docs: create RETRO.md, flatten BACKLOG to unbuilt-work-only
RETRO.md never existed, so every shipped/pending-QA item piled up in BACKLOG. Create it (Pending live-QA + Landed sections) and move all shipped code there. Rewrite BACKLOG flat, grouped by actionability (active epic / ready / blocked / won't-build) instead of by spec, one line per item.
This commit is contained in:
+80
-250
@@ -1,269 +1,99 @@
|
|||||||
# CORREX — BACKLOG
|
# CORREX — BACKLOG (live unbuilt work only)
|
||||||
|
|
||||||
> **⚠️ MAINTENANCE RULE — READ FIRST**
|
> **Rules.** This file is *only* outstanding work. Shipped code lives in `RETRO.md` (Pending live-QA →
|
||||||
> **When an item here is resolved, MOVE it out of this file and into `RETRO.md`.**
|
> Landed). When you ship something: move it straight to `RETRO.md` under *Pending live-QA*, don't leave it
|
||||||
> Do not just tick a box and leave it. Cut the entry, paste it into `RETRO.md`
|
> here. After shipping, draft its QA: `/qa-plan <commits|spec>` → `docs/qa/QA-<feature>.md`.
|
||||||
> with the resolving commit hash(es) and the date it landed/was verified. This file
|
> Pointers (commits, spec §) are point-in-time — verify against current code before acting.
|
||||||
> is the *live* outstanding-work list; `RETRO.md` is the archive of what got done.
|
|
||||||
> "Resolved" = built **and** verified (live-QA passed where a QA gate is noted).
|
|
||||||
> Items marked **SHIPPED (pending live-QA)** stay here until their QA gate passes,
|
|
||||||
> then they move.
|
|
||||||
>
|
|
||||||
> **QA RULE — after a feature is done, plan its QA before calling it resolved.**
|
|
||||||
> Run `/qa-plan <commits|spec>` (or copy `docs/qa/TEMPLATE.md` by hand) to produce a
|
|
||||||
> `docs/qa/QA-<feature>.md` with observable-evidence checks. A feature is not "resolved"
|
|
||||||
> until that plan passes live. On PASS → move to `RETRO.md`; on FAIL → refile the misses
|
|
||||||
> here as numbered findings.
|
|
||||||
|
|
||||||
Synthesized 2026-06-14 from the five `docs/plans/2026-06-13-*.md` design specs and
|
|
||||||
session memory. Pointers are commit hashes / spec sections, not gospel — verify
|
|
||||||
against current code before acting (memory is point-in-time).
|
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## A. Observability spec — `docs/plans/2026-06-13-observability-spec.md`
|
## ★ Active epic — Plan-generation pipeline · `docs/plans/plan-pipeline-spec.md`
|
||||||
|
|
||||||
Metrics + CLI + TUI pane and the health backbone are shipped (fe94140, 4f6bfa8,
|
Turns a freestyle prompt into a confirmed `ExecutionPlan` via bounded **multi-candidate generation →
|
||||||
f8fd260) — those are RETRO candidates once live-QA'd. Remaining:
|
deterministic lint → structured critique → tournament → operator selection**. For the founding constraint
|
||||||
|
(local models are weak planners): narrow every model call, deterministic Kotlin joints, operator is the
|
||||||
|
terminal verifier. Generalizes today's degenerate N=1 freestyle planning. Slice 1 (lint) shipped → RETRO.
|
||||||
|
|
||||||
- [~] **§4 LLAMA_SERVER health probe** — **SHIPPED (pending live-QA)** `aaf896d`. Liveness via
|
- [ ] **Slice 2 — multi-candidate round-1 + templates** (§4): `PlanTemplate` library, template-select +
|
||||||
`GET /health` + tokens/sec degradation watch (windowed avg of recorded `InferenceCompletedEvent`s,
|
slot-fill, GBNF-constrained, N₁=3 high-temp → `PlanCandidateGeneratedEvent`.
|
||||||
opt-in via `llama_tps_warn_below`). Plugs into the existing `HealthMonitor`. QA gate in §F →
|
- [ ] **Slice 3 — critique + aggregate** (§6/§7): one-shot GBNF critic per survivor →
|
||||||
`docs/qa/QA-llama-health-probe.md`.
