agent-inspect 6.10.0 → 6.12.0

package/CHANGELOG.md

@@ -1,5 +1,17 @@
 # Changelog
 
+## 6.12.0
+
+### Minor Changes
+
+- 3ee1692: Consolidation and stable launch candidate: positioning/portfolio tiers, install kits, honest packed/native/MCP matrices, PARTIAL design-partner trial worksheets, package maintenance audit (keep fixed group through v6), comparison/interop handoff, and launch demo checklist. No schema break; no new packages; no default upload; trial results not fabricated.
+
+## 6.11.0
+
+### Minor Changes
+
+- 1b5d5d8: Local coding-agent debug loop: MCP server executable, protocol hardening, curated flagship read-only tools, first-causal-failure engine, safe evidence/contract tools, client configure CLI, Cursor/Claude/Codex/Gemini instructions, no-key debug-loop recipe, protocol/privacy conformance corpus, and packed MCP consumer smoke. No schema break; no new root/core dependencies; local stdio only; redaction defaults not weakened.
+
 ## 6.10.0
 
 ### Minor Changes

package/README.md

@@ -8,18 +8,13 @@
 <h1 align="center">agent-inspect</h1>
 
 <p align="center">
-  <strong>Debug, regression-test, and safely share TypeScript AI-agent behavior—locally.</strong>
+  <strong>The local evidence debugger for TypeScript agents—faithful execution trees, deterministic regression checks, share-checked evidence, and coding-agent access without a collector or account.</strong>
 </p>
 
 <p align="center">
   <sub>No account · no default upload · metadata-only by default · optional customer-owned Studio</sub>
 </p>
 
