🤖 Guidance pass fixes: attacker structure carry-over, reviewer test/flag checks, gremlin handoff note, stale fork and Zathras text

2026-10-17 00:50:01 +02:00
parent 5b5fe14221
commit 0f2aee6bc9
6 changed files with 14 additions and 11 deletions
@@ -36,7 +36,7 @@ The plan you receive has already been attacked and reshaped into phases and bloc
   - Stop a gremlin with `TaskStop` on its background Bash call.
   - Each brief says whether the gremlin commits and which paths it may touch.
 3. **Gate between blocks.** The cheap check the plan or project config names (compile, typecheck). Not a review.
-4. **Tests once**, at phase end. Fix the fallout in that last block. A child's "tests pass" is a claim: report green only from your own test run, and if a fix changed a test, name it in the phase close and leave judging it to the reviewer.
+4. **Tests once**, at phase end. Fix the fallout in that last block. A child's "tests pass" is a claim: report green only from your own test run, and if any block or fix changed or deleted an existing test, name it in the phase close and leave judging it to the reviewer.
 5. **Run log.** One short handoff note per block, then the phase close with the deviations and flags for the reviewer; "none" is a normal answer, and a real deviation is never left out.
 6. **Hand back.** Igor dispatches the phase review.

@@ -28,7 +28,8 @@ Test the plan adversarially against the code as it is now:
 Write a new build plan; the original stays as written.

 - Phases that each end in a testable state; blocks that one owner can finish.
- Per block: owner model, gate, what may stay broken until the next block (defaults from `spire:project` `## Build`). The build runs a cheap gate between blocks and the tests once per phase; an extra review at a hotspot needs a stated reason.
+- Per block: owner (a gremlin for a complex block, a fresh Sonnet or Haiku agent for a mechanical one), gate, what may stay broken until the next block (defaults from `spire:project` `## Build`). The build runs a cheap gate between blocks and the tests once per phase; an extra review at a hotspot needs a stated reason.
+- Carry over the plan's code structure (signatures included) and per-module size estimate, adjusted where the attack changes them.
 - Scope cut back to the goal: each block traces to a box, and cutting never removes a failure path or a test a box names. Code in the plan only where its exact form is the decision.
 - Decisions the user must make, listed.
 - A risk list for the build. It is not the reviewer's scope.
@@ -17,8 +17,9 @@ You review a phase you did not build. The brief names the build plan, the run lo

 - Run the gates and tests named in the brief or in `spire:project` `## Build`.
 - Trace concrete scenarios through the changed code.
- Read every flag in the run log's handoff notes; answer one in the report only where it changes a finding or a verdict.
+- Check every flag in the run log's handoff notes; report one only where it changes a finding or a verdict.
 - Check the phase's diff for **weakened checks** (loosened assertions, downgraded errors, deleted tests) and **tests that cannot fail**; each one you find is a finding, and the search stays inside the diff.
+- A behaviour or failure path the plan names with no test is a finding.
 - End with a short **Size and unrequested surface** section: size against the plan's estimate, and what was built that no plan box asked for, one line each. You list; Igor and the user decide, and an unplanned addition may be a good one.
 - The attack's risk list is not your scope. Look where the code tells you to.