|
`CritiqueFinding{stageId,severity,finding,suggestedChange}` (first consumer of the role-rel §6 schema);
|
||||||
- [~] **§4 EVENT_STORE health probe** — **SHIPPED (pending live-QA)** `7a1362c`. Times a cheap
|
deterministic dedupe/contradiction-drop/severity-sort → `DefectList` → `PlanCritiqueCompletedEvent`.
|
||||||
`lastGlobalSequence()` read as a responsiveness heartbeat (DEGRADED on throw or over
|
- [ ] **Slice 4 — round-2 + tournament + operator selection** (§8/§9): N₂=2 low-temp regen from best
|
||||||
`event_store_latency_warn_ms`); read-only by design (no probe writes into the log). QA gate in §F →
|
survivor + DefectList; deterministic ranking; top-2 → operator at the approval gate (**this is the TUI
|
||||||
`docs/qa/QA-event-store-health-probe.md`.
|
plan-comparison view**). Reject-both → `PlanGenerationFailedEvent`.
|
||||||
- [~] **§4/§3 live health TUI pane** — **SHIPPED (pending live-QA)** `fd67a6c`. `OverlayHealth` (key `H` /
|
- [ ] **Slice 5 — preference-pair logging** (§10): `PreferencePairRecordedEvent` (winner/loser/context),
|
||||||
palette "health checks") mirrors the stats pane: pull-based fetch over WS
|
Bradley–Terry data for the future learned ranker (§12, deferred).
|
||||||
(`GetHealthChecks` → `health.checks`/`HealthReport`), per-subject status with degraded loud, visible
|
- [ ] **Slice 1b — plan file/symbol grounding**: extend the lint to ground the compiled plan's file paths
|
||||||
fallback when disabled. QA gate in §F → `docs/qa/QA-health-tui-pane.md`. **With all three probes +
|
(reuse `BriefReferenceExtractor` + `worldProbe`, record per invariant #9) and symbols (needs the index
|
||||||
this pane, §4 health-checks is feature-complete in code** — retire as a unit once the QA gates pass.
|
from "symbol grounding" below).
|
||||||
- [ ] **§3 tier-2 stats** — full session-completion summary pane polish (basic pane shipped).
|
|
||||||
- 🚫 **§3 tier-3 Prometheus/Grafana export** — spec says "deferred indefinitely". **Do not build.**
|
|
||||||
|
|
||||||
## B. Role reliability spec — `docs/plans/2026-06-13-role-reliability-spec.md`
|
Caveats: `PlanConfirmedEvent` does **not** exist — extend `ExecutionPlanLockedEvent` with a candidate ref.
|
||||||
|
Module home: new `:core:planning`. Spec §11 — never execute a stage, auto-confirm, LLM-aggregate/rank,
|
||||||
|
mutate a candidate in place, or exceed 2 gen rounds / 1 critique round. Defect dedup: pin + version it.
|
||||||
|
|
||||||
§3 analyst keystone (894969d), entity grounding (b050dc4), §2 write-manifest (4e5e4e5),
|
## Ready to build (unblocked)
|
||||||
and §5 reviewer prompt/needs wiring (3467826) are shipped — RETRO candidates. Remaining:
|
|
||||||
|
|
||||||
- [~] **§5 reviewer static-first INFRA** — **SHIPPED (pending live-QA)** `365eb8a`. A stage declares
|
- [ ] **architect contradiction-check** (role-rel §4) — L3 over decision journal + ADRs →
|
||||||
`static_analysis = [commands]`; after it produces its artifact a deterministic harness gate
|
`PossibleContradictionFlag` (display-only in v1).
|
||||||
(`runStaticAnalysis`) runs each command (compiler/detekt/formatters) in the workspace root,
|
- [ ] **symbol grounding** (role-rel §3) — needs a real symbol index (file-path grounding done); also
|
||||||
records a `StaticAnalysisCompletedEvent` (invariant #9; recorded live, folded on replay), and on
|
unblocks plan-lint Slice 1b symbol resolution. (`ctx.py` subprocess vs in-process tree-sitter — the
|
||||||
any non-clean command fails the stage retryably with the output fed back verbatim (§2). Only
|
replay story prefers in-process + versioned.)
|
||||||
static-clean output reaches the reviewer, so its context excludes static findings *mechanically*
|
- [ ] **tier-2 stats polish** (obs §3) — session-completion summary pane (basic pane shipped).