-<p align="center">
-  AgentInspect turns agent runs into <strong>customer-owned evidence</strong>: execution trees,
-  deterministic contracts, CI gates, verified-safe bundles, and optional self-hosted review.
-</p>
-
 <p align="center">
   <a href="https://agentinspect.vercel.app/">Website</a> ·
   <a href="https://agentinspect.vercel.app/docs/">Docs</a> ·
@@ -38,6 +33,16 @@
 npm install agent-inspect
 ```
 
+## Hero flow
+
+```text
+1. Capture one real run
+2. Find the causal failure
+3. Ask your coding agent to inspect it
+4. Lock the fix with a contract
+5. Attach the share-checked evidence
+```
+
 ## Three workflows
 
 | Workflow | What you do |
@@ -46,7 +51,9 @@ npm install agent-inspect
 | **Prevent one regression** | TraceContract / `check` → suite / cohort → CI gate |
 | **Share one safe artifact** | Redact → `verify-safe` → offline bundle → optional Studio review |
 
-**Review as a team (optional):** workspace + optional SQLite index → customer-owned [Studio Beta](https://github.com/rajudandigam/agent-inspect/tree/main/packages/studio) (no AgentInspect-hosted cloud).
+**Coding-agent loop (optional):** local read-only [`@agent-inspect/mcp-server`](https://www.npmjs.com/package/@agent-inspect/mcp-server) — see [CODING-AGENT-LOOP.md](https://github.com/rajudandigam/agent-inspect/blob/main/docs/CODING-AGENT-LOOP.md).
+
+**Review as a team (optional):** workspace + optional SQLite index → customer-owned [Studio Beta](https://github.com/rajudandigam/agent-inspect/tree/main/packages/studio) (no AgentInspect-hosted cloud). Portfolio tiers: [POSITIONING-AND-PORTFOLIO.md](https://github.com/rajudandigam/agent-inspect/blob/main/docs/POSITIONING-AND-PORTFOLIO.md).
 
 <p align="center">
   <img src="https://raw.githubusercontent.com/rajudandigam/agent-inspect/main/docs/assets/readme-product-loop.svg?sanitize=true" alt="Capture or import → understand → enforce → verify and bundle → review locally or in customer-owned Studio" width="900">
@@ -131,7 +138,7 @@ Details: [Safe sharing](https://github.com/rajudandigam/agent-inspect/blob/main/
 
 ## Project status
 
-**Current release:** **6.10.0** (eighteen linked npm packages). Technical launch candidate; external pilot evidence pending. Persisted schema **1.0**. Node.js **≥ 20**. **v7 not scheduled.**
+**Current release:** **6.12.0** (eighteen linked npm packages). Technical launch candidate; external pilot evidence pending. Persisted schema **1.0**. Node.js **≥ 20**. **v7 not scheduled.**
 
 [Roadmap](ROADMAP.md) · [Pilot kit](https://github.com/rajudandigam/agent-inspect/blob/main/docs/PRE-V7-PILOT-KIT.md) · [Changelog](CHANGELOG.md)
 
@@ -146,18 +153,29 @@ Details: [Safe sharing](https://github.com/rajudandigam/agent-inspect/blob/main/
 See [Compare](https://github.com/rajudandigam/agent-inspect/blob/main/docs/COMPARE.md).
 
 <details>
-<summary><strong>Package family (18 public packages)</strong></summary>
+<summary><strong>Package family (18 linked packages · tiered presentation)</strong></summary>
+
+Canonical tiers: [POSITIONING-AND-PORTFOLIO.md](https://github.com/rajudandigam/agent-inspect/blob/main/docs/POSITIONING-AND-PORTFOLIO.md) · [SUPPORT-LEVELS.md](https://github.com/rajudandigam/agent-inspect/blob/main/docs/SUPPORT-LEVELS.md).
+
+### Tier A — Flagship
+
+| Package | Purpose |
+| ------- | ------- |
+| [`agent-inspect`](https://www.npmjs.com/package/agent-inspect) | Core APIs + CLI + evidence |
+| [`@agent-inspect/redact`](https://www.npmjs.com/package/@agent-inspect/redact) | Deterministic redaction |
+| [`@agent-inspect/mcp-server`](https://www.npmjs.com/package/@agent-inspect/mcp-server) | Read-only MCP coding-agent loop (Preview) |
+
+### Tier B — Official integrations
 
 ### Framework adapters
 
 | Package | Purpose |
 | ------- | ------- |
-| [`agent-inspect`](https://www.npmjs.com/package/agent-inspect) | Core APIs + CLI |
 | [`@agent-inspect/ai-sdk`](https://www.npmjs.com/package/@agent-inspect/ai-sdk) | AI SDK telemetry |
 | [`@agent-inspect/openai-agents`](https://www.npmjs.com/package/@agent-inspect/openai-agents) | OpenAI Agents processor |
