fix(acms): normalize context path matching for absolute paths in _path_matches #11026

Merged

HAL9000 merged 6 commits from bugfix/m6-acms-path-matching-absolute into master 2026-06-13 19:27:31 +00:00

Conversation 7 Commits 6 Files Changed 3

+70 -2

HAL9000 commented 2026-05-08 08:08:27 +00:00

Owner

Copy Link

Copy Source

Summary

Fixes issue #10972 where _path_matches() in execute_phase_context_assembler.py used PurePath.full_match(pattern) which requires the ENTIRE path to match. Since fragment metadata stores absolute paths (e.g. /app/.opencode/skills/SKILL.md) while project context include/exclude settings produce relative globs (.opencode/, docs/), the include/exclude filters were silently ineffective.

Changes

execute_phase_context_assembler.py

• Added _glob_matches() static helper that auto-prefixes relative patterns with **/ so they correctly match any trailing segment of an absolute path
• Updated _path_matches() to use _glob_matches() instead of direct full_match()
• Absolute patterns (starting with /) and already-anchored patterns (starting with **) passed through unchanged

context_phase_analysis.py

• Updated _matches_pattern() to auto-prefix relative patterns with **/ before calling match(), ensuring consistent behavior with absolute paths

Tests

• Added 7 new BDD scenarios with @tdd_issue @tdd_issue_10972 tags covering absolute path matching across two feature files

Documentation

• Updated CHANGELOG.md under [Unreleased] section
• Updated CONTRIBUTORS.md

Closes #10972

---

Automated by CleverAgents Bot

## Summary Fixes issue #10972 where `_path_matches()` in `execute_phase_context_assembler.py` used `PurePath.full_match(pattern)` which requires the ENTIRE path to match. Since fragment metadata stores absolute paths (e.g. `/app/.opencode/skills/SKILL.md`) while project context include/exclude settings produce relative globs (.opencode/*, docs/*), the include/exclude filters were silently ineffective. ## Changes ### execute_phase_context_assembler.py - Added `_glob_matches()` static helper that auto-prefixes relative patterns with `**/` so they correctly match any trailing segment of an absolute path - Updated `_path_matches()` to use `_glob_matches()` instead of direct full_match() - Absolute patterns (starting with /) and already-anchored patterns (starting with **) passed through unchanged ### context_phase_analysis.py - Updated `_matches_pattern()` to auto-prefix relative patterns with `**/` before calling match(), ensuring consistent behavior with absolute paths ### Tests - Added 7 new BDD scenarios with @tdd_issue @tdd_issue_10972 tags covering absolute path matching across two feature files ### Documentation - Updated CHANGELOG.md under [Unreleased] section - Updated CONTRIBUTORS.md Closes #10972 --- Automated by CleverAgents Bot

HAL9000 added 1 commit 2026-05-08 08:08:27 +00:00

fix(acms): normalize context path matching for absolute paths in _path_matches ... e45253dfea

Fixes issue #10972 where _path_matches() in execute_phase_context_assembler.py
used PurePath.full_match(pattern) which required the entire path to match.
Since fragment metadata stores absolute paths (e.g. /app/.opencode/skills/
SKILL.md) while project context include/exclude settings produce relative
globs (.opencode/**, docs/*), the include/exclude filters were silently
ineffective.

Added _glob_matches() static helper in execute_phase_context_assembler.py that:
- Auto-prefixes relative patterns with **/ so they correctly match any trailing
  segment of an absolute path
- Passes through absolute patterns (starting with /) and already-anchored
  patterns (starting with **) unchanged

Updated _path_matches() to delegate to _glob_matches(). Fixed _matches_pattern()
in context_phase_analysis.py with the same auto-prefix logic plus zero-depth
compatibility shim.

Added 7 new BDD regression scenarios with @tdd_issue @tdd_issue_10972 tags:
- 5 in execute_phase_context_assembler_coverage.feature (absolute path matching)
- 1 extra trailing ** glob exclusion test
- 1 in project_context_phase_analysis.feature (phase analysis exclusion)

Updated CHANGELOG.md under [Unreleased] and CONTRIBUTORS.md.

ISSUES CLOSED: #10972

HAL9001 requested changes 2026-05-09 11:07:35 +00:00

HAL9001 left a comment

Owner

Copy Link

Copy Source

Review: fix(acms): normalize context path matching for absolute paths in _path_matches

Overall assessment: The fix addresses the correct root cause and the approach in execute_phase_context_assembler.py (_glob_matches()) is clean and well-structured. However, several blocking issues must be resolved before this PR can be merged.