|
||||||
(resolved upstream) — no output-parsing, no shared-findings schema needed. `ProcessStaticAnalysis-
|
- [ ] **full Go↔Kotlin per-event render matrix** (TUI §2) — golden-fixture tests asserting a render for
|
||||||
Runner` is the injected adapter (nullable seam; null → logged no-op). Prompt half was `3467826`.
|
every event type (partially covered today).
|
||||||
QA gate in §F → `docs/qa/QA-static-first-reviewer.md`.
|
- [ ] **approval ergonomics audit** (TUI §3) — single-key y/n/e for T0–T2, mandatory confirm T3+, queued
|
||||||
- ⏸ **§6 `CritiqueFinding` schema** — **build with §C★ Slice 3 (the plan critic), not standalone.** No
|
approvals as a navigable list (never modal-stacked). Verify against current band impl.
|
||||||
live consumer today (assessed 2026-06-14): zero `CritiqueFinding` references anywhere (the old "test
|
- [ ] **render markdown in chat turns** (TUI) — currently ignored.
|
||||||
expectations exist" note was stale — none do), and **no plan critic** exists yet. The one reviewer
|
- [ ] **session list / resume view** (TUI) — no way to see a prior session after server restart + reopen;
|
||||||
that exists emits `review_report` = `verdict` + free-text `notes`; code reads only `verdict`, and the
|
`GET /sessions` data exists server-side.
|
||||||
implementer reads `notes` as prose fine. The schema's first real consumer is the plan critic
|
- [ ] **research follow-ups** (§D): batch fetch-approval at source-list level (not per-URL); dedicated
|
||||||
(plan-pipeline-spec §6) — it lands there. The role-reliability reviewer is the second reuse.
|
`SourceFetched`/`LowQualityExtraction` events (quality+sha currently in `ToolExecutionCompleted`
|
||||||
- ⏸ **§6 `CriticCalibrationProjection` (= addenda A3)** — a further layer on top of `CritiqueFinding`:
|
metadata); dynamic per-session egress allowlist; **web approval client** (third client on the Ktor
|
||||||
correlates critique findings with runtime stage outcomes (`CritiqueOutcomeCorrelatedEvent`). Needs
|
bus, behind WireGuard/Tailscale, never public); fresh-machine runtime install (copy `research.toml` +
|
||||||
runtime critique/outcome history to exist first (spec ordering #5) — i.e. after Slice 3 ships and
|
`prompts/` + `schemas/` + config entries into `~/.config/correx`).
|
||||||
runs. Don't build before there's data for it to fold.
|
- [ ] **low-sev hardening** (§G): turnId prefix collision — `startsWith("repomap:$repoRoot")` collides
|
||||||
- [ ] **§4 architect contradiction-check** — L3 retrieval over decision journal + ADRs →
|
`/repo` vs `/repo2`; fix = trailing `:` in 3 places (ProjectMemoryService write+check,
|
||||||
`PossibleContradictionFlag` (display-only in v1). Unbuilt.
|
L3RepoKnowledgeRetriever). Narration lane lag — drop queued pause narrations once their approval
|
||||||
- [ ] **§3 symbol grounding** — deferred; needs a real symbol index (file-path grounding done).
|
resolves. WorkspaceStateProbe fingerprint — hashes `path|mtime|size` without newline separators
|
||||||
- [ ] **§2 dynamic plan-derived diff manifest** — allowed files from the `impl_plan`
|
(cosmetic, deterministic).
|
||||||
artifact. Future refinement; static per-stage `writes = [globs]` form is shipped.
|
- [ ] **gamedev/Godot** (§I): `.cs` in `RepoMapIndexer` SYMBOL_PATTERNS (if the repo is Godot Mono; `.gd`
|
||||||
- ⚠️ **§4 architect ADR shape** (`alternativesConsidered` required non-empty) —
|
+ `.md` shipped `81a21bf`/`f521ac8`); structural `.tscn`/`.tres` validator (node-tree-aware diff).
|
||||||
**DELIBERATELY NOT TAKEN.** Conflicts with the standing "don't raise alternatives
|
|
||||||
unless real cost/breakage" preference already encoded in `architect.md`. Revisit only
|
|
||||||
with an explicit rationale; do not add by default.
