@azure-id/orc 0.56.1 → 1.0.0

package/templates/skills/orc/config.md

@@ -1,389 +1,137 @@
-# ORC — Config
-
-This file is the **shipped defaults**. Central knobs the orchestrator reads at
-run start. Override any value for a single run without editing the file.
-
-## Config resolution (defaults ← override file)
-
-At run start, resolve **each key independently** as: **default (this file), then
-the user override on top.** The override lives at `.claude/orc.config.yaml`
-(project `.claude/` root), holds ONLY the keys the user changed, and is written
-exclusively by the **`orc config`** CLI. It sits OUTSIDE `templates/`, so `orc
-update` never clobbers it.
-
-Per-key means: a key present in `orc.config.yaml` uses the override value; a key
-NOT present there falls back to this file's default — independently, key by key.
-Example: if the override contains only `max_wave_tasks: 5`, then `max_wave_tasks`
-is 5 and every other key (`batch_pause_every`, `rubric_bands`, `max_scouts`,
-`default_analysis_depth`, …) still comes from this file's defaults. If the
-override file is absent entirely, use these defaults unchanged. A per-run inline
-override still wins over both.
-
-> Config editing is a CLI concern, not a slash command — it's pure file I/O, so
-> it runs deterministically with zero model tokens. Users run **`orc config`**
-> (interactive menu) or `orc config set <key> <value>` in their terminal; this
-> skill only READS the resolved values at run start.
-
-```yaml
-# --- Wave grouping ---
-max_wave_tasks: 3          # max parallel tasks per wave (hard cap; overflow → next wave).
-                           # Waves are computed for EVERY run (sequential too) —
-                           # dispatch style is intra-wave concurrency only.
-
-# --- Batch pausing ---
-batch_pause_every: 2       # waves between MANDATORY stop-and-continue pauses.
-                           # After wave W, if W % N == 0 AND a later wave exists,
-                           # the stop is a HARD gate (not orchestrator judgment) —
-                           # see references/stop-and-resume.md. The exact schedule
-                           # is confirmed at intake (Phase 2) and stored as
-                           # pause_schedule in the checkpoint.
-
-# --- Rubric width (the "metrix") ---
-rubric_bands: 5            # how many scoring bands the rubric REPORTS. Range 2–8.
-                           # Granularity only — it no longer selects a preset.
-                           # The score→model mapping is the SINGLE 8-band table
-                           # below, used regardless of this value.
-
-# --- Analysis (System Analyst) ---
-max_scouts: 3              # max parallel read-only code scouts in DEEP analysis mode
-default_analysis_depth: standard   # standard | deep — depth gate default (run still confirms)
-
-# --- Test authoring (opt-in Phase 6.5; ORC writes test cases, never runs them) ---
-generate_tests: false      # author test cases before ship? (run confirms at intake)
-
-# --- Code-pattern findings (make executors match the project's house style) ---
-pattern_findings: ask      # ask | on | off — on an FE/BE cache miss during /orc:
-                           #   ask → P0 prompt (learn via orc-pattern, or agnostic)
-                           #   on  → auto-codify on miss, no prompt
-                           #   off → always agnostic (invariants only), never ask
-orc_wiki_pattern_findings: false  # orc-wiki also codifies ALL detected langs during
-                                  #   its scan (rides under the wiki's scan-consent)
-
-# --- Repair memory (gotchas — what this project has already gotten wrong) ---
-gotchas: on                # on | off — record a gotcha when a repair loop goes
-                           #   red → green, and inject the SCOPE-MATCHING ones
-                           #   into executor slices. Lives at
-                           #   .claude/orc/gotchas.md — outside templates/, never
-                           #   in the install manifest, so update/prune can never
-                           #   touch it. NEVER injected unfiltered.
-gotchas_max: 40            # live entries before the lowest-value tail is archived
-                           #   to gotchas-archive.md (archived, never deleted).
-
-# --- Mock example + drift recovery (Phase 6.7 — implementation lanes only) ---
-mock_example: ask          # ask | on | off — post-verify mocked runnable example
-                           #   (mock-examples/<change-slug>/ at project root; NEVER
-                           #   committed — ship never stages it, no .gitignore edit):
-                           #   ask → MANDATORY offer after a green verify/smoke gate
-                           #   on  → always build; off → never. Drift answer →
-                           #   DRIFT-FROM recovery (_shared/drift-recovery.md, cap 2).
