correx/RETRO.md

CORREX — RETRO (archive of what got done)

Counterpart to BACKLOG.md (live unbuilt work only). Two states here: Pending live-QA = shipped in code, awaiting live verification (has a docs/qa/QA-*.md plan or a stated gate). Landed = built and verified, or no QA gate needed. Flow: ship a feature → move it straight here under Pending live-QA (do NOT leave it in BACKLOG) → when its QA plan passes, move it down to Landed with the run date. On QA FAIL, refile the misses into BACKLOG as numbered findings.

---

Pending live-QA

Shipped in code, prompt-/server-/network-dependent, not yet live-verified. Each names commit(s) + the evidence to check.

• §4 health-checks (3 probes + TUI pane — retire as one unit) — llama-server probe aaf896d (docs/qa/QA-llama-health-probe.md), event-store probe 7a1362c (docs/qa/QA-event-store-health-probe.md), live health TUI pane fd67a6c over the backbone f8fd260 (docs/qa/QA-health-tui-pane.md). Needs a real llama-server + server up.
• Static-first reviewer gate — 365eb8a (prompt half 3467826). docs/qa/QA-static-first-reviewer.md: clean→reviewer runs, non-clean→StaticAnalysisCompleted+retryable fail w/ output fed back, gate-OFF absence, no-runner WARN, replay reads recorded findings. Needs an implementer-capable model + a workspace whose static_analysis commands can be made to pass/fail.
• Brief echo-back gate — bcc59d2. docs/qa/QA-brief-echo-gate.md: faithful echo→planner runs, dropped requirement→BriefEchoMismatchEvent+retryable fail, hallucinated file flagged, symbols non-blocking, replay stable, non-opted pipeline is a no-op. Needs a planner-capable model + runtime install (schema/prompt/artifacts block).
• Plan-lint (plan-pipeline §5, Slice 1) — 68136e7. docs/qa/QA-plan-lint.md: unproduced_need / trap_state → PlanLintCompleted + ExecutionPlanRejected(source=lint) + no lock; review-loop NOT trapped; soft findings non-blocking; replay stable. Logic is unit-covered → confirmatory pass.
• Epic 15 — observability/replay tooling — a7d5211..75703ec. Gate: server up → correx events / correx replay on a real session, confirm MDC sessionIds in logs.
• Research workflow (core, ON by default) — fb1d970..378ee39. Needs SearXNG + network: exercise triage→fetch-approval→report→artifact viewer. (Unbuilt follow-ups stay in BACKLOG.)
• Idea board — 3ac0a14..02e963d. Needs a real router model to emit the {"ideas":[…]} block.
• Clarification loop + workflow-propose panel — prompt-dependent (need a real router/analyst model to emit the structured JSON blocks). clarcard.go / proposecard.go.
• TUI kernel-steering + AMD gauge — fresh live-QA: approve+note actually revising the same stage's output; AMD VRAM/RAM gauge on the real box.
• Unit-tested-only fixes (not live-verified) — 1a7eb05 (verdict-edge rejection), e195c79 (stale-parking OrchestrationPaused ABANDONED_STALE), df3ee0b (bare-id narration model match).

Landed (built & verified, or no QA gate)

• Freestyle mode epic — 63e5bce..4d1b4ff. Two-phase planning→execution; live-QA gate B4 PASSED 2026-06-12. (Deferred follow-ups live in BACKLOG.)
• Router triage + repo-knowledge epic — ac458d8..1976d8a. Live QA PASSED 2026-06-11 (all 7 checks after fixes 07819ec/50602b0).
• Single-project consistency epic — fba2bbb..ed0dca8. T1–T10 (phantom fix, plan-rejected event+gate, ProjectProfile L0, retry/critic feedback, architect vocabulary).
• Observability §3 — metrics + correx stats + TUI stats pane — fe94140, 4f6bfa8.
• Role-reliability shipped halves — §3 analyst keystone 894969d, §3 entity grounding (ground_references → BriefGroundingCheckedEvent, FS probe) b050dc4, §2 write-manifest (ManifestContainmentRule) 4e5e4e5, §5 reviewer narrow-question prompt/needs 3467826.
• TUI requirements shipped halves — §2 last-event clock + unknown-event fallback 8b896b5, §5.1 deterministic command-approval parse card 65df3f4.

---

2026-06-26 — Merged feat/backlog-burndown into master

master had advanced 16 commits past where feat/backlog-burndown branched, and the two had independently built four of the same features. The merge kept master's implementation for each overlap (more complete / wired to production / more robust) and dropped the feature branch's parallel constellation:

• llama-server health probe — kept master's event-store-backed tokens/sec probe; dropped the branch's LlamaLivenessClient/HttpLlamaLivenessClient (liveness-only, throughput unwired).
• event-store probe — kept master's EventStoreHealthProbe; dropped the branch's EventStoreLatencyProbe.
• brief echo-back gate — kept master's BriefEchoDiff (Jaccard token-overlap, tolerant of rewording); dropped the branch's BriefEchoComparator/BriefEchoExtractor (exact set-diff).
• static-first reviewer — kept master's command/exit-code gate (StaticAnalysisRunner + ProcessStaticAnalysisRunner, production-wired); dropped the branch's structured-finding static_check stage (StaticCheckStageExecutor, StaticFinding, ContextFeedback exclusion) which was a no-op pending a production runner. Its structured-findings model is filed as a follow-up in BACKLOG so it isn't lost.

Net-new feature-branch work brought in and kept (master had none of these):

• Native task tracking — task aggregate + agent tools (task_create/task_update/ task_context/task_search wired into analyst/implementer/reviewer), dependency-aware work graph (blockers/ready), claim/cite/scope/stale-write gates, task_decompose, REST surface, CLI, git-driven status, markdown export, and the TUI task board (OverlayTasks, T key).
• Critique-outcome producer (role-rel §6) — CritiqueOutcomeCorrelator + CritiqueFindingsRecordedEvent/CritiqueOutcomeCorrelatedEvent + the per-model calibration chain (master had explicitly deferred §6). Dormant until the reviewer emits structured findings (live-QA).
• Stage-level plan checkpointing (C-A2) — emitStageCheckpoint folded into runPostStageGates.
• L0 standing context — CLAUDE.md / AGENTS.md injected as agent-instruction context entries.
• Cross-session grants + TUI — PROJECT/GLOBAL grant scopes + revoke, grant viewer, @ file picker, session resume browser (OverlaySessions, R key).