|
|
||||||
|
|
||||||
## C. Plan pipeline addenda — `docs/plans/2026-06-13-plan-pipeline-addenda.md`
|
## Blocked / sequenced (don't start yet)
|
||||||
|
|
||||||
These are amendments to the base **plan-generation pipeline** spec (§C★ below). A1 is shipped
|
- [ ] **`CritiqueFinding` schema** (role-rel §6) — lands with Slice 3 (its first consumer); no consumer
|
||||||
(bcc59d2) — RETRO candidate once live-QA'd. A2 is **superseded** (see below); A3 is the critique
|
until then. **`CriticCalibrationProjection`** (= addenda A3) — after Slice 3 *runs*; needs runtime
|
||||||
calibration layer (tracked under §B §6).
|
critique/outcome history (`CritiqueOutcomeCorrelatedEvent`) to exist first.
|
||||||
|
- [ ] **dynamic plan-derived diff manifest** (role-rel §2) — allowed files from the `impl_plan` artifact;
|
||||||
|
refinement over the shipped static per-stage `writes=[globs]`.
|
||||||
|
- [ ] **§5.2 command-card LLM annotation layer** (TUI) — deferred by spec until layer 1 is used.
|
||||||
|
- [ ] **idea board → profile promotion** — deferred hook; auto-captured ideas promote into
|
||||||
|
`.correx/project.toml`.
|
||||||
|
- [ ] **freestyle follow-ups** (§H): graph re-routing by preemptive steering (mid-execution input can't
|
||||||
|
re-route the compiled graph yet); child-session `SubagentRunner` (seam exists; sequential only);
|
||||||
|
post-lock `ApprovalDecisionResolvedEvent.userSteering` → L0 promotion.
|
||||||
|
- [ ] **scene editing + event-log fine-tuning dataset** (§I, far future) — ⚠️ fine-tuning is on CLAUDE.md's
|
||||||
|
not-implemented list; needs an explicit epic + operator de-listing, not an incidental add.
|
||||||
|
|
||||||
- [~] **A1 brief echo-back gate** — **SHIPPED (pending live-QA)** `bcc59d2`. New `brief_echo` stage
|
## Won't build / deferred-by-design (don't re-litigate)
|
||||||
before the planner in `role_pipeline`: the model restates the analyst brief as a structured
|
|
||||||
artifact; a deterministic gate (`checkBriefEcho`, opt-in `brief_echo=true`) diffs the restatement
|
|
||||||
vs the brief — dropped requirements (Jaccard coverage < 0.34) or hallucinated files →
|
|
||||||
`BriefEchoMismatchEvent` + retryable stage failure, so a misread brief never reaches plan
|
|
||||||
generation. Pure replay-safe diff (`BriefEchoDiff`); symbols recorded but non-blocking in v1.
|
|
||||||
QA gate in §F → `docs/qa/QA-brief-echo-gate.md`. `freestyle_planning` wiring is a follow-up.
|
|
||||||
- 🚫 **A2 stage-level plan checkpointing** — **SUPERSEDED, do not build.** The spec predates the
|
|
||||||
machinery that now carries this weight. In the current design the "confirmed plan" is the
|
|
||||||
freestyle `execution_plan` → `ExecutionPlanCompiler` → `WorkflowGraph`, and per-stage
|
|
||||||
reconciliation against the plan's produces-slots *already happens* in phase-2 execution:
|
|
||||||
`verifyProduces` checks every `stage.produces` slot (sourced from the plan JSON) against
|
|
||||||
`ArtifactCreatedEvent`s and fails retryably → surfaces on exhaustion; `ManifestContainmentRule`
|
|
||||||
blocks out-of-plan writes; the validation pipeline checks content vs kind schema. The only net-new
|
|
||||||
bits A2 adds are a positive `StageCheckpointPassedEvent` + terminal-vs-retryable halt — and the
|
|
||||||
sole consumer of the former is A3 calibration, which is itself ordering-blocked. Revisit only if a
|
|
||||||
real consumer for a positive per-stage checkpoint event appears. (Assessed 2026-06-14.)
|
|
||||||
- [ ] **A3 critique calibration tracking** — **= §B §6 `CriticCalibrationProjection`** (build once, two
|
|
||||||
consumers). Tracked under §B §6; needs runtime critique/outcome history first (spec ordering #5).