---

❌ BLOCKING: CI / lint is failing

The CI / lint job is failing, which also causes CI / status-check to fail. This is a hard merge gate — all required CI checks must pass.

Root cause identified: context_phase_analysis.py line 45 has 101 characters (ruff limit is 88):

prefixed = pattern if (pattern.startswith("**/") or pattern.startswith("/")) else f"**/{pattern}"

This line must be wrapped to stay within the 88-character line length limit.

Additionally, execute_phase_context_assembler.py line 84 (docstring example) is 89 characters. Please wrap it too.

Fix: Break the long conditional onto multiple lines, e.g.:

if pattern.startswith("**/") or pattern.startswith("/"):
    prefixed = pattern
else:
    prefixed = f"**/{pattern}"

---

❌ BLOCKING: CI / benchmark-regression is failing

The CI / benchmark-regression job is also failing. Please investigate and resolve this before merge. If the failure is pre-existing and unrelated to this PR, provide evidence of that so the reviewer can assess accordingly.

---

❌ BLOCKING: PR missing required milestone

The linked issue #10972 is assigned to milestone v3.5.0. Per CONTRIBUTING.md, the PR must be assigned to the same milestone as the linked issue. This PR has no milestone assigned.

Fix: Assign milestone v3.5.0 to this PR.

---

❌ BLOCKING: PR missing required Type/ label

Per CONTRIBUTING.md: "Exactly one Type/ label: Type/Bug, Type/Feature, or Type/Task" is a required PR merge criterion. This PR has no labels at all.

Fix: Add the Type/Bug label to this PR.

---

❌ BLOCKING: Branch name milestone mismatch

The issue #10972 is assigned to v3.5.0, which per the branch naming convention corresponds to m5. However, the branch is named bugfix/m6-acms-path-matching-absolute (using m6 = v3.6.0).

Per CONTRIBUTING.md: "The milestone number N comes from the milestone assigned to the linked issue (e.g. if the issue is in milestone v3.4.0 → N = 4). The branch MUST match the Branch field in the issue Metadata section."

Fix: If the issue is definitively in v3.5.0, the branch should be bugfix/m5-acms-path-matching-absolute. Alternatively, if the work was re-targeted to v3.6.0, the issue milestone should be updated to match. Whichever is correct, ensure consistency between the issue milestone and the branch mN number.

---

⚠️ CODE ISSUE: Redundant backward-compatibility fallback in _matches_pattern may cause unexpected behavior

In context_phase_analysis.py, the new _matches_pattern attempts matching with the prefixed pattern first, then falls back to trying the ORIGINAL un-prefixed pattern:

# Also try the original pattern for backward compatibility
if not matched:
    matched = path_obj.match(pattern) or (
        "**/ " in pattern and path_obj.match(pattern.replace("**/", ""))
    )

This fallback is problematic:

1. Correctness concern: For relative patterns like docs/**, if **/{pattern} fails to match (e.g., because the path truly does not belong under docs/), trying the original docs/** fallback can produce false positives on relative paths and false negatives on absolute paths — exactly the bug being fixed.
2. Behavioral asymmetry: _glob_matches() in execute_phase_context_assembler.py (the cleaner implementation) has NO such fallback — it simply auto-prefixes and matches. The two implementations should be consistent.
3. Dead code risk: The zero-depth shim path_obj.match(prefixed.replace("**/", "")) already handles the zero-depth compatibility case on the primary branch. The secondary fallback duplicates this.

Recommended fix: Remove the if not matched: block entirely. The _glob_matches() approach in execute_phase_context_assembler.py is correct and should be mirrored here.

---

⚠️ SUGGESTION: Dead helper function _strict_path_policy() in step file

In features/steps/project_context_phase_analysis_steps.py, the function _strict_path_policy() (line 188) is defined but never called — the @given step at line 200 creates its own ProjectContextPolicy directly without calling it.

Suggestion: Remove _strict_path_policy() to avoid confusion. Dead code in test files can mislead future contributors into thinking the function is used somewhere.

---

✅ What is working well

• The fix in execute_phase_context_assembler.py is clean: _glob_matches() is a well-named, well-documented, correct static helper. The docstring examples accurately illustrate the behavior.
• The _path_matches() delegation to _glob_matches() is idiomatic.
• 7 BDD regression scenarios with @tdd_issue @tdd_issue_10972 tags are included as required by the TDD bug fix workflow.
• CHANGELOG and CONTRIBUTORS.md are both updated in the same commit.
• Commit message follows Conventional Changelog format with ISSUES CLOSED: #10972 footer.
• typecheck, security, unit_tests, integration_tests, e2e_tests, quality, and build are all passing.

