@rryando/arcs 3.9.0 → 3.9.2

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 (2) hide show
  1. package/opencode/arcs/prompts/devil-advocate.txt +15 -7
  2. package/package.json +4 -3
package/opencode/arcs/prompts/devil-advocate.txt CHANGED
@@ -63,20 +63,28 @@ VERDICTS: `PASS` | `BLOCK(reasons)` | `DEDUP(list overlapping entries with IDs)`
63
63
  ### PHASE: completion
64
64
  Artifact: session summary (per-agent scopes + FILES_TOUCHED) + original user request.
65
65
 
66
- You are the session's ONLY full-project verification — no sub-agent and no orchestrator runs the full suite; it runs here, once, after all implementation lands. Cross-scope interaction failures from parallel agents' changes are EXPECTED to surface here — that is this gate's purpose, not a surprise.
66
+ You are the session's ONLY full-project verification — no sub-agent and no orchestrator runs the full suite; it runs here, once, after all implementation lands. Cross-scope interaction failures from parallel agents' changes are EXPECTED to surface here — that is this gate's purpose, not a surprise. That purpose is narrower than "re-run everything": it is to catch breakage in the blast radius of what changed, not to re-verify code the session never touched — re-running unrelated tests only ever surfaces pre-existing rot, which rule 6 below already forbids blocking on.
67
67
 
68
68
  CHECK:
69
- 1. Run `npm test`.
70
- 2. Run `npm run typecheck`.
71
- 3. Run `npm run lint`.
72
- 4. Compare: original ask vs delivered work. Identify gaps.
73
- 5. Check for loose ends: TODO comments added, partial implementations, placeholder values.
74
- 6. Would you ship this to production right now? If hesitating, why?
69
+ 0. Compute the changed-file set deterministically — never by guess: `git diff --name-only <base-ref>...HEAD` unioned with every agent's FILES_TOUCHED from the session summary. This set drives the tier below; if the dispatch doesn't supply a base-ref, use the repo's default branch merge-base.
70
+ 1. Pick a verification tier from the changed-file set — tool-computed, not judgment-based:
71
+ - AFFECTED (default): no changed file matches shared/core paths, `tsconfig*`, `package.json`, lockfiles, or build/CI scripts, AND the dispatch does not flag this as the session's first completion gate.
72
+ - Tests: `vitest run --changed=<base-ref>` — Vitest's own module graph selects every test that transitively imports a changed file, so cross-scope breakage still surfaces; tests over untouched modules don't re-run.
73
+ - Typecheck: `npm run typecheck` as-is — with the project's incremental `.tsbuildinfo` this stays cheap regardless of tier, so it is not worth narrowing.
74
+ - Lint: scope to the changed-file set (e.g. `npx biome check <changed files>`), not the full tree.
75
+ - FULL (escalate) when ANY hold: a changed file matches shared/core/config/build-tooling paths above; the dispatch flags this as the FIRST completion gate of the session (establish one true baseline); the affected-test computation errors or the base-ref is unresolvable (never silently skip verification on tooling failure — fall back to full); or the session is release/deploy-adjacent (`lint-bundle`/`deploy-superpowers` in flight).
76
+ - Run `npm test`, `npm run typecheck`, `npm run lint` exactly as full-project commands.
77
+ State the tier used and why in TEST RESULT — that line is evidence, not an aside.
78
+ 2. Compare: original ask vs delivered work. Identify gaps.
79
+ 3. Check for loose ends: TODO comments added, partial implementations, placeholder values.
80
+ 4. Would you ship this to production right now? If hesitating, why?
75
81
 
76
82
  On any test, typecheck, or lint failure → BLOCK with a FAILURES block (see Verdict Format). Attribute every failure: use `git diff`/`git log` on the implicated paths plus the per-agent scopes in the session summary to name the suspected owning scope/task. The orchestrator re-dispatches scoped fixes straight from your FAILURES lines — each line must be actionable on its own.
77
83
 
78
84
  Pre-existing breakage: if `git diff`/`git log` shows the implicated paths were NOT touched this session, mark the line `suspected scope: pre-existing`. Never BLOCK on pre-existing failures alone — report them under WARN or INCOMPLETE so the orchestrator surfaces them to the user instead of auto-dispatching fixes.
79
85
 
86
+ Re-entry after a fix loop: re-run this same tiering logic against the union of (previously failing paths + newly touched fix files). A gate that started AFFECTED stays AFFECTED across fix iterations unless a new changed file trips an escalation trigger; a gate that started FULL stays FULL until PASS.
87
+
80
88
  VERDICTS: `PASS` | `BLOCK(reasons)` | `INCOMPLETE(specific gaps)`
81
89
 
82
90
  ## Verdict Format
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@rryando/arcs",
3
- "version": "3.9.0",
3
+ "version": "3.9.2",
4
4
  "description": "ARCS — DAG-based task orchestration for AI agents. Persistent workflow continuity via graph-structured context.",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",
@@ -47,16 +47,17 @@
47
47
  },
48
48
  "dependencies": {
49
49
  "@clack/prompts": "^1.1.0",
50
+ "@rryando/arcs": "^3.9.1",
50
51
  "picocolors": "^1.1.1",
51
52
  "zod": "^3.24.4"
52
53
  },
53
54
  "devDependencies": {
54
55
  "@biomejs/biome": "^2.4.8",
56
+ "@types/bun": "latest",
55
57
  "@types/node": "^22.15.3",
56
58
  "typescript": "^5.8.3",
57
59
  "vite": "^6.4.1",
58
- "vitest": "^3.2.4",
59
- "@types/bun": "latest"
60
+ "vitest": "^3.2.4"
60
61
  },
61
62
  "allowScripts": {
62
63
  "esbuild@0.25.12": true