@calliopelabs/cli 3.6.0 → 3.8.0

package/docs/task-feedback.md

@@ -0,0 +1,77 @@
+# Reviewed task feedback
+
+Hosts discover this interface explicitly through
+`calliope improve host-capabilities --contract-version 2 --json` or the
+`taskFeedbackCapabilities()` library API. Default/version-1 host discovery and
+the existing execution capability contract retain their original shapes.
+
+`recordTaskFeedback` records one native-policy-reviewed assessment of an exact
+completed task attempt. It does not mark the task accepted, change a check,
+allocate execution, award a numeric reward or activate a learned policy. A host's
+claimed user/workflow identity is not independently authenticated by this API.
+The trust boundary is the operator-owned native permission decision and store.
+
+```ts
+import {randomUUID} from 'node:crypto';
+import {inspectTaskOutcome, recordTaskFeedback} from
+  '@calliopelabs/cli/dist/improvement/index.js';
+
+const selection = {taskId, attempt, executionRevision};
+const observation = await inspectTaskOutcome(cwd, runId, selection, options);
+const result = await recordTaskFeedback(cwd, runId, {
+  version: 1,
+  id: randomUUID(),
+  selection,
+  observationHash: observation.hash,
+  assessment: {decision: 'accepted', reason: 'Reviewed against the requested result.'},
+  references: [{kind: 'workflow', id: workflowId, revision: workflowHash}],
+}, options);
+```
+
+The caller first presents the native observation and assessment for review.
+The request binds its exact observation hash and execution revision. The shared
+permission resolver applies plan-mode denial, hooks, policy and mutation
+confirmation. Missing confirmation denies by default. An operator may explicitly
+provide the usual native noninteractive permission options; request data cannot
+set its own trust or approval. The writer checks current run approval, ownership,
+revision, retained artifact bytes and accounting again before commit.
+
+Requests accept only the versioned identity, assessment and optional declared
+workflow/skill/policy references. Each reference has a bounded ID and immutable
+revision hash. Unknown fields, including reward, cost, check results and trust
+flags, are rejected. The native configuration hash identifies the actual task,
+agent and applied strategy at that attempt, including prior strategy restoration
+after withdrawal. Declared external references are reviewed metadata; they do not
+prove the content of an external workflow or skill.
+
+## Persistence and inspection
+
+The receipt is a version-12 event in the existing private execution journal.
+Its source includes the native run, manifest, plan, approval, configuration,
+graph, task/start/session and attempt identities. Older journal readers that
+cannot read version 12 must refuse it. The previous journal versions are unchanged.
+At most 64 receipts can be retained in one run, inside the existing journal byte
+limits. Preserve the run when that limit is reached.
+
+Identical request IDs and payloads return the same receipt after rechecking
+native permission. Changed payloads cannot reuse an ID. A lost acknowledgement
+does not append another event, reset the original clock or alter reservations.
+
+`taskFeedbackHistory(cwd, runId, options)` returns recorded receipt history, with
+an explicit notice that its outcome evidence has not been revalidated.
+`inspectTaskFeedback(cwd, runId, feedbackId, options)` reuses `inspectTaskOutcome`
+to verify native evidence and derive current checks, duration and accounting.
+An active coordinator or altered artifact refuses inspection. A later native
+outcome change, including explicit task acceptance, marks the old assessment
+`stale`. Late billing settlement updates the observed accounting without
+rewriting the assessment or converting unknown costs to zero.
+
+Both inspection APIs return `{data, redacted}`. Known credentials are rejected
+on write. Read-time redaction also protects strings that later become configured
+credentials; redacted display data is not a byte-for-byte copy of the retained
+receipt. No raw worker prose, tool logs or artifact contents are imported into
+the assessment record.
+
+Cross-run learned strategy selection, training data admission, reward weighting,
+baseline/held-out evaluation and candidate activation/withdrawal remain separate
+work under #413. This receipt API does not claim those capabilities.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@calliopelabs/cli",
-  "version": "3.6.0",
+  "version": "3.8.0",
   "description": "The private-AI agent CLI - one terminal agent for any model backend, including the ones you run yourself",
   "keywords": [
     "ai",
@@ -34,14 +34,22 @@
   "files": [
     "dist",
     "README.md",
+    "docs/claude-plan.md",
     "scripts/verify-runlog.mjs",
     "docs/migration-*.md",
     "docs/migration-example-*.json",
     "docs/delegation-ledger.md",
-    "docs/releases/3.6.0.md"
+    "docs/improvement-cycles.md",
+    "docs/task-feedback.md",
+    "docs/acp.md",
+    "docs/releases/3.7.0.md",
+    "docs/releases/3.6.0.md",
+    "docs/chatgpt-plan.md",
+    "docs/releases/3.8.0.md",
+    "docs/reviewed-provider-metadata.md"
   ],
   "scripts": {
-    "build": "tsc && chmod +x dist/bin.js",
+    "build": "tsc && node scripts/build-metadata.mjs && chmod +x dist/bin.js",
     "dev": "tsc --watch",
     "start": "node dist/bin.js",
     "test": "vitest run",
@@ -63,21 +71,22 @@
     "capture:semantics": "npm run build && node scripts/conformance/capture-semantic.mjs"
   },
   "dependencies": {
-    "@agentclientprotocol/sdk": "2.0.2",
-    "@anthropic-ai/sdk": "0.135.0",
-    "@aws-sdk/credential-provider-ini": "3.973.19",
-    "@aws-sdk/credential-provider-node": "3.972.86",
+    "@agentclientprotocol/sdk": "2.2.0",
+    "@anthropic-ai/sdk": "1.3.0",
+    "@aws-sdk/credential-provider-ini": "3.973.24",
+    "@aws-sdk/credential-provider-node": "3.972.91",
     "@google/genai": "^2.22.0",
     "@inquirer/prompts": "^8.5.2",
-    "conf": "^15.1.0",
-    "ink": "^7.1.0",
-    "openai": "^6.46.0",
+    "conf": "16.0.0",
+    "ink": "8.0.0",
+    "jose": "6.2.15",
+    "openai": "7.43.0",
     "react": "^19.2.3",
-    "sql.js": "1.15.0",
+    "sql.js": "1.15.2",
     "string-width": "8.3.0",
     "ws": "8.22.0",
     "yaml": "^2.8.2",
-    "zod": "4.6.6"
+    "zod": "4.6.7"
   },
   "devDependencies": {
     "@types/node": "^26.1.1",