mi/werkrevisor
1
0
Fork 0
Code Issues Pull Requests 4 Actions Packages Projects Releases Wiki Activity

werkrevisor 0.8.0: repository config layer, clear context reasons, docs only as diff #5

Merged
mi merged 4 commits from claude-code/repo-config-and-clear-context-reasons into main 2026-10-05 16:01:00 +02:00
Conversation 1 Commits 4 Files Changed 25
+1233 -269
claude-code commented 2026-10-05 15:56:06 +02:00
Collaborator
Copy Link
Copy Source

werkrevisor 0.8.0: repository config layer, clear context reasons, docs only as diff.

  • Config layers: built-in defaults < host < .werkrevisor.toml read from the PR base; the repository may only tighten cost and model limits, and .werkrevisor.toml is always a risky path.
  • One clear reason per cause instead of one line per file.
  • Documentation files go to the model only as diff and are judged against the writing style in AGENTS.md.
  • AGENTS.md with the shared writing style.

Details: the PR document under docs/prs/.

🤖 Generated with Claude Code

werkrevisor 0.8.0: repository config layer, clear context reasons, docs only as diff. - Config layers: built-in defaults < host < `.werkrevisor.toml` read from the PR base; the repository may only tighten cost and model limits, and `.werkrevisor.toml` is always a risky path. - One clear reason per cause instead of one line per file. - Documentation files go to the model only as diff and are judged against the writing style in AGENTS.md. - AGENTS.md with the shared writing style. Details: the PR document under `docs/prs/`. 🤖 Generated with [Claude Code](https://claude.com/claude-code)
claude-code added 4 commits 2026-10-05 15:56:06 +02:00
docs: AGENTS.md and the PR document for PR#5 4b2f193cc4 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
werkrevisor 0.8.0: repository config, aggregated reasons, docs only as diff 0b685eb357 
- .werkrevisor.toml at the base commit is a config layer on top of the host config;
  host-only keys are refused, limits can only be lowered, hard-YELLOW paths only added.
- .werkrevisor.toml is a built-in hard-YELLOW path; an invalid change of it is RED.
- Files left out of the full-file context give one reason per cause with at most 3 examples.
- Documentation goes to the model only as diff.
- The review instructions ask the model to judge docs against the writing style.
- config/werkrevisor.toml keeps only the host part; the rest moves to .werkrevisor.toml.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
docs: README and German guides describe the config layers of 0.8.0 40d5244eaa 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
docs: PR#5 document states the scenarios and the solution
werkator build succeeded after 00:05
Details
ai-review/assessment AI findings; a developer approval after checking them unlocks the merge; review requested from mi
Details
ai-review/gate build succeeded after 00:01
Details
d4779154e4 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
claude-code marked the pull request as ready for review 2026-10-05 15:56:11 +02:00
ai-reviewer commented 2026-10-05 15:57:51 +02:00
Collaborator
Copy Link
Copy Source

🟠 werkrevisor: ORANGE / FINDINGS

Change kind: mixed.

