@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.
Files changed (107) hide show
  1. package/CHANGELOG.md +69 -0
  2. package/README-id.md +38 -39
  3. package/README.md +36 -35
  4. package/bin/build-agents.js +109 -109
  5. package/bin/cli.js +35 -33
  6. package/bin/onboarding-content.js +4 -4
  7. package/bin/pricing.json +207 -200
  8. package/bin/verify-contracts.js +2 -2
  9. package/bin/verify-package.js +7 -7
  10. package/bin/webui/css/04-motion.css +162 -152
  11. package/bin/webui/css/panels/knowledge.css +563 -116
  12. package/bin/webui/fixtures/extra.js +2036 -2036
  13. package/bin/webui/fixtures/hookui.js +5 -5
  14. package/bin/webui/fixtures/settings.js +305 -305
  15. package/bin/webui/i18n/en/knowledge.json +117 -2
  16. package/bin/webui/i18n/id/knowledge.json +117 -2
  17. package/bin/webui/js/panels/knowledge.js +552 -7
  18. package/bin/webui/js/panels/overview.js +13 -4
  19. package/mock-run/context-combiner.md +100 -100
  20. package/mock-run/orc-budget.md +534 -534
  21. package/mock-run/orc-challenge-council.md +262 -262
  22. package/mock-run/orc-ultra.md +103 -103
  23. package/package.json +1 -1
  24. package/templates/agents/MODEL-MAPPING.md +43 -43
  25. package/templates/agents/orc-advisor-opus-5-xhigh.md +56 -56
  26. package/templates/agents/orc-analyze-mini-opus-5-med.md +60 -60
  27. package/templates/agents/orc-analyze-mini-sonnet-5-high.md +58 -58
  28. package/templates/agents/orc-challenge-advisor-opus-5-med.md +75 -75
  29. package/templates/agents/orc-challenge-contrarian-opus-5-high.md +110 -110
  30. package/templates/agents/orc-challenge-executor-opus-5-med.md +114 -114
  31. package/templates/agents/orc-challenge-expansionist-opus-5-med.md +112 -112
  32. package/templates/agents/orc-challenge-judge-opus-5-high.md +132 -132
  33. package/templates/agents/orc-challenge-outsider-opus-5-low.md +109 -109
  34. package/templates/agents/orc-challenge-principles-opus-5-high.md +109 -109
  35. package/templates/agents/orc-challenge-reader-opus-5-low.md +90 -90
  36. package/templates/agents/orc-claude-writer-opus-5-med.md +55 -55
  37. package/templates/agents/orc-context-combiner-opus-5-high.md +88 -88
  38. package/templates/agents/orc-doc-checker-opus-5-low.md +108 -108
  39. package/templates/agents/orc-doc-writer-opus-5-med.md +134 -134
  40. package/templates/agents/orc-executor-opus-5-high.md +2 -2
  41. package/templates/agents/orc-executor-opus-5-low.md +2 -2
  42. package/templates/agents/orc-executor-opus-5-med.md +2 -2
  43. package/templates/agents/orc-graph-noter-sonnet-4-6-med.md +1 -1
  44. package/templates/agents/orc-judge-opus-5-xhigh.md +85 -85
  45. package/templates/agents/orc-learn-writer-opus-5-low.md +73 -73
  46. package/templates/agents/orc-pattern-codifier-opus-5-med.md +65 -65
  47. package/templates/agents/orc-planner-mini-opus-5-med.md +4 -4
  48. package/templates/agents/orc-planner-mini-sonnet-5-high.md +1 -1
  49. package/templates/agents/orc-planner-opus-5-med.md +160 -160
  50. package/templates/agents/orc-recon-opus-5-low.md +3 -3
  51. package/templates/agents/orc-retro-opus-5-med.md +3 -3
  52. package/templates/agents/orc-reviewer-opus-5-med.md +60 -60
  53. package/templates/agents/orc-scout-opus-5-low.md +40 -40
  54. package/templates/agents/orc-system-analyst-opus-5-high.md +120 -120
  55. package/templates/agents/orc-test-author-opus-5-med.md +71 -71
  56. package/templates/agents/orc-test-designer-opus-5-high.md +158 -158
  57. package/templates/agents/orc-test-interpreter-opus-5-low.md +130 -130
  58. package/templates/agents/orc-verifier-opus-5-med.md +69 -69
  59. package/templates/agents/orc-wiki-scanner-opus-5-med.md +81 -81
  60. package/templates/commands/orc-ultra.md +17 -17
