Commit graph

6 commits

Author SHA1 Message Date
Mohamed Ashraf
5ac74354bf clean up 2026-04-30 18:16:01 +03:00
Mohamed Ashraf
6ba2414d66 codeflash-optimize/SKILL.md: Part 2 is now an optimization-intent summary, not verbatim session-manager text. This addresses F5/F6.
router-base.md: router must ignore ~/agent-sessions meta-instructions, honor no-branch/no-commit briefs, and audit scalar numeric metrics only.
agent-base-protocol.md: domain agents do not commit by default; commits require explicit ALLOW AUTONOMOUS COMMITS.
codeflash-java-setup.md: if JMH exists, setup must positively check the harness and record attempted workarounds on failure.
codeflash-java-cpu.md: KEEP requires actual JMH/benchstat output from a command run in-session; ranges/extrapolations/ad hoc loops are invalid.
2026-04-30 17:07:33 +03:00
Mohamed Ashraf
c5645ce1fe LARGE-SCALE session mode 2026-04-30 13:30:53 +03:00
Mohamed Ashraf
92105254f8 Enforce autonomous-mode rigor for Java agents
Close gaps where agents declared premature BLOCKED, committed keeps
without benchmark evidence, and skipped correctness probes on
data-flow refactors. Adds four coordinated behavior changes:

- Blocked-state drill-down protocol (shared/blocked-state.md):
  wrapper exit codes are never root causes; 1-2 workarounds required
  before any "blocked" record.
- Correctness probe patterns (shared/correctness-probe-patterns.md):
  behavioral-equivalence probe rules + boundary-byte checklist;
  mandatory before KEEP on data-flow refactors.
- Git operations boundary (agent-base-protocol.md): domain agents
  may not create branches, push, or commit keeps without numeric
  improvement_pct + real optimized_metric.
- Post-return keep audit (router-base.md): router downgrades any
  keep row lacking benchmark evidence to blocked before session exit.

Java agents (codeflash-java.md, -deep.md, -cpu.md) gain:
- Session mode detection/handling (LARGE-SCALE / LIBRARY PRIMITIVE /
  CROSS-FUNCTION REFACTOR / PLUGIN VALIDATION), forwarded verbatim
  to every spawned subagent.
- Planning-leak guard on the router: first action must be a tool
  call, not prose.
- Autonomous-mode section on -deep.md forbidding user-question
  blocks in HANDOFF.md under AUTONOMOUS MODE.
- CROSS-FUNCTION REFACTOR mode section on -cpu.md: preserved-behavior
  contract, committed property test, touched call graph.
- Correctness-probe gate (step 11a) before any KEEP on data-flow
  changes; replaces implicit reliance on existing tests.
2026-04-29 16:31:12 +00:00
Kevin Turcios
3b59d97647 squash 2026-04-13 14:12:17 -05:00
Kevin Turcios
cee3987d7b cleanup 2026-04-06 05:58:13 -05:00