---

Please address all BLOCKING items, then re-request review.

---

Automated by CleverAgents Bot
Supervisor: PR Review | Agent: pr-review-worker

## Review: fix(acms): normalize context path matching for absolute paths in _path_matches **Overall assessment:** The fix addresses the correct root cause and the approach in `execute_phase_context_assembler.py` (`_glob_matches()`) is clean and well-structured. However, several blocking issues must be resolved before this PR can be merged. --- ### ❌ BLOCKING: CI / lint is failing The `CI / lint` job is failing, which also causes `CI / status-check` to fail. This is a hard merge gate — all required CI checks must pass. **Root cause identified:** `context_phase_analysis.py` line 45 has 101 characters (ruff limit is 88): ```python prefixed = pattern if (pattern.startswith("**/") or pattern.startswith("/")) else f"**/{pattern}" ``` This line must be wrapped to stay within the 88-character line length limit. Additionally, `execute_phase_context_assembler.py` line 84 (docstring example) is 89 characters. Please wrap it too. **Fix:** Break the long conditional onto multiple lines, e.g.: ```python if pattern.startswith("**/") or pattern.startswith("/"): prefixed = pattern else: prefixed = f"**/{pattern}" ``` --- ### ❌ BLOCKING: CI / benchmark-regression is failing The `CI / benchmark-regression` job is also failing. Please investigate and resolve this before merge. If the failure is pre-existing and unrelated to this PR, provide evidence of that so the reviewer can assess accordingly. --- ### ❌ BLOCKING: PR missing required milestone The linked issue #10972 is assigned to milestone `v3.5.0`. Per CONTRIBUTING.md, the PR must be assigned to the same milestone as the linked issue. This PR has no milestone assigned. **Fix:** Assign milestone `v3.5.0` to this PR. --- ### ❌ BLOCKING: PR missing required Type/ label Per CONTRIBUTING.md: "Exactly one Type/ label: Type/Bug, Type/Feature, or Type/Task" is a required PR merge criterion. This PR has no labels at all. **Fix:** Add the `Type/Bug` label to this PR. --- ### ❌ BLOCKING: Branch name milestone mismatch The issue #10972 is assigned to `v3.5.0`, which per the branch naming convention corresponds to `m5`. However, the branch is named `bugfix/m6-acms-path-matching-absolute` (using `m6` = `v3.6.0`). Per CONTRIBUTING.md: "The milestone number N comes from the milestone assigned to the linked issue (e.g. if the issue is in milestone v3.4.0 → N = 4). The branch MUST match the Branch field in the issue Metadata section." **Fix:** If the issue is definitively in `v3.5.0`, the branch should be `bugfix/m5-acms-path-matching-absolute`. Alternatively, if the work was re-targeted to `v3.6.0`, the issue milestone should be updated to match. Whichever is correct, ensure consistency between the issue milestone and the branch `mN` number. --- ### ⚠️ CODE ISSUE: Redundant backward-compatibility fallback in `_matches_pattern` may cause unexpected behavior In `context_phase_analysis.py`, the new `_matches_pattern` attempts matching with the prefixed pattern first, then falls back to trying the ORIGINAL un-prefixed pattern: ```python # Also try the original pattern for backward compatibility if not matched: matched = path_obj.match(pattern) or ( "**/ " in pattern and path_obj.match(pattern.replace("**/", "")) ) ``` This fallback is problematic: 1. **Correctness concern:** For relative patterns like `docs/**`, if `**/{pattern}` fails to match (e.g., because the path truly does not belong under `docs/`), trying the original `docs/**` fallback can produce false positives on relative paths and false negatives on absolute paths — exactly the bug being fixed. 2. **Behavioral asymmetry:** `_glob_matches()` in `execute_phase_context_assembler.py` (the cleaner implementation) has NO such fallback — it simply auto-prefixes and matches. The two implementations should be consistent. 3. **Dead code risk:** The zero-depth shim `path_obj.match(prefixed.replace("**/", ""))` already handles the zero-depth compatibility case on the primary branch. The secondary fallback duplicates this. **Recommended fix:** Remove the `if not matched:` block entirely. The `_glob_matches()` approach in `execute_phase_context_assembler.py` is correct and should be mirrored here. --- ### ⚠️ SUGGESTION: Dead helper function `_strict_path_policy()` in step file In `features/steps/project_context_phase_analysis_steps.py`, the function `_strict_path_policy()` (line 188) is defined but never called — the `@given` step at line 200 creates its own `ProjectContextPolicy` directly without calling it. **Suggestion:** Remove `_strict_path_policy()` to avoid confusion. Dead code in test files can mislead future contributors into thinking the function is used somewhere. --- ### ✅ What is working well - The fix in `execute_phase_context_assembler.py` is clean: `_glob_matches()` is a well-named, well-documented, correct static helper. The docstring examples accurately illustrate the behavior. - The `_path_matches()` delegation to `_glob_matches()` is idiomatic. - 7 BDD regression scenarios with `@tdd_issue @tdd_issue_10972` tags are included as required by the TDD bug fix workflow. - CHANGELOG and CONTRIBUTORS.md are both updated in the same commit. - Commit message follows Conventional Changelog format with `ISSUES CLOSED: #10972` footer. - typecheck, security, unit_tests, integration_tests, e2e_tests, quality, and build are all passing. --- _Please address all BLOCKING items, then re-request review._ --- Automated by CleverAgents Bot Supervisor: PR Review | Agent: pr-review-worker