  61. package/templates/commands/orc-verify.md +11 -11
  62. package/templates/hooks/README.md +2 -2
  63. package/templates/hooks/orc-effort-guard.js +178 -178
  64. package/templates/hooks/orc-statusline.js +6 -6
  65. package/templates/skills/_shared/code-graph.md +1 -1
  66. package/templates/skills/_shared/config-precedence.md +198 -198
  67. package/templates/skills/_shared/extra-dispatch.md +1346 -1346
  68. package/templates/skills/_shared/opus5-only.md +8 -8
  69. package/templates/skills/_shared/phases/analyst-gates.md +136 -136
  70. package/templates/skills/_shared/phases/review.md +1 -1
  71. package/templates/skills/_shared/phases/trace.md +1 -1
  72. package/templates/skills/_shared/return-validation.md +1 -1
  73. package/templates/skills/context-combiner/SKILL.md +1 -1
  74. package/templates/skills/context-combiner/schemas/combined-report.md +78 -78
  75. package/templates/skills/orc/README.md +2 -2
  76. package/templates/skills/orc/SKILL.md +7 -7
  77. package/templates/skills/orc/config.md +9 -9
  78. package/templates/skills/orc/examples/full-run-mock.md +73 -73
  79. package/templates/skills/orc/references/effort-and-mode.md +222 -222
  80. package/templates/skills/orc/references/preflight-report.md +2 -2
  81. package/templates/skills/orc/references/ultra-mode.md +3 -3
  82. package/templates/skills/orc/subskills/orc-planner/SKILL.md +2 -2
  83. package/templates/skills/orc/subskills/orc-planner-mini/SKILL.md +121 -121
  84. package/templates/skills/orc/subskills/orc-review-verify/SKILL.md +76 -76
  85. package/templates/skills/orc/subskills/orc-testgen/SKILL.md +45 -45
  86. package/templates/skills/orc-analyze/SKILL.md +2 -2
  87. package/templates/skills/orc-analyze/examples/analyze-mock.md +42 -42
  88. package/templates/skills/orc-analyze/schemas/report-audit.md +83 -83
  89. package/templates/skills/orc-analyze/schemas/report-prose.md +63 -63
  90. package/templates/skills/orc-analyze/schemas/report-requirement.md +78 -78
  91. package/templates/skills/orc-challenge/README.md +142 -142
  92. package/templates/skills/orc-challenge/examples/council-full-roster.md +273 -273
  93. package/templates/skills/orc-challenge/references/council.md +315 -315
  94. package/templates/skills/orc-challenge/references/intake.md +171 -171
  95. package/templates/skills/orc-claude/SKILL.md +14 -14
  96. package/templates/skills/orc-diy/README.md +143 -143
  97. package/templates/skills/orc-diy/references/flow-schema.md +1 -1
  98. package/templates/skills/orc-doc/README.md +229 -229
  99. package/templates/skills/orc-doc/examples/orc-doc-prd-run.md +325 -325
  100. package/templates/skills/orc-doc/references/chunking.md +527 -527
  101. package/templates/skills/orc-fast/SKILL.md +1 -1
  102. package/templates/skills/orc-learn/SKILL.md +14 -14
  103. package/templates/skills/orc-learn/examples/learn-run-mock.md +61 -61
  104. package/templates/skills/orc-mini/SKILL.md +3 -3
  105. package/templates/skills/orc-verify/SKILL.md +15 -15
  106. package/templates/skills/orc-verify/examples/verify-mock.md +33 -33
  107. package/templates/skills/orc-wiki/references/extra.md +1 -1
@@ -1,143 +1,143 @@
1
- # ORC-DIY — Build your own ORC flow
2
-
3
- > This guide is intentionally separate from the main project README. The root
4
- > README covers installing and using the shipped lanes; **everything about
5
- > composing your own lane lives here.**
6
-
7
- ORC-DIY lets you assemble a custom orchestrator pipeline from ORC's real
8
- parts — keep the phases you want, drop the ones you don't, pick the session
9
- tier, and decide how autonomous the run is. The shape is chosen entirely in
10
- your **terminal** (deterministic, zero model tokens); Claude only ever runs
11
- the flow you compiled.
