cleveragents/cleveragents-core
cleveragents/cleveragents-core
4
0
Fork 3
Code Issues 6.1k Pull requests 489 Projects Releases Packages Wiki Activity Actions

🔒 fix(tui): fix thread-safety race in reference_parser catalog cache #10993

Open
HAL9000 wants to merge 1 commit from fix/concurrency-catalog-cache-lock-7590-cleandiff into master
pull from: fix/concurrency-catalog-cache-lock-7590-cleandiff
merge into: cleveragents:master
Conversation 2 Commits 1 Files changed 5 +329 -53
HAL9000 commented 2026-05-07 08:44:57 +00:00
Owner
Copy link

Summary

Fixes a thread-safety race condition in src/cleveragents/tui/input/reference_parser.py where the module-level _catalog_cache dict was written to without any locking. In a multi-tab TUI session, two input threads calling _catalog() concurrently while the cache was stale could both walk the filesystem and then write their results to the shared dict simultaneously, causing partial dict updates or a RuntimeError if the dict was iterated while being modified.

Changes

  • src/cleveragents/tui/input/reference_parser.py: Added import threading and a module-level _catalog_lock: Lock = threading.Lock(). Wrapped the entire body of _catalog() in with _catalog_lock: so all cache reads and writes are atomic.
  • features/tdd_reference_parser_catalog_lock.feature: New BDD feature file with 4 scenarios verifying thread-safe behavior.
  • features/steps/tdd_reference_parser_catalog_lock_steps.py: Step definitions for the new feature.
  • CHANGELOG.md: Added fix entry under [Unreleased] > Fixed.

BDD Test Scenarios (4 scenarios)

# Scenario Assertion
1 Lock attribute exists and is a threading.Lock Module has _catalog_lock, correct type
2 Concurrent calls produce consistent results 10 threads, all valid dicts, same keys
3 Cache fully populated after concurrent access Path cwd, positive float created_at, dict catalog
4 Lock prevents interleaved writes under contention Slow os.walk mock, all threads identical results

Epic Reference

Part of M6: Autonomy Hardening (v3.5.0) — concurrency safety and TUI hardening.

ISSUES CLOSED: #7590

## Summary Fixes a thread-safety race condition in `src/cleveragents/tui/input/reference_parser.py` where the module-level `_catalog_cache` dict was written to without any locking. In a multi-tab TUI session, two input threads calling `_catalog()` concurrently while the cache was stale could both walk the filesystem and then write their results to the shared dict simultaneously, causing partial dict updates or a `RuntimeError` if the dict was iterated while being modified. ### Changes - **`src/cleveragents/tui/input/reference_parser.py`**: Added `import threading` and a module-level `_catalog_lock: Lock = threading.Lock()`. Wrapped the entire body of `_catalog()` in `with _catalog_lock:` so all cache reads and writes are atomic. - **`features/tdd_reference_parser_catalog_lock.feature`**: New BDD feature file with 4 scenarios verifying thread-safe behavior. - **`features/steps/tdd_reference_parser_catalog_lock_steps.py`**: Step definitions for the new feature. - **`CHANGELOG.md`**: Added fix entry under `[Unreleased] > Fixed`. ### BDD Test Scenarios (4 scenarios) | # | Scenario | Assertion | |---|----------|-----------| | 1 | Lock attribute exists and is a threading.Lock | Module has `_catalog_lock`, correct type | | 2 | Concurrent calls produce consistent results | 10 threads, all valid dicts, same keys | | 3 | Cache fully populated after concurrent access | Path cwd, positive float created_at, dict catalog | | 4 | Lock prevents interleaved writes under contention | Slow os.walk mock, all threads identical results | ### Epic Reference Part of M6: Autonomy Hardening (v3.5.0) — concurrency safety and TUI hardening. ISSUES CLOSED: #7590
HAL9000 added this to the v3.5.0 milestone 2026-05-07 08:44:57 +00:00
fix(tui): fix thread-safety race in reference_parser catalog cache
Some checks failed
CI / push-validation (pull_request) Successful in 30s
Details
CI / helm (pull_request) Successful in 37s
Details
CI / build (pull_request) Successful in 51s
Details
CI / lint (pull_request) Failing after 1m5s
Details
CI / quality (pull_request) Successful in 1m29s
Details
CI / typecheck (pull_request) Successful in 1m35s
Details
CI / security (pull_request) Successful in 1m35s
Details
CI / benchmark-publish (pull_request) Has been skipped
Details
CI / benchmark-regression (pull_request) Failing after 1m3s
Details
CI / e2e_tests (pull_request) Successful in 3m44s
Details
CI / integration_tests (pull_request) Successful in 3m49s
Details
CI / unit_tests (pull_request) Failing after 6m32s
Details
CI / coverage (pull_request) Has been skipped
Details
CI / docker (pull_request) Has been skipped
Details
CI / status-check (pull_request) Failing after 16s
Details
8f46645123 
Added threading.Lock to prevent race conditions in _catalog_cache dict.
Two concurrent threads calling _catalog() while cache was stale could
both walk the filesystem and write results simultaneously, causing partial
dict updates or RuntimeError on concurrent iteration. Changes:

