werkrevisor 0.31.2: the TypeScript template, measured on codecharta #68

Merged
ai-reviewer merged 2 commits from claude-code/typescript-template-calibration into main 2026-10-09 21:36:01 +02:00
Collaborator

See the PR document.

🤖 Generated with Claude Code

See [the PR document](docs/prs/2026-10-09-PR%2368-typescript-template-calibration.md). 🤖 Generated with [Claude Code](https://claude.com/claude-code)
claude-code added 1 commit 2026-10-09 21:29:38 +02:00
PR document: the TypeScript template, measured on codecharta
werkator build succeeded after 00:35
werkator/werkrevisor-statistics build succeeded after 00:46
6247835510
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
mi added 1 commit 2026-10-09 21:34:30 +02:00
TypeScript template: shared_state asks for the risky kind, unsafe_navigation from 0.85, critical_user_actions from 0.9 (0.31.2)
werkator build succeeded after 00:10
werkator/werkrevisor-statistics build succeeded after 00:35
ai-review/assessment AI review passed; approved by werkrevisor; merge scheduled for when the checks succeed
ai-review/gate build succeeded after 00:52
977018202f
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
claude-code marked the pull request as ready for review 2026-10-09 21:35:08 +02:00
Collaborator

🟢 werkrevisor: GREEN / PASS

Change kind: mixed.

Reasons

  • hint 2 changed file(s) that neither weaken the checks nor touch security according to Jev
  • hint 1 build change(s) of low risk according to Jev: statistics/build.gradle.kts (weakens checks 0.02, risk 0.00, security 0.01)
  • hint 4 section(s) of the PR document agree with the change summary of openrouter/minimax/minimax-m3 according to Jev
  • hint 1 finding(s) of low severity or rated minor by Jev: docs/werkrevisor.werkbaum:286
  • hint model recommends merge with caution

Findings

  1. Werkbaum Number Contradicts Data at docs/werkrevisor.werkbaum:286, severity unknown, counted as medium

    hint; Jev: real 0.83, severity 1.9 of 3

    The Werkbaum says "the security question rates three of them at most 0.11" right after naming three planted defects (xss, token_handling, third_party_requests). Per the PR document table, the security question rates token_handling at 0.96, so only two of those three are at most 0.11 (xss 0.02 and third_party_requests 0.11). Reading "them" as all six planted defects, four are at most 0.11 (xss 0.02, third_party_requests 0.11, critical_user_actions 0.04, shared_state 0.01). Either way, the count "three" does not match the measurements the Werkbaum is supposed to record.

Classifier

4 of 4 units passed all questions (1 PR document(s)).

Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 8614, calls 1, tokens in 8321 / out 11760 (reasoning included in out), duration 49.3 s, cost 0.0166 USD (reported), classifier `jev-1.13.0` calls 4, tokens in 3315, cost 0.0001 USD, finding judge `jev-1.13.0` calls 1, tokens in 1316, cost 0.0001 USD, change summary `openrouter/minimax/minimax-m3` via Minimax calls 1, tokens in 1252 / out 565, cost 0.0010 USD (reported), PR document check `jev-1.13.0` calls 4, tokens in 4635, cost 0.0002 USD, build file judge `jev-1.13.0` calls 3, tokens in 1885, cost 0.0001 USD, phases: path_judge 0.2 s, classifier 0.3 s, change_summary 3.4 s, doc_check 0.3 s, context 0.2 s, model_review 44.4 s, finding_judge 0.3 s, config: defaults + host + repository (.werkrevisor.toml at main 832cf79).
Reviewed head `977018202f83b76489177fa2a4ed41c5fdae8c45` against base `832cf7927525f7f86b3bfac3c8827b2f90ea634c`, werkrevisor 0.31.1.
<!-- werkrevisor:977018202f83b76489177fa2a4ed41c5fdae8c45 --> <!-- werkrevisor-verdict:GREEN --> ## 🟢 werkrevisor: GREEN / PASS Change kind: `mixed`. ### Reasons - **hint** 2 changed file(s) that neither weaken the checks nor touch security according to Jev - **hint** 1 build change(s) of low risk according to Jev: statistics/build.gradle.kts (weakens checks 0.02, risk 0.00, security 0.01) - **hint** 4 section(s) of the PR document agree with the change summary of openrouter/minimax/minimax-m3 according to Jev - **hint** 1 finding(s) of low severity or rated minor by Jev: docs/werkrevisor.werkbaum:286 - **hint** model recommends merge with caution ### Findings 1. **Werkbaum Number Contradicts Data** at `docs/werkrevisor.werkbaum:286`, severity unknown, counted as medium hint; Jev: real 0.83, severity 1.9 of 3 The Werkbaum says "the security question rates three of them at most 0.11" right after naming three planted defects (xss, token_handling, third_party_requests). Per the PR document table, the security question rates token_handling at 0.96, so only two of those three are at most 0.11 (xss 0.02 and third_party_requests 0.11). Reading "them" as all six planted defects, four are at most 0.11 (xss 0.02, third_party_requests 0.11, critical_user_actions 0.04, shared_state 0.01). Either way, the count "three" does not match the measurements the Werkbaum is supposed to record. ### Classifier 4 of 4 units passed all questions (1 PR document(s)). <sub> Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 8614, calls 1, tokens in 8321 / out 11760 (reasoning included in out), duration 49.3 s, cost 0.0166 USD (reported), classifier `jev-1.13.0` calls 4, tokens in 3315, cost 0.0001 USD, finding judge `jev-1.13.0` calls 1, tokens in 1316, cost 0.0001 USD, change summary `openrouter/minimax/minimax-m3` via Minimax calls 1, tokens in 1252 / out 565, cost 0.0010 USD (reported), PR document check `jev-1.13.0` calls 4, tokens in 4635, cost 0.0002 USD, build file judge `jev-1.13.0` calls 3, tokens in 1885, cost 0.0001 USD, phases: path_judge 0.2 s, classifier 0.3 s, change_summary 3.4 s, doc_check 0.3 s, context 0.2 s, model_review 44.4 s, finding_judge 0.3 s, config: defaults + host + repository (.werkrevisor.toml at main 832cf79).<br> Reviewed head `977018202f83b76489177fa2a4ed41c5fdae8c45` against base `832cf7927525f7f86b3bfac3c8827b2f90ea634c`, werkrevisor 0.31.1. </sub>
ai-reviewer left a comment
Collaborator

werkrevisor: GREEN / PASS for 977018202f83b76489177fa2a4ed41c5fdae8c45.
The result comment of werkrevisor holds the details.

werkrevisor: GREEN / PASS for `977018202f83b76489177fa2a4ed41c5fdae8c45`. The result comment of werkrevisor holds the details. <!-- werkrevisor-review:977018202f83b76489177fa2a4ed41c5fdae8c45 -->
ai-reviewer scheduled this pull request to auto merge when all checks succeed 2026-10-09 21:35:59 +02:00
ai-reviewer merged commit 62eb8948ca into main 2026-10-09 21:36:01 +02:00
ai-reviewer deleted branch claude-code/typescript-template-calibration 2026-10-09 21:36:02 +02:00
Sign in to join this conversation.
No Reviewers
No labels
3 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: mi/werkrevisor#68