P0: require authoritative evidence for policy findings

.claude-plugin/marketplace.json

@@ -10,7 +10,7 @@
       "name": "agents-shipgate",
       "source": "./plugins/claude-code",
       "description": "Run Agents Shipgate Tool-Use Readiness workflows from Claude Code: detect whether Shipgate applies, bootstrap the advisory gate, verify agent-capability PRs, and triage findings without fabricating human approval. Requires the agents-shipgate CLI (pipx install agents-shipgate, runtime contract 15).",
-      "version": "0.16.0b4",
+      "version": "0.16.0b5",
       "author": {
         "name": "Three Moons Lab",
         "url": "https://threemoonslab.com/"

.well-known/agents-shipgate.json

@@ -3,7 +3,7 @@
   "name": "agents-shipgate",
   "display_name": "Agents Shipgate",
   "tagline": "The deterministic merge gate for AI-generated agent capability changes",
-  "version": "0.16.0b4",
+  "version": "0.16.0b5",
   "license": "Apache-2.0",
   "publisher": {
     "name": "Three Moons Lab",
@@ -172,16 +172,16 @@
   "codex_boundary_result_schema_path": "docs/codex-boundary-result-schema.v2.json",
   "agent_boundary_result_schema_version": "shipgate.agent_boundary_result/v1",
   "agent_boundary_result_schema_path": "docs/agent-boundary-result-schema.v1.json",
-  "report_schema_version": "0.32",
-  "packet_schema_version": "0.10",
-  "verifier_schema_version": "0.3",
+  "report_schema_version": "0.33",
+  "packet_schema_version": "0.11",
+  "verifier_schema_version": "0.4",
   "verify_run_schema_version": "shipgate.verify_run/v2",
-  "agent_handoff_schema_version": "shipgate.agent_handoff/v3",
-  "agent_handoff_schema_path": "docs/agent-handoff-schema.v3.json",
+  "agent_handoff_schema_version": "shipgate.agent_handoff/v4",
+  "agent_handoff_schema_path": "docs/agent-handoff-schema.v4.json",
   "agent_handoff_artifact": "agents-shipgate-reports/agent-handoff.json",
-  "contract_version": "15",
+  "contract_version": "16",
   "minimum_control_contract_version": "14",
-  "local_agent_contract_schema_version": "4",
+  "local_agent_contract_schema_version": "5",
   "inputs": [
     "mcp",
     "openapi",
@@ -242,8 +242,8 @@
     "scenario": "scenario.json",
     "governance_benchmark_result": "benchmark/agent-pr-governance/results/result.json"
   },
-  "capability_lock_schema_version": "0.5",
-  "capability_lock_diff_schema_version": "0.6",
+  "capability_lock_schema_version": "0.6",
+  "capability_lock_diff_schema_version": "0.7",
   "preflight_schema_version": "0.3",
   "attestation_schema_version": "0.4",
   "registry_schema_version": "0.3",
@@ -252,7 +252,7 @@
   "host_grants_baseline_schema_version": "0.2",
   "host_grants_drift_schema_version": "0.2",
   "trigger_catalog_schema_version": "0.2",
-  "capability_standard_version": "0.4",
+  "capability_standard_version": "0.5",
   "governance_benchmark_catalog_schema_version": "0.2",
   "governance_benchmark_result_schema_version": "0.2",
   "supporting_provisional_surfaces": [
@@ -396,17 +396,17 @@
   "static_verdict_disclaimer": "This verdict covers deterministic static evidence only. Agents Shipgate did not execute the agent or prove runtime behavior, tool routing, credential enforcement, or safety.",
   "schemas": {
     "manifest": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/manifest-v0.1.json",
-    "report": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/report-schema.v0.32.json",
+    "report": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/report-schema.v0.33.json",
     "agent_result": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/agent-result-schema.v2.json",
     "agent_boundary_result": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/agent-boundary-result-schema.v1.json",
     "codex_boundary_result": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/codex-boundary-result-schema.v2.json",
-    "verifier": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/verifier-schema.v0.3.json",
+    "verifier": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/verifier-schema.v0.4.json",
     "verify_run": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/verify-run-schema.v2.json",
-    "agent_handoff": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/agent-handoff-schema.v3.json",
-    "packet": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/packet-schema.v0.10.json",
+    "agent_handoff": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/agent-handoff-schema.v4.json",
+    "packet": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/packet-schema.v0.11.json",
     "preflight": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/preflight-schema.v0.3.json",
-    "capability_lock": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/capability-lock-schema.v0.5.json",
-    "capability_lock_diff": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/capability-lock-diff-schema.v0.6.json",
+    "capability_lock": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/capability-lock-schema.v0.6.json",
+    "capability_lock_diff": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/capability-lock-diff-schema.v0.7.json",
     "governance_benchmark_catalog": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/governance-benchmark-catalog-schema.v0.2.json",
     "governance_benchmark_result": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/governance-benchmark-result-schema.v0.2.json",
     "feedback": "https://raw.githubusercontent.com/ThreeMoonsLab/agents-shipgate/main/docs/feedback-schema.v0.1.json",

