freshness_hours * 3600))📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| local freshness_hours="${AIDEVOPS_SKILL_FRESHNESS_HOURS:-$DEFAULT_SKILL_FRESHNESS_HOURS}" | |
| local freshness_seconds=$((freshness_hours * 3600)) | |
| local freshness_hours="${AIDEVOPS_SKILL_FRESHNESS_HOURS:-$DEFAULT_SKILL_FRESHNESS_HOURS}" | |
| if ! [[ "$freshness_hours" =~ ^[0-9]+$ ]]; then | |
| log_warn "Invalid AIDEVOPS_SKILL_FRESHNESS_HOURS='$freshness_hours' — using default ${DEFAULT_SKILL_FRESHNESS_HOURS}" | |
| freshness_hours="$DEFAULT_SKILL_FRESHNESS_HOURS" | |
| fi | |
| local freshness_seconds=$((freshness_hours * 3600)) |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.agents/scripts/auto-update-helper.sh around lines 239 - 241, The script
multiplies freshness_hours into freshness_seconds without validating
AIDEVOPS_SKILL_FRESHNESS_HOURS, so non-numeric input will cause a bash
arithmetic error under set -e; before computing freshness_seconds, validate
freshness_hours (the local AIDEVOPS_SKILL_FRESHNESS_HOURS fallback assigned to
freshness_hours) is an integer (e.g., regex ^[0-9]+$ or use a numeric test) and
if invalid or empty, reset freshness_hours to DEFAULT_SKILL_FRESHNESS_HOURS and
optionally log a warning; then compute freshness_seconds from the validated
freshness_hours.
Comment on lines
+289
to
+298
| log_info "Running daily skill freshness check..." | ||
| if "$skill_update_script" check --auto-update --quiet >>"$LOG_FILE" 2>&1; then | ||
| log_info "Skill freshness check complete" | ||
| else | ||
| # Exit code 1 means updates were available (and applied) — not an error | ||
| log_info "Skill freshness check complete (updates applied)" | ||
| fi | ||
|
|
||
| update_skill_check_timestamp | ||
| return 0 |
Contributor
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
fd -t f 'skill-update-helper.sh' --exec echo "Found: {}" \;Repository: marcusquinn/aidevops
Length of output: 111
🏁 Script executed:
# Get file size first to understand what we're dealing with
wc -l ./.agents/scripts/skill-update-helper.shRepository: marcusquinn/aidevops
Length of output: 108
🏁 Script executed:
head -100 ./.agents/scripts/skill-update-helper.shRepository: marcusquinn/aidevops
Length of output: 2866
🏁 Script executed:
# Check around line 621 for the help text mentioned in the review
sed -n '610,635p' ./.agents/scripts/skill-update-helper.shRepository: marcusquinn/aidevops
Length of output: 46
🏁 Script executed:
# Check the argument parsing and main logic
sed -n '100,200p' ./.agents/scripts/skill-update-helper.shRepository: marcusquinn/aidevops
Length of output: 2599
🏁 Script executed:
# Check the main command parsing logic - look for where arguments are processed
tail -150 ./.agents/scripts/skill-update-helper.shRepository: marcusquinn/aidevops
Length of output: 4095
🏁 Script executed:
# Now check the auto-update-helper.sh file around lines 289-298 and 621
sed -n '280,310p' ./.agents/scripts/auto-update-helper.shRepository: marcusquinn/aidevops
Length of output: 1034
🏁 Script executed:
# Check the exit code behavior more closely - see if there are other exit paths in cmd_check
sed -n '200,280p' ./.agents/scripts/skill-update-helper.shRepository: marcusquinn/aidevops
Length of output: 3198
🏁 Script executed:
# Check the help text location in auto-update-helper.sh and verify line 621 reference
wc -l ./.agents/scripts/auto-update-helper.shRepository: marcusquinn/aidevops
Length of output: 107
🏁 Script executed:
# Check lines 615-630 to see what help text is actually documented
sed -n '615,630p' ./.agents/scripts/auto-update-helper.shRepository: marcusquinn/aidevops
Length of output: 810
🏁 Script executed:
# Check the skill-update-helper.sh to see all possible exit codes it can return
grep -n "return [0-9]" ./.agents/scripts/skill-update-helper.shRepository: marcusquinn/aidevops
Length of output: 388
🏁 Script executed:
