@azure-id/orc 1.9.1 → 1.9.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +69 -0
- package/README-id.md +38 -39
- package/README.md +36 -35
- package/bin/build-agents.js +109 -109
- package/bin/cli.js +35 -33
- package/bin/onboarding-content.js +4 -4
- package/bin/pricing.json +207 -200
- package/bin/verify-contracts.js +2 -2
- package/bin/verify-package.js +7 -7
- package/bin/webui/css/04-motion.css +162 -152
- package/bin/webui/css/panels/knowledge.css +563 -116
- package/bin/webui/fixtures/extra.js +2036 -2036
- package/bin/webui/fixtures/hookui.js +5 -5
- package/bin/webui/fixtures/settings.js +305 -305
- package/bin/webui/i18n/en/knowledge.json +117 -2
- package/bin/webui/i18n/id/knowledge.json +117 -2
- package/bin/webui/js/panels/knowledge.js +552 -7
- package/bin/webui/js/panels/overview.js +13 -4
- package/mock-run/context-combiner.md +100 -100
- package/mock-run/orc-budget.md +534 -534
- package/mock-run/orc-challenge-council.md +262 -262
- package/mock-run/orc-ultra.md +103 -103
- package/package.json +1 -1
- package/templates/agents/MODEL-MAPPING.md +43 -43
- package/templates/agents/orc-advisor-opus-5-xhigh.md +56 -56
- package/templates/agents/orc-analyze-mini-opus-5-med.md +60 -60
- package/templates/agents/orc-analyze-mini-sonnet-5-high.md +58 -58
- package/templates/agents/orc-challenge-advisor-opus-5-med.md +75 -75
- package/templates/agents/orc-challenge-contrarian-opus-5-high.md +110 -110
- package/templates/agents/orc-challenge-executor-opus-5-med.md +114 -114
- package/templates/agents/orc-challenge-expansionist-opus-5-med.md +112 -112
- package/templates/agents/orc-challenge-judge-opus-5-high.md +132 -132
- package/templates/agents/orc-challenge-outsider-opus-5-low.md +109 -109
- package/templates/agents/orc-challenge-principles-opus-5-high.md +109 -109
- package/templates/agents/orc-challenge-reader-opus-5-low.md +90 -90
- package/templates/agents/orc-claude-writer-opus-5-med.md +55 -55
- package/templates/agents/orc-context-combiner-opus-5-high.md +88 -88
- package/templates/agents/orc-doc-checker-opus-5-low.md +108 -108
- package/templates/agents/orc-doc-writer-opus-5-med.md +134 -134
- package/templates/agents/orc-executor-opus-5-high.md +2 -2
- package/templates/agents/orc-executor-opus-5-low.md +2 -2
- package/templates/agents/orc-executor-opus-5-med.md +2 -2
- package/templates/agents/orc-graph-noter-sonnet-4-6-med.md +1 -1
- package/templates/agents/orc-judge-opus-5-xhigh.md +85 -85
- package/templates/agents/orc-learn-writer-opus-5-low.md +73 -73
- package/templates/agents/orc-pattern-codifier-opus-5-med.md +65 -65
- package/templates/agents/orc-planner-mini-opus-5-med.md +4 -4
- package/templates/agents/orc-planner-mini-sonnet-5-high.md +1 -1
- package/templates/agents/orc-planner-opus-5-med.md +160 -160
- package/templates/agents/orc-recon-opus-5-low.md +3 -3
- package/templates/agents/orc-retro-opus-5-med.md +3 -3
- package/templates/agents/orc-reviewer-opus-5-med.md +60 -60
- package/templates/agents/orc-scout-opus-5-low.md +40 -40
- package/templates/agents/orc-system-analyst-opus-5-high.md +120 -120
- package/templates/agents/orc-test-author-opus-5-med.md +71 -71
- package/templates/agents/orc-test-designer-opus-5-high.md +158 -158
- package/templates/agents/orc-test-interpreter-opus-5-low.md +130 -130
- package/templates/agents/orc-verifier-opus-5-med.md +69 -69
- package/templates/agents/orc-wiki-scanner-opus-5-med.md +81 -81
- package/templates/commands/orc-ultra.md +17 -17
- package/templates/commands/orc-verify.md +11 -11
- package/templates/hooks/README.md +2 -2
- package/templates/hooks/orc-effort-guard.js +178 -178
- package/templates/hooks/orc-statusline.js +6 -6
- package/templates/skills/_shared/code-graph.md +1 -1
- package/templates/skills/_shared/config-precedence.md +198 -198
- package/templates/skills/_shared/extra-dispatch.md +1346 -1346
- package/templates/skills/_shared/opus5-only.md +8 -8
- package/templates/skills/_shared/phases/analyst-gates.md +136 -136
- package/templates/skills/_shared/phases/review.md +1 -1
- package/templates/skills/_shared/phases/trace.md +1 -1