AGENTS.md

@@ -1,3 +1,3 @@
 # Agents Shipgate · Agent Instructions
 
 Authoritative instructions for AI coding agents (Claude Code, Codex, Cursor, Aider, Cline, Windsurf, Devin, or any other harness — see [`docs/agents/any-coding-agent.md`](docs/agents/any-coding-agent.md)) working **with** this repository or a project that uses Agents Shipgate.
@@ -363,7 +363,7 @@
 - Audit envelopes: `release_decision.contribution_rules[]`, `policy_audit`,
   `privacy_audit`, `heuristics_filter` — explanatory, never a second gate
 
-The current schema is [`docs/report-schema.v0.32.json`](docs/report-schema.v0.32.json). Emitted reports carry `report_schema_version: "0.32"`; v0.32 adds the required Conductor OSS framework summary over v0.31's root-reachable binding contract. A `passed` result requires a complete root-reachable static binding graph plus complete, conflict-free identity, effect, and authority evidence for every reachable action, evaluation of all applicable controls, and no policy condition requiring review. Every release decision explicitly carries `static_analysis_only: true`, `runtime_behavior_verified: false`, and `static_verdict_disclaimer`; packet §1 mirrors them. Binding and semantic gaps are not Findings and cannot be suppressed or baselined. See [`docs/passed-verdict-contract.md`](docs/passed-verdict-contract.md) for the exact claim and [`docs/agent-contract-current.md`](docs/agent-contract-current.md) for version history. v0.31 remains frozen at [`docs/report-schema.v0.31.json`](docs/report-schema.v0.31.json).
+The current schema is [`docs/report-schema.v0.33.json`](docs/report-schema.v0.33.json). Emitted reports carry `report_schema_version: "0.33"`; typed predicate support prevents heuristic evidence from being upgraded by policy severity or block metadata. A `passed` result requires a complete root-reachable static binding graph plus complete, conflict-free identity, effect, authority, and applicable-policy evidence for every reachable action. Every release decision explicitly carries `static_analysis_only: true`, `runtime_behavior_verified: false`, and `static_verdict_disclaimer`; packet §1 mirrors them. Binding, semantic, and policy-applicability gaps are not Findings and cannot be suppressed or baselined. See [`docs/passed-verdict-contract.md`](docs/passed-verdict-contract.md) for the exact claim and [`docs/agent-contract-current.md`](docs/agent-contract-current.md) for version history. v0.32 remains frozen at [`docs/report-schema.v0.32.json`](docs/report-schema.v0.32.json).
 
 **Release gating signal**: prefer `release_decision.decision` (`"blocked" | "review_required" | "insufficient_evidence" | "passed"`) over `summary.status`. The new field is **baseline-aware** — a baseline-matched critical surfaces in `release_decision.review_items` (accepted debt), not `release_decision.blockers`. `summary.status` stays baseline-blind for v0.7 compatibility, so a baseline-matched-only critical produces both `summary.status = "release_blockers_detected"` AND `release_decision.decision = "review_required"` (intentional divergence — see [STABILITY.md](STABILITY.md#release_decisiondecision-vs-summarystatus)). `insufficient_evidence` (added v0.14) signals that the scan saw too many low-confidence tools or source-loader warnings to be trustworthy; consumers that switch on the enum must fall back to `review_required` for unknown future values.
 