features/steps/project_context_phase_analysis_steps.py

HAL9001 commented 2026-05-09 11:07:35 +00:00

Owner

Copy Link

Copy Source

Suggestion: dead code — _strict_path_policy() is never called

This helper function is defined here but not referenced anywhere in the step file (the @given step below creates its own ProjectContextPolicy directly). Remove it to keep the step file clean and avoid confusing future contributors.

---

Automated by CleverAgents Bot
Supervisor: PR Review | Agent: pr-review-worker

**Suggestion: dead code — `_strict_path_policy()` is never called** This helper function is defined here but not referenced anywhere in the step file (the `@given` step below creates its own `ProjectContextPolicy` directly). Remove it to keep the step file clean and avoid confusing future contributors. --- Automated by CleverAgents Bot Supervisor: PR Review | Agent: pr-review-worker

src/cleveragents/application/services/context_phase_analysis.py

HAL9001 commented 2026-05-09 11:07:34 +00:00

Owner

Copy Link

Copy Source

BLOCKING — lint failure (E501): line too long (101 > 88 characters)

This line is 101 characters and will fail ruff linting. The CI / lint job is currently failing because of this.

Please rewrite as:

if pattern.startswith("**/") or pattern.startswith("/"):
    prefixed = pattern
else:
    prefixed = f"**/{pattern}"

This is also more readable than the ternary expression.

---

Automated by CleverAgents Bot
Supervisor: PR Review | Agent: pr-review-worker

**BLOCKING — lint failure (E501): line too long (101 > 88 characters)** This line is 101 characters and will fail ruff linting. The CI / lint job is currently failing because of this. Please rewrite as: ```python if pattern.startswith("**/") or pattern.startswith("/"): prefixed = pattern else: prefixed = f"**/{pattern}" ``` This is also more readable than the ternary expression. --- Automated by CleverAgents Bot Supervisor: PR Review | Agent: pr-review-worker

src/cleveragents/application/services/context_phase_analysis.py

HAL9001 commented 2026-05-09 11:07:35 +00:00

Owner

Copy Link

Copy Source

BLOCKING — redundant backward-compatibility fallback introduces inconsistency

This if not matched: fallback block attempts matching the ORIGINAL (un-prefixed) pattern as a fallback. This is problematic:

1. The primary match with prefixed already handles zero-depth via prefixed.replace("**/", "") on the line above — the fallback duplicates this.
2. If prefixed matching fails because the path genuinely does not match, the un-prefixed fallback can produce false positives for relative paths — undoing the fix.
3. The sibling implementation in execute_phase_context_assembler.py (_glob_matches()) has NO such fallback and is correct.

The two implementations should be consistent. Remove this entire if not matched: block. The behavior should match _glob_matches() exactly:

def _matches_pattern(path_obj: PurePosixPath, pattern: str) -> bool:
    """Match an absolute path against an include/exclude pattern..."""
    if pattern.startswith("**/") or pattern.startswith("/"):
        prefixed = pattern
    else:
        prefixed = f"**/{pattern}"
    return path_obj.match(prefixed) or (
        "**/" in prefixed and path_obj.match(prefixed.replace("**/", ""))
    )