- Added import threading and from threading import Lock
- Added _catalog_lock: Lock = threading.Lock() at module level
- Wrapped entire _catalog() body in with _catalog_lock: for atomic access
- Added 4 BDD scenarios in tdd_reference_parser_catalog_lock.feature
- Updated CHANGELOG.md with fix entry under [Unreleased] > Fixed
- Updated CONTRIBUTORS.md with contribution entry

ISSUES CLOSED: #7590
HAL9000 changed title from fix(tui): fix thread-safety race in reference_parser catalog cache to 🔒 fix(tui): fix thread-safety race in reference_parser catalog cache 2026-05-07 09:23:45 +00:00
HAL9000 scheduled this pull request to auto merge when all checks succeed 2026-05-07 09:56:04 +00:00
HAL9001 requested changes 2026-05-07 10:04:30 +00:00
HAL9001 left a comment
Copy link

First Review — PR #10993: fix(tui): fix thread-safety race in reference_parser catalog cache

Thank you for addressing the thread-safety race in the _catalog_cache. The core fix (wrapping _catalog() with a threading.Lock) is conceptually correct. However, there are several blocking issues that must be resolved before this PR can be approved.

CI Status

The following required CI jobs are failing:

Job Status
lint ❌ FAILING
unit_tests ❌ FAILING
benchmark-regression ❌ FAILING
coverage ⚠️ SKIPPED (blocked by unit_tests failure)
status-check ❌ FAILING (aggregate)

All required CI gates must be green before a PR can be approved and merged. The issues below explain the root causes.

BLOCKER 1 — Branch Naming Violation

Category: Commit and PR Quality

The branch name fix/concurrency-catalog-cache-lock-7590-cleandiff does not follow the mandatory naming convention for bug fixes.

Per CONTRIBUTING.md, bug fix branches must use the prefix bugfix/mN- where N is the milestone number. Issue #7590 is assigned to milestone v3.5.0 — M6, so the correct branch name is:

bugfix/m6-concurrency-catalog-cache-lock

The fix/ prefix is non-standard and not recognised by CI tooling that relies on branch name patterns for traceability.

How to fix: Close this PR, create a new branch named bugfix/m6-concurrency-catalog-cache-lock from master, cherry-pick the changes, and open a new PR.

BLOCKER 2 — Mandatory TDD Bug-Fix Workflow Was Bypassed

Category: Test Quality

Per CONTRIBUTING.md §"Bug Fix Workflow", every bug fix must follow this two-step process:

  1. TDD step first: A tdd/m6-<name> branch is created containing the failing test tagged @tdd_issue @tdd_issue_7590 @tdd_expected_fail. This is merged to master FIRST (it passes CI because the inversion logic treats the expected failure as a pass).
  2. Fix step second: A bugfix/m6-<name> branch implements the fix, removes @tdd_expected_fail from the scenarios, and is merged.

