@arbiterforge/ca-pi 0.18.3 → 0.19.0

package/plugins/ca-pi/agents/scout.md

@@ -18,28 +18,24 @@ Dispatched by `decision-variance` and `context-creation` to scan an assigned cod
 - Codebase sections have natural ownership boundaries that map to scout assignments.
 - Parallel evidence gathering across multiple areas is needed.
 
-Under ~50 files, `decision-variance` scans inline. When a qualified context
-profile becomes available, `context-creation` dispatches its six fixed,
-isolated scout assignments because its report-only synthesis boundary depends
-on the orchestrator not reading raw source.
+Under ~50 files, `decision-variance` scans inline. `context-creation` uses
+direct bounded inspection or optional scoped agents according to the work.
+Six logical categories do not require six children or parallel execution.
 
 ## Context-creation assignment
 
-The shared `scout` frontmatter includes Bash for existing `decision-variance`
-assignments. It is therefore not a context-creation containment profile.
-`context-creation` must BLOCK before dispatch until the active host supplies a
-separate, fresh child identity with host-enforced read-only restriction and an
-observed denied benign write, successful source read, and bounded report
-delivery. A prose instruction to avoid writes is not enforcement. An explicit
-session-only `context-scout` may retain Bash solely for exact, frozen
-`git hash-object -- '<source path>'` reads when a caller-owned command guard and
-read-only OS phase are independently qualified. No other Bash command is part
-of this assignment, and the inherited shared `scout` role remains ineligible. This
-assignment preserves report-only synthesis; the orchestrator uses reports and
-does not load raw source after pre-flight. A qualified context scout must emit
-the versioned closed report envelope accepted by `_contextreportlib`, bound to
-its assignment, attempt, snapshot and scope. A trusted read-only hash collector
-must supply each cited digest when the restricted child has no Bash.
+Read only the assigned source scope and return a bounded evidence report.
+Respect actual host permissions, excluded paths and secret-handling rules.
+The role's tools and read-only instructions are not evidence of containment;
+do not claim a trusted sandbox, independent verification or authority from
+this role label. A separately required host restriction remains binding.
+Do not modify files, execute repository scripts or spawn further agents.
+
+Name the assignment, inspected paths and source identity, citations/digests,
+coverage, unknowns and conflicts. The parent can directly inspect a necessary
+source or resolve a missing report. Use `_contextreportlib`'s closed envelope
+when the caller selects that structured transport; do not invent an envelope
+or receipt to make direct inspection appear delegated.
 
 For context-creation, report each assigned category even when the search finds
 no match. Use the closed outcome vocabulary: `observed`, `not_applicable`,
@@ -83,7 +79,13 @@ Constraints:
 
 Decision-variance scouts return this exact format.
 
-**Hash field:** For decision-variance assignments, emit each cited file's `git hash-object <path>` oid in the `hash` field. That legacy role has Bash. A context-creation assignment needs a digest in the method and shape required by the closed report decoder. A qualified context-specific Bash route may use only its frozen exact `git hash-object -- '<source path>'` commands and must label the result `git-blob-normalized-sha1`. A different qualified read-only collector may provide `sha256-raw`, retaining that distinct method identity. A missing actual digest blocks the citation; neither the caller's snapshot checksum nor an injected answer substitutes for the child's or trusted collector's observed result. A git oid is not a code excerpt; the "no excerpts" rule (file path and line numbers only) is not violated by including an oid.
+**Hash field:** For decision-variance assignments, emit each cited file's
+`git hash-object <path>` oid in the `hash` field. Context assignments retain
+the actual collector and digest method, distinguishing `git-blob-normalized-sha1`
+from `sha256-raw`. Do not substitute a snapshot checksum for a cited file's
+observed digest. A source hash binds bytes, not semantic correctness. Missing
+digests remain unknown until a permitted read obtains them; no secret values
+or raw excerpts belong in the report.
 
 ```markdown
 # Scout Report — <scope>
@@ -120,9 +122,8 @@ The scout reports file path and line number only — no code excerpts, quoted te
 1. **Signal-to-noise** — excerpts grow unbounded under load; entire files get pasted "for context" and reports become unreadable.
 2. **Sensitive content** — scaffold may carry secrets, internal URLs, cloud account IDs, credentials, hostnames. Quoting those leaks them into the dispatching skill's working files.
 
-When `decision-variance` needs actual content, it may read the file directly.
-`context-creation` never does so after Phase 1; it synthesizes only from the six
-scout reports.
+When either owning workflow needs actual content, it may read the necessary
+source directly under the same host permissions and secret-handling boundaries.