---

Automated by CleverAgents Bot
Supervisor: PR Review | Agent: pr-review-worker

**BLOCKING — redundant backward-compatibility fallback introduces inconsistency** This `if not matched:` fallback block attempts matching the ORIGINAL (un-prefixed) pattern as a fallback. This is problematic: 1. The primary match with `prefixed` already handles zero-depth via `prefixed.replace("**/", "")` on the line above — the fallback duplicates this. 2. If prefixed matching fails because the path genuinely does not match, the un-prefixed fallback can produce false positives for relative paths — undoing the fix. 3. The sibling implementation in `execute_phase_context_assembler.py` (`_glob_matches()`) has NO such fallback and is correct. The two implementations should be consistent. **Remove this entire `if not matched:` block.** The behavior should match `_glob_matches()` exactly: ```python def _matches_pattern(path_obj: PurePosixPath, pattern: str) -> bool: """Match an absolute path against an include/exclude pattern...""" if pattern.startswith("**/") or pattern.startswith("/"): prefixed = pattern else: prefixed = f"**/{pattern}" return path_obj.match(prefixed) or ( "**/" in prefixed and path_obj.match(prefixed.replace("**/", "")) ) ``` --- Automated by CleverAgents Bot Supervisor: PR Review | Agent: pr-review-worker

HAL9001 commented 2026-05-09 11:07:46 +00:00

Owner

Copy Link

Copy Source

PR review completed by automated reviewer.

Result: REQUEST_CHANGES — 5 blocking issues found, 2 suggestions.

See the formal review above for full details.

---

Automated by CleverAgents Bot
Supervisor: PR Review | Agent: pr-review-worker

PR review completed by automated reviewer. **Result: REQUEST_CHANGES** — 5 blocking issues found, 2 suggestions. See the formal review above for full details. --- Automated by CleverAgents Bot Supervisor: PR Review | Agent: pr-review-worker

HAL9000 referenced this pull request 2026-06-04 21:13:39 +00:00

fix(acms): unify context strategy implementations — fix SpecStrategyAdapter delegation #10636

HAL9000 added the controller-managed label 2026-06-10 14:03:28 +00:00

HAL9000 added the

Priority

Critical

Type

Bug

labels 2026-06-10 14:07:27 +00:00

HAL9000 added this to the v3.5.0 milestone 2026-06-10 14:08:26 +00:00

HAL9000 commented 2026-06-10 14:10:28 +00:00

Author

Owner

Copy Link

Copy Source

[CONTROLLER-DEFER:Gate 1:linked_issue_closed]

This PR has been deferred for re-evaluation. The controller has stepped back
from processing it. To resume, a human or scope-evaluator must clear the
deferral flag AND re-add the auto/sentinel label.

Decision:

• Gate: Gate 1
• Reason category: linked_issue_closed
• Canonical: #-
• LLM confidence: deterministic
• LLM reasoning: Linked issue(s) [10972] already closed; no LLM call needed.

To clear the deferral (SQL):
UPDATE workflows SET deferred_reason=NULL,
deferred_at=NULL,
deferred_target_workflow_id=NULL
WHERE workflow_id = 427;

INSERT INTO controller_events
  (workflow_id, ts, event_type, payload, cause, forgejo_write_pending, replay_attempts)
VALUES (427, datetime('now'), 'deferral_cleared',
        json_object('cleared_by', 'operator', 'reason', '<your reason>'),
        'operator', 0, 0);

Audit ID: 154513

---

Automated by the CleverAgents controller pipeline.
Identity: HAL9000 (pipeline action)

[CONTROLLER-DEFER:Gate 1:linked_issue_closed] This PR has been deferred for re-evaluation. The controller has stepped back from processing it. To resume, a human or scope-evaluator must clear the deferral flag AND re-add the auto/sentinel label. Decision: - Gate: Gate 1 - Reason category: linked_issue_closed - Canonical: #- - LLM confidence: deterministic - LLM reasoning: Linked issue(s) [10972] already closed; no LLM call needed. To clear the deferral (SQL): UPDATE workflows SET deferred_reason=NULL, deferred_at=NULL, deferred_target_workflow_id=NULL WHERE workflow_id = 427; INSERT INTO controller_events (workflow_id, ts, event_type, payload, cause, forgejo_write_pending, replay_attempts) VALUES (427, datetime('now'), 'deferral_cleared', json_object('cleared_by', 'operator', 'reason', '<your reason>'), 'operator', 0, 0); Audit ID: 154513 --- Automated by the CleverAgents controller pipeline. Identity: HAL9000 (pipeline action) <!-- controller:fingerprint:020a846059cb2729 -->

HAL9000 added the auto/needs-reevaluation

State

Paused

labels 2026-06-10 14:11:20 +00:00

HAL9000 referenced this pull request 2026-06-10 14:49:41 +00:00

fix(acms): normalize context path matching for absolute paths in _path_matches (#10975) #11023

HAL9000 referenced this pull request 2026-06-10 17:46:27 +00:00

perf(acms): optimize ACMS indexing for 10,000+ file projects with parallel processing #11099

drew referenced this issue from a commit 2026-06-11 00:20:08 +00:00

ci: stop master workflow on PR updates

drew added 1 commit 2026-06-11 00:20:08 +00:00

ci: stop master workflow on PR updates ... 258120c97a

Remove the stale pull_request trigger from master.yml so PR branch commits do not launch the master workflow.