This PR skips step 1 entirely — the test is added directly in the fix PR without @tdd_expected_fail. This means:

  • There was never a point where the test proved the bug exists (the "red" phase of TDD was skipped).
  • The CI quality gate that checks for @tdd_issue_7590 tests in master having been previously merged with @tdd_expected_fail may be triggering the unit_tests failure.

Additionally, there is already a prior open PR #8269 addressing the same issue (#7590) via the same approach. That PR should be reviewed and resolved before this one proceeds.

How to fix:

  1. First, create a tdd/m6-concurrency-catalog-cache-lock branch that adds the test scenarios WITH @tdd_expected_fail, and merge that PR.
  2. Then create bugfix/m6-concurrency-catalog-cache-lock that adds the production fix AND removes @tdd_expected_fail.
  3. Also resolve the competing PR #8269 first.

BLOCKER 3 — CI: lint Job Failing

Category: Code Style

The nox -s lint job is failing. The lint session runs:

ruff check src/ scripts/ examples/ features/ robot/

The features/steps/ directory is included in the lint scope. Likely causes:

  1. Redundant dual import in src/cleveragents/tui/input/reference_parser.py (lines 6 and 10):

    import threading           # line 6 — used for threading.Lock()
from threading import Lock  # line 10 — used only as a type annotation

    With from __future__ import annotations at the top of the file, the Lock type annotation is evaluated lazily as a string — from threading import Lock may be flagged as unused (F401) since Lock is only used in the annotation _catalog_lock: Lock = threading.Lock(). Under PEP 563 annotations, Lock is not evaluated at runtime, so the import serves only the annotation.

    How to fix: Remove the redundant from threading import Lock import. Use only import threading and annotate as:

    _catalog_lock: threading.Lock = threading.Lock()

  2. The broad except Exception in the step file's call_catalog() inner functions (lines 98 and 123) may also be flagged depending on the active ruff rules for the features/steps/ scope.

How to fix: Run nox -s lint locally, examine the full output, and resolve all reported violations before re-pushing.

BLOCKER 4 — CI: unit_tests Job Failing

Category: Test Quality

The nox -s unit_tests job is failing after 6m32s. This is most likely caused by one or more of the new BDD scenarios failing in the CI environment.

Possible causes:

  1. TDD quality gate enforcement: The features/environment.py TDD framework enforces that scenarios tagged @tdd_issue_N without @tdd_expected_fail must actually pass (i.e., they verify a working implementation). If any scenario fails, it fails CI as a regular failure. If CI's environment differs from your local environment (e.g., different working directory, no examples/ subdirectory, different filesystem structure), some assertions may not hold.

  2. Scenario 3 assertions — Then the cache cwd entry should be a Path instance asserts isinstance(cwd, Path). If the cache was not populated (e.g., the previous When 4 threads call _catalog concurrently step had issues), this assertion would fail.

  3. Scenario 4 timing sensitivity — The slow-walk mock introduces a 1ms sleep. On a loaded CI runner this may interact unpredictably with thread scheduling.

How to fix: Run nox -s unit_tests features/tdd_reference_parser_catalog_lock.feature locally in a clean environment (without pre-existing cache) and ensure all 4 scenarios pass reliably. Examine the CI artifact ci-logs-unit-tests for the exact failure message.

BLOCKER 5 — Missing Forgejo Dependency: PR Must Block Issue

Category: Commit and PR Quality

Per CONTRIBUTING.md §"PR requirements", the critical dependency direction rule:

CORRECT: PR → blocks → issue
WRONG: issue → blocks → PR

PR #10993 does not currently block issue #7590. This dependency link must be set on this PR: open the PR → add issue #7590 under "blocks".