- package/templates/skills/_shared/return-validation.md +1 -1
- package/templates/skills/context-combiner/SKILL.md +1 -1
- package/templates/skills/context-combiner/schemas/combined-report.md +78 -78
- package/templates/skills/orc/README.md +2 -2
- package/templates/skills/orc/SKILL.md +7 -7
- package/templates/skills/orc/config.md +9 -9
- package/templates/skills/orc/examples/full-run-mock.md +73 -73
- package/templates/skills/orc/references/effort-and-mode.md +222 -222
- package/templates/skills/orc/references/preflight-report.md +2 -2
- package/templates/skills/orc/references/ultra-mode.md +3 -3
- package/templates/skills/orc/subskills/orc-planner/SKILL.md +2 -2
- package/templates/skills/orc/subskills/orc-planner-mini/SKILL.md +121 -121
- package/templates/skills/orc/subskills/orc-review-verify/SKILL.md +76 -76
- package/templates/skills/orc/subskills/orc-testgen/SKILL.md +45 -45
- package/templates/skills/orc-analyze/SKILL.md +2 -2
- package/templates/skills/orc-analyze/examples/analyze-mock.md +42 -42
- package/templates/skills/orc-analyze/schemas/report-audit.md +83 -83
- package/templates/skills/orc-analyze/schemas/report-prose.md +63 -63
- package/templates/skills/orc-analyze/schemas/report-requirement.md +78 -78
- package/templates/skills/orc-challenge/README.md +142 -142
- package/templates/skills/orc-challenge/examples/council-full-roster.md +273 -273
- package/templates/skills/orc-challenge/references/council.md +315 -315
- package/templates/skills/orc-challenge/references/intake.md +171 -171
- package/templates/skills/orc-claude/SKILL.md +14 -14
- package/templates/skills/orc-diy/README.md +143 -143
- package/templates/skills/orc-diy/references/flow-schema.md +1 -1
- package/templates/skills/orc-doc/README.md +229 -229
- package/templates/skills/orc-doc/examples/orc-doc-prd-run.md +325 -325
- package/templates/skills/orc-doc/references/chunking.md +527 -527
- package/templates/skills/orc-fast/SKILL.md +1 -1
- package/templates/skills/orc-learn/SKILL.md +14 -14
- package/templates/skills/orc-learn/examples/learn-run-mock.md +61 -61
- package/templates/skills/orc-mini/SKILL.md +3 -3
- package/templates/skills/orc-verify/SKILL.md +15 -15
- package/templates/skills/orc-verify/examples/verify-mock.md +33 -33
- package/templates/skills/orc-wiki/references/extra.md +1 -1
|
@@ -99,7 +99,7 @@ migration) and write the intent-spec + a minimal checkpoint.
|
|
|
99
99
|
## Phase F2 — Slice build + dispatch (ONE executor)
|
|
100
100
|
|
|
101
101
|
Build one slice for `orc-executor-sonnet-4-6-high` (dispatch BY NAME; model
|
|
102
|
-
pinned in the agent file). **Under `opus5_only` it is `orc-executor-opus-5-low`** — forced, and while that mode is on this lane needs an Opus 5 main session, so the "runs fine at Sonnet medium" premise applies only with it off (`../_shared/opus5-only.md`).
|
|
102
|
+
pinned in the agent file). **Under `opus5_only` it is `orc-executor-opus-5-low`** — forced, and while that mode is on this lane needs an Opus 5.5 main session, so the "runs fine at Sonnet medium" premise applies only with it off (`../_shared/opus5-only.md`).
|
|
103
103
|
|
|
104
104
|
**Extra (`extra_enabled`, `../_shared/extra-dispatch.md`):** the same slice may run off Claude. **This lane has no score at all, so it holds a POSITION, not a band:** resolve `orc extra resolve --slot fast-executor --json` (set with `orc extra role set fast-executor <profile>/<model>`). No row on that slot = Claude, and that is an answer, not a gap. The `extra:` line joins the F0 preflight (P0, printed whenever the gate is on) and NAMES the agent it displaces — `orc-executor-sonnet-4-6-high`; dispatch through `orc extra dispatch --task <file> --json` with `slot: "fast-executor"` and **no `score`** (both is refused by name); validate with `return-validation.md` **§2b, not §2**; a failure runs `orc extra reconcile <task_id>` FIRST — a worktree that moved is RESUMED, never re-done — then falls back to that same pinned agent BY NAME, announced. Extra is orthogonal to the knowledge gate — a fresh wiki and a cached pattern are still required, and a foreign worker gets the same pointers-not-content slice.