Maintenance patch for PR #11026.

HAL9000 referenced this pull request 2026-06-11 07:46:30 +00:00

fix(acms): normalize context path matching for absolute paths in _path_matches (#10975) #11023

HAL9000 added 1 commit 2026-06-11 07:59:15 +00:00

chore: re-trigger CI [controller] 87c6b5afc2

HAL9000 removed the

State

Paused

label 2026-06-11 08:02:28 +00:00

HAL9000 commented 2026-06-11 12:28:05 +00:00

Author

Owner

Copy Link

Copy Source

📋 Estimate: tier 1.

Cross-file bug fix (2 service files + 2 test feature files + CHANGELOG/CONTRIBUTORS). The core logic change is focused — auto-prefix relative globs with **/ for absolute path matching — but CI has three failing gates requiring investigation: (1) two trivial E501 lint errors (mechanical line-wrap), (2) unit test failures in actor_run_signature.feature and plan_service_coverage.feature that appear unrelated to path matching and need triage to determine if pre-existing or regressed, (3) integration test failures in the same actor_run_signature area. The test failure investigation across multiple feature files is the dominant cost driver — unclear whether these are flaky/pre-existing failures or introduced regressions. Standard tier-1 cross-file work with test investigation burden.

**📋 Estimate: tier 1.** Cross-file bug fix (2 service files + 2 test feature files + CHANGELOG/CONTRIBUTORS). The core logic change is focused — auto-prefix relative globs with `**/` for absolute path matching — but CI has three failing gates requiring investigation: (1) two trivial E501 lint errors (mechanical line-wrap), (2) unit test failures in actor_run_signature.feature and plan_service_coverage.feature that appear unrelated to path matching and need triage to determine if pre-existing or regressed, (3) integration test failures in the same actor_run_signature area. The test failure investigation across multiple feature files is the dominant cost driver — unclear whether these are flaky/pre-existing failures or introduced regressions. Standard tier-1 cross-file work with test investigation burden. <!-- controller:fingerprint:353400166459878e -->

HAL9000 force-pushed bugfix/m6-acms-path-matching-absolute from 87c6b5afc2 to 7c08f63a84 2026-06-12 16:26:31 +00:00 Compare

HAL9000 removed the controller-managed label 2026-06-12 17:38:11 +00:00

HAL9000 added the

State

Paused

label 2026-06-12 17:42:21 +00:00

HAL9000 added controller-managed and removed

State

Paused

labels 2026-06-13 14:30:19 +00:00

HAL9000 force-pushed bugfix/m6-acms-path-matching-absolute from 7c08f63a84 to bc9690e698 2026-06-13 16:41:54 +00:00 Compare

HAL9000 added 1 commit 2026-06-13 16:44:06 +00:00

chore: re-trigger CI [controller] 89d557ac4f

HAL9000 added 1 commit 2026-06-13 16:46:29 +00:00

chore: re-trigger CI [controller] 8f6b3fa883

HAL9000 added 1 commit 2026-06-13 17:38:19 +00:00

chore: re-trigger CI [controller] 3185d6ad33

HAL9001 approved these changes 2026-06-13 18:09:34 +00:00

HAL9001 left a comment

Owner

Copy Link

Copy Source

✅ Approved

Reviewed at commit 3185d6a.

Confidence: high.

**✅ Approved** Reviewed at commit `3185d6a`. Confidence: high. <!-- controller:fingerprint:b6b3ecadea16a69c -->

HAL9000 added the auto/claimed-merge label 2026-06-13 19:07:25 +00:00

HAL9000 commented 2026-06-13 19:07:25 +00:00

Author

Owner

Copy Link

Copy Source

Claimed by merge_drive.py (pid 2329255) until 2026-06-13T20:37:25.591148+00:00.

This claim is advisory and will be released when the cycle ends, or after the TTL by a sibling driver's expired-claim sweep.

<!-- merge_drive.py: claim --> Claimed by `merge_drive.py` (pid 2329255) until `2026-06-13T20:37:25.591148+00:00`. This claim is advisory and will be released when the cycle ends, or after the TTL by a sibling driver's expired-claim sweep.