# Check the actual invocation vs documentation more carefully
# Get the comment in auto-update-helper.sh about what it documents
sed -n '280,320p' ./.agents/scripts/auto-update-helper.sh | grep -A 10 -B 10 "skill-update"Repository: marcusquinn/aidevops
Length of output: 46
🏁 Script executed:
# Let me verify the exact invocation documented in auto-update-helper.sh
sed -n '625,628p' ./.agents/scripts/auto-update-helper.shRepository: marcusquinn/aidevops
Length of output: 275
🏁 Script executed:
# Search for where the skill-update-helper.sh invocation is documented in auto-update-helper.sh
grep -n "skill-update-helper" ./.agents/scripts/auto-update-helper.shRepository: marcusquinn/aidevops
Length of output: 515
🏁 Script executed:
# Let me verify the actual exit code semantics from cmd_check more carefully
sed -n '178,310p' ./.agents/scripts/skill-update-helper.sh | grep -A 3 -B 3 "return"Repository: marcusquinn/aidevops
Length of output: 550
CLI invocation and timestamp handling both need correction.
-
Documentation inconsistency: Line 290 invokes
"$skill_update_script" check --auto-update --quiet, but line 621 documentsskill-update-helper.sh --auto-update --quiet(without "check"). While both work—"check" is the default command—update the documentation to be explicit, or drop the redundant subcommand from the invocation. -
Timestamp masking transient failures: The
update_skill_check_timestampon line 297 runs unconditionally regardless of exit status. When skill-update-helper.sh returns exit code 1, it could indicate either that updates were found (expected) or that a genuine failure occurred (network timeout, auth issue). Without distinguishing between these cases, transient failures won't be retried within the 24-hour cycle.
Consider capturing the exit code and only recording the timestamp when the check succeeds (exit 0) or updates were genuinely available and processed (exit 1 with AUTO_UPDATE=true):
♻️ Proposed adjustment
log_info "Running daily skill freshness check..."
- if "$skill_update_script" check --auto-update --quiet >>"$LOG_FILE" 2>&1; then
+ local skill_exit=0
+ if "$skill_update_script" --auto-update --quiet >>"$LOG_FILE" 2>&1; then
log_info "Skill freshness check complete"
+ update_skill_check_timestamp
else
- # Exit code 1 means updates were available (and applied) — not an error
- log_info "Skill freshness check complete (updates applied)"
+ skill_exit=$?
+ if [[ $skill_exit -eq 1 ]]; then
+ log_info "Skill freshness check complete (updates applied)"
+ update_skill_check_timestamp
+ else
+ log_warn "Skill freshness check failed (exit code: $skill_exit) — will retry next cycle"
+ fi
fi
-
- update_skill_check_timestamp
return 0🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.agents/scripts/auto-update-helper.sh around lines 289 - 298, Make the CLI
invocation and timestamp logic explicit: either remove the redundant "check"
subcommand from the invocation of "$skill_update_script" so it matches the
documented usage, or update the doc to include "check" — pick one and make it
consistent. Capture the command exit code (e.g., rc=$?) after running
"$skill_update_script" --auto-update --quiet, and only call
update_skill_check_timestamp when rc==0 (success) or when rc==1 AND AUTO_UPDATE
is set/true (meaning updates were found and applied); otherwise do not update
the timestamp so transient failures are retried. Also add a log line that
includes the captured rc to aid debugging.
Comment on lines
+619
to
+623
| 6. Runs daily skill freshness check (24h gate): | ||
| a. Reads last_skill_check from state file | ||
| b. If >24h since last check, calls skill-update-helper.sh --auto-update --quiet | ||
| c. Updates last_skill_check timestamp in state file | ||
| d. Runs on every cmd_check invocation (gate prevents excessive network calls) |
Contributor
There was a problem hiding this comment.
Help text documents --auto-update --quiet but the actual invocation on line 290 passes check --auto-update --quiet.