12
-
13
- ```
14
- orc diy init → orc diy set … (repeat) → orc diy compile → /orc-diy <request>
15
- (config created) (shape your flow) (build the flow) (run it)
16
- ```
17
-
18
- ## 1. Bootstrap
19
-
20
- **Easiest path — the interactive composer.** Run bare `orc diy` in a real
21
- terminal: it creates the flow if none exists (pick full-lane defaults or a
22
- preset from a numbered list), then lets you shape every key with numbered
23
- pick-lists, shows the live gate status and validation issues as you go, and
24
- offers to compile on exit. Everything below is the same thing, non-interactive:
25
-
26
- ```bash
27
- orc diy # interactive composer (create + shape + compile)
28
- orc diy init # scriptable: create the default config (full-lane shape)
29
- orc diy init --preset lean # or start from a preset: lean | paranoid | solo-fast
30
- ```
31
-
32
- This writes three project-scoped files (there is no global variant — `orc
33
- diy` rejects `--global`; one flow per project):
34
-
35
- | File | What it is | Who writes it |
36
- |---|---|---|
37
- | `.claude/orc-diy.config.yaml` | your flow choices | the CLI only |
38
- | `.claude/orc/diy/flow.md` | human-readable flow spec (regenerated on every change) | the CLI only |
39
- | `.claude/orc/diy/flow.lock.json` | hashes + compile stamp — the gate's state | the CLI only |
40
-
41
- ## 2. Shape the flow
42
-
43
- ```bash
44
- orc diy show # current flow + gate status (READY / STALE / UNCONFIGURED)
45
- orc diy set review blocking-only
46
- orc diy set verify smoke
47
- orc diy set scoring off
48
- orc diy set fixed_executor orc-executor-sonnet-5-high
49
- orc diy set session_tier opus-4-7-med
50
- orc diy set autonomy semi
51
- orc diy validate # re-check cross-key rules any time
52
- ```
53
-
54
- **`opus5_only` does not reach this lane.** That config forces every other
55
- lane's roles to Opus 5, but a DIY flow's executors come from `flow.lock.json`,
56
- which only `orc diy compile` writes. To run this lane on Opus 5, set
57
- `fixed_executor`/`session_tier` here and re-compile.
58
-
59
- The full key table lives in `references/flow-schema.md`. Highlights:
60
-
61
- - **Phases** — `analyze`, `review`, `security`, `verify`, `testgen`,
62
- `summary`, `wiki_gate`: each phase has off/on/strictness values. Order is
63
- fixed; you choose presence and strictness.
64
- - **Scoring** — `scoring on` keeps the per-task rubric; `scoring off` skips
65
- it and sends every task to your `fixed_executor`.
66
- - **Session tier** — `session_tier` is the model+effort the compiled flow
67
- requires. DIY is SEPARATE from the baseline /orc rule — pick any tier from the
68
- full grid: `sonnet-4-6-{med,high}`, `opus-4-7-{med,high}`,
69
- `opus-4-8-{med,high,xhigh,max}`, `opus-5-{med,high,xhigh,max}`,
70
- `fable-5-{med,high,xhigh,max}` (default
71
- `opus-5-high` — D29 moved it there at v1.0.0 so the wizard's own default
72
- does not clip the two Opus 5 bands the score table ships). The effort guard enforces the effort half deterministically
73
- (the compiled effort OR higher on the ladder); the statusline warns on the
74
- model half. Executor choices above the tier are rejected at validate time; the
75
- score table is clipped to the tier at compile time.