-
-# --- TDD anchor (plan-time acceptance tests; full orc + ultra ALWAYS on) ---
-# SCOPED (v0.41.0): each tdd_spec entry carries a `disposition` derived from the
-# planner's facets — new-surface | behavior-change get tests; covered-by-existing
-# (cites an existing test) and no-behavior (constants, translation strings, docs,
-# config) get NONE; no-runner is the whole-run exemption. A task with a cited
-# facets.risk[] can NEVER be scoped out. There is no key for this: a switch here
-# would just restore the tautological tests it removes.
-tdd_loop_max: 3            # max implement→test→repair iterations per task in the
-                           #   TDD gate; cap hit → STOP SEQUENCE + honest red report.
-                           #   Lane policy (fixed, not configurable): full orc +
-                           #   ultra always on · orc-mini ONE intake question ·
-                           #   orc-fast off (no planner) · orc-diy `tdd` flow key ·
-                           #   standalone /orc-plan ON (a saved plan's only consumers
-                           #   are the TDD-always build lanes, so a plan with no
-                           #   tdd_spec is unusable by the lane that runs it).
-
-# --- Stacked PRs (Phase 8 gate; full /orc + /orc-ultra only) ---
-stacked_pr: ask             # ask | on | off — what happens when the change is too
-                            #   big for one PR (threshold below):
-                            #   ask → ONE P0 question (stack it, or one regular PR)
-                            #   on  → take "yes" without asking
-                            #   off → never offer; always one regular PR
-                            #   Never fires in orc-mini / orc-fast (the fast lane
-                            #   never stops the chat) or orc-diy (compile-owned).
-stacked_pr_loc: 1000        # change LoC (additions+deletions, exclusions applied)
-                            #   >= this → stack candidate. SAME number is the
-                            #   per-layer LoC ceiling: a change that cannot fit in
-                            #   one layer's budget is what is worth stacking.
-stacked_pr_files: 20        # changed files >= this → stack candidate; also the
-                            #   per-layer hard max (soft target = half of it).
-stacked_pr_max_layers: 6    # soft layer cap: <= cap proceed · cap+1..cap+2 warn +
-                            #   explicit override · beyond → STOP (multiple stacks
-                            #   or a phased release). N layers = N full CI runs.
-
-# --- Security pass (opt-in Phase 5.5; OFF by default) ---
-security_review: off       # off | ask | on — fires only on runs where a task
-                           #   scored ≥ 70 (the existing risk floor):
-                           #   off → skip silently (default)
-                           #   ask → one prompt after review, user decides
-                           #   on  → dispatch the security pass without asking
-
-# --- Run cost budget (opt-in hard stop; OFF by default) ---
-run_budget_dispatches: 0   # 0 = off. Above 0, the Phase-1 `forecast:` block
-                           #   estimates how many subagents this run will
-                           #   dispatch; exceeding this number STOPS the run
-                           #   before wave 1 — a hard gate with the batch
-                           #   pause's discipline, never a hint — and offers
-                           #   proceed / a cheaper lane / re-plan smaller.
-
-# --- Opus-5-only dispatch (HARD-GATED, FORCING — default off) ---
-opus5_only: false          # true → EVERY dispatched role resolves to a claude-opus-5
-                           #   agent, effort as the only cost dial. Outranks BOTH
-                           #   rubric_bands_override and the whole fable5_* block.
-                           #   Never forced: the Haiku trace writer, orc-diy (compile-
-                           #   owned). Needs an Opus 5 main session or every dispatch
-                           #   downgrades. See _shared/opus5-only.md.
-
-# --- Fable 5 role override (HARD-GATED — nothing changes unless enabled) ---
-#     (entirely INERT while opus5_only: true)
-fable5_enabled: false      # master gate. false = inert (this whole block does nothing).
-fable5_effort: medium      # medium | high | xhigh | max — effort for the Fable 5 role agents.
-                           #   The `orc config set fable5_effort` CLI rewrites the effort:
-                           #   line in the installed orc-<role>-fable-5 agents.
-fable5_roles: []           # subset of [analyze, plan, advisor, judge, review]. Each listed
-                           #   role dispatches its orc-<role>-fable-5 variant instead of the
-                           #   default. advisor/judge are ultra-lane only. Empty = no effect.
-
-# --- Artifact locations (internal by default) ---
-run_dir: .claude/orc/run                  # run folders (checkpoint, state-of-play,
-                                          #   intent-spec). Lives OUTSIDE the payload
-                                          #   trees `orc update` replaces, so an
-                                          #   update/doctor --fix can never destroy a
-                                          #   mid-run checkpoint. Pre-0.34.1 state at
-                                          #   .claude/skills/orc/run/ is migrated once.