|
|
||||||
Not duplicated here.
|
|
||||||
|
|
||||||
## C★. Plan-generation pipeline epic — `docs/plans/plan-pipeline-spec.md` (base spec)
|
- 🚫 **obs tier-3 Prometheus/Grafana export** — spec says "deferred indefinitely."
|
||||||
|
- 🚫 **plan checkpointing** (addenda A2) — superseded: `verifyProduces` + `ManifestContainmentRule` +
|
||||||
The foundation the §C addenda amend. Turns a freestyle prompt into a confirmed `ExecutionPlan` via
|
validation already reconcile execution vs the compiled plan; only net-new bit fed a consumer (A3) that
|
||||||
**bounded multi-candidate generation + deterministic lint + structured critique + tournament + operator
|
isn't ready. Revisit only if a positive per-stage checkpoint event gains a real consumer.
|
||||||
selection** — built for the project's founding constraint (local models are weak planners): narrow every
|
- 🚫 **research non-responsibilities** — no headless browser, no LLM-based extraction, no public approval
|
||||||
model call, keep every joint deterministic Kotlin, make the *operator* the terminal verifier. Replaces the
|
endpoint.
|
||||||
single-plan freestyle planning phase.
|
- ⚠️ **architect ADR shape** (`alternativesConsidered` required non-empty, role-rel §4) — conflicts with
|
||||||
|
the standing "don't raise alternatives unless real cost/breakage" preference in `architect.md`.
|
||||||
**Build state:** freestyle already ships a **degenerate N=1 version** (analyst brief → one
|
- ⚠️ **`PreemptRedirectEvent` producer** (QA bug #6) — B3 hard re-route unreachable from the TUI; skipped
|
||||||
`execution_plan` → `ExecutionPlanCompiler` → operator `requestPlanApproval` → `ExecutionPlanLockedEvent`).
|
by design. Build only if the hard-reroute path is actually wanted.
|
||||||
Substrate in place: `GbnfGrammarConverter`, repo-map, L3 retrieval, CAS, approval gate, and a **partial
|
|
||||||
lint** inside `ExecutionPlanCompiler` (reachability, unknown-kind, edge field-condition). The pipeline
|
|
||||||
generalizes this to N candidates. ⚠️ Spec says `PlanConfirmedEvent` is "existing" — it is **not**; the
|
|
||||||
built analog is `ExecutionPlanLockedEvent` (extend it with a candidate ref; don't add a parallel event).
|
|
||||||
|
|
||||||
Slices (spec §, in build order):
|
|
||||||
|
|
||||||
- [~] **Slice 1 — §5 deterministic lint** — **SHIPPED (pending live-QA)** `68136e7`. Pure-Kotlin
|
|
||||||
`PlanLinter` over the compiled `WorkflowGraph`, run in `FreestyleDriver` before lock; records
|
|
||||||
`PlanLintCompletedEvent` (pure function of the recorded plan → replay-safe, no env observation),
|
|
||||||
and a hard failure → `ExecutionPlanRejectedEvent(source="lint")` before the operator is asked or
|
|
||||||
the plan locks. **Hard:** `unproduced_need` (real gap — the freestyle compiler never checked needs),
|
|
||||||
`trap_state` (no path to terminal; uses terminal-reachability so verdict-gated review loops pass).
|
|
||||||
**Soft (non-blocking):** `stage_count`, `fan_out`, `empty_brief`, `duplicate_brief`. QA gate in §F →
|
|
||||||
`docs/qa/QA-plan-lint.md`. **Deferred to Slice 1b:** file-path grounding + symbol resolution (env;
|
|
||||||
symbols need an index, §B §3), token-budget/ADR-bypass checks, a dedicated `:core:planning` module.
|
|
||||||
- [ ] **Slice 2 — §4 multi-candidate round-1 + templates.** `PlanTemplate` library, template-select +
|
|
||||||
slot-fill, GBNF-constrained, N₁=3 high-temp. `PlanCandidateGeneratedEvent`.
|
|
||||||
- [ ] **Slice 3 — §6 critique + §7 aggregate.** One-shot GBNF critic per survivor →
|
|
||||||
`CritiqueFinding {stageId, severity, finding, suggestedChange}` (= §B §6 schema, first consumer);
|
|
||||||
deterministic dedupe/contradiction-drop/severity-sort → `DefectList`. `PlanCritiqueCompletedEvent`.