|
|
105
105
|
|
|
@@ -23,7 +23,7 @@ it — the human-onboarding lane. It is NOT the wiki: the wiki grounds the
|
|
|
23
23
|
|
|
24
24
|
**Dispatch, don't do.** Whatever model this chat runs on, the skill only picks
|
|
25
25
|
the topic/mode and spawns `orc-learn-writer-opus-5-low` (the pinned
|
|
26
|
-
engine) — the deepening scan + all writes run at Opus 5 low regardless of
|
|
26
|
+
engine) — the deepening scan + all writes run at Opus 5.5 low regardless of
|
|
27
27
|
the caller's tier. The skill's only self-writes are the behavior-trace
|
|
28
28
|
markers around the spawn. Interactivity is DELIBERATELY minimal but non-zero
|
|
29
29
|
(unlike orc-claude): exactly one question per mode — "which feature?" (INIT)
|
|
@@ -173,16 +173,16 @@ exit code, and never re-derive a state word — the CLI's state words are the on
|
|
|
173
173
|
state words, and **an exit code is an ANSWER wherever that contract says so, not
|
|
174
174
|
a failure**. A call the answer does not name is a call this lane does not make.
|
|
175
175
|
Exit ≠ 0 from the catalogue itself → say the CLI is unavailable and name the
|
|
176
|
-
command you are about to run, out loud, before running it.
|
|
177
|
-
|
|
178
|
-
## Rules — the anti-slop card (`../_shared/phases/rules.md`)
|
|
179
|
-
|
|
180
|
-
`orc rules slice --lane orc-learn --json` is the ONLY assembler; never build
|
|
181
|
-
the card here. It rides under the house rules and above the task —
|
|
182
|
-
**house rules > your project's rules > ORC's own packs** — and its `line` prints
|
|
183
|
-
VERBATIM at preflight. Returns gain `rules_applied[]`, `rules_conflicts[]` (a gap,
|
|
184
|
-
never a silent choice) and `rules_overridden[]`.
|
|
185
|
-
## Waiting mid-run (`/orc-wait`)
|
|
186
|
-
|
|
187
|
-
Canonical: `../_shared/wait.md`. **`a lane that waits without a hand-back` has broken this contract.**
|
|
188
|
-
Checkpoint **none** · safe point **single dispatch**. Nothing here to checkpoint, so all three modes behave identically — say so rather than asking. Never begin a wait between a dispatch and its validated return, or before the smoke gate has reported.
|
|
176
|
+
command you are about to run, out loud, before running it.
|
|
177
|
+
|
|
178
|
+
## Rules — the anti-slop card (`../_shared/phases/rules.md`)
|
|
179
|
+
|
|
180
|
+
`orc rules slice --lane orc-learn --json` is the ONLY assembler; never build
|
|
181
|
+
the card here. It rides under the house rules and above the task —
|
|
182
|
+
**house rules > your project's rules > ORC's own packs** — and its `line` prints
|
|
183
|
+
VERBATIM at preflight. Returns gain `rules_applied[]`, `rules_conflicts[]` (a gap,
|
|
184
|
+
never a silent choice) and `rules_overridden[]`.
|
|
185
|
+
## Waiting mid-run (`/orc-wait`)
|
|
186
|
+
|
|
187
|
+
Canonical: `../_shared/wait.md`. **`a lane that waits without a hand-back` has broken this contract.**
|
|
188
|
+
Checkpoint **none** · safe point **single dispatch**. Nothing here to checkpoint, so all three modes behave identically — say so rather than asking. Never begin a wait between a dispatch and its validated return, or before the smoke gate has reported.
|
|
@@ -1,61 +1,61 @@
|
|
|
1
|
-
# Worked example — orc-learn runs (mock; orient only, never execute from this)
|
|
2
|
-
|
|
3
|
-
## Run 1 — INIT with a fresh wiki
|
|
4
|
-
|
|
5
|
-
U: /orc-learn
|
|
6
|
-
C: Repo root found. Reads wiki/INDEX.md + the wiki manifest → tier FRESH.