76
- - **Autonomy** — `interactive` (all asks), `semi` (routine asks
77
- auto-accepted), `hands-off` (only hard stops + ship). Locked safety rules
78
- are never overridden — see `references/locked-blocks.md` for what you can
79
- NEVER configure away.
80
- - **Ship** — `ship_mode`: `ask`, `commit`, `pr`, or `report-only`.
81
-
82
- ## 3. Compile
83
-
84
- ```bash
85
- orc diy compile # deterministic stitch — no model, no tokens
86
- ```
87
-
88
- The compiler validates, cherry-picks the needed references from your
89
- installed orc skill, stitches `.claude/orc/diy/FLOW-COMPILED.md`, and stamps
90
- `flow.lock.json`. Details: `references/compile.md`.
91
-
92
- **Every change requires a recompile.** The gate flips to STALE whenever:
93
- - you change any key (`orc diy set` …),
94
- - you update orc (`orc update` / `orc upgrade`),
95
- - the compiled file is edited or deleted.
96
-
97
- `/orc-diy` will not run a stale flow — it names the reason, tells you to run
98
- `orc diy compile`, and offers the regular `/orc` lane for the request at
99
- hand. `/orc-diy compile` in a session just runs the same CLI compiler.
100
-
101
- ## 4. Run
102
-
103
- ```
104
- /orc-diy implement the CSV export endpoint
105
- ```
106
-
107
- The stub skill checks the gate, then follows your compiled flow: same run
108
- folders, checkpoints, subagents, and evidence rules as the full lane — minus
109
- the phases you removed, plus the strictness you chose.
110
-
111
- ## Presets
112
-
113
- | Preset | Shape |
114
- |---|---|
115
- | `lean` | analyze off, review blocking-only, verify smoke, summary short |
116
- | `paranoid` | analyze full, security always, testgen on, verify full |
117
- | `solo-fast` | scoring off → one Sonnet 5 high executor, review off, verify smoke, autonomy semi |
118
-
119
- Presets are just config bundles — inspect with `orc diy show`, tweak with
120
- `set`, and compile like any other flow.
121
-
122
- ## Command reference
123
-
124
- ```
125
- orc diy INTERACTIVE composer (create/shape/compile in one menu)
126
- orc diy init [--preset <name>] [--force] create (or overwrite) the config
127
- orc diy show flow table + gate status
128
- orc diy status [--json] gate status only (used by the skill/hooks)
129
- orc diy set <key> <value> change one key (invalidates the compile)
130
- orc diy validate run cross-key validation
131
- orc diy compile build FLOW-COMPILED.md + stamp the lock
132
- orc diy reset delete config, flow, lock, and compiled file
133
- ```
134
-
135
- ## Boundaries (read before getting creative)
136
-
137
- - The CLI is the only writer. Never hand-edit the config, the lock, or the
138
- compiled flow — and never ask Claude to; the skill refuses by contract.
139
- - `references/locked-blocks.md` is compiled into every flow verbatim: the
140
- orchestrator never implements, checkpoint discipline, wave conflict rules,
141
- the severity ladder, and red-build ship blocking are not yours to remove.
142
- - orc-diy needs the orc skill installed next to it (it cherry-picks by
143
- reference); `orc init` installs both.
1
+ # ORC-DIY — Build your own ORC flow
2
+
3
+ > This guide is intentionally separate from the main project README. The root
4
+ > README covers installing and using the shipped lanes; **everything about
5
+ > composing your own lane lives here.**
6
+
7
+ ORC-DIY lets you assemble a custom orchestrator pipeline from ORC's real
8
+ parts — keep the phases you want, drop the ones you don't, pick the session
9
+ tier, and decide how autonomous the run is. The shape is chosen entirely in
10
+ your **terminal** (deterministic, zero model tokens); Claude only ever runs
11
+ the flow you compiled.