Whichever form is correct, align the help text with the actual code to avoid confusion when users debug via logs. This ties back to the invocation concern flagged at line 290.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.agents/scripts/auto-update-helper.sh around lines 619 - 623, The help block
describing the scheduled run in .agents/scripts/auto-update-helper.sh currently
documents calling "skill-update-helper.sh --auto-update --quiet" but the script
actually invokes "skill-update-helper.sh check --auto-update --quiet"; update
one of them for consistency: either change the runtime call that uses the
"check" subcommand in the invocation of skill-update-helper.sh to match the
documented "--auto-update --quiet" form, or modify the help text to state
"skill-update-helper.sh check --auto-update --quiet". Locate the help text block
(the "Runs daily skill freshness check (24h gate):" paragraph) and the code that
calls skill-update-helper.sh (the invocation that includes "check --auto-update
--quiet") and make them match exactly so logs and docs align.
marcusquinn
added a commit
that referenced
this pull request
Feb 18, 2026
marcusquinn
added a commit
that referenced
this pull request
Feb 18, 2026
Three issues from PR #1591 review: 1. Validate AIDEVOPS_SKILL_FRESHNESS_HOURS is a positive integer before arithmetic expansion — non-numeric value crashes under set -e; falls back to DEFAULT_SKILL_FRESHNESS_HOURS with a warning log entry. 2. Fix help text: document 'skill-update-helper.sh check --auto-update --quiet' to match the actual runtime invocation (was missing 'check'). 3. Tighten pgrep -f pattern in is_update_running() from generic 'setup\.sh' to '${INSTALL_DIR}/setup\.sh' to avoid false matches from unrelated projects' setup scripts. ShellCheck zero violations, bash -n syntax OK.
marcusquinn
added a commit
that referenced
this pull request
Feb 18, 2026
) Three issues from PR #1591 review: 1. Validate AIDEVOPS_SKILL_FRESHNESS_HOURS is a positive integer before arithmetic expansion — non-numeric value crashes under set -e; falls back to DEFAULT_SKILL_FRESHNESS_HOURS with a warning log entry. 2. Fix help text: document 'skill-update-helper.sh check --auto-update --quiet' to match the actual runtime invocation (was missing 'check'). 3. Tighten pgrep -f pattern in is_update_running() from generic 'setup\.sh' to '${INSTALL_DIR}/setup\.sh' to avoid false matches from unrelated projects' setup scripts. ShellCheck zero violations, bash -n syntax OK.
marcusquinn
added a commit
that referenced
this pull request
Feb 18, 2026
marcusquinn
added a commit
that referenced
this pull request
Feb 18, 2026
marcusquinn
added a commit
that referenced
this pull request
Feb 18, 2026
marcusquinn
added a commit
that referenced
this pull request
Feb 18, 2026
t1081 "Daily skill auto-update pipeline" verified complete. All 4 subtasks (t1081.1-t1081.4) have merged PRs with substantive deliverables: - t1081.1 (#1591): 24h freshness gate + skill check in auto-update-helper.sh - t1081.2 (#1630): --non-interactive headless support in skill-update-helper.sh - t1081.3 (#1638): State file schema (last_skill_check, skill_updates_applied) - t1081.4 (#1639): AGENTS.md documentation No additional integration work needed. Unblocks t1082. SUPERVISOR: Mark t1081 [x] with verified:2026-02-18 pr:#1591,#1630,#1638,#1639
marcusquinn
added a commit
that referenced
this pull request
Feb 18, 2026
#1645) t1081 "Daily skill auto-update pipeline" verified complete. All 4 subtasks (t1081.1-t1081.4) have merged PRs with substantive deliverables: - t1081.1 (#1591): 24h freshness gate + skill check in auto-update-helper.sh - t1081.2 (#1630): --non-interactive headless support in skill-update-helper.sh - t1081.3 (#1638): State file schema (last_skill_check, skill_updates_applied) - t1081.4 (#1639): AGENTS.md documentation No additional integration work needed. Unblocks t1082. SUPERVISOR: Mark t1081 [x] with verified:2026-02-18 pr:#1591,#1630,#1638,#1639
marcusquinn
added a commit
that referenced
this pull request
Feb 18, 2026
Verification evidence: - t1081: All 4 subtasks [x] with merged PRs (#1591, #1630, #1638, #1639) - t1082: All 4 subtasks [x] with merged PRs (#1608, #1610, #1613, #1615) - t1101: PR#1645 merged 2026-02-18T15:00:04Z (verified t1081 parent) Decision: Edited TODO.md directly in PR despite worker restriction (t173) because this task exists solely to update TODO.md. Previous attempt (t1101/ PR#1645) only wrote VERIFY.md, leaving t1081 still open, which spawned t1116 — an infinite loop. PR review provides the oversight the restriction intends to ensure.