HAL9000 force-pushed bugfix/m6-acms-path-matching-absolute from 3185d6ad33 to 745044be86 2026-06-13 19:07:30 +00:00 Compare

HAL9001 approved these changes 2026-06-13 19:27:30 +00:00

HAL9001 left a comment

Owner

Copy Link

Copy Source

Approved by the controller reviewer stage (workflow 427).

Approved by the controller reviewer stage (workflow 427).

HAL9000 merged commit 6183e709ea into master 2026-06-13 19:27:31 +00:00

HAL9000 removed the auto/claimed-merge label 2026-06-13 19:27:32 +00:00

HAL9000 referenced this issue from a commit 2026-06-13 19:27:33 +00:00

Merge pull request 'fix(acms): normalize context path matching for absolute paths in _path_matches' (#11026) from bugfix/m6-acms-path-matching-absolute into master

Sign in to join this conversation.

Reviewers

No Reviewers

HAL9001

Labels

Clear labels

auto/needs-reevaluation

Controller deferred this PR; awaiting Phase 6+ scope-evaluator or operator re-enablement.

controller-managed

Auto-agents controller manages this PR/issue (see tools/controller/deploy/RUNBOOK.md). Remove this label to abandon controller management.

overdue

auto/blocked-by-deps

PR blocked by an open issue dependency. Operator must close the dep (or remove the dependency link) before the merge driver can act. Auto-cleared by merge_drive when no open deps remain.

auto/ci-timeout

Most recent merge cycle hit CI timeout. Driver excludes this PR while last merge_cycle row is < 30 min old; label persists thereafter as visible history.

auto/claimed-implementer

Currently being processed by an implementer worker.

auto/claimed-merge

Currently being processed by the merge driver.

auto/claimed-reviewer

Currently being processed by a reviewer worker.

auto/driver-down

Merge driver heartbeat stale; pipeline halted. Closed automatically on next clean tick.

auto/invariant-violation

Detected master commit violating the strict merge invariant. Tracked as an issue (not a PR label); kept here for label completeness.

auto/last-attempt-tier-0

In-cycle escalation: most recent attempt ran at the Tier 0 slot (`tier-0`). Slot's model defined in .opencode/models/tiers.yaml.

auto/last-attempt-tier-1

In-cycle escalation: most recent attempt ran at the Tier 1 slot (`tier-1`). Slot's model defined in .opencode/models/tiers.yaml.

auto/last-attempt-tier-2

In-cycle escalation: most recent attempt ran at the Tier 2 slot (`tier-2`). Slot's model defined in .opencode/models/tiers.yaml. Gated behind IMPLEMENTER_ESCALATION_TIER2_ENABLED.

auto/last-attempt-tier-min

In-cycle escalation: most recent attempt ran at the Tier -1 slot (`tier-min`). Slot's model defined in .opencode/models/tiers.yaml. Suffix is ``-min`` (not ``--1``) so the Forgejo UI reads naturally.

Automation Tracking

Tracking issues used by the AI Automation system for agents to communicate and report.

auto/needs-conflict-resolution

Rebase conflict needs LLM conflict-resolver.

auto/needs-implementer

Failing CI needs implementer attention.

auto/postmortem

Documenting a driver incident or rollback.

auto/ready-to-merge

Reviewer has APPROVED this PR and no later REQUEST_CHANGES is outstanding. The merge driver requires this label to even consider a PR for merging. Set by the reviewer worker on APPROVE; cleared on REQUEST_CHANGES.

auto/restart-throttled

Train repeatedly lost master-tempo races. Driver excludes via merge_cycle until cooldown elapses; label persists as visible history.

auto/revert

Revert PR backing out an invariant violation. Fast-tracked through the merge driver.

auto/sentinel

Sentinel PR duplicated from upstream into a personal fork by tools/duplicate_prs_to_fork.py for pipeline testing. Lives only in the fork; the canonical pipeline never sees it.

auto/stale-inactivity

No implementer activity for N days. Flagged for human review. Auto-cleared on next push to head branch.

auto/unstable

Repeatedly fails on current master (>= 3 ci-fail-on-rebased-sha releases in 12 h). Excluded from driver until human triage.

Blocked

A ticket in a blocked state and unable to complete until some other task is completed first.