-analyzer_dir: .claude/skills/orc/analyzer
-planner_dir:  .claude/skills/orc/planner
-report_out_dir: analyst_report            # project-root copy target on report-only
-
-orchestrator_model: claude-opus-4-8       # main session; high effort (never downgraded)
-
-# --- Retro delivery (/orc-retro files its report upstream; PR preferred, issue fallback) ---
-retro_repo: azure-id/orc      # GitHub owner/repo that receives retro reports.
-                              # /orc-retro REQUIRES a delivery channel (authed gh
-                              # CLI or a GitHub MCP) and refuses to run without one.
-
-# --- Behavior trace logging (PERMANENT — always on, not a toggle) ---
-# Every ORC run writes a persistent behavior trace; there is no on/off key.
-log_dir: .claude/orc/logs     # persistent trace folder — NEVER deleted on completion
-
-# --- Wiki freshness (COVERAGE-RELATIVE, computed on read by `orc wiki status`) ---
-wiki_fresh_max: 10            # per-doc commit distance < this → FRESH (silent)
-wiki_aging_max: 30            # distance ≤ this → AGING (notice); beyond → STALE
-wiki_refresh_ask_tasks: 3     # post-ship refresh ask fires when tasks ≥ this…
-wiki_refresh_ask_files: 10    # …or the run's touched files exceed this (full/ultra lanes)
-
-# --- Cross-repo crosslink snapshot freshness (Signal-B; DAY-based, computed on read) ---
-crosslink_fresh_days: 10      # days since sync ≤ this → FRESH cross-repo hint
-crosslink_aging_days: 15      # ≤ this → AGING; beyond → STALE (advisory only, never blocks)
-
-# --- Wiki delta refresh (`orc wiki impact` — the default refresh path) ---
-wiki_delta_full_threshold: 30 # TOUCHED docs above this % of registered docs →
-                              #   impact recommends a FULL refresh (user decides;
-                              #   never silently full)
-```
-
-## Score → model table (executor agent dispatched by name)
-
-The orchestrator scores each task 0–100, then maps to a model via this SINGLE
-canonical 8-band table, and dispatches the matching **executor agent**. There is
-no longer a narrow/wide preset choice — `rubric_bands` sets scoring granularity
-only, never which table is used.
-
-| Score | Model | Effort | Executor agent |
-|-------|-------|--------|----------------|
-| [0,30)   | claude-haiku-4-5  | —      | orc-executor-haiku-4-5 |
-| [30,40)  | claude-sonnet-4-6 | medium | orc-executor-sonnet-4-6-med |
-| [40,55)  | claude-sonnet-4-6 | high   | orc-executor-sonnet-4-6-high |
-| [55,65)  | claude-sonnet-5   | high   | orc-executor-sonnet-5-high |
-| [65,70)  | claude-opus-4-7   | medium | orc-executor-opus-4-7-med |
-| [70,80)  | claude-opus-4-7   | high   | orc-executor-opus-4-7-high |
-| [80,90)  | claude-opus-4-8   | high   | orc-executor-opus-4-8-high |
-| [90,100] | claude-opus-5     | high   | orc-executor-opus-5-high |
-
-(Haiku has no effort ladder — that agent carries no `effort:` field.) The risk
-floor (≥70) lands `orc-executor-opus-4-7-high` at minimum in THIS table — under
-the Opus-5-only preset below it lands `orc-executor-opus-5-med` instead. The top
-band dispatches **Opus 5 high** — it needs an Opus 5 MAIN session or it silently
-falls back to the session model (the tier-honesty rule reports the downgrade).
-
-### The Opus-5-only ladder (`opus5_only`, default **false**)
-
-One model, EFFORT as the cost dial. Off by default; nothing changes until set.
-
-| Score | Model | Effort | Executor agent |
-|-------|-------|--------|----------------|
-| [0,40)   | claude-opus-5 | low    | orc-executor-opus-5-low |
-| [40,80)  | claude-opus-5 | medium | orc-executor-opus-5-med |
-| [80,100] | claude-opus-5 | high   | orc-executor-opus-5-high |
-
-Rationale (why the key exists): deep SWE-benchmark work on cost vs efficiency
-across Claude models finds a single Opus 5 agent with the effort ladder the
-most efficient setup — model-class variety traded for effort variety.
-**Tier cost:** today ONE band in eight needs an Opus 5 main session; with this
-on, EVERY dispatch does, so a lower session downgrades every task (warn-only —
-a hook can gate effort, never model). **Scope:** this key is NOT executor-only.
-It also forces every fixed role (see below) across every lane. orc-diy's table
-stays compile-owned and reads only `orc-diy.config.yaml`, never this file.
-
-### Resolution — highest wins
-
-1. `opus5_only: true` — the 3-band preset above, and every fixed role forced to
-   its Opus 5 variant. It FORCES: while on, it outranks BOTH a hand-written
-   `rubric_bands_override` and the whole Fable 5 role override.