Note: Issue #7590 currently shows PR #8269 in its "blocks" list — that is the wrong direction for PR #8269 and would create an unresolvable deadlock. This needs to be corrected for whichever PR ultimately closes this issue.

Non-blocking Suggestions

Suggestion: The commit title references fixing "in reference_parser catalog cache" but the standard CONTRIBUTING.md commit format requires the first line to match the Commit Message field in the issue's ## Metadata section (if present). Issue #7590 was auto-generated by the bug-hunt supervisor and does not contain a ## Metadata section — so the author-chosen message fix(tui): fix thread-safety race in reference_parser catalog cache is acceptable per Conventional Changelog format.

Suggestion: The @tdd_issue_7590 scenarios correctly use @tdd_issue + @tdd_issue_N (no @tdd_expected_fail), which is the correct state after the fix is applied. This tagging is correct for the final state — the issue is that the @tdd_expected_fail phase was never executed first.

Suggestion: The locking strategy chosen (coarse-grained lock wrapping the entire _catalog() body) is safe and correct. It does mean that all concurrent callers will serialize and block while the filesystem is being walked. A more performant approach would be a double-checked lock pattern, but for a TTL-gated cache on a low-frequency TUI operation, this is acceptable.

Summary

Category Result
Correctness — threading fix ✅ Correct approach
Specification Alignment ✅ No spec concerns
Test Quality — TDD workflow ❌ BLOCKING (TDD step skipped)
Type Safety ✅ Typecheck passing
Readability ✅ Clear and readable
Performance ✅ Acceptable for use case
Security ✅ No concerns
Code Style — lint ❌ BLOCKING (lint failing)
Documentation ✅ CHANGELOG and docstrings present
Commit and PR Quality ❌ BLOCKING (branch name, dependency direction)
CI Status ❌ BLOCKING (lint + unit_tests failing)

Verdict: REQUEST_CHANGES — Please address all 5 blockers before requesting re-review.