|
|
7
|
-
Presents the wiki's feature areas; user picks "orders". Slug: `orders`.
|
|
8
|
-
Spawns orc-learn-writer-opus-5-low with mode=init, covers from the
|
|
9
|
-
orders doc's globs (the skill never writes the docs itself).
|
|
10
|
-
W: Reads the orders wiki doc for boundary + contracts, re-verifies against
|
|
11
|
-
code. Deepens: maps 14 functions (file:line), traces one real flow —
|
|
12
|
-
POST /orders → validate (routes/orders.ts:31) → price (pricing.ts:88) →
|
|
13
|
-
persist (repo/orders.ts:15) → emit event → 201. Harvests 3 invariants,
|
|
14
|
-
4 why-this-way findings, 2 couplings.
|
|
15
|
-
W: Writes learning-docs/orders/knowledge.md (fingerprint header:
|
|
16
|
-
source_commit=HEAD, 9 hashed files; functions & flow; contracts; verify
|
|
17
|
-
commands from the wiki manifest's `commands`) and learning.md (mental
|
|
18
|
-
model, walkthrough of the SAME flow, 3 change recipes, gotchas, FAQ ×6).
|
|
19
|
-
Derives learning-docs/INDEX.md. Returns functions_mapped=14,
|
|
20
|
-
flow_traced=true, faq_count=6, actual_model=claude-opus-5,
|
|
21
|
-
actual_effort=low.
|
|
22
|
-
C: Relays the report. `learning-docs/` not in .gitignore → offers the line;
|
|
23
|
-
user accepts → appended.
|
|
24
|
-
|
|
25
|
-
## Run 2 — INIT, no wiki
|
|
26
|
-
|
|
27
|
-
U: /orc-learn focus=src/billing
|
|
28
|
-
C: No wiki/ → tier none (traced all the same). Asks only to confirm the
|
|
29
|
-
feature ("billing", from the focus pointer). Writer does a TARGETED scan
|
|
30
|
-
of src/billing/** only — never repo-wide — then deepens and writes the
|
|
31
|
-
pair as above.
|
|
32
|
-
|
|
33
|
-
## Run 3 — REFRESH, multi-select
|
|
34
|
-
|
|
35
|
-
U: /orc-learn refresh
|
|
36
|
-
C: Reads each learning-docs/*/knowledge.md header; computes tiers on read:
|
|
37
|
-
orders STALE (drift hit pricing.ts), billing FRESH. Shows BOTH with
|
|
38
|
-
flags; user picks orders only. One writer dispatch regenerates the orders
|
|
39
|
-
pair (new source_commit, recomputed hashes, changelog line), re-derives
|
|
40
|
-
INDEX.md. billing: byte-untouched.
|
|
41
|
-
|
|
42
|
-
## Run 4 — behavior trace (permanent, always on)
|
|
43
|
-
|
|
44
|
-
The skill writes the run pointer (`run-learn-<slug>-<DDMMYY>-<HHMMSS>.txt` into
|
|
45
|
-
`log_dir`) before the spawn, records these events as they happen, and — as a
|
|
46
|
-
single-dispatch lane — dispatches the trace writer ONCE at run end to append
|
|
47
|
-
them (`SPAWN`/`RETURN` come from the `orc-trace.js` hook as they occur):
|
|
48
|
-
|
|
49
|
-
```
|
|
50
|
-
[170726 10:02:01.050] writer WIKI-CONSULT tier=FRESH :: topic-pick
|
|
51
|
-
[170726 10:02:44.310] writer DISPATCH orc-learn-writer :: init orders expect=opus-5/low
|
|
52
|
-
[170726 10:02:44.420] hook SPAWN orc-learn-writer-opus-5-low
|
|
53
|
-
[170726 10:06:12.900] hook RETURN
|
|
54
|
-
[170726 10:06:13.010] writer VERIFY writer actual=claude-opus-5/low ✅ MATCH
|
|
55
|
-
[170726 10:06:13.120] writer FINISH :: init orders
|
|
56
|
-
```
|
|
57
|
-
|
|
58
|
-
Then the writer packet returns and the run pointer is deleted (in that order).
|
|
59
|
-
REFRESH traces one DISPATCH/VERIFY pair per
|
|
60
|
-
selected feature, ending `FINISH :: refresh <n> features`. No phase/score/
|
|
61
|
-
finding/verdict markers — this lane runs none of those phases.