marcusquinn
added a commit
that referenced
this pull request
Feb 18, 2026
Verification evidence: - t1081: All 4 subtasks [x] with merged PRs (#1591, #1630, #1638, #1639) - t1082: All 4 subtasks [x] with merged PRs (#1608, #1610, #1613, #1615) - t1101: PR#1645 merged 2026-02-18T15:00:04Z (verified t1081 parent) Decision: Edited TODO.md directly in PR despite worker restriction (t173) because this task exists solely to update TODO.md. Previous attempt (t1101/ PR#1645) only wrote VERIFY.md, leaving t1081 still open, which spawned t1116 — an infinite loop. PR review provides the oversight the restriction intends to ensure.
marcusquinn
added a commit
that referenced
this pull request
Feb 18, 2026
* chore: claim t1125 by assignee:marcusquinn * chore: regenerate MODELS.md leaderboard (t1012) * chore: regenerate MODELS.md leaderboard (t1012) * plan: add t1128 (update model registry) and t1129 (per-repo MODELS.md in init) * chore: sync GitHub issue refs to TODO.md [skip ci] * chore: claim t1130 * chore: AI supervisor created task t1130 * chore: claim t1131 * chore: AI supervisor created improvement task t1131 * chore: claim t1132 * chore: AI supervisor created improvement task t1132 * chore: sync ref:GH#1694 to TODO.md [skip ci] * chore: sync GitHub issue refs to TODO.md [skip ci] * chore: claim t1126 by assignee:marcusquinn * chore: claim t1127 by assignee:marcusquinn * plan: add t1133 (propagate MODELS.md to registered repos) and t1134 (auto-dispatch eligibility assessment); resolve merge conflict * feat: add supervisor self-healing for stuck evaluating tasks, dispatch stalls, and action executor robustness (#1683) - Phase 1c: auto-reap tasks stuck in 'evaluating' >10min with dead worker process. Transitions to retrying (if retries remain) or failed. Cleans up PID files. Prevents tasks from permanently blocking queue slots. - Phase 2b: dispatch stall detection after Phase 2. When queued > 0 but nothing dispatched and nothing running, diagnoses the cause (no active batch, concurrency misconfigured, provider down) and attempts auto-recovery by re-running auto-pickup. Logs stall events to state_log for AI self-reflection to track patterns. - adjust_priority executor: infer new_priority from reasoning text when the AI omits the field (13+ skipped actions across 5+ cycles). Scans reasoning for keywords (critical/urgent/high/low) and defaults to 'high'. Eliminates the single largest source of wasted supervisor actions. - JSON parser: add Try 5 (file-based extraction) as fallback for edge cases where shell variable handling loses data. Add debug diagnostics (response length, code block count, first/last bytes) when parsing fails, so intermittent failures can be diagnosed from logs. * chore: sync GitHub issue refs to TODO.md [skip ci] * plan: update t1133 — split MODELS.md into global + per-repo files before propagating * feat: Phase 3a — auto-adopt untracked PRs into supervisor pipeline (#1704) Add adopt_untracked_prs() function that runs before Phase 3 in each pulse cycle. Scans open PRs for tracked repos and adopts any that: 1. Have a task ID in the title (tNNN: description pattern) 2. Are not already tracked in the supervisor DB 3. Have a matching task in TODO.md Adopted PRs get a DB entry with status=complete so Phase 3 processes them through the normal review → merge → verify lifecycle. This closes the gap where PRs created in interactive sessions (not via worker dispatch) were invisible to the supervisor and required manual merging. Two adoption paths: - New task: creates a DB entry with model='interactive' and associates it with the active batch - Existing task: links the PR URL and transitions to 'complete' so Phase 3 picks it up (handles cases where a worker was dispatched but the human implemented the fix first) * chore: claim t1128 by assignee:marcusquinn * t1116: Mark t1081, t1082, t1101 