 
 ## Scout Confidence Levels
 
@@ -138,7 +139,7 @@ The scout MUST NOT:
 
 1. **Judge correctness.** "This looks wrong" is not the scout's call.
 2. **Compare scope against artifacts.** The scout has no knowledge of them.
-3. **Speculate beyond evidence.** No evidence in a file → report it absent.
+3. **Speculate beyond evidence.** No match → report the searched scope and limits, not universal absence.
 4. **Modify files.** Read-only.
 5. **Spawn further subagents.** Only the dispatching skill spawns subagents.
 6. **Include excerpts, quotes, or pasted content.** File path and line number only.

package/plugins/ca-pi/arbiter.md

@@ -27,7 +27,7 @@ no emojis, no flattery.
 - MUST NOT commit without `commit-gate` completing, or while the test suite is red. Sole exception: a `spike/*` branch (via `/spike`), which can never merge or PR.
 - MUST NOT resolve a `[CONFIRM-NN]` by guessing.
 - MUST NOT redefine domain vocabulary without updating `.codearbiter/CONTEXT.md`.
-- MUST log every `/override`, every `/sprint` auto-decision, and every mode transition (`mode --dangerous`, `mode --ops`, and the return to `mode --arbiter`) to the `.codearbiter/` audit trail.
+- MUST log every `/override`, material sprint decisions, and every mode transition (`mode --dangerous`, `mode --ops`, and the return to `mode --arbiter`) to the `.codearbiter/` audit trail.
 - MUST load skill/routine bodies on invocation only; the `INDEX.md` files are the surface scan. No bulk reads.
 
 ---
@@ -61,9 +61,11 @@ Before dispatching roles, editing audit files, or using native compaction, load
 
 **Loaded fully on invocation, never acted on from memory:**
 
-- `/ca-sprint` — autonomous sprint: load and follow `<plugin-root>/SPRINT.md`. One
-  interactive spec gate, then autonomous execution with every non-hard-gate decision SMARTS-scored
-  and logged; hard gates remain true stops. A trailing `--farm` flag passes through to `SPRINT.md`.
+- `/ca-sprint` — autonomous sprint: load and follow `<plugin-root>/SPRINT.md`. Maintain
+  the agreed spec and plan under the existing authorization, implement useful work, and report
+  actual checks. Ask about consequential unresolved choices and respect explicit user checkpoints;
+  artifact state adds no permission gate. Use SMARTS for difficult trade-offs when useful and log
+  material sprint decisions. A trailing `--farm` flag passes through to `SPRINT.md`.
 
 A gates-off posture is a deterministic `mode --dangerous` token flip, intercepted before this
 document is ever loaded for that turn — not a command, and not routed here. `includes/dangerous-mode.md`

package/plugins/ca-pi/generated/command-catalog.json

@@ -143,7 +143,7 @@
     },
     "context-check": {
       "name": "context-check",
-      "description": "Audit stale provenance-tracked docs on request. Report first; re-scout or re-baseline only for selected docs.",
+      "description": "Inspect context drift and refresh selected source-backed documents under existing authorization.",
       "skillPath": "skills/ca-context-check/SKILL.md",
       "visibility": "alias",
       "workflow": "operate",
@@ -152,7 +152,7 @@
     },
     "create-context": {
       "name": "create-context",
-      "description": "Build project context from an existing codebase through isolated scouts, resolve gaps, and preserve initialization gates.",
+      "description": "Build source-backed project context through bounded inspection, optional agents, and safe selected writes.",
       "skillPath": "skills/ca-create-context/SKILL.md",
       "visibility": "alias",
       "workflow": "initialize",
@@ -170,7 +170,7 @@
     },
     "decompose": {
       "name": "decompose",
-      "description": "Develop greenfield project context through a layered interview, preserve decisions, and initialize only after the required gates.",
+      "description": "Develop greenfield context from a durable interview and initialize it through the native context writer.",