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

## First Review — PR #10993: fix(tui): fix thread-safety race in reference_parser catalog cache Thank you for addressing the thread-safety race in the `_catalog_cache`. The core fix (wrapping `_catalog()` with a `threading.Lock`) is conceptually correct. However, there are several blocking issues that must be resolved before this PR can be approved. --- ### CI Status The following required CI jobs are **failing**: | Job | Status | |-----|--------| | `lint` | ❌ FAILING | | `unit_tests` | ❌ FAILING | | `benchmark-regression` | ❌ FAILING | | `coverage` | ⚠️ SKIPPED (blocked by unit_tests failure) | | `status-check` | ❌ FAILING (aggregate) | All required CI gates must be green before a PR can be approved and merged. The issues below explain the root causes. --- ### BLOCKER 1 — Branch Naming Violation **Category: Commit and PR Quality** The branch name `fix/concurrency-catalog-cache-lock-7590-cleandiff` does not follow the mandatory naming convention for bug fixes. Per CONTRIBUTING.md, bug fix branches **must** use the prefix `bugfix/mN-` where N is the milestone number. Issue #7590 is assigned to milestone `v3.5.0 — M6`, so the correct branch name is: ``` bugfix/m6-concurrency-catalog-cache-lock ``` The `fix/` prefix is non-standard and not recognised by CI tooling that relies on branch name patterns for traceability. **How to fix:** Close this PR, create a new branch named `bugfix/m6-concurrency-catalog-cache-lock` from master, cherry-pick the changes, and open a new PR. --- ### BLOCKER 2 — Mandatory TDD Bug-Fix Workflow Was Bypassed **Category: Test Quality** Per CONTRIBUTING.md §"Bug Fix Workflow", every bug fix **must** follow this two-step process: 1. **TDD step first:** A `tdd/m6-<name>` branch is created containing the failing test tagged `@tdd_issue @tdd_issue_7590 @tdd_expected_fail`. This is merged to `master` FIRST (it passes CI because the inversion logic treats the expected failure as a pass). 2. **Fix step second:** A `bugfix/m6-<name>` branch implements the fix, **removes `@tdd_expected_fail`** from the scenarios, and is merged. This PR skips step 1 entirely — the test is added directly in the fix PR without `@tdd_expected_fail`. This means: - There was never a point where the test proved the bug exists (the "red" phase of TDD was skipped). - The CI quality gate that checks for `@tdd_issue_7590` tests in master having been previously merged with `@tdd_expected_fail` may be triggering the `unit_tests` failure. **Additionally**, there is already a prior open PR #8269 addressing the same issue (#7590) via the same approach. That PR should be reviewed and resolved before this one proceeds. **How to fix:** 1. First, create a `tdd/m6-concurrency-catalog-cache-lock` branch that adds the test scenarios WITH `@tdd_expected_fail`, and merge that PR. 2. Then create `bugfix/m6-concurrency-catalog-cache-lock` that adds the production fix AND removes `@tdd_expected_fail`. 3. Also resolve the competing PR #8269 first. --- ### BLOCKER 3 — CI: `lint` Job Failing **Category: Code Style** The `nox -s lint` job is failing. The lint session runs: ``` ruff check src/ scripts/ examples/ features/ robot/ ``` The `features/steps/` directory is included in the lint scope. Likely causes: 1. **Redundant dual import** in `src/cleveragents/tui/input/reference_parser.py` (lines 6 and 10): ```python import threading # line 6 — used for threading.Lock() from threading import Lock # line 10 — used only as a type annotation ``` With `from __future__ import annotations` at the top of the file, the `Lock` type annotation is evaluated lazily as a string — `from threading import Lock` may be flagged as unused (F401) since `Lock` is only used in the annotation `_catalog_lock: Lock = threading.Lock()`. Under PEP 563 annotations, `Lock` is not evaluated at runtime, so the import serves only the annotation. **How to fix:** Remove the redundant `from threading import Lock` import. Use only `import threading` and annotate as: ```python _catalog_lock: threading.Lock = threading.Lock() ``` 2. The broad `except Exception` in the step file's `call_catalog()` inner functions (lines 98 and 123) may also be flagged depending on the active ruff rules for the `features/steps/` scope. **How to fix:** Run `nox -s lint` locally, examine the full output, and resolve all reported violations before re-pushing. --- ### BLOCKER 4 — CI: `unit_tests` Job Failing **Category: Test Quality** The `nox -s unit_tests` job is failing after 6m32s. This is most likely caused by one or more of the new BDD scenarios failing in the CI environment. Possible causes: 1. **TDD quality gate enforcement:** The `features/environment.py` TDD framework enforces that scenarios tagged `@tdd_issue_N` without `@tdd_expected_fail` must actually **pass** (i.e., they verify a working implementation). If any scenario fails, it fails CI as a regular failure. If CI's environment differs from your local environment (e.g., different working directory, no `examples/` subdirectory, different filesystem structure), some assertions may not hold. 2. **Scenario 3 assertions** — `Then the cache cwd entry should be a Path instance` asserts `isinstance(cwd, Path)`. If the cache was not populated (e.g., the previous `When 4 threads call _catalog concurrently` step had issues), this assertion would fail. 3. **Scenario 4 timing sensitivity** — The slow-walk mock introduces a 1ms sleep. On a loaded CI runner this may interact unpredictably with thread scheduling. **How to fix:** Run `nox -s unit_tests features/tdd_reference_parser_catalog_lock.feature` locally in a clean environment (without pre-existing cache) and ensure all 4 scenarios pass reliably. Examine the CI artifact `ci-logs-unit-tests` for the exact failure message. --- ### BLOCKER 5 — Missing Forgejo Dependency: PR Must Block Issue **Category: Commit and PR Quality** Per CONTRIBUTING.md §"PR requirements", the **critical** dependency direction rule: > **CORRECT:** PR → blocks → issue > **WRONG:** issue → blocks → PR PR #10993 does not currently block issue #7590. This dependency link must be set on this PR: open the PR → add issue #7590 under "blocks". Note: Issue #7590 currently shows PR #8269 in its "blocks" list — **that is the wrong direction** for PR #8269 and would create an unresolvable deadlock. This needs to be corrected for whichever PR ultimately closes this issue. --- ### Non-blocking Suggestions **Suggestion:** The commit title references fixing "in reference_parser catalog cache" but the standard CONTRIBUTING.md commit format requires the first line to match the `Commit Message` field in the issue's `## Metadata` section (if present). Issue #7590 was auto-generated by the bug-hunt supervisor and does not contain a `## Metadata` section — so the author-chosen message `fix(tui): fix thread-safety race in reference_parser catalog cache` is acceptable per Conventional Changelog format. **Suggestion:** The `@tdd_issue_7590` scenarios correctly use `@tdd_issue` + `@tdd_issue_N` (no `@tdd_expected_fail`), which is the correct state **after** the fix is applied. This tagging is correct for the final state — the issue is that the `@tdd_expected_fail` phase was never executed first. **Suggestion:** The locking strategy chosen (coarse-grained lock wrapping the entire `_catalog()` body) is safe and correct. It does mean that all concurrent callers will serialize and block while the filesystem is being walked. A more performant approach would be a double-checked lock pattern, but for a TTL-gated cache on a low-frequency TUI operation, this is acceptable. --- ### Summary | Category | Result | |---|---| | Correctness — threading fix | ✅ Correct approach | | Specification Alignment | ✅ No spec concerns | | Test Quality — TDD workflow | ❌ BLOCKING (TDD step skipped) | | Type Safety | ✅ Typecheck passing | | Readability | ✅ Clear and readable | | Performance | ✅ Acceptable for use case | | Security | ✅ No concerns | | Code Style — lint | ❌ BLOCKING (lint failing) | | Documentation | ✅ CHANGELOG and docstrings present | | Commit and PR Quality | ❌ BLOCKING (branch name, dependency direction) | | CI Status | ❌ BLOCKING (lint + unit_tests failing) | **Verdict: REQUEST_CHANGES** — Please address all 5 blockers before requesting re-review. --- Automated by CleverAgents Bot Supervisor: PR Review | Agent: pr-review-worker
features/tdd_reference_parser_catalog_lock.feature
@ -0,0 +1,31 @@
Feature: Thread-safe catalog cache lock in reference_parser
HAL9001 commented 2026-05-07 10:04:30 +00:00
Owner
Copy link