|
|
||||||
- [ ] **Slice 4 — §8 round-2 + §9 tournament + operator selection.** N₂=2 low-temp regen from best
|
|
||||||
survivor + DefectList; deterministic ranking; **top-2 → operator** at the approval gate
|
|
||||||
(**= §E §3/§4 plan comparison view**, the terminal UI). Reject-both → `PlanGenerationFailedEvent`.
|
|
||||||
- [ ] **Slice 5 — §10 preference-pair logging.** `PreferencePairRecordedEvent` (winner/loser/context)
|
|
||||||
falls out of selection; Bradley–Terry data for the future learned ranker (§12, deferred).
|
|
||||||
|
|
||||||
Open questions to resolve while building (spec §13): module home (recommend new `:core:planning`);
|
|
||||||
symbol resolution `ctx.py` subprocess vs in-process tree-sitter (subprocess = env observation → record,
|
|
||||||
never re-run on replay); defect-string dedup algorithm (pin it, version it). ⚠️ Spec lists "graph contains
|
|
||||||
cycles" as a hard failure, but freestyle plans legitimately contain verdict-gated review loops
|
|
||||||
(implementer⇄reviewer) — Slice 1 must only fail cycles **without** an exit edge, not all cycles.
|
|
||||||
|
|
||||||
🚫 Non-responsibilities (spec §11): the pipeline never executes a stage, never auto-confirms, never uses an
|
|
||||||
LLM to aggregate/rank, never mutates a candidate in place, never exceeds 2 gen rounds / 1 critique round.
|
|
||||||
|
|
||||||
## D. Research workflow spec — `docs/plans/2026-06-13-research-workflow-spec.md`
|
|
||||||
|
|
||||||
Core workflow is **SHIPPED end-to-end, ON by default** (fb1d970..378ee39): extractor +
|
|
||||||
web_search (T1) + web_fetch (T2) in `:infrastructure:tools`, `research.toml`
|
|
||||||
(decompose→gather→report), schemas, prompts. Remaining:
|
|
||||||
|
|
||||||
- [ ] **Live-QA the full run** — could not validate in-session (no SearXNG/network in sandbox).
|
|
||||||
Needs SearXNG running; exercise triage→fetch-approval→report→artifact viewer.
|
|
||||||
- [ ] **§6 web approval client** — the one larger unbuilt piece. Third client on the existing
|
|
||||||
Ktor REST+WS bus: approval cards + event strip + session list. Behind WireGuard/Tailscale
|
|
||||||
only, never public. Independent track (spec ordering #5).
|
|
||||||
- [ ] **§3 batch fetch-approval at source-list level** — currently per-fetch T2; operator
|
|
||||||
should approve the source list once, not each URL.
|
|
||||||
- [ ] **Dedicated `SourceFetched` / `LowQualityExtraction` events** — quality +
|
|
||||||
content_sha256 currently ride inside `ToolExecutionCompletedEvent` metadata only.
|
|
||||||
- [ ] **Dynamic per-session egress allowlist** — currently static `networkAllowedHosts` + T2 gate.
|
|
||||||
- [ ] **Fresh-machine runtime install** — copy `research.toml` + `prompts/` + `schemas/` and
|
|
||||||
the `[[artifacts]]` / `[tools.research]` config entries into `~/.config/correx`
|
|
||||||
(already done on this box; repo source is `examples/workflows/` + `docs/schemas/`).
|
|
||||||
- 🚫 No headless browser, no LLM-based extraction, no public approval endpoint (non-responsibilities).
|
|
||||||
|
|
||||||
## E. TUI requirements spec — `docs/plans/2026-06-13-tui-requirements-spec.md`
|
|
||||||
|
|
||||||
§2 last-event clock + unknown-event fallback (8b896b5) and §5.1 deterministic command-parse
|
|
||||||
card (65df3f4) are shipped — RETRO candidates. Remaining:
|
|
||||||
|
|
||||||
- [ ] **§2 full Go↔Kotlin per-event-type render matrix** — golden-fixture tests asserting a
|
|
||||||
defined render for every event type (last §2 bullet; partially covered today).