|
|
1
|
+
# Worked example — orc-learn runs (mock; orient only, never execute from this)
|
|
2
|
+
|
|
3
|
+
## Run 1 — INIT with a fresh wiki
|
|
4
|
+
|
|
5
|
+
U: /orc-learn
|
|
6
|
+
C: Repo root found. Reads wiki/INDEX.md + the wiki manifest → tier FRESH.
|
|
7
|
+
Presents the wiki's feature areas; user picks "orders". Slug: `orders`.
|
|
8
|
+
Spawns orc-learn-writer-opus-5-low with mode=init, covers from the
|
|
9
|
+
orders doc's globs (the skill never writes the docs itself).
|
|
10
|
+
W: Reads the orders wiki doc for boundary + contracts, re-verifies against
|
|
11
|
+
code. Deepens: maps 14 functions (file:line), traces one real flow —
|
|
12
|
+
POST /orders → validate (routes/orders.ts:31) → price (pricing.ts:88) →
|
|
13
|
+
persist (repo/orders.ts:15) → emit event → 201. Harvests 3 invariants,
|
|
14
|
+
4 why-this-way findings, 2 couplings.
|
|
15
|
+
W: Writes learning-docs/orders/knowledge.md (fingerprint header:
|
|
16
|
+
source_commit=HEAD, 9 hashed files; functions & flow; contracts; verify
|
|
17
|
+
commands from the wiki manifest's `commands`) and learning.md (mental
|
|
18
|
+
model, walkthrough of the SAME flow, 3 change recipes, gotchas, FAQ ×6).
|
|
19
|
+
Derives learning-docs/INDEX.md. Returns functions_mapped=14,
|
|
20
|
+
flow_traced=true, faq_count=6, actual_model=claude-opus-5-5,
|
|
21
|
+
actual_effort=low.
|
|
22
|
+
C: Relays the report. `learning-docs/` not in .gitignore → offers the line;
|
|
23
|
+
user accepts → appended.
|
|
24
|
+
|
|
25
|
+
## Run 2 — INIT, no wiki
|
|
26
|
+
|
|
27
|
+
U: /orc-learn focus=src/billing
|
|
28
|
+
C: No wiki/ → tier none (traced all the same). Asks only to confirm the
|
|
29
|
+
feature ("billing", from the focus pointer). Writer does a TARGETED scan
|
|
30
|
+
of src/billing/** only — never repo-wide — then deepens and writes the
|
|
31
|
+
pair as above.
|
|
32
|
+
|
|
33
|
+
## Run 3 — REFRESH, multi-select
|
|
34
|
+
|
|
35
|
+
U: /orc-learn refresh
|
|
36
|
+
C: Reads each learning-docs/*/knowledge.md header; computes tiers on read:
|
|
37
|
+
orders STALE (drift hit pricing.ts), billing FRESH. Shows BOTH with
|
|
38
|
+
flags; user picks orders only. One writer dispatch regenerates the orders
|
|
39
|
+
pair (new source_commit, recomputed hashes, changelog line), re-derives
|
|
40
|
+
INDEX.md. billing: byte-untouched.
|
|
41
|
+
|
|
42
|
+
## Run 4 — behavior trace (permanent, always on)
|
|
43
|
+
|
|
44
|
+
The skill writes the run pointer (`run-learn-<slug>-<DDMMYY>-<HHMMSS>.txt` into
|
|
45
|
+
`log_dir`) before the spawn, records these events as they happen, and — as a
|
|
46
|
+
single-dispatch lane — dispatches the trace writer ONCE at run end to append
|
|
47
|
+
them (`SPAWN`/`RETURN` come from the `orc-trace.js` hook as they occur):
|
|
48
|
+
|
|
49
|
+
```
|
|
50
|
+
[170726 10:02:01.050] writer WIKI-CONSULT tier=FRESH :: topic-pick
|
|
51
|
+
[170726 10:02:44.310] writer DISPATCH orc-learn-writer :: init orders expect=opus-5/low
|
|
52
|
+
[170726 10:02:44.420] hook SPAWN orc-learn-writer-opus-5-low
|
|
53
|
+
[170726 10:06:12.900] hook RETURN
|
|
54
|
+
[170726 10:06:13.010] writer VERIFY writer actual=claude-opus-5-5/low ✅ MATCH
|
|
55
|
+
[170726 10:06:13.120] writer FINISH :: init orders
|
|
56
|
+
```
|
|
57
|
+
|
|
58
|
+
Then the writer packet returns and the run pointer is deleted (in that order).