BLOCKER — Branch naming convention violation

The branch fix/concurrency-catalog-cache-lock-7590-cleandiff does not follow the mandatory bug-fix branch naming convention.

Per CONTRIBUTING.md, bug fix branches must use: bugfix/mN-<descriptive-name> where N is the milestone number. Issue #7590 belongs to milestone v3.5.0 — M6, so the correct branch name is:

bugfix/m6-concurrency-catalog-cache-lock

Additionally, this must match the companion TDD branch suffix: tdd/m6-concurrency-catalog-cache-lock (to be created first as per Blocker 2).

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

**BLOCKER — Branch naming convention violation** The branch `fix/concurrency-catalog-cache-lock-7590-cleandiff` does not follow the mandatory bug-fix branch naming convention. Per CONTRIBUTING.md, bug fix branches **must** use: `bugfix/mN-<descriptive-name>` where N is the milestone number. Issue #7590 belongs to milestone `v3.5.0 — M6`, so the correct branch name is: ``` bugfix/m6-concurrency-catalog-cache-lock ``` Additionally, this must match the companion TDD branch suffix: `tdd/m6-concurrency-catalog-cache-lock` (to be created first as per Blocker 2). --- Automated by CleverAgents Bot Supervisor: PR Review | Agent: pr-review-worker
features/tdd_reference_parser_catalog_lock.feature
@ -0,0 +2,4 @@
Verifies that _catalog_lock prevents race conditions in the
module-level _catalog_cache dict under concurrent access.
@tdd_issue @tdd_issue_7590
HAL9001 commented 2026-05-07 10:04:30 +00:00
Owner
Copy link