Reasons

  • YELLOW test changes are not purely additive: tests/test_classifier.py:173 removes a test or assertion, tests/test_classifier.py:181 removes a test or assertion, tests/test_classifier.py:306 removes a test or assertion, tests/test_fullfiles.py:49 removes a test or assertion, tests/test_fullfiles.py:57 removes a test or assertion and 2 more
  • YELLOW change kind 'mixed' (main code, tests, other files, docs); AI-approvable are only: docs only, tests only added, docs and tests, refactoring with unchanged tests
  • YELLOW risky paths changed: config/hsadmin-ng.toml (config/), config/werkprobe.toml (config/), config/werkrevisor.toml (config/**), werkrevisor/config.py (werkrevisor/config.py), werkrevisor/gitea.py (werkrevisor/gitea.py)
  • ORANGE PR too large for an AI-only approval: 1063 changed lines (docs not counted) exceed [size] max_changed_lines = 800; please review it yourself
  • YELLOW full-file context incomplete: docs/prs/2026-10-05-PR#5-repository-config-and-clear-context-reasons.md (all files together would exceed [review] max_full_files_chars = 120000)
  • YELLOW full-file context incomplete: tests/test_classifier.py (all files together would exceed [review] max_full_files_chars = 120000)
  • YELLOW full-file context incomplete: tests/test_config_budget_redact.py (all files together would exceed [review] max_full_files_chars = 120000)
  • YELLOW full-file context incomplete: tests/test_config_layers.py (all files together would exceed [review] max_full_files_chars = 120000)
  • YELLOW full-file context incomplete: tests/test_fullfiles.py (all files together would exceed [review] max_full_files_chars = 120000)
  • YELLOW full-file context incomplete: tests/test_rules.py (all files together would exceed [review] max_full_files_chars = 120000)
  • YELLOW full-file context incomplete: werkrevisor/classifier.py (all files together would exceed [review] max_full_files_chars = 120000)
  • YELLOW full-file context incomplete: werkrevisor/cli.py (all files together would exceed [review] max_full_files_chars = 120000)
  • YELLOW full-file context incomplete: werkrevisor/config.py (all files together would exceed [review] max_full_files_chars = 120000)
  • YELLOW full-file context incomplete: werkrevisor/fullfiles.py (all files together would exceed [review] max_full_files_chars = 120000)
  • YELLOW full-file context incomplete: werkrevisor/gitea.py (all files together would exceed [review] max_full_files_chars = 120000)
  • YELLOW full-file context incomplete: werkrevisor/report.py (all files together would exceed [review] max_full_files_chars = 120000)
  • YELLOW full-file context incomplete: werkrevisor/review.py (all files together would exceed [review] max_full_files_chars = 120000)
  • YELLOW full-file context incomplete: werkrevisor/rules.py (all files together would exceed [review] max_full_files_chars = 120000)
  • YELLOW full-file context incomplete: werkrevisor/verdict.py (all files together would exceed [review] max_full_files_chars = 120000)
  • YELLOW no AI review: the PR needs about 84641 input tokens, more than the limit of 80000 derived from [budget] max_usd_per_review = 0.40
Usage: model `openrouter/anthropic/claude-sonnet-5.5`, LLM skipped (too large), duration 0.8 s, no model call, cost 0 USD.
Reviewed head `d4779154e4a444754fc521d559aa7252e2a9b793` against base `3d174cc8a50310b2cd33d51b00f494e1777ec57c`, werkrevisor 0.7.0.
<!-- werkrevisor:d4779154e4a444754fc521d559aa7252e2a9b793 --> <!-- werkrevisor-verdict:ORANGE --> ## 🟠 werkrevisor: ORANGE / FINDINGS Change kind: `mixed`. ### Reasons - **YELLOW** test changes are not purely additive: tests/test_classifier.py:173 removes a test or assertion, tests/test_classifier.py:181 removes a test or assertion, tests/test_classifier.py:306 removes a test or assertion, tests/test_fullfiles.py:49 removes a test or assertion, tests/test_fullfiles.py:57 removes a test or assertion and 2 more - **YELLOW** change kind 'mixed' (main code, tests, other files, docs); AI-approvable are only: docs only, tests only added, docs and tests, refactoring with unchanged tests - **YELLOW** risky paths changed: config/hsadmin-ng.toml (config/**), config/werkprobe.toml (config/**), config/werkrevisor.toml (config/**), werkrevisor/config.py (werkrevisor/config.py), werkrevisor/gitea.py (werkrevisor/gitea.py) - **ORANGE** PR too large for an AI-only approval: 1063 changed lines (docs not counted) exceed [size] max_changed_lines = 800; please review it yourself - **YELLOW** full-file context incomplete: docs/prs/2026-10-05-PR#5-repository-config-and-clear-context-reasons.md (all files together would exceed [review] max_full_files_chars = 120000) - **YELLOW** full-file context incomplete: tests/test_classifier.py (all files together would exceed [review] max_full_files_chars = 120000) - **YELLOW** full-file context incomplete: tests/test_config_budget_redact.py (all files together would exceed [review] max_full_files_chars = 120000) - **YELLOW** full-file context incomplete: tests/test_config_layers.py (all files together would exceed [review] max_full_files_chars = 120000) - **YELLOW** full-file context incomplete: tests/test_fullfiles.py (all files together would exceed [review] max_full_files_chars = 120000) - **YELLOW** full-file context incomplete: tests/test_rules.py (all files together would exceed [review] max_full_files_chars = 120000) - **YELLOW** full-file context incomplete: werkrevisor/classifier.py (all files together would exceed [review] max_full_files_chars = 120000) - **YELLOW** full-file context incomplete: werkrevisor/cli.py (all files together would exceed [review] max_full_files_chars = 120000) - **YELLOW** full-file context incomplete: werkrevisor/config.py (all files together would exceed [review] max_full_files_chars = 120000) - **YELLOW** full-file context incomplete: werkrevisor/fullfiles.py (all files together would exceed [review] max_full_files_chars = 120000) - **YELLOW** full-file context incomplete: werkrevisor/gitea.py (all files together would exceed [review] max_full_files_chars = 120000) - **YELLOW** full-file context incomplete: werkrevisor/report.py (all files together would exceed [review] max_full_files_chars = 120000) - **YELLOW** full-file context incomplete: werkrevisor/review.py (all files together would exceed [review] max_full_files_chars = 120000) - **YELLOW** full-file context incomplete: werkrevisor/rules.py (all files together would exceed [review] max_full_files_chars = 120000) - **YELLOW** full-file context incomplete: werkrevisor/verdict.py (all files together would exceed [review] max_full_files_chars = 120000) - **YELLOW** no AI review: the PR needs about 84641 input tokens, more than the limit of 80000 derived from [budget] max_usd_per_review = 0.40 <sub> Usage: model `openrouter/anthropic/claude-sonnet-5.5`, LLM skipped (too large), duration 0.8 s, no model call, cost 0 USD.<br> Reviewed head `d4779154e4a444754fc521d559aa7252e2a9b793` against base `3d174cc8a50310b2cd33d51b00f494e1777ec57c`, werkrevisor 0.7.0. </sub>
ai-reviewer requested review from mi 2026-10-05 15:57:51 +02:00
mi merged commit 667cbe94be into main 2026-10-05 16:01:00 +02:00
mi deleted branch claude-code/repo-config-and-clear-context-reasons 2026-10-05 16:01:00 +02:00
Sign in to join this conversation.
Reviewers
No Reviewers
mi
Labels
No items
No labels
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
ai-reviewer claude-code mi
No Assignees
2 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: mi/werkrevisor#5