fix: preserve valid reviewer coverage during output repair

[zzwong]

Summary

Preserve valid review results when coverage lists repeat a file, and make assignment-scope errors easier to correct. In the observed failure, 73 entries represented 71 assigned files. Two duplicate pairs caused the result to be discarded; the retry then lost coverage and introduced an out-of-assignment claim.

Changes

• Treat repeated inspected or skipped paths as one coverage claim without adding coverage or suppressing findings.
• Report invalid coverage positions using zero-based array indexes without echoing rejected path text into instructions. Preserve the retry-summary length cap.
• Keep out-of-assignment claims, conflicting inspected/skipped claims, missing coverage, and incomplete tool evidence blocking approval.

Verification

• Decoder regression tests failed before the repair and passed afterward.
• Structured-retry, missing-coverage, approval-clamp, and tool-evidence checks passed.
• Recorded-output replay normalized 73 entries to exactly 71 assigned claims; the invalid retry remained rejected.
• Verified the actual reviewer assignment after post-selection coverage expansion against the per-reviewer artifacts.
• Lint and build passed with Go 1.26.
• Full local tests passed except the installed-runtime preflight test, which timed out invoking its help command and reproduced on targeted rerun. No adapter behavior changes here.
• All 10 CI checks passed. The first test job hit a helper-startup deadline; a failed-job rerun passed without code changes. Three targeted local runs also passed; the timeout's root cause is not established.

Live outcome

A scoped local binary completed a live review with valid output from all six reviewers. The repository reviewer reported 71 inspected files, zero skipped files, and zero findings. The replay isolates the decoder repair; the live run demonstrates workflow completion rather than sole causation or guaranteed validation of future output. Application-specific identifiers and evidence are retained privately.

For reproduction, compare the recorded prompt's assignment.files with the corresponding per-reviewer slices and initial structured output. Post-selection expansion precedes reviewer validation-scope construction.

Closes #586.

[monit-reviewer]

Automated PR Review

Reviewed commit: 16f7916eb4c1
Profile: open-cli-collective-review - Posting as: monit-reviewer

Summary

Reviewer	Findings
go:implementation-tests	0
structure:repo-health	0

Approval Withheld

No blocking or major findings were reported. Approval is withheld because this run did not cover the change:

• unassigned — ⚠️ unassigned: changed files were not assigned to a selected reviewer
• 1 file inspected by no reviewer:
  • docs/llm-task-artifacts.md

Re-running the same review reproduces this: a reviewer that declined a file declines it again. Closing the gap means bringing these paths into the remit of a reviewer that will read them, or establishing that they need no review.

Reviewer Coverage

• go:implementation-tests — complete (broad); skipped: none; constraints: none
• structure:repo-health — complete (broad); inspected 2 assigned files (4 inspected across reviewers): internal/llm/contracts.go, internal/pipeline/pipeline_test.go; skipped: none; constraints: Review scoped to the two assigned changed files.
• unassigned — ⚠️ unassigned; skipped: docs/llm-task-artifacts.md; changed files were not assigned to a selected reviewer

Inspected files (4)

• internal/llm/adapter_test.go
• internal/llm/contracts.go
• internal/llm/contracts_test.go
• internal/pipeline/pipeline_test.go

0 PR discussion threads considered. 0 summarized; 0 resolved.

---

Completed in 1m 43s | $0.04 | openai-codex/gpt-5.6-terra | cr 0.10.299

Field	Value
Model	openai-codex/gpt-5.6-terra
Reviewers	go:implementation-tests, structure:repo-health
Engine	pi_rpc · openai-codex/gpt-5.6-terra
Reviewed by	cr · monit-reviewer
Duration	1m 43s wall · 2m 41s compute
Cost	$0.04
Tokens	10.7k in / 1.1k out

Per-workstream usage

• orchestrator-selection — openai-codex/gpt-5.6-terra
  • In: 6.2k
  • Out: 311
  • Cache read: 0
  • Cache create: 0
  • Cost: $0.02
  • Duration: 8s
• go:implementation-tests — openai-codex/gpt-5.6-terra
  • In: 2.0k
  • Out: 442
  • Cache read: 27.1k
  • Cache create: 0
  • Cost: $0.01
  • Duration: 1m 21s
• structure:repo-health — openai-codex/gpt-5.6-terra
  • In: 1.2k
  • Out: 297
  • Cache read: 14.8k
  • Cache create: 0
  • Cost: $0.01
  • Duration: 1m 07s
• orchestrator-rollup — openai-codex/gpt-5.6-terra
  • In: 1.2k
  • Out: 38
  • Cache read: 2.8k
  • Cache create: 0
  • Cost: $0.00
  • Duration: 4s

[monit-reviewer]

Automated PR Review

Reviewed commit: 16f7916eb4c1
Profile: open-cli-collective-review - Posting as: monit-reviewer

Summary

Reviewer	Findings
go:implementation-tests	0
structure:repo-health	0

Reviewer Coverage

• go:implementation-tests — complete (constrained); inspected 4 assigned files (5 inspected across reviewers): internal/llm/adapter_test.go, internal/llm/contracts.go, internal/llm/contracts_test.go, internal/pipeline/pipeline_test.go; skipped: none; constraints: Review limited to the assigned changed Go implementation and test files; tests were inspected but not executed.
• structure:repo-health — complete (constrained); inspected 3 assigned files (5 inspected across reviewers): docs/llm-task-artifacts.md, internal/llm/contracts.go, internal/pipeline/pipeline_test.go; skipped: none; constraints: none

Inspected files (5)

• docs/llm-task-artifacts.md
• internal/llm/adapter_test.go
• internal/llm/contracts.go
• internal/llm/contracts_test.go
• internal/pipeline/pipeline_test.go

0 PR discussion threads considered. 0 summarized; 0 resolved.

---

Completed in 1m 51s | $0.03 | openai-codex/gpt-5.6-terra | cr 0.10.299

Field	Value
Model	openai-codex/gpt-5.6-terra
Reviewers	go:implementation-tests, structure:repo-health
Engine	pi_rpc · openai-codex/gpt-5.6-terra
Reviewed by	cr · monit-reviewer
Duration	1m 51s wall · 3m 06s compute
Cost	$0.03
Tokens	7.5k in / 781 out

Per-workstream usage

• go:implementation-tests — openai-codex/gpt-5.6-terra
  • In: 1.9k
  • Out: 402
  • Cache read: 23.0k
  • Cache create: 0
  • Cost: $0.01
  • Duration: 1m 27s
• structure:repo-health — openai-codex/gpt-5.6-terra
  • In: 1.6k
  • Out: 342
  • Cache read: 28.2k
  • Cache create: 0
  • Cost: $0.01
  • Duration: 1m 37s
• orchestrator-rollup — openai-codex/gpt-5.6-terra
  • In: 4.0k
  • Out: 37
  • Cache read: 0
  • Cache create: 0
  • Cost: $0.01
  • Duration: 2s