|
|
||||||
- [ ] **§3/§4 plan comparison view** — **= §C★ Slice 4** (the operator-selection terminal UI of the
|
|
||||||
plan-generation pipeline, spec §9): top-2 candidates side-by-side with lint/critique findings
|
|
||||||
rendered inline. Blocked until the pipeline produces candidates; tracked under §C★.
|
|
||||||
- [ ] **§3 approval ergonomics audit** — single-key y/n/e for T0–T2, mandatory confirm T3+,
|
|
||||||
queued-approval navigable list (never modal-stacked). Verify against current band impl.
|
|
||||||
- [ ] **Render markdown in chat turns** (QA feature note b) — TUI currently ignores md.
|
|
||||||
- [ ] **Session list / resume view** (QA feature note c) — after server restart + TUI reopen
|
|
||||||
there's no way to see a prior session or its state; `GET /sessions` data exists server-side.
|
|
||||||
- [ ] **Idea board → profile promotion** — deferred hook; auto-captured ideas promote into the
|
|
||||||
curated `.correx/project.toml` profile. (Board itself shipped 3ac0a14..02e963d.)
|
|
||||||
- ⏸ **§5.2 command-card LLM annotation layer** — deferred by spec ("ship layer 1, live with it,
|
|
||||||
then decide whether layer 2 earns its place"). Build only after using layer 1.
|
|
||||||
|
|
||||||
## F. In-flight QA gates (move to RETRO when each passes)
|
|
||||||
|
|
||||||
These are SHIPPED in code but prompt-/server-/network-dependent and not yet live-verified:
|
|
||||||
|
|
||||||
- [ ] **Epic 15 live-QA gate** — server up → `correx events` / `correx replay` on a real
|
|
||||||
session, confirm MDC sessionIds in logs. (Code complete a7d5211..75703ec.)
|
|
||||||
- [ ] **Idea board live-QA** — needs a real router model to emit the `{"ideas":[…]}` block.
|
|
||||||
- [ ] **Clarification loop + workflow-propose panel live-QA** — both prompt-dependent (need a
|
|
||||||
real router/analyst model to emit the structured json blocks).
|
|
||||||
- [ ] **Research workflow live-QA** — see §D.
|
|
||||||
- [ ] **LLAMA_SERVER health probe live-QA** — `aaf896d`; needs a real llama-server to ping.
|
|
||||||
Plan: `docs/qa/QA-llama-health-probe.md` (liveness up/down/restore, non-2xx, tps degrade,
|
|
||||||
restart hysteresis, replay independence).
|
|
||||||
- [ ] **EVENT_STORE health probe live-QA** — `7a1362c`. Plan: `docs/qa/QA-event-store-health-probe.md`
|
|
||||||
(responsive→HEALTHY, no-log-pollution, slow/throw→DEGRADED, restore hysteresis, replay independence).
|
|
||||||
- [ ] **Health TUI pane live-QA** — `fd67a6c`. Plan: `docs/qa/QA-health-tui-pane.md` (`H` opens/fetches,
|
|
||||||
matches `correx health`, degraded loud, disabled fallback, resize, live wire-contract values).
|
|
||||||
- [ ] **Brief echo-back gate live-QA** — `bcc59d2`; needs a real planner-capable model + runtime install
|
|
||||||
(schema/prompt/artifacts block). Plan: `docs/qa/QA-brief-echo-gate.md` (faithful echo→planner runs,
|
|
||||||
dropped requirement→`BriefEchoMismatchEvent`+retryable fail, hallucinated file flagged, symbols
|
|
||||||
non-blocking, replay recomputes identically, non-opted pipeline is a no-op).
|
|
||||||
- [ ] **Static-first reviewer gate live-QA** — `365eb8a`; needs a real implementer-capable model + a
|
|
||||||
workspace whose configured `static_analysis` commands can be made to pass/fail on demand (and the
|
|
||||||
gate uncommented in the copied `role_pipeline.toml`). Plan: `docs/qa/QA-static-first-reviewer.md`
|
|
||||||
(clean→reviewer runs, non-clean→`StaticAnalysisCompleted`+retryable fail w/ output fed back,
|
|
||||||
gate-OFF absence check, no-runner no-op WARN, replay reads recorded findings without re-running).
|
|
||||||
- [ ] **Plan-lint (§C★ Slice 1) live-QA** — `68136e7`; logic is unit-covered, so this is confirmatory:
|
|
||||||
needs a freestyle run reaching the plan-lock gate (+ a crafted bad plan to force the reject path).