-2. `rubric_bands_override` — hand-written `{min, max, agent}` rows (hand-edit
-   only; deliberately not a CLI key). Wins over the default table.
-3. the default 8-band table.
-
-`rubric_bands` sets scoring GRANULARITY only, in every case — it never selects a
-table. Whichever table resolves, **show it** with the Phase 2 scoring table and
-record the mode in the `CONFIG` trace line: an un-shown table is as unaccountable
-as an un-shown number.
-
-### Override
-To use custom band edges/models, set `rubric_bands_override:` with your own
-list of `{min, max, agent}` rows; the orchestrator uses it instead of the table.
-
-## Fixed-role agents (not score-mapped)
-| Role | Agent |
-|------|-------|
-| System Analyst | orc-system-analyst-opus-5-high |
-| Requirement Planner | orc-planner-opus-5-med |
-| Reviewer | orc-reviewer-opus-5-med |
-| Verifier | orc-verifier-opus-5-med |
-| Mini analyst | orc-analyze-mini-sonnet-5-high |
-| Mini planner | orc-planner-mini-sonnet-5-high |
-| Mini executor | orc-executor-sonnet-5-high (reused) |
-| Pattern codifier | orc-pattern-codifier-sonnet-5-high |
-| Ultra advisor (/orc-ultra only) | orc-advisor-opus-5-xhigh |
-| Ultra judge (/orc-ultra only) | orc-judge-opus-5-xhigh |
-
-**Opus-5-only override (forcing):** when `opus5_only: true`, every role above
-that is not already `claude-opus-5` dispatches its Opus 5 variant instead —
-mini analyst → `orc-analyze-mini-opus-5-med`, mini planner →
-`orc-planner-mini-opus-5-med`, mini executor → `orc-executor-opus-5-low`,
-pattern codifier → `orc-pattern-codifier-opus-5-med` — plus the roles owned by
-other lanes (scout, wiki scanner, CLAUDE.md writer, retro miner, fast
-executor). The full mapping, the two exclusions (the Haiku trace writer and
-orc-diy) and the tier consequence are in `../_shared/opus5-only.md`. It
-outranks the Fable 5 override below.
-
-**Fable 5 role override:** (INERT while `opus5_only: true`) when
-`fable5_enabled: true`, each role in
-`fable5_roles` dispatches its `orc-<role>-fable-5` variant INSTEAD of the default
-above (`analyze`→`orc-analyst-fable-5`, `plan`→`orc-planner-fable-5`,
-`advisor`→`orc-advisor-fable-5`, `judge`→`orc-judge-fable-5`,
-`review`→`orc-reviewer-fable-5`). Same slice, same contract. See
-`../_shared/fable5-override.md`.
-
-## Rules
-- Read at run start via the resolution rule above (defaults ← `orc.config.yaml`
-  override). Missing values use defaults (max_wave_tasks 3, batch_pause_every 2,
-  rubric_bands 5, max_scouts 3, default_analysis_depth standard,
-  generate_tests false, pattern_findings ask, security_review off).
-  Behavior-trace logging is not listed here — it is PERMANENT (always on).
-- `generate_tests` gates the opt-in Phase 6.5 (Test Authoring, default OFF). When
-  on, after Verify the orchestrator dispatches `orc-test-author-opus-5-med` to
-  WRITE test cases (automated files + `TEST-PLAN.md` + a curl bundle for HTTP
-  APIs) — it never runs them; the user tests manually. The manual deliverables
-  are pinned to a visible **`test-generator/<change-slug>/`** folder at the
-  project root (not `.claude/`, not the run folder) and are committed on ship.
-  Full lane runs it as Phase 6.5; orc-mini also offers it (opt-in end-of-run ask
-  on a GREEN smoke gate).
-- `max_scouts` caps the parallel scouts fanned out in the analyst's DEEP mode
-  (never exceeds it, same as max_wave_tasks caps a wave).
-- `default_analysis_depth` only presets the analyst's standard/deep gate — the
-  run still confirms; deep never auto-escalates without consent.
-- `rubric_bands` sets HOW MANY bands the rubric REPORTS (finer or coarser score
-  granularity) — it no longer selects a preset. The score→model mapping is the
-  single 8-band table above, used regardless of `rubric_bands`.
-- max_wave_tasks is a hard cap in wave-grouping.
-- `batch_pause_every` is a DETERMINISTIC hard gate, not a cadence hint: after
-  wave W, `W % N == 0` with a later wave remaining forces the stop sequence
-  (references/stop-and-resume.md). The schedule is computed and confirmed at
-  Phase 2 intake and persisted as `pause_schedule` so resumes enforce it too.