       "skillPath": "skills/ca-decompose/SKILL.md",
       "visibility": "alias",
       "workflow": "initialize",
@@ -188,7 +188,7 @@
     },
     "feature": {
       "name": "feature",
-      "description": "Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation.",
+      "description": "Build an authorized feature from a maintained specification, testable criteria and useful plan, without duplicating user approval.",
       "skillPath": "skills/ca-feature/SKILL.md",
       "visibility": "core",
       "workflow": "change",
@@ -311,7 +311,7 @@
     },
     "sprint": {
       "name": "sprint",
-      "description": "Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops.",
+      "description": "Run an autonomous sprint from maintained specs and plans, with truthful verification and no duplicate artifact approval ceremonies.",
       "skillPath": "skills/ca-sprint/SKILL.md",
       "visibility": "core",
       "workflow": "change",

package/plugins/ca-pi/helpers/artifacts/release.json

@@ -2,47 +2,47 @@
   "format": "codearbiter.artifact-release/0.1.0",
   "version": "0.1.0",
   "protocol": "codearbiter.artifact-api/0.1.0",
-  "schema_version": "0.3.1",
+  "schema_version": "0.3.2",
   "binaries": {
     "darwin/amd64": {
       "file": "ca-artifact-darwin-amd64",
-      "sha256": "42f302c05c66b22294bff0bdacbd28d5373ddd64b447f087a4532cd99f0a1b6c",
+      "sha256": "1849b2d8abaa5ef76a4f1682bc75ba2fcf452b55d3c66f7bb6a16b141558438d",
       "native_tested": true
     },
     "darwin/arm64": {
       "file": "ca-artifact-darwin-arm64",
-      "sha256": "adf818a92d6d45db8d13a4ec685b2e2e14ddd19d0978c3d820541c45ed5cd4d9",
+      "sha256": "7ee24e5ddd330a2b52336470cd28635b7f1ea16a235fd377058952d5696b0e15",
       "native_tested": true
     },
     "linux/amd64": {
       "file": "ca-artifact-linux-amd64",
-      "sha256": "8090a552d8a40bd3d37075eb81005d4e2bc4cdefac3ecb04cef8d72ef00f64d5",
+      "sha256": "1d20e9dfdc663c4f3d82f82cb1df861261304acf439f604f7bddc33a79f6af91",
       "native_tested": true
     },
     "linux/arm64": {
       "file": "ca-artifact-linux-arm64",
-      "sha256": "0e65ced478bc490e80d6ab5323d307ceffdf42830709563cd6740ef5f35fb069",
+      "sha256": "94a54eb7e83a4992a4ee78b98b7946d2332e2a007ad7fd4ec14a3e332ad16651",
       "native_tested": true
     },
     "windows/amd64": {
       "file": "ca-artifact-windows-amd64.exe",
-      "sha256": "687e362c216634b531371b4238d129a5f09df716d8cf73b6123f20d4c40c9d36",
+      "sha256": "d8f0bafd5f1949d93e87fb3cec7222ad9757087e30f7ea06268f148897f5b5a7",
       "native_tested": true
     },
     "windows/arm64": {
       "file": "ca-artifact-windows-arm64.exe",
-      "sha256": "bc4920311a4e3768439b9c35bd0aca77f1ab964011d7812dd8932fc7360527a0",
+      "sha256": "be36ede70afe3dfc57afcd1ff2f5be5b36134ac383998c10145809bd0b80f459",
       "native_tested": true
     }
   },
   "context_qualification": {
     "darwin/amd64": {
-      "source_commit": "0e96f44ac68b2d17d5bb8b4a75a72ea35e41193e",
+      "source_commit": "36685a40ab035074be04bb7204618acbb0a2dfdf",
       "workflow": ".github/workflows/ci.yml",
-      "run_id": "38467644295",
-      "binary_sha256": "42f302c05c66b22294bff0bdacbd28d5373ddd64b447f087a4532cd99f0a1b6c",
-      "observation_sha256": "aba4d166fee93b949db5c489e11c855afce427a2491e52973c561f8f102f2535",
-      "module_sha256": "e482ad7b0c9264711828ac8404c624517b893981b45712d70ead0fb0ef3b5522",
+      "run_id": "38995632892",
+      "binary_sha256": "1849b2d8abaa5ef76a4f1682bc75ba2fcf452b55d3c66f7bb6a16b141558438d",
+      "observation_sha256": "4b2b1f09e54d99fe7e7cc0ca177b80c2ac5d47e6428eddd551453a13ac2b272f",
+      "module_sha256": "91fed16f177e249d082638387a5f6e8d38dcb33604f357e8296b2f0124a4ca2a",
       "native_cases": [
         "TestContextBoundedRender",
         "TestContextDocumentContract",
@@ -53,12 +53,12 @@
       ]
     },
     "darwin/arm64": {