12
+
13
+ ```
14
+ orc diy init → orc diy set … (repeat) → orc diy compile → /orc-diy <request>
15
+ (config created) (shape your flow) (build the flow) (run it)
16
+ ```
17
+
18
+ ## 1. Bootstrap
19
+
20
+ **Easiest path — the interactive composer.** Run bare `orc diy` in a real
21
+ terminal: it creates the flow if none exists (pick full-lane defaults or a
22
+ preset from a numbered list), then lets you shape every key with numbered
23
+ pick-lists, shows the live gate status and validation issues as you go, and
24
+ offers to compile on exit. Everything below is the same thing, non-interactive:
25
+
26
+ ```bash
27
+ orc diy # interactive composer (create + shape + compile)
28
+ orc diy init # scriptable: create the default config (full-lane shape)
29
+ orc diy init --preset lean # or start from a preset: lean | paranoid | solo-fast
30
+ ```
31
+
32
+ This writes three project-scoped files (there is no global variant — `orc
33
+ diy` rejects `--global`; one flow per project):
34
+
35
+ | File | What it is | Who writes it |
36
+ |---|---|---|
37
+ | `.claude/orc-diy.config.yaml` | your flow choices | the CLI only |
38
+ | `.claude/orc/diy/flow.md` | human-readable flow spec (regenerated on every change) | the CLI only |
39
+ | `.claude/orc/diy/flow.lock.json` | hashes + compile stamp — the gate's state | the CLI only |
40
+
41
+ ## 2. Shape the flow
42
+
43
+ ```bash
44
+ orc diy show # current flow + gate status (READY / STALE / UNCONFIGURED)
45
+ orc diy set review blocking-only
46
+ orc diy set verify smoke
47
+ orc diy set scoring off
48
+ orc diy set fixed_executor orc-executor-sonnet-5-high
49
+ orc diy set session_tier opus-4-7-med
50
+ orc diy set autonomy semi
51
+ orc diy validate # re-check cross-key rules any time
52
+ ```
53
+
54
+ **`opus5_only` does not reach this lane.** That config forces every other
55
+ lane's roles to Opus 5.5, but a DIY flow's executors come from `flow.lock.json`,
56
+ which only `orc diy compile` writes. To run this lane on Opus 5.5, set
57
+ `fixed_executor`/`session_tier` here and re-compile.
58
+
59
+ The full key table lives in `references/flow-schema.md`. Highlights:
60
+
61
+ - **Phases** — `analyze`, `review`, `security`, `verify`, `testgen`,
62
+ `summary`, `wiki_gate`: each phase has off/on/strictness values. Order is
63
+ fixed; you choose presence and strictness.
64
+ - **Scoring** — `scoring on` keeps the per-task rubric; `scoring off` skips
65
+ it and sends every task to your `fixed_executor`.
66
+ - **Session tier** — `session_tier` is the model+effort the compiled flow
67
+ requires. DIY is SEPARATE from the baseline /orc rule — pick any tier from the
68
+ full grid: `sonnet-4-6-{med,high}`, `opus-4-7-{med,high}`,
69
+ `opus-4-8-{med,high,xhigh,max}`, `opus-5-{med,high,xhigh,max}`,
70
+ `fable-5-{med,high,xhigh,max}` (default
71
+ `opus-5-high` — D29 moved it there at v1.0.0 so the wizard's own default
72
+ does not clip the two Opus 5.5 bands the score table ships). The effort guard enforces the effort half deterministically
73
+ (the compiled effort OR higher on the ladder); the statusline warns on the
74
+ model half. Executor choices above the tier are rejected at validate time; the
75
+ score table is clipped to the tier at compile time.