-- Behavior-trace logging is PERMANENT (always on) — there is no `logging` key.
-  Every run, the orchestrator follows `references/trace-protocol.md` and the
-  `orc-trace.js` hook writes a persistent `.txt` under `log_dir`. The hook is the
-  deterministic guarantee: it bootstraps `log_dir` + the run pointer itself and
-  segments the run with `PHASE-EDGE` lines, so a usable trace exists even if the
-  orchestrator never narrates. The RICH narration is dispatched per phase to the
-  pinned Haiku trace writer — never appended from memory.
-- `log_dir` is the persistent trace folder; its top level holds the run `.txt`
-  plus its sidecars (`.pending.json`, `.jsonl`). Unlike the decision log
-  (`run/…md`, deleted on success) traces are NEVER auto-deleted — post-hoc
-  review is the point.
-- `retro_repo` is where `/orc-retro` files its calibration report (PR preferred,
-  issue fallback, AI-readable markdown). The retro hard-gates on a delivery
-  channel — an authed gh CLI or a GitHub MCP server — and does not run at all
-  when neither exists. See the `orc-retro` skill.
-- `pattern_findings` gates the code-pattern subsystem (default `ask`). On an FE/BE
-  cache MISS during Phase 3 dispatch: `ask` → P0 prompt (learn conventions via the
-  `orc-pattern` skill, or proceed language-agnostic); `on` → auto-codify, no prompt;
-  `off` → always agnostic (invariants enforced, conventions imitate neighbor files),
-  never ask. A cache HIT is used silently regardless. The codifier
-  (`orc-pattern-codifier-sonnet-5-high`) writes `.claude/orc/patterns/<lang>-pattern.md`,
-  reused by future runs. See the `orc-pattern` skill.
-- `orc_wiki_pattern_findings` (default `false`, on/off only — no `ask`, because the
-  wiki's scan already has consent) makes `orc-wiki` codify ALL detected languages as
-  a byproduct of its full scan, pre-warming the pattern cache so later `/orc` runs
-  never hit the `pattern_findings` prompt.
-- `fable5_enabled` / `fable5_effort` / `fable5_roles` gate the **Fable 5 role
-  override** (default OFF — a hard P0 gate). Nothing changes unless
-  `fable5_enabled: true`. Then each role in `fable5_roles` (subset of
-  `analyze, plan, advisor, judge, review`) dispatches its `orc-<role>-fable-5`
-  agent instead of the default; `advisor`/`judge` apply only under `/orc-ultra`.
-  `fable5_effort` (medium default) sets those agents' effort — the CLI rewrites
-  their frontmatter on set. Enabled with empty `fable5_roles` = no effect (the
-  CLI warns). The whole block is INERT while `opus5_only: true`. See
-  `../_shared/fable5-override.md`.
-- `opus5_only` (default `false`) is a **forcing** dispatch mode: every scored
-  executor AND every fixed role resolves to a `claude-opus-5` agent, with effort
-  as the only cost dial. While on it outranks `rubric_bands_override` and the
-  entire `fable5_*` block. Two things are never forced: the pinned Haiku trace
-  writer, and orc-diy (compile-owned). Every dispatch then needs an Opus 5 main
-  session — including `/orc-fast`, whose Sonnet-medium session premise holds
-  only while this is off. See `../_shared/opus5-only.md`.
-- **Ultra lane has no config key** — `/orc-ultra` forces its overrides
-  run-scoped (deep analyze, `pattern_findings` on, `generate_tests` on,
-  `security_review` on, executor tier floor) and NEVER writes them to
-  `orc.config.yaml`. See the orc skill's `references/ultra-mode.md`.
-- `wiki_fresh_max` / `wiki_aging_max` set the wiki freshness tier edges. The
-  tier is ALWAYS computed on read, and **`orc wiki status` is the only thing
-  that computes it** (v0.41.0 — `--json` for a machine-readable `.tier`): never
-  hand-run a `git rev-list` against `.claude/orc/wiki-meta.json`. Freshness is
-  **coverage-relative** — a doc is stale only when commits since ITS OWN
-  `scanned_commit` touched files IT covers, and the wiki's tier is its worst
-  doc. (Measuring from the manifest's `scan_commit` — the OLDEST doc's anchor,
-  which a delta refresh deliberately leaves frozen — reported the same hash and
-  a growing distance forever, so the wiki read STALE no matter how often it was
-  refreshed.) A STRUCTURAL blind spot degrades the tier ONE step, never past
-  AGING: that is a coverage gap, not doc rot. FRESH → silent, AGING → notice,
-  STALE → warn (full/mini lanes) or the orc-fast user gate. See
-  `../orc-wiki/references/staleness.md`.