 | [`@agent-inspect/langchain`](https://www.npmjs.com/package/@agent-inspect/langchain) | LangChain callbacks |
 
-### Testing / evaluation
+### Tier B — Testing / evaluation
 
 | Package | Purpose |
 | ------- | ------- |
@@ -166,7 +184,7 @@ See [Compare](https://github.com/rajudandigam/agent-inspect/blob/main/docs/COMPA
 | [`@agent-inspect/vitest`](https://www.npmjs.com/package/@agent-inspect/vitest) | Vitest reporter |
 | [`@agent-inspect/jest`](https://www.npmjs.com/package/@agent-inspect/jest) | Jest reporter |
 
-### Safety
+### Tier C — Optional supporting (Safety)
 
 | Package | Purpose |
 | ------- | ------- |
@@ -174,7 +192,7 @@ See [Compare](https://github.com/rajudandigam/agent-inspect/blob/main/docs/COMPA
 | [`@agent-inspect/guardrails`](https://www.npmjs.com/package/@agent-inspect/guardrails) | Deterministic guardrail rules |
 | [`@agent-inspect/circuit`](https://www.npmjs.com/package/@agent-inspect/circuit) | Loop / retry / timeout analyzers |
 
-### Developer surfaces
+### Tier C — Optional supporting (Developer surfaces)
 
 | Package | Purpose |
 | ------- | ------- |
@@ -183,14 +201,14 @@ See [Compare](https://github.com/rajudandigam/agent-inspect/blob/main/docs/COMPA
 | [`@agent-inspect/mcp`](https://www.npmjs.com/package/@agent-inspect/mcp) | MCP client tracing |
 | [`@agent-inspect/mcp-server`](https://www.npmjs.com/package/@agent-inspect/mcp-server) | Read-only MCP server (Preview) |
 
-### Team / self-hosted
+### Tier C — Optional supporting (Team / self-hosted)
 
 | Package | Purpose |
 | ------- | ------- |
 | [`@agent-inspect/index-sqlite`](https://www.npmjs.com/package/@agent-inspect/index-sqlite) | Optional SQLite index (Beta) |
 | [`@agent-inspect/studio`](https://www.npmjs.com/package/@agent-inspect/studio) | Customer-owned Studio (Beta) |
 
-### Extension / interop
+### Tier C — Optional supporting (Extension / interop)
 
 | Package | Purpose |
 | ------- | ------- |

package/docs/ADOPTION.md

@@ -25,6 +25,10 @@ npx agent-inspect verify-safe <run-id> --dir .agent-inspect
 
 No API keys required for the init demo. See [examples/starters/](../examples/starters/README.md).
 
+## Install kits
+
+Copyable task kits (LangGraph, portable evidence, AI SDK, OpenAI Agents, CI): [INSTALL-KITS.md](./INSTALL-KITS.md).
+
 ## Choose a starter
 
 | Goal | Starter |

package/docs/CLI.md

@@ -1052,3 +1052,14 @@ See:
 
 - `docs/KNOWN-ISSUES.md`
 - `docs/LIMITATIONS.md`
+
+
+## MCP configure (v6.11+)
+
+```bash
+agent-inspect mcp configure --client cursor
+agent-inspect mcp configure --client claude-code --project-local
+agent-inspect mcp configure --client cursor --project-local --write --yes
+```
+
+Dry-run by default. Writes project-local files only with `--project-local --write --yes`. No network; share redaction by default. See [CODING-AGENT-LOOP.md](./CODING-AGENT-LOOP.md) and [coding-agent-instructions/](./coding-agent-instructions/).

package/docs/COMPARE.md

@@ -4,6 +4,28 @@ AgentInspect is a local-first trace workbench for TypeScript AI agents: capture
 
 **Docs site:** [https://agentinspect.vercel.app/docs/compare/](https://agentinspect.vercel.app/docs/compare/)
 
+
+
+## Complementary handoff (v6.12)
+
+Position AgentInspect as the **inner-loop local evidence** layer:
+
+```text
+local evidence and inner-loop debugging → AgentInspect
+production observability → LangSmith / Langfuse / MLflow / Phoenix / APM
+prompt/output and red-team eval → Promptfoo / Evalite / other eval tools
+generic OTel trace access via MCP → OTel MCP servers
+```
+
+Handoff story:
+
+```text
+debug locally with AgentInspect
+export OpenInference/OTLP when production tooling is needed
+```
+
+Portfolio presentation: [POSITIONING-AND-PORTFOLIO.md](./POSITIONING-AND-PORTFOLIO.md).
+
 ## Category comparison
 
 | Dimension | AgentInspect | Hosted dashboards (LangSmith, Langfuse) | Eval platforms (Braintrust) | Production APM / OTel pipelines |

package/docs/DEMO-SCRIPT.md

@@ -86,3 +86,15 @@ See [FIRST-TRACE-IN-5-MINUTES.md](./FIRST-TRACE-IN-5-MINUTES.md).