|
|
59
|
+
REFRESH traces one DISPATCH/VERIFY pair per
|
|
60
|
+
selected feature, ending `FINISH :: refresh <n> features`. No phase/score/
|
|
61
|
+
finding/verdict markers — this lane runs none of those phases.
|
|
@@ -16,7 +16,7 @@ below. Load its references and schemas by path — the HOT-PATH essentials
|
|
|
16
16
|
(dispatch names, return-contract fields, artifact path) are inlined here so
|
|
17
17
|
nothing is reconstructed from "full minus deltas."
|
|
18
18
|
|
|
19
|
-
Run as **Opus 4.8 high**, or Opus 5 / Fable 5 at medium+ (as full; never downgrade).
|
|
19
|
+
Run as **Opus 4.8 high**, or Opus 5.5 / Fable 5 at medium+ (as full; never downgrade).
|
|
20
20
|
**You never implement — you spawn.** The one exception is the **smoke gate**: a
|
|
21
21
|
read-only build+test run, not implementation — you still never write code.
|
|
22
22
|
**Worked example** (orient only — never execute from it): `examples/mini-run-mock.md`.
|
|
@@ -158,7 +158,7 @@ mini skipped. Record the switch in the decision log.
|
|
|
158
158
|
|
|
159
159
|
## Dispatch via named agents (canonical name-map — dispatch BY these names)
|
|
160
160
|
|
|
161
|
-
Models pinned in `.claude/agents/`; look one up here, never reconstruct a name (agent = skill-name + model-effort suffix). See `.claude/agents/MODEL-MAPPING.md`. `opus5_only: true` FORCES the right column and needs an Opus 5 main session — mini's cheap-lane premise is off while it is on (`../_shared/opus5-only.md`).
|
|
161
|
+
Models pinned in `.claude/agents/`; look one up here, never reconstruct a name (agent = skill-name + model-effort suffix). See `.claude/agents/MODEL-MAPPING.md`. `opus5_only: true` FORCES the right column and needs an Opus 5.5 main session — mini's cheap-lane premise is off while it is on (`../_shared/opus5-only.md`).
|
|
162
162
|
|
|
163
163
|
**Extra (`extra_enabled`, `../_shared/extra-dispatch.md`):** mini's ONE executor may run off Claude. It has no score, so resolve the pinned executor's **BAND, both edges, and require them to agree** — a partially covering row keeps the run on Claude and the preflight says so. Print the `extra:` line at intake whenever the gate is on (P0: `a lane that sends work off Claude without saying so`); dispatch via `orc extra dispatch --task <file> --json` with the IDENTICAL slice; validate with `return-validation.md` **§2b, not §2** (⛔ SUBSTITUTION replaces the downgrade check); a failure runs `orc extra reconcile <task_id>` FIRST — a worktree that moved is RESUMED, never re-done — then falls back to the pinned Claude agent, announced. A cited-risk change never leaves Claude (`extra_risk_tasks`, default `off`) — and mini's complexity read is not a substitute for that gate.
|
|
164
164
|
|
|
@@ -167,7 +167,7 @@ Models pinned in `.claude/agents/`; look one up here, never reconstruct a name (
|
|
|
167
167
|
| mini analysis (docs only) | `orc-analyze-mini-sonnet-5-high` | claude-sonnet-5 / high | `orc-analyze-mini-opus-5-med` |
|
|
168
168
|
| mini planning | `orc-planner-mini-sonnet-5-high` | claude-sonnet-5 / high | `orc-planner-mini-opus-5-med` |
|
|
169
169
|
| mini execution | `orc-executor-sonnet-5-high` | claude-sonnet-5 / high | `orc-executor-opus-5-low` |
|
|
170
|
-
| test authoring (opt-in) | `orc-test-author-opus-5-med` | claude-opus-5 / medium | unchanged |
|
|
170
|
+
| test authoring (opt-in) | `orc-test-author-opus-5-med` | claude-opus-5-5 / medium | unchanged |
|
|
171
171
|
|
|
172
172
|
## Config
|
|
173
173
|
|
|
@@ -5,7 +5,7 @@ description: >
|
|
|
5
5
|
"/orc-verify", or "check the modified files". Runs INDEPENDENTLY —
|
|
6
6
|
no orchestrator, no planning, no run folder required. Verifies only the
|
|
7
7
|
git-modified changes in the working tree and shows a summary of results. Uses
|
|
8
|
-
Opus 5 medium effort. Read-only: it reports, it does not fix or commit.
|
|
8
|
+
Opus 5.5 medium effort. Read-only: it reports, it does not fix or commit.