-- `wiki_refresh_ask_tasks` / `wiki_refresh_ask_files` set the BIG-run trigger
-  for the post-ship wiki refresh ask (full + ultra lanes only; guarded on a
-  non-empty wiki). Judged by FINAL counts at ship time.
-- `crosslink_fresh_days` / `crosslink_aging_days` set the day edges for the
-  cross-repo crosslink snapshot age (Signal B — the only day-based tier in the
-  constellation; two repos share no commit axis). The effective cross-repo tier
-  is `min(Signal-A provider-wiki-tier, Signal-B snapshot-age)`, computed on read,
-  advisory only — a stale crosslink warns, never blocks. See
-  `../orc-wiki/references/crosslink.md` + `../orc-wiki/references/staleness.md`.
-- `run_budget_dispatches` (default `0` = off) is the only cost gate ORC has that
-  fires BEFORE money is spent. The Phase-1 `forecast:` block already estimates
-  the run's subagent count from the plan (`references/preflight-report.md`); this
-  key turns that estimate into a **hard stop before wave 1** when it is exceeded
-  — same discipline as `batch_pause_every`, so a run never dispatches past an
-  unacknowledged budget stop. It offers proceed · switch to a cheaper lane ·
-  re-plan smaller, and emits `GATE budget stop|pass :: forecast=<n> limit=<m>`.
-  At `0` the gate never fires and no `GATE budget` line is emitted at all.
-  The estimate is a floor: repairs and requeues push the real count up, never
-  down — so set the budget as a "stop and make me think" line, not a quota.
-- `security_review` gates the opt-in Phase 5.5 security pass (default `off`).
-  The trigger is the EXISTING risk floor: it can only fire on a run where at
-  least one task scored ≥ 70 (security/money/migrations/auth). `ask` → one
-  prompt after review; `on` → dispatch without asking; `off` → skip silently.
-  The pass reuses the reviewer (`phase=security`) with the checklist from
-  `references/security-checklist.md`, sweeping only the run's changed files
-  (wraps Semgrep if installed, never installs tooling). Findings use the same
-  P0–P3 ladder + hard-rule-5 handling.
+# ORC — Config
+
+The **values** are not here any more. `bin/cli.js`'s registry holds every key,
+its default, its validator, its family and its rank, and `orc lane config orc
+--json` resolves them for a run. Restating them here produced a second table
+that drifted from the first.
+
+What stays here is the part the CLI cannot hand you: the score→model table, the
+fixed-role pins, and where each subsystem's own rule is written down.
+
+## Resolution
+
+**ONE resolver, and it is not you:** `orc lane config orc --json`. Obey
+`effective`, print every line in `announce[]` VERBATIM at preflight, and honour
+`stops[]` before wave 1. Never re-derive a value, a precedence or an inertness
+from `.claude/orc.config.yaml` — a key this lane does not read is not in the
+answer, and a key another key shadows comes back already marked. Exit ≠ 0 → say
+the CLI is unavailable and fall back to `../_shared/config-precedence.md`'s
+documented defaults, out loud.
+
+Read a family top-down and **stop at the first rank that resolves**; a rank
+compares only INSIDE its family. Ranks, families, gates, lane-level inertness,
+the `announce[]` boundary and the CLI-absent floor:
+**`../_shared/config-precedence.md`.**
+
+## Score → model table (executor agent dispatched by name)
+
+The orchestrator scores each task 0–100, then maps to a model via this SINGLE
+canonical 6-band table, and dispatches the matching **executor agent**.
+`rubric_bands` sets scoring granularity only — it never selects a table.
+
+| Score | Model | Effort | Executor agent |
+|-------|-------|--------|----------------|
+| [0,30)   | claude-haiku-4-5  | —      | orc-executor-haiku-4-5 |
+| [30,40)  | claude-sonnet-4-6 | medium | orc-executor-sonnet-4-6-med |
+| [40,55)  | claude-sonnet-4-6 | high   | orc-executor-sonnet-4-6-high |
+| [55,65)  | claude-sonnet-5   | high   | orc-executor-sonnet-5-high |
+| [65,90)  | claude-opus-5     | low    | orc-executor-opus-5-low |
+| [90,100] | claude-opus-5     | medium | orc-executor-opus-5-med |
+
+(Haiku has no effort ladder — that agent carries no `effort:` field.) The risk
+floor (≥70) lands `orc-executor-opus-5-low` at minimum in THIS table. Above ~65
+the useful dial stopped being the model GENERATION and became the EFFORT, which
+is why the old four Opus rows are two. **Every band from 65 needs an Opus 5 MAIN
+session** or it silently falls back to the session model (the tier-honesty rule
+reports the downgrade) — two bands where it used to be one, and that is the cost
+of this table.