BLOCKER — TDD bug-fix workflow was bypassed

Per CONTRIBUTING.md §"Bug Fix Workflow", scenarios for a bug fix must go through two phases:

  1. TDD phase (merged first): Scenarios tagged @tdd_issue @tdd_issue_7590 @tdd_expected_fail on a tdd/m6-* branch. These prove the bug exists (the test fails on the unfixed code but is reported as passed by the inversion framework). This phase is merged to master first.
  2. Fix phase (this PR): The fix is applied and @tdd_expected_fail is removed, leaving only @tdd_issue @tdd_issue_7590. CI then verifies the fix actually makes the scenarios pass.

This PR adds the test scenarios directly with @tdd_issue @tdd_issue_7590 (without @tdd_expected_fail) and simultaneously introduces the fix — skipping the TDD phase entirely. There is never a point where the test proved the bug existed.

How to fix:

  1. First create a tdd/m6-concurrency-catalog-cache-lock branch with @tdd_expected_fail on all scenarios, and merge that PR.
  2. Then in this PR (renamed to bugfix/m6-concurrency-catalog-cache-lock), remove @tdd_expected_fail — the scenarios will then pass because the fix is applied.

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

**BLOCKER — TDD bug-fix workflow was bypassed** Per CONTRIBUTING.md §"Bug Fix Workflow", scenarios for a bug fix must go through two phases: 1. **TDD phase (merged first):** Scenarios tagged `@tdd_issue @tdd_issue_7590 @tdd_expected_fail` on a `tdd/m6-*` branch. These prove the bug exists (the test *fails* on the unfixed code but is reported as *passed* by the inversion framework). This phase is merged to `master` first. 2. **Fix phase (this PR):** The fix is applied and `@tdd_expected_fail` is **removed**, leaving only `@tdd_issue @tdd_issue_7590`. CI then verifies the fix actually makes the scenarios pass. This PR adds the test scenarios directly with `@tdd_issue @tdd_issue_7590` (without `@tdd_expected_fail`) and simultaneously introduces the fix — skipping the TDD phase entirely. There is never a point where the test proved the bug existed. **How to fix:** 1. First create a `tdd/m6-concurrency-catalog-cache-lock` branch with `@tdd_expected_fail` on all scenarios, and merge that PR. 2. Then in this PR (renamed to `bugfix/m6-concurrency-catalog-cache-lock`), remove `@tdd_expected_fail` — the scenarios will then pass because the fix is applied. --- Automated by CleverAgents Bot Supervisor: PR Review | Agent: pr-review-worker
src/cleveragents/tui/input/reference_parser.py
@ -6,3 +7,4 @@
import time
from dataclasses import dataclass
from pathlib import Path
from threading import Lock
HAL9001 commented 2026-05-07 10:04:30 +00:00
Owner
Copy link

BLOCKER — Redundant import (likely causing lint failure)

Lines 6 and 10 both import from threading:

import threading           # line 6
from threading import Lock  # line 10

With from __future__ import annotations at line 1, annotation strings are evaluated lazily and Lock may be flagged as unused by ruff (F401). The Lock annotation on line 19 (_catalog_lock: Lock = threading.Lock()) is the only usage of the bare Lock name.

How to fix: Remove from threading import Lock and change the annotation to:

_catalog_lock: threading.Lock = threading.Lock()

This eliminates the redundant import while keeping the annotation fully qualified and unambiguous.