|
|
9
9
|
---
|
|
10
10
|
|
|
11
11
|
# ORC-VERIFY (standalone)
|
|
@@ -13,7 +13,7 @@ description: >
|
|
|
13
13
|
A focused, dependency-free verify pass. No intake, no planning, no checkpoint —
|
|
14
14
|
you point it at your uncommitted work and it tells you what's wrong.
|
|
15
15
|
|
|
16
|
-
Run as Opus 5, medium effort.
|
|
16
|
+
Run as Opus 5.5, medium effort.
|
|
17
17
|
|
|
18
18
|
**Worked example** (orient only — never execute from it): `examples/verify-mock.md`.
|
|
19
19
|
|
|
@@ -97,16 +97,16 @@ exit code, and never re-derive a state word — the CLI's state words are the on
|
|
|
97
97
|
state words, and **an exit code is an ANSWER wherever that contract says so, not
|
|
98
98
|
a failure**. A call the answer does not name is a call this lane does not make.
|
|
99
99
|
Exit ≠ 0 from the catalogue itself → say the CLI is unavailable and name the
|
|
100
|
-
command you are about to run, out loud, before running it.
|
|
101
|
-
|
|
102
|
-
## Rules — the anti-slop card (`../_shared/phases/rules.md`)
|
|
103
|
-
|
|
104
|
-
`orc rules slice --lane orc-verify --json` is the ONLY assembler; never build
|
|
105
|
-
the card here. It rides under the house rules and above the task —
|
|
106
|
-
**house rules > your project's rules > ORC's own packs** — and its `line` prints
|
|
107
|
-
VERBATIM at preflight. Returns gain `rules_applied[]`, `rules_conflicts[]` (a gap,
|
|
108
|
-
never a silent choice) and `rules_overridden[]`.
|
|
109
|
-
## Waiting mid-run (`/orc-wait`)
|
|
110
|
-
|
|
111
|
-
Canonical: `../_shared/wait.md`. **`a lane that waits without a hand-back` has broken this contract.**
|
|
112
|
-
Checkpoint **none** · safe point **single dispatch**. Nothing here to checkpoint, so all three modes behave identically — say so rather than asking. Never begin a wait between a dispatch and its validated return, or before the smoke gate has reported.
|
|
100
|
+
command you are about to run, out loud, before running it.
|
|
101
|
+
|
|
102
|
+
## Rules — the anti-slop card (`../_shared/phases/rules.md`)
|
|
103
|
+
|
|
104
|
+
`orc rules slice --lane orc-verify --json` is the ONLY assembler; never build
|
|
105
|
+
the card here. It rides under the house rules and above the task —
|
|
106
|
+
**house rules > your project's rules > ORC's own packs** — and its `line` prints
|
|
107
|
+
VERBATIM at preflight. Returns gain `rules_applied[]`, `rules_conflicts[]` (a gap,
|
|
108
|
+
never a silent choice) and `rules_overridden[]`.
|
|
109
|
+
## Waiting mid-run (`/orc-wait`)
|
|
110
|
+
|
|
111
|
+
Canonical: `../_shared/wait.md`. **`a lane that waits without a hand-back` has broken this contract.**
|
|
112
|
+
Checkpoint **none** · safe point **single dispatch**. Nothing here to checkpoint, so all three modes behave identically — say so rather than asking. Never begin a wait between a dispatch and its validated return, or before the smoke gate has reported.
|
|
@@ -1,33 +1,33 @@
|
|
|
1
|
-
# Example — Annotated Standalone Verify (dry run)
|
|
2
|
-
|
|
3
|
-
V: = verifier (Opus 5 medium) · U: = user. Nothing real. Runs INDEPENDENTLY — no
|
|
4
|
-
orchestrator, no planning, no run folder. Read-only: it reports, never fixes or commits.
|
|
5
|
-
|
|
6
|
-
U: /orc-verify
|
|
7
|
-
|
|
8
|
-
## Scope — git-modified changes only
|
|
9
|
-
V: [git status/diff] 3 modified files: api/routes/orders.py, api/schemas.py,
|
|
10
|
-
tests/test_orders.py. Nothing staged beyond the working tree — verifying exactly
|
|
11
|
-
these changes (no repo-wide sweep).
|
|
12
|
-
|
|
13
|
-
## Build + tests
|
|
14
|
-
V: [detects Python/poetry/pytest]
|
|
15
|
-
$ poetry run pytest tests/test_orders.py → 11 passed
|
|
16
|
-
$ poetry run mypy api/ → clean
|
|
17
|
-
Build/type/test: GREEN.
