claude-code
  • Joined on 2026-10-05
claude-code pushed to claude-code/reasons-sorted-by-severity at mi/werkrevisor 2026-10-05 19:34:06 +02:00
b7336ad62f test: werkrevisor's own config allows mechanical_only now
claude-code pushed to claude-code/reasons-sorted-by-severity at mi/werkrevisor 2026-10-05 19:33:05 +02:00
f076dcdfa2 werkrevisor 0.13.1: the comment lists the reasons from the most to the least severe
674ba9a2cb docs: PR#12 document for reasons sorted by severity
Compare 2 commits »
claude-code created branch claude-code/reasons-sorted-by-severity in mi/werkrevisor 2026-10-05 19:33:05 +02:00
claude-code created pull request mi/werkrevisor#12 2026-10-05 19:33:05 +02:00
WIP: werkrevisor 0.13.1: reasons sorted by severity
claude-code pushed to claude-code/mechanical-changes-skip-model at mi/werkrevisor 2026-10-05 19:26:34 +02:00
28567bcb9e docs: Scenario#11.11 states the size limit and an observable Then, as Jev asked
claude-code pushed to claude-code/mechanical-changes-skip-model at mi/werkrevisor 2026-10-05 19:24:59 +02:00
ccad3614c1 an unknown change kind in a changed .werkrevisor.toml gives YELLOW, not RED
e4957f555e .werkrevisor.toml stays unchanged until 0.13.0 is deployed
92014add0a docs: PR#11 document completed with scenarios, solution and decisions
f51e47f629 werkrevisor 0.13.0: README and docs describe [mechanical]
564ee30276 mechanical files do not count for the size limits
Compare 8 commits »
claude-code created branch claude-code/mechanical-changes-skip-model in mi/werkrevisor 2026-10-05 19:24:59 +02:00
claude-code created pull request mi/werkrevisor#11 2026-10-05 19:24:59 +02:00
WIP: werkrevisor 0.13.0: mechanical file changes skip the model
claude-code pushed to claude-code/jev-low-confidence-ignored at mi/werkrevisor 2026-10-05 18:51:33 +02:00
ffa9813e32 review: PR#10 scenarios state their data and link the tests that verify them
claude-code pushed to claude-code/jev-low-confidence-ignored at mi/werkrevisor 2026-10-05 18:49:29 +02:00
dc162d28d1 docs: werkrevisor 0.12.0 ignores Jev answers with low confidence, calibration result
2ac37e656e Jev answers with low confidence no longer give YELLOW
2de23be050 docs: PR#10 document for ignoring Jev answers with low confidence
Compare 3 commits »
claude-code created branch claude-code/jev-low-confidence-ignored in mi/werkrevisor 2026-10-05 18:49:29 +02:00
claude-code created pull request mi/werkrevisor#10 2026-10-05 18:49:28 +02:00
WIP: werkrevisor 0.12.0: Jev answers with low confidence are ignored
bd3ea67252 review: a refused prompt is YELLOW in every attempt, the dead pruning path is removed (PR#9)
91561fb9d2 review: only PR-Agent's notice below a file header marks a file unreadable (PR#9)
a14d955993 review: decide once per review on the token count and keep the usage of earlier calls (PR#9)
Compare 2 commits »
eb2823f3d7 Test data assembles the private-key marker, so the secret scan does not skip the model review
claude-code created pull request mi/werkrevisor#9 2026-10-05 17:44:23 +02:00
WIP: werkrevisor 0.11.0: exact token count, focused style review
e9193fe66b docs: complete the PR#9 document with test links, answered questions and follow-ups
a471db0cb4 werkrevisor 0.11.0: document the token count and token_count_factor
4ca955a61b Leave the countable writing rules to werkrevisor in the review instructions
547bfb1b40 Count the exact PR-Agent prompt with o200k_base before the model call
26c901c5fb docs: PR#9 document for the exact token count and the focused style review
Compare 5 commits »
8b3f8f716b docs: PR#8 document says what harmless_only permits and why it is allowed
99fd34d1f6 werkrevisor allows the change kinds feature_with_tests and harmless_only for itself