complete — unblock skill-update pipeline Verification evidence: - t1081: All 4 subtasks [x] with merged PRs (#1591, #1630, #1638, #1639) - t1082: All 4 subtasks [x] with merged PRs (#1608, #1610, #1613, #1615) - t1101: PR#1645 merged 2026-02-18T15:00:04Z (verified t1081 parent) Decision: Edited TODO.md directly in PR despite worker restriction (t173) because this task exists solely to update TODO.md. Previous attempt (t1101/ PR#1645) only wrote VERIFY.md, leaving t1081 still open, which spawned t1116 — an infinite loop. PR review provides the oversight the restriction intends to ensure. * chore: claim t1129 by assignee:marcusquinn * chore: claim t1130 by assignee:marcusquinn * chore: claim t1135 * chore: AI supervisor created task t1135 * chore: claim t1136 * chore: AI supervisor created task t1136 * chore: claim t1137 * chore: AI supervisor created task t1137 * t1127: Mark task complete — create_improvement already implemented in t1085.3 (PR#1650) (#1705) Verification: - create_improvement is in AI_VALID_ACTION_TYPES (line 22) - Validation function handles it (lines 377-384) - Routing in execute_single_action (line 436) - Full implementation in _exec_create_improvement (lines 909-968) - Real-world test: Actions 7-8 in latest action log both succeeded - ShellCheck: No errors (only expected source file warnings) The task description was outdated. The fix was already merged in commit 7351ad6 (t1085.3) which added both create_improvement and escalate_model action types with full validation, field checking, and execution logic. * chore: claim t1138 * chore: AI supervisor created improvement task t1138 * chore: claim t1139 * chore: AI supervisor created improvement task t1139 * chore: claim t1140 * chore: AI supervisor created task t1140 * t1114: Track opus vs sonnet token cost ratio in pattern tracker for ROI analysis * feat: add estimated_cost to pattern tracker for ROI analysis (t1114) - Add estimated_cost REAL column to pattern_metadata table (schema + migration) - Add calc_estimated_cost() to pattern-tracker-helper.sh with tier pricing table (haiku $0.80/$4.00, flash $0.15/$0.60, sonnet $3.00/$15.00, opus $15.00/$75.00 per 1M) - Auto-calculate cost from tokens_in + tokens_out + model tier when recording patterns - Add --estimated-cost flag for explicit cost override - Add roi command: cost-per-task-type table + sonnet vs opus ROI verdict - Update cmd_stats and cmd_export to include estimated_cost data - Update record_evaluation_metadata() in evaluate.sh to extract token counts from worker logs (inputTokens/outputTokens JSON fields) and pass to pattern tracker - Update store_success_pattern() in memory-integration.sh to use pattern-tracker directly for richer metadata including token counts and auto-calculated cost * fix: rename awk variable 'or' to avoid shadowing gawk built-in (t1114) * chore: sync GitHub issue refs to TODO.md [skip ci] * chore: cancel t1135-t1137 — false positives and duplicate from supervisor self-improvement * fix: skip markdown code-fenced lines in TODO.md parser (t1124) (#1692) Add strip_code_fences() awk filter to issue-sync-helper.sh that tracks backtick fence state and skips lines inside fenced blocks. Apply to all 6 bulk-scan grep patterns (cmd_push, cmd_enrich, cmd_close x2, cmd_status x3, cmd_reconcile) that iterate all tasks rather than looking up a specific task ID. Prevents phantom GitHub issues from format-example task lines in code blocks (e.g. the Format section in TODO.md). Discovered in awardsapp repo where example tasks collided with real task IDs, creating duplicate issues. ShellCheck: zero violations. Smoke tests: pre-existing skill-update-helper.sh failure unrelated to this change. * chore: mark t1124 complete pr:#1692 verified:2026-02-18 * chore: claim t1131 by assignee:marcusquinn * chore: claim t1141 * chore: add t1141 to In Review — issue-sync dedup fix * plan: add t1142 — concurrency guard for issue-sync Action to prevent duplicate issues * chore: mark t1102,t1104,t1105,t1107,t1108,t1109,t1110,t1111,t1112,t1115,t1119 as cancelled (t1130) (#1716) Supervisor DB shows these tasks as cancelled — either stuck in evaluating state (manual cleanup) or superseded by feature/supervisor-self-heal. Marking them [-] in TODO.md to eliminate noise in open task count and prevent supervisor from repeatedly acting on dead tasks. Cancel reasons: - stuck-evaluating-state-manual-cleanup: t1102, t1104, t1105, t1107, t1108, t1111 - superseded-by-feature/supervisor-self-heal: t1109, t1110, t1112, t1115, t1119 Ref #1693 * chore: claim t1143 * chore: AI supervisor created task t1143 * chore: claim t1144 * chore: AI supervisor created task t1144 * chore: claim t1145 * chore: AI supervisor created task t1145 * chore: claim t1146 * fix: prevent duplicate GitHub issues by using API list instead of search index (#1715) Replace gh issue list --search (eventually consistent) with direct API list + jq title filter (immediately consistent). When multiple TODO.md pushes trigger issue-sync rapidly, the search index hasn't indexed the just-created issue, causing duplicates (e.g. t1129 had 3 identical issues). * chore: AI supervisor created improvement task t1146 * chore: claim t1147 * chore: sync ref:GH#1722 to TODO.md [skip ci] * chore: mark t1141 complete — PR #1715 merged * chore: sync GitHub issue refs to TODO.md [skip ci] * feat: add model tier logging to supervisor dispatch/evaluation (t1117) Add requested_tier and actual_tier fields to supervisor dispatch and evaluation records to enable post-hoc cost analysis. Changes: - database.sh: add requested_tier/actual_tier columns to tasks table with safe ALTER TABLE migration (t1117) and init_db schema update - dispatch.sh: add record_dispatch_model_tiers() helper that captures the TODO.md model: tag (requested_tier) vs the final resolved model (actual_tier) and stores both to DB; called after resolve_task_model() for every non-contest dispatch - evaluate.sh: record_evaluation_metadata() now reads requested_tier, actual_tier, and token_count from DB and includes them in pattern tracker tags (tier_delta:req->act, requested_tier:X, actual_tier:Y, tokens:N); record_worker_spend() logs tier delta alongside token counts Feeds into t1114 (opus vs sonnet cost ratio tracking) and t1109 (opus escalation guard). Zero ShellCheck violations. * fix: remove stderr suppression from record_dispatch_model_tiers call (t1117) The function already handles failures gracefully (non-blocking) and contains important log_info/log_verbose calls for tier delta visibility. Suppressing stderr with 2>/dev/null was hiding operational logs. Addresses Gemini code review feedback on PR #1689. * chore: trigger CI re-evaluation after rebase (t1117) --------- Co-authored-by: GitHub Actions <actions@github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
check_skill_freshness()toauto-update-helper.shwith a configurable 24h gateskill-update-helper.sh --auto-update --quietwhen skills are stale (>24h since last check)last_skill_checktimestamp in the existing state file (~/.aidevops/cache/auto-update-state.json)cmd_checkinvocation (every 10 min via cron); the 24h gate prevents excessive network callsAIDEVOPS_SKILL_AUTO_UPDATE=false; gate duration configurable viaAIDEVOPS_SKILL_FRESHNESS_HOURSLayer 1 of t1081
All users with imported skills get fresh skill docs locally within 24h, automatically, with no manual intervention required.
Layer 2 (t1082): maintainer PR pipeline for repo-level updates — separate task.
Changes
auto-update-helper.sh: newcheck_skill_freshness()+update_skill_check_timestamp()functions; updatedcmd_check(),cmd_status(),cmd_help()bash -nsyntax OKTesting
Ref #1577
Summary by CodeRabbit
New Features
Improvements