|
|
18
|
-
|
|
19
|
-
## Diff sanity + findings (P0–P3 ladder)
|
|
20
|
-
V: Walks each hunk against intent inferred from the diff (every P0–P2 finding
|
|
21
|
-
anchored: file:line + the offending line quoted VERBATIM, else auto-P3):
|
|
22
|
-
⛔ P1 api/routes/orders.py:42 — quote: `async def get_order(order_id: str):`
|
|
23
|
-
— new `/orders/{id}` route has no auth decorator; every sibling route
|
|
24
|
-
uses `@require_auth`. Security risk — likely unintended.
|
|
25
|
-
(Not P0: build/tests are green.)
|
|
26
|
-
• P3 api/schemas.py:18 — field `createdAt` breaks the snake_case convention
|
|
27
|
-
used elsewhere (`created_at`).
|
|
28
|
-
• P2 tests/test_orders.py — no negative-path test for a missing id.
|
|
29
|
-
|
|
30
|
-
## Summary (read-only — no edits, no commit)
|
|
31
|
-
V: 1 P1, 1 P2, 1 P3. Tests green but the missing auth decorator gates the
|
|
32
|
-
commit (P0/P1 = fix before commit; P2/P3 advisory). I don't edit or commit —
|
|
33
|
-
hand this to /orc or fix manually, then re-run /orc-verify.
|
|
1
|
+
# Example — Annotated Standalone Verify (dry run)
|
|
2
|
+
|
|
3
|
+
V: = verifier (Opus 5.5 medium) · U: = user. Nothing real. Runs INDEPENDENTLY — no
|
|
4
|
+
orchestrator, no planning, no run folder. Read-only: it reports, never fixes or commits.
|
|
5
|
+
|
|
6
|
+
U: /orc-verify
|
|
7
|
+
|
|
8
|
+
## Scope — git-modified changes only
|
|
9
|
+
V: [git status/diff] 3 modified files: api/routes/orders.py, api/schemas.py,
|
|
10
|
+
tests/test_orders.py. Nothing staged beyond the working tree — verifying exactly
|
|
11
|
+
these changes (no repo-wide sweep).
|
|
12
|
+
|
|
13
|
+
## Build + tests
|
|
14
|
+
V: [detects Python/poetry/pytest]
|
|
15
|
+
$ poetry run pytest tests/test_orders.py → 11 passed
|
|
16
|
+
$ poetry run mypy api/ → clean
|
|
17
|
+
Build/type/test: GREEN.
|
|
18
|
+
|
|
19
|
+
## Diff sanity + findings (P0–P3 ladder)
|
|
20
|
+
V: Walks each hunk against intent inferred from the diff (every P0–P2 finding
|
|
21
|
+
anchored: file:line + the offending line quoted VERBATIM, else auto-P3):
|
|
22
|
+
⛔ P1 api/routes/orders.py:42 — quote: `async def get_order(order_id: str):`
|
|
23
|
+
— new `/orders/{id}` route has no auth decorator; every sibling route
|
|
24
|
+
uses `@require_auth`. Security risk — likely unintended.
|
|
25
|
+
(Not P0: build/tests are green.)
|
|
26
|
+
• P3 api/schemas.py:18 — field `createdAt` breaks the snake_case convention
|
|
27
|
+
used elsewhere (`created_at`).
|
|
28
|
+
• P2 tests/test_orders.py — no negative-path test for a missing id.
|
|
29
|
+
|
|
30
|
+
## Summary (read-only — no edits, no commit)
|
|
31
|
+
V: 1 P1, 1 P2, 1 P3. Tests green but the missing auth decorator gates the
|
|
32
|
+
commit (P0/P1 = fix before commit; P2/P3 advisory). I don't edit or commit —
|
|
33
|
+
hand this to /orc or fix manually, then re-run /orc-verify.
|
|
@@ -20,7 +20,7 @@ tier:
|
|
|
20
20
|
| `wiki-scanner-light` | `orc-wiki-scanner-sonnet-5-high` |
|
|
21
21
|
|
|
22
22
|
Both collapse onto `orc-wiki-scanner-opus-5-med` while `opus5_only` is on, which
|
|
23
|
-
is why this adds **no agent and no pair**. Two slots and one Opus 5 agent is not
|
|
23
|
+
is why this adds **no agent and no pair**. Two slots and one Opus 5.5 agent is not
|
|
24
24
|
a contradiction: a slot names the POSITION, not the model.
|
|
25
25
|
|
|
26
26
|
```
|