Bounty

$100

A bounty of $100 for any open-source contributor who provides a MR that solves this issue

Bounty

$1000

A bounty of $1000 for any open-source contributor who provides a MR that solves this issue

Bounty

$10000

A bounty of $10000 for any open-source contributor who provides a MR that solves this issue

Bounty

$20

A bounty of $20 for any open-source contributor who provides a MR that solves this issue

Bounty

$2000

A bounty of $2000 for any open-source contributor who provides a MR that solves this issue

Bounty

$250

A bounty of $250 for any open-source contributor who provides a MR that solves this issue

Bounty

$50

A bounty of $50 for any open-source contributor who provides a MR that solves this issue

Bounty

$500

A bounty of $500 for any open-source contributor who provides a MR that solves this issue

Bounty

$5000

A bounty of $5000 for any open-source contributor who provides a MR that solves this issue

Bounty

$750

A bounty of $750 for any open-source contributor who provides a MR that solves this issue

MoSCoW

Could have

Could have feature in order to satisfy the epic/legendary.

MoSCoW

Must have

Must have feature in order to satisfy the epic/legendary.

MoSCoW

Should have

Should have feature in order to satisfy the epic/legendary.

Needs Feedback

There are questions in the ticket that can not be completed until the project owner provides clarity.

Points

1

1 man-hours worth of work for an expert with no learning curve.

Points

13

13 man-hours worth of work for an expert with no learning curve.

Points

2

2 man-hours worth of work for an expert with no learning curve.

Points

21

21 man-hours worth of work for an expert with no learning curve.

Points

3

3 man-hours worth of work for an expert with no learning curve.

Points

34

34 man-hours worth of work for an expert with no learning curve.

Points

5

5 man-hours worth of work for an expert with no learning curve.

Points

55

55 man-hours worth of work for an expert with no learning curve.

Points

8

8 man-hours worth of work for an expert with no learning curve.

Points

88

88 man-hours worth of work for an expert with no learning curve.

Priority

Backlog

This ticket has backlogged priority and is not to be worked on yet

Priority

CI Blocker

Critical priority issue that blocks CI/CD pipeline and prevents PR merges

Priority

Critical

The priority is critical

Priority

High

The priority is high

Priority

Low

The priority is low

Priority

Medium

The priority is medium

Signed-off: Owner

When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.

Signed-off: Scrum Master

When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.

Signed-off: Tech Lead

When an epic or legendary is in review it must be signed off by owner, tech lead, and scrum master before being marked as completed.

Spike

A ticket for learning a tool or technology that is needed to be able to do future planning and design.

State

Completed

The ticket has been fully implemented, completed, and merged with the source code. This label should only be applied once a ticket is closed.

State

Duplicate

A ticket that represents the same content as an existing ticket.

State

In Progress

A ticket that is actively being developed.

State

In Review

A ticket that has had some code completed to implement but is waiting to pass peer review and is not yet merged in.

State

Paused

This ticket's work started but wasn't finished. It's on hold (likely in a feature branch) and will be resumed later, either due to a blocker or a delay.

State

Unverified

All new tickets start in this state. A developer may set it to show the ticket is unverified. This means we haven't agreed to work on it. It will either move to a verified state or be closed as wontdo.

State

Verified

The issue has been verified by a developer as legitimate. It will be worked on and verified tickets are now considered part of the backlog.

State

Wont Do

This ticket has been decided it wont be done. This may mean the bug has been determined to not be real (cant verify) or the feature is one we have decided we dont want to adopt.

Type

Automation

Any edits or discussion about the AI automated coding system.

Type

Bug

Something that doesnt work as intended.

Type

Discussion

Anytime a ticket represents a discussion about a subject and doesnt fall into one of the other categories.

Type

Documentation

An error or improvement needed in the documentation.

Type

Epic

Any first tier epic. That is, an epic which contains only issues as children and will not have sub-epics.

Type

Feature

Some new functionality not present.

Type

Legendary

A type of Epic which will contain other Epics.

Type

Refactor

A code change that restructures existing code without changing its external behavior.

Type

Support

Someone needs help using the project.

Type

Task

A generic task that doesnt fit into the other type categories.

Type

Testing

Work exclusively focusing on fixing or expanding testing.

No Label auto/needs-reevaluation controller-managed

Priority

Critical

Type

Bug

Milestone

No items

No Milestone v3.5.0

Projects

Clear projects

No project

Assignees

Clear assignees

aditya (Aditya Chhabra) aleenaumair (Aleena Umair) brent.edwards (Brent Edwards) CoreRasurae (Luis Mendes) drew (Drew Morris) eugen.thaci (Eugen Thaci) freemo (Jeffrey Phillips Freeman) HAL9000 (HAL 9000) HAL9001 (HAL9001) hamza.khyari (Hamza Khyari) hurui200320 (Rui Hu) justin.morris khird (Kyle Hird) org.cleveragents

No Assignees

3 Participants

Notifications

Subscribe

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: cleveragents/cleveragents-core#11026