76
+ - **Autonomy** — `interactive` (all asks), `semi` (routine asks
77
+ auto-accepted), `hands-off` (only hard stops + ship). Locked safety rules
78
+ are never overridden — see `references/locked-blocks.md` for what you can
79
+ NEVER configure away.
80
+ - **Ship** — `ship_mode`: `ask`, `commit`, `pr`, or `report-only`.
81
+
82
+ ## 3. Compile
83
+
84
+ ```bash
85
+ orc diy compile # deterministic stitch — no model, no tokens
86
+ ```
87
+
88
+ The compiler validates, cherry-picks the needed references from your
89
+ installed orc skill, stitches `.claude/orc/diy/FLOW-COMPILED.md`, and stamps
90
+ `flow.lock.json`. Details: `references/compile.md`.
91
+
92
+ **Every change requires a recompile.** The gate flips to STALE whenever:
93
+ - you change any key (`orc diy set` …),
94
+ - you update orc (`orc update` / `orc upgrade`),
95
+ - the compiled file is edited or deleted.
96
+
97
+ `/orc-diy` will not run a stale flow — it names the reason, tells you to run
98
+ `orc diy compile`, and offers the regular `/orc` lane for the request at
99
+ hand. `/orc-diy compile` in a session just runs the same CLI compiler.
100
+
101
+ ## 4. Run
102
+
103
+ ```
104
+ /orc-diy implement the CSV export endpoint
105
+ ```
106
+
107
+ The stub skill checks the gate, then follows your compiled flow: same run
108
+ folders, checkpoints, subagents, and evidence rules as the full lane — minus
109
+ the phases you removed, plus the strictness you chose.
110
+
111
+ ## Presets
112
+
113
+ | Preset | Shape |
114
+ |---|---|
115
+ | `lean` | analyze off, review blocking-only, verify smoke, summary short |
116
+ | `paranoid` | analyze full, security always, testgen on, verify full |
117
+ | `solo-fast` | scoring off → one Sonnet 5 high executor, review off, verify smoke, autonomy semi |
118
+
119
+ Presets are just config bundles — inspect with `orc diy show`, tweak with
120
+ `set`, and compile like any other flow.
121
+
122
+ ## Command reference
123
+
124
+ ```
125
+ orc diy INTERACTIVE composer (create/shape/compile in one menu)
126
+ orc diy init [--preset <name>] [--force] create (or overwrite) the config
127
+ orc diy show flow table + gate status
128
+ orc diy status [--json] gate status only (used by the skill/hooks)
129
+ orc diy set <key> <value> change one key (invalidates the compile)
130
+ orc diy validate run cross-key validation
131
+ orc diy compile build FLOW-COMPILED.md + stamp the lock
132
+ orc diy reset delete config, flow, lock, and compiled file
133
+ ```
134
+
135
+ ## Boundaries (read before getting creative)
136
+
137
+ - The CLI is the only writer. Never hand-edit the config, the lock, or the
138
+ compiled flow — and never ask Claude to; the skill refuses by contract.
139
+ - `references/locked-blocks.md` is compiled into every flow verbatim: the
140
+ orchestrator never implements, checkpoint discipline, wave conflict rules,
141
+ the severity ladder, and red-build ship blocking are not yours to remove.
142
+ - orc-diy needs the orc skill installed next to it (it cherry-picks by
143
+ reference); `orc init` installs both.
@@ -60,7 +60,7 @@ Warnings (written, reported):
60
60
  - `autonomy: hands-off` with `ship_mode: commit` or `pr` (fully unattended
61
61
  git actions).
62
62
  - `session_tier` below `opus-5-med` with `review`/`verify` on: the pinned
63
- Opus 5 reviewer/verifier agents will silently run at the session's model —
63
+ Opus 5.5 reviewer/verifier agents will silently run at the session's model —
64
64
  the flow still works, honesty-checked by the tier-honesty locked rule.
65
65
 
66
66
  ## `flow.lock.json` (machine state — written by the CLI only)