|
|
||||||
Plan: `docs/qa/QA-plan-lint.md` (unproduced_need/trap_state → `PlanLintCompleted`+`ExecutionPlan-
|
|
||||||
Rejected(source=lint)`+no lock; review-loop NOT trapped; soft findings non-blocking; replay stable).
|
|
||||||
- [ ] **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).
|
|
||||||
|
|
||||||
## G. Low-severity hardening
|
|
||||||
|
|
||||||
- [ ] **turnId prefix collision** — `startsWith("repomap:$repoRoot")` can collide where one
|
|
||||||
root path prefixes another (`/repo` vs `/repo2`). Fix = trailing `:` delimiter in 3
|
|
||||||
places (ProjectMemoryService write+check, L3RepoKnowledgeRetriever filter).
|
|
||||||
- [ ] **Narration lane lag** — stale pause-trigger narrations blend with current workflow
|
|
||||||
status; drop queued pause narrations once their approval resolves.
|
|
||||||
- [ ] **WorkspaceStateProbe fingerprint** — hashes `path|mtime|size` without newline separators
|
|
||||||
though the docstring says "lines". Internally consistent/deterministic; cosmetic.
|
|
||||||
- ⚠️ **`PreemptRedirectEvent` has no producer** (QA bug #6) — B3 hard re-route is unreachable
|
|
||||||
from the TUI. Intended flow: steering → router proposes → operator confirms. Skipped by
|
|
||||||
design; build only if the hard-reroute path is actually wanted.
|
|
||||||
|
|
||||||
## H. Freestyle mode — deferred follow-ups (epic COMPLETE, B4 PASSED)
|
|
||||||
|
|
||||||
- [ ] **Graph re-routing by preemptive steering** — only priority-directive surfacing is built
|
|
||||||
today; mid-execution input cannot re-route the compiled graph.
|
|
||||||
- [ ] **Child-session `SubagentRunner` impl** — seam exists (`InSessionSubagentRunner`);
|
|
||||||
child-session is the intended drop-in swap. Sequential only (no-parallel-agents invariant).
|
|
||||||
- [ ] **Post-lock `ApprovalDecisionResolvedEvent.userSteering` → L0 promotion** — currently
|
|
||||||
stays L2; out of freestyle's exercised path (gate is pre-lock).
|
|
||||||
|
|
||||||
## I. Gamedev / Godot readiness (operator intent)
|
|
||||||
|
|
||||||
- [ ] **`.cs` in `RepoMapIndexer` SYMBOL_PATTERNS** — add if the gamedev repo is Godot Mono
|
|
||||||
(`.gd` and `.md` headings already shipped: 81a21bf, f521ac8).
|
|
||||||
- [ ] **Structural `.tscn` / `.tres` validator** — parse scene format, node-tree-aware diff
|
|
||||||
preview. Prerequisite validation layer before any scene editing.
|
|
||||||
- [ ] **(far future) Scene editing behind approval+diff** + derive a fine-tuning dataset from
|
|
||||||
the event log. ⚠️ Fine-tuning is on CLAUDE.md's intentionally-NOT-implemented list — needs
|
|
||||||
an explicit epic + operator de-listing, not an incidental add.
|
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## Ops notes (not backlog items, but bite repeatedly)
|
## Ops notes (bite repeatedly)
|
||||||
|
|
||||||
- Config copies of `examples/*` in `~/.config/correx` go **stale silently** — e.g. a missing
|
- Config copies of `examples/*` in `~/.config/correx` go **stale silently** (e.g. a missing
|
||||||
`inject_artifact_kinds` in a copied workflow TOML caused invented artifact kinds. Re-sync
|
`inject_artifact_kinds` → invented artifact kinds). Re-sync after editing repo examples.
|
||||||
after editing the repo examples.
|
|
||||||
- **Do not rebuild jars while the server JVM is running** — lazy classloading breaks
|
- **Do not rebuild jars while the server JVM is running** — lazy classloading breaks
|
||||||
(`NoClassDefFoundError`). Stop the server first.
|
(`NoClassDefFoundError`). Stop the server first.
|
||||||
|
|||||||
@@ -0,0 +1,57 @@
|
|||||||
|
# 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`.
|
||||||
Reference in New Issue
Block a user