 - **Framework:** switch to `examples/starters/ai-sdk` for adapter path
 
 Related: [VIDEO-WALKTHROUGH-SCRIPT.md](./VIDEO-WALKTHROUGH-SCRIPT.md) · [SCREENSHOTS.md](./SCREENSHOTS.md)
+
+
+## Optional MCP beat (30s)
+
+If time allows after inspect:
+
+```bash
+npx agent-inspect mcp configure --client cursor --dry-run
+npx @agent-inspect/mcp-server --dir .agent-inspect --help
+```
+
+Point to [CODING-AGENT-LOOP.md](./CODING-AGENT-LOOP.md) and the coding-agent-debug-loop starter. Stay read-only; do not claim a live partner session unless one is on the call.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agent-inspect",
-  "version": "6.10.0",
+  "version": "6.12.0",
   "license": "MIT",
   "type": "module",
   "description": "Debug, regression-test, and safely share TypeScript AI-agent behavior locally — no account, no default upload, metadata-only by default",

package/packages/cli/dist/{chunk-36IJ76LH.mjs → chunk-XTAA733P.mjs}

@@ -10754,5 +10754,5 @@ function renderGateReport(result, options = {}) {
 }
 
 export { COHORT_METRIC_IDS, DEFAULT_SUITE_ARTIFACTS_DIR, EVIDENCE_FORMAT_VERSION, EVIDENCE_HTML_FILENAME, EVIDENCE_MANIFEST_FILENAME, Redactor, TraceDirectory, TraceReadError, TreeBuilder, aggregateBundleSafeStatus, aggregateSessionCheckResults, analyzeCohort, applyProfileMetadataCaps, assertBundlePathContained, assertEvidenceRelativePath, buildActivitySummary, buildBundleMetadata, buildBundleSummaryMarkdown, buildEvidenceCausalFailureViewHtml, buildEvidenceCiPackage, buildEvidenceCircuitViewHtml, buildEvidenceContractsViewHtml, buildEvidenceDiffViewHtml, buildEvidenceHtmlShell, buildEvidenceManifest, buildEvidenceOutcomesViewHtml, buildEvidenceProvenanceViewHtml, buildEvidenceSafetyViewHtml, buildEvidenceTimelineViewHtml, buildEvidenceToolsLlmViewHtml, buildEvidenceTreeViewHtml, buildLocalExplanation, buildPlaceholderArtifact, buildRunSummary, buildRunTimeline, buildRunWhatSummary, buildSessionIndex, buildTraceStats, buildZipArchive, bundleFailsOnSafety, bundleRunAssetRelativePath, collectTraceSchemaVersions, compactAttributes, createBaselineRegressionRule, createLlmUsageRule, createMaxStepDurationRule, createObservedOutcomeRule, createRequireCompletedRule, createRunDepthRule, createRunDurationRule, createRunStatusRule, createSafetyOversizedAttributeRule, createSafetyRawContentRule, createSafetyRedactionRule, createSafetySecretPatternRule, createStallDetectionRule, createStructureCycleRule, createStructureOrphanRule, createStructureParallelWidthRule, createStructureRelationshipRule, createToolUsageRule, defaultBundleOutputPath, defaultSuiteConfigTemplate, diffRuns, diffTraceEvents, enrichSessionRunRecord, escapeHtml, escapeMarkdown, extractMetadata, extractOutcomesFromTraceEvents, filterMetasBySessionScope, filterTraces, flattenTree, formatDuration2 as formatDuration, formatTimestamp, gateHasThresholds, getIndent, getTraceFilePath, inferEvidenceFileRole, isAgentInspectTrace, isPersistedInspectEvent, loadSessionRunRecords, loadSuiteConfig, loadTraceMetadataList, manualTraceEventsToComparableRun, nanoid, normalizeBundleOutputPath, openTrace, parseCohortMetricList, parseDuration, parseDurationFilter, parseGateList, parseTraceJsonl, persistedInspectEventsToTraceEvents, renderActivitySummaryHuman, renderCohortReport, renderErrorLine, renderGateReport, renderObservedOutcomesHtml, renderObservedOutcomesMarkdown, renderRunDiff, renderRunWhat, renderStepLine, renderSuiteReport, renderTimeline, renderTraceStats, resolveBundleRunIds, resolveRedactionProfile, resolveSuiteTemplate, resolveTraceDir, runGate, runSuite, runTraceChecks, safeString, sanitizeBundleRunId, searchTraces, serializeEvidenceManifest, sha256Hex, stableJson, summarizeObservedOutcomes, traceEventToPersistedInspectEvent, truncateName, truncateStringForProfile, validateEvent, validateSuiteConfig, verifyEvidenceDirectory, zeroKinds };
-//# sourceMappingURL=chunk-36IJ76LH.mjs.map
-//# sourceMappingURL=chunk-36IJ76LH.mjs.map
+//# sourceMappingURL=chunk-XTAA733P.mjs.map
+//# sourceMappingURL=chunk-XTAA733P.mjs.map