-      "source_commit": "0e96f44ac68b2d17d5bb8b4a75a72ea35e41193e",
+      "source_commit": "36685a40ab035074be04bb7204618acbb0a2dfdf",
       "workflow": ".github/workflows/ci.yml",
-      "run_id": "38467644295",
-      "binary_sha256": "adf818a92d6d45db8d13a4ec685b2e2e14ddd19d0978c3d820541c45ed5cd4d9",
-      "observation_sha256": "b072ecf41993067d01ba63d09de0eceec46fc37a62f9289c9f18140549feb360",
-      "module_sha256": "e482ad7b0c9264711828ac8404c624517b893981b45712d70ead0fb0ef3b5522",
+      "run_id": "38995632892",
+      "binary_sha256": "7ee24e5ddd330a2b52336470cd28635b7f1ea16a235fd377058952d5696b0e15",
+      "observation_sha256": "3a30a7b8a8d719ac8f261f3c9094bae62a5d9e3db31b565dc401d21486ed48f3",
+      "module_sha256": "91fed16f177e249d082638387a5f6e8d38dcb33604f357e8296b2f0124a4ca2a",
       "native_cases": [
         "TestContextBoundedRender",
         "TestContextDocumentContract",
@@ -69,12 +69,12 @@
       ]
     },
     "linux/amd64": {
-      "source_commit": "0e96f44ac68b2d17d5bb8b4a75a72ea35e41193e",
+      "source_commit": "36685a40ab035074be04bb7204618acbb0a2dfdf",
       "workflow": ".github/workflows/ci.yml",
-      "run_id": "38467644295",
-      "binary_sha256": "8090a552d8a40bd3d37075eb81005d4e2bc4cdefac3ecb04cef8d72ef00f64d5",
-      "observation_sha256": "a7feff5b0805cad3778559ea988bd4c0469b794c84f04b0edb8f7a4e9b6a3121",
-      "module_sha256": "e482ad7b0c9264711828ac8404c624517b893981b45712d70ead0fb0ef3b5522",
+      "run_id": "38995632892",
+      "binary_sha256": "1d20e9dfdc663c4f3d82f82cb1df861261304acf439f604f7bddc33a79f6af91",
+      "observation_sha256": "d977095e8db3aa5bd71fd2db318292d6c6da3aa716b1253ae7ad0fe95780c475",
+      "module_sha256": "91fed16f177e249d082638387a5f6e8d38dcb33604f357e8296b2f0124a4ca2a",
       "native_cases": [
         "TestContextBoundedRender",
         "TestContextDocumentContract",
@@ -85,12 +85,12 @@
       ]
     },
     "linux/arm64": {
-      "source_commit": "0e96f44ac68b2d17d5bb8b4a75a72ea35e41193e",
+      "source_commit": "36685a40ab035074be04bb7204618acbb0a2dfdf",
       "workflow": ".github/workflows/ci.yml",
-      "run_id": "38467644295",
-      "binary_sha256": "0e65ced478bc490e80d6ab5323d307ceffdf42830709563cd6740ef5f35fb069",
-      "observation_sha256": "197e0321d9bd36cadb453b90be82c6c92bdddeacf1cb4f45fb9b72e2d560bf86",
-      "module_sha256": "e482ad7b0c9264711828ac8404c624517b893981b45712d70ead0fb0ef3b5522",
+      "run_id": "38995632892",
+      "binary_sha256": "94a54eb7e83a4992a4ee78b98b7946d2332e2a007ad7fd4ec14a3e332ad16651",
+      "observation_sha256": "24d3bdce7f5044e3c5dda44b0f2a5ccd37bd0821408aa8f62b5b329aacd8e98b",
+      "module_sha256": "91fed16f177e249d082638387a5f6e8d38dcb33604f357e8296b2f0124a4ca2a",
       "native_cases": [
         "TestContextBoundedRender",
         "TestContextDocumentContract",
@@ -101,12 +101,12 @@
       ]
     },
     "windows/amd64": {
-      "source_commit": "0e96f44ac68b2d17d5bb8b4a75a72ea35e41193e",
+      "source_commit": "36685a40ab035074be04bb7204618acbb0a2dfdf",
       "workflow": ".github/workflows/ci.yml",
-      "run_id": "38467644295",
-      "binary_sha256": "687e362c216634b531371b4238d129a5f09df716d8cf73b6123f20d4c40c9d36",
-      "observation_sha256": "b60d2cad282358a382579eebff46acfcf2620817cbe5b27f3dd2c8c469203147",
-      "module_sha256": "e482ad7b0c9264711828ac8404c624517b893981b45712d70ead0fb0ef3b5522",
+      "run_id": "38995632892",
+      "binary_sha256": "d8f0bafd5f1949d93e87fb3cec7222ad9757087e30f7ea06268f148897f5b5a7",
+      "observation_sha256": "eb42182fceca7bdb85924d382a8cf3917fb49b9c2a8a32ccd563a3acab245547",
+      "module_sha256": "91fed16f177e249d082638387a5f6e8d38dcb33604f357e8296b2f0124a4ca2a",
       "native_cases": [
         "TestContextBoundedRender",
         "TestContextDocumentContract",
@@ -117,12 +117,12 @@
       ]
     },
     "windows/arm64": {
-      "source_commit": "0e96f44ac68b2d17d5bb8b4a75a72ea35e41193e",