+
+**Four executors are named by NO band** — `orc-executor-opus-4-7-med`,
+`orc-executor-opus-4-7-high`, `orc-executor-opus-4-8-high` and
+`orc-executor-opus-5-high`. They still ship, reachable through
+`rubric_bands_override`, `orc diy`'s `fixed_executor` and `extra_fallback_agent`.
+Not deleted, because this is a TABLE change and not a model change — and an
+agent's model change is always a rename.
+
+### The Opus-5-only ladder (`opus5_only`, default **false**)
+
+One model, EFFORT as the cost dial. Off by default; nothing changes until set.
+
+| Score | Model | Effort | Executor agent |
+|-------|-------|--------|----------------|
+| [0,90)   | claude-opus-5 | low    | orc-executor-opus-5-low |
+| [90,100] | claude-opus-5 | medium | orc-executor-opus-5-med |
+
+Two bands, sharing the 90 edge with the default table's top two rows. That
+symmetry is the point: once the default table's high end is already Opus 5 with
+effort as the dial, this mode differs from it only BELOW 65, so a third band
+would be a distinction the default table stopped making.
+
+**Tier cost:** today TWO bands in six need an Opus 5 main session; with this on,
+EVERY dispatch does, so a lower session downgrades every task (warn-only — a
+hook can gate effort, never model). **Scope:** it is NOT executor-only — it also
+forces every fixed role below, across every lane. orc-diy's table
+stays compile-owned and reads only `orc-diy.config.yaml`, never this file.
+Full mapping and the two exclusions: `../_shared/opus5-only.md`.
+
+Whichever table resolves, **show it** with the Phase 2 scoring table and record
+the mode in the `CONFIG` trace line: an un-shown table is as unaccountable as an
+un-shown number.
+
+## Fixed-role agents (not score-mapped)
+
+| Role | Agent |
+|------|-------|
+| System Analyst | orc-system-analyst-opus-5-high |
+| Requirement Planner | orc-planner-opus-5-med |
+| Reviewer | orc-reviewer-opus-5-med |
+| Verifier | orc-verifier-opus-5-med |
+| Mini analyst | orc-analyze-mini-sonnet-5-high |
+| Mini planner | orc-planner-mini-sonnet-5-high |
+| Mini executor | orc-executor-sonnet-5-high (reused) |
+| Pattern codifier | orc-pattern-codifier-sonnet-5-high |
+| Ultra advisor (/orc-ultra only) | orc-advisor-opus-5-xhigh |
+| Ultra judge (/orc-ultra only) | orc-judge-opus-5-xhigh |
+
+Under `opus5_only`, every role above that is not already `claude-opus-5`
+dispatches its Opus 5 variant instead — plus the roles owned by other lanes
+(scout, wiki scanner, CLAUDE.md writer, retro miner, fast executor).
+
+## Where each subsystem's rule is written down
+
+A key's default and validator come from the resolver. These are the RULES the
+value participates in, and each has exactly one canonical copy.
+
+| Subsystem | The rule, in one line | Canonical prose |
+|---|---|---|
+| Wave grouping | `max_wave_tasks` is a hard cap, never a target | `../_shared/phases/wave-grouping.md` |
+| Batch pause | `batch_pause_every` is a DETERMINISTIC hard gate, not a cadence hint: after wave W, `W % N == 0` with a later wave remaining forces the stop sequence. Computed and confirmed at Phase 2 intake, persisted as `pause_schedule` so a resume enforces it too | `../_shared/phases/stop-resume.md` |
+| Run budget | `run_budget_dispatches` turns the Phase-1 forecast into a hard stop BEFORE wave 1 and emits `` `GATE budget stop\|pass ``. At `0` no line is emitted at all. The estimate is a FLOOR — repairs push the real count up, never down | `references/preflight-report.md` |
+| Analysis depth | `default_analysis_depth` only presets the standard/deep gate; the run still confirms, and deep never auto-escalates without consent. `max_scouts` caps the parallel scouts the same way a wave is capped | `../orc-analyze/SKILL.md` |
+| TDD | every plan carries `tdd_spec`; each entry's `disposition` is DERIVED from the planner's `facets`, and a task with a cited `facets.risk[]` can never be scoped out. `tdd_loop_max` caps the repair loop, then STOP + an honest red report. There is deliberately no key for the scoping — one would restore the tautological tests it removes | `SKILL.md` Phase 6 · `schemas/planning-output.md` |