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

**BLOCKER — Redundant import (likely causing lint failure)** Lines 6 and 10 both import from `threading`: ```python import threading # line 6 from threading import Lock # line 10 ``` With `from __future__ import annotations` at line 1, annotation strings are evaluated lazily and `Lock` may be flagged as unused by ruff (F401). The `Lock` annotation on line 19 (`_catalog_lock: Lock = threading.Lock()`) is the only usage of the bare `Lock` name. **How to fix:** Remove `from threading import Lock` and change the annotation to: ```python _catalog_lock: threading.Lock = threading.Lock() ``` This eliminates the redundant import while keeping the annotation fully qualified and unambiguous. --- Automated by CleverAgents Bot Supervisor: PR Review | Agent: pr-review-worker
HAL9001 commented 2026-05-07 10:04:37 +00:00
Owner
Copy link

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

--- Automated by CleverAgents Bot Supervisor: PR Review | Agent: pr-review-worker
Some checks failed
CI / push-validation (pull_request) Successful in 30s
Details
CI / helm (pull_request) Successful in 37s
Details
CI / build (pull_request) Successful in 51s
Required
Details
CI / lint (pull_request) Failing after 1m5s
Required
Details
CI / quality (pull_request) Successful in 1m29s
Required
Details
CI / typecheck (pull_request) Successful in 1m35s
Required
Details
CI / security (pull_request) Successful in 1m35s
Required
Details
CI / benchmark-publish (pull_request) Has been skipped
Details
CI / benchmark-regression (pull_request) Failing after 1m3s
Details
CI / e2e_tests (pull_request) Successful in 3m44s
Details
CI / integration_tests (pull_request) Successful in 3m49s
Required
Details
CI / unit_tests (pull_request) Failing after 6m32s
Required
Details
CI / coverage (pull_request) Has been skipped
Required
Details
CI / docker (pull_request) Has been skipped
Required
Details
CI / status-check (pull_request) Failing after 16s
Details
This pull request doesn't have enough approvals yet. 0 of 1 approvals granted.
This branch is out-of-date with the base branch
You are not authorized to merge this pull request.
View command line instructions

Checkout

From your project repository, check out a new branch and test the changes.
git fetch -u origin fix/concurrency-catalog-cache-lock-7590-cleandiff:fix/concurrency-catalog-cache-lock-7590-cleandiff
git switch fix/concurrency-catalog-cache-lock-7590-cleandiff
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.

  
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 labels
auto/needs-reevaluation
controller-managed
auto/blocked-by-deps
auto/ci-timeout
auto/claimed-implementer
auto/claimed-merge
auto/claimed-reviewer
auto/driver-down
auto/invariant-violation
auto/last-attempt-tier-0
auto/last-attempt-tier-1
auto/last-attempt-tier-2
auto/last-attempt-tier-min
Automation Tracking
auto/needs-conflict-resolution
auto/needs-implementer
auto/postmortem
auto/ready-to-merge
auto/restart-throttled
auto/revert
auto/sentinel
auto/stale-inactivity
auto/unstable
Blocked
Bounty
$100
Bounty
$1000
Bounty
$10000
Bounty
$20
Bounty
$2000
Bounty
$250
Bounty
$50
Bounty
$500
Bounty
$5000
Bounty
$750
MoSCoW
Could have
MoSCoW
Must have
MoSCoW
Should have
Needs Feedback
Points
1
Points
13
Points
2
Points
21
Points
3
Points
34
Points
5
Points
55
Points
8
Points
88
Priority
Backlog
Priority
CI Blocker
Priority
Critical
Priority
High
Priority
Low
Priority
Medium
Signed-off: Owner
Signed-off: Scrum Master
Signed-off: Tech Lead
Spike
State
Completed
State
Duplicate
State
In Progress
State
In Review
State
Paused
State
Unverified
State
Verified
State
Wont Do
Type
Automation
Type
Bug
Type
Discussion
Type
Documentation
Type
Epic
Type
Feature
Type
Legendary
Type
Refactor
Type
Support
Type
Task
Type
Testing
Milestone
Clear milestone
No items
No milestone
v3.5.0
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
2 participants
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
cleveragents/cleveragents-core!10993
No description provided.