+      "source_commit": "36685a40ab035074be04bb7204618acbb0a2dfdf",
       "workflow": ".github/workflows/ci.yml",
-      "run_id": "38467644295",
-      "binary_sha256": "bc4920311a4e3768439b9c35bd0aca77f1ab964011d7812dd8932fc7360527a0",
-      "observation_sha256": "9211b4fc92a9cc819a120d2e71c08bdfb75a3996f8eb433bd7b9a426121c50ef",
-      "module_sha256": "e482ad7b0c9264711828ac8404c624517b893981b45712d70ead0fb0ef3b5522",
+      "run_id": "38995632892",
+      "binary_sha256": "be36ede70afe3dfc57afcd1ff2f5be5b36134ac383998c10145809bd0b80f459",
+      "observation_sha256": "12b1ba42509dd791bebf60df616608e7dbf50359175f90a3cf7a857c3c82cad8",
+      "module_sha256": "91fed16f177e249d082638387a5f6e8d38dcb33604f357e8296b2f0124a4ca2a",
       "native_cases": [
         "TestContextBoundedRender",
         "TestContextDocumentContract",

package/plugins/ca-pi/hooks/_approvallib.py

@@ -345,6 +345,38 @@ def cancel_user_approval(root: str | Path, artifact_id: str) -> dict[str, Any]:
     return {"artifact_id": artifact_id, "cancelled": True}
 
 
+def retire_unanswered_user_approval(
+    root: str | Path, artifact_id: str, *, reason: str,
+) -> dict[str, Any]:
+    """Retire only an unsubmitted historical paired prompt, not an approval.
+
+    The older single-artifact 0.1 marker cannot establish whether a reply
+    was captured and its write outcome lost. It is therefore not eligible
+    for this automatic cleanup. The paired adapter serializes cancellation
+    against the genuine reply consumer and checks the durable submission.
+    """
+    if (not isinstance(artifact_id, str) or re.fullmatch(r"[A-Z][A-Z0-9-]{1,79}", artifact_id) is None
+            or not isinstance(reason, str) or not reason.strip()
+            or len(reason.encode("utf-8")) > 2048):
+        raise ApprovalError("INVALID_RETIREMENT", "retirement requires a valid artifact ID and bounded nonblank reason")
+    root = Path(root).resolve(strict=True)
+    pending = _load_pending(root)
+    if pending is None or pending["artifact_id"] != artifact_id:
+        raise ApprovalError("NO_PENDING_APPROVAL", "no matching pending approval request")
+    if pending["format"] != "codearbiter.pending-user-approval/0.2.0":
+        raise ApprovalError("LEGACY_APPROVAL_RECOVERY_REQUIRED",
+                            "single-artifact pending state cannot prove a user reply was unsubmitted")
+    import _sprintapprovallib
+    # Uses the existing private per-repository lock and independently checks
+    # the current marker and durable submission before deleting either route.
+    _sprintapprovallib.cancel(root, pending)
+    return {
+        "artifact_id": artifact_id, "disposition": "unanswered_prompt_superseded",
+        "reason": reason.strip(), "authority_granted": False, "mutation_attempted": False,
+    }
+
+
+
 def consume_user_approval(
     root: str | Path,
     client: Any,
@@ -489,6 +521,10 @@ def main(argv: list[str] | None = None) -> int:
     cancel = sub.add_parser("cancel")
     cancel.add_argument("--root", required=True)
     cancel.add_argument("--artifact-id", required=True)
+    retire = sub.add_parser("retire")
+    retire.add_argument("--root", required=True)
+    retire.add_argument("--artifact-id", required=True)
+    retire.add_argument("--reason", required=True)
     pair = sub.add_parser("arm-sprint")
     pair.add_argument("--root", required=True)
     pair.add_argument("--spec-id", required=True)
@@ -504,6 +540,11 @@ def main(argv: list[str] | None = None) -> int:
     if args.command == "cancel":
         print(json.dumps(cancel_user_approval(args.root, args.artifact_id)))
         return 0
+    if args.command == "retire":
+        print(json.dumps(retire_unanswered_user_approval(
+            args.root, args.artifact_id, reason=args.reason,
+        )))
+        return 0
     client = _artifactlib.ArtifactClient(
         args.root, _artifactlib.helper_installation(__file__)
     )