+| Test authoring | `generate_tests` gates the opt-in Phase 6.5: it WRITES cases and never runs them, pinned to a visible `test-generator/<change-slug>/` at the project root | `../orc-verify/SKILL.md` |
+| Mock example | `mock_example` gates the post-verify runnable example under `mock-examples/`, which is NEVER committed; on drift, `drift-recovery.md` (`DRIFT-FROM`) is capped at 2 loops | `../_shared/drift-recovery.md` |
+| Code patterns | `pattern_findings` gates the codifier on an FE/BE cache MISS; a cache HIT is used silently regardless. `orc_wiki_pattern_findings` pre-warms the cache during a wiki scan | `../orc-pattern/SKILL.md` |
+| Repair memory | `gotchas` / `gotchas_max` govern `.claude/orc/gotchas.md` — recorded only on a red → green repair, injected scope-matched, never unfiltered | `../_shared/gotchas.md` |
+| Security | `security_review` gates the opt-in Phase 5.5, and can only fire on a run with a task scored ≥ 70 | `../_shared/phases/security-checklist.md` |
+| Wiki freshness | `wiki_fresh_max` / `wiki_aging_max` set the tier edges. The tier is COVERAGE-RELATIVE and computed on read, and `orc wiki status` is the only thing that computes it — never hand-run a `git rev-list` against `wiki-meta.json`. A STRUCTURAL blind spot degrades ONE step and never past `AGING` | `../orc-wiki/references/staleness.md` |
+| Wiki refresh | `wiki_refresh_ask_tasks` / `wiki_refresh_ask_files` set the big-run post-ship ask, judged by FINAL counts. `orc wiki impact` decides delta vs full, and `wiki_delta_full_threshold` is when a FULL refresh is recommended — never silent | `../orc-wiki/references/staleness.md` |
+| Crosslink | `crosslink_fresh_days` / `crosslink_aging_days` are DAY-based (two repos share no commit axis); the effective tier is `min(provider-wiki tier, snapshot age)`, advisory only — a stale crosslink warns, never blocks | `../orc-wiki/references/crosslink.md` |
+| Foreign dispatch | `extra_enabled` and the `extra_*` block; every armed run prints its `extra:` line at Phase 1 | `../_shared/extra-dispatch.md` |
+| Stacked PRs | the `stacked_pr*` keys gate the Phase 8 stack (full `/orc` + `/orc-ultra` only) | `../orc-pr-setup/SKILL.md` |
+| Retro | `retro_repo` is where `/orc-retro` files its report; it hard-gates on a delivery channel and does not run at all without one | `../orc-retro/SKILL.md` |
+| Paths | `log_dir` (traces, NEVER auto-deleted), `run_dir` (`.claude/orc/run` — outside the installer's blast radius), and the analyst/planner/report dirs | `../_shared/config-precedence.md` |
+| Ultra | **no config key at all** — `/orc-ultra` forces its overrides RUN-SCOPED and never writes them to `orc.config.yaml` | `references/ultra-mode.md` |
+
+**TDD — Lane policy (fixed, not configurable).** Full orc + ultra always on ·
+orc-mini asks ONE intake question · orc-fast off (no planner) · orc-diy composes
+it as the `tdd` flow key · standalone `/orc-plan` ON, because a saved plan's only
+consumers are the TDD-always build lanes, so a plan with no `tdd_spec` is
+unusable by the lane that runs it.
+
+**Behavior-trace logging is PERMANENT — there is no key.** Every run writes a
+persistent trace under `log_dir`; the `orc-trace.js` hook is the deterministic
+guarantee, bootstrapping the pointer itself and segmenting the run with
+`PHASE-EDGE` lines, so a usable trace exists even if the orchestrator never
+narrates. The rich narration is DISPATCHED per phase to the pinned Haiku trace
+writer — never appended from memory. See `../_shared/phases/trace.md`.

package/templates/skills/orc/examples/full-run-mock.md

@@ -66,7 +66,7 @@ O: ✓ committed → pushed → run/merchant-notifications/DRP-482-add-merchant-
    Log deleted · checkpoint + dispatch log KEPT · completion dispatch report shown → "Run /usage to see your remaining limits."
 
 ## What this exercises
-always-spawn (even cheap tasks get a subagent) · facet-scored arithmetic · 8-band ladder ·
+always-spawn (even cheap tasks get a subagent) · facet-scored arithmetic · 6-band ladder ·
 per-run folder run/merchant-notifications/ · usage reminder (no programmatic /usage) ·
 planner grounding spot-check catching a hallucinated path · executor evidence (verbatim
 build/test proof) · reviewer quote spot-check before any P0/P1 action ·