@@ -443,7 +443,7 @@
 ### Where is the report schema?
 
 Parse `agents-shipgate-reports/report.json` and validate against
-[`docs/report-schema.v0.32.json`](docs/report-schema.v0.32.json) (current).
+[`docs/report-schema.v0.33.json`](docs/report-schema.v0.33.json) (current).
 Older reports (`report_schema_version: "0.10"`) validate against the
 frozen [`docs/report-schema.v0.10.json`](docs/report-schema.v0.10.json).
 Do not scrape Markdown when JSON is available.
@@ -481,7 +481,8 @@
 | What | Path | Stable |
 |---|---|---|
 | Manifest schema | [`docs/manifest-v0.1.json`](docs/manifest-v0.1.json) | `0.1` |
-| Report schema (current) | [`docs/report-schema.v0.32.json`](docs/report-schema.v0.32.json) | `0.32` |
+| Report schema (current) | [`docs/report-schema.v0.33.json`](docs/report-schema.v0.33.json) | `0.33` |
+| Report schema (v0.32 frozen reference) | [`docs/report-schema.v0.32.json`](docs/report-schema.v0.32.json) | `0.32` |
 | Report schema (v0.31 frozen reference) | [`docs/report-schema.v0.31.json`](docs/report-schema.v0.31.json) | `0.31` |
 | Report schema (v0.30 frozen reference) | [`docs/report-schema.v0.30.json`](docs/report-schema.v0.30.json) | `0.30` |
 | Report schema (v0.29 frozen reference) | [`docs/report-schema.v0.29.json`](docs/report-schema.v0.29.json) | `0.29` |
@@ -490,7 +491,7 @@
 | Report schema (v0.26 frozen reference) | [`docs/report-schema.v0.26.json`](docs/report-schema.v0.26.json) | `0.26` |
 | Report schema (v0.25 frozen reference) | [`docs/report-schema.v0.25.json`](docs/report-schema.v0.25.json) | `0.25` |
 | Verify-run schema | [`docs/verify-run-schema.v2.json`](docs/verify-run-schema.v2.json) | `shipgate.verify_run/v2` |
-| Agent handoff schema | [`docs/agent-handoff-schema.v3.json`](docs/agent-handoff-schema.v3.json) | `shipgate.agent_handoff/v3` |
+| Agent handoff schema | [`docs/agent-handoff-schema.v4.json`](docs/agent-handoff-schema.v4.json) | `shipgate.agent_handoff/v4` |
 | Agent boundary result schema | [`docs/agent-boundary-result-schema.v1.json`](docs/agent-boundary-result-schema.v1.json) | `shipgate.agent_boundary_result/v1` |
 | Codex boundary result schema (deprecated frozen projection) | [`docs/codex-boundary-result-schema.v2.json`](docs/codex-boundary-result-schema.v2.json) | `shipgate.codex_boundary_result/v2` |
 | Report schema (v0.24 frozen reference) | [`docs/report-schema.v0.24.json`](docs/report-schema.v0.24.json) | `0.24` |
@@ -512,17 +513,17 @@
 | Report schema (v0.8 frozen reference) | [`docs/report-schema.v0.8.json`](docs/report-schema.v0.8.json) | `0.8` |
 | Report schema (v0.7 frozen reference) | [`docs/report-schema.v0.7.json`](docs/report-schema.v0.7.json) | `0.7` |
 | Report schema (v0.6 frozen reference) | [`docs/report-schema.v0.6.json`](docs/report-schema.v0.6.json) | `0.6` |
-| Packet schema (Release Evidence Packet, latest) | [`docs/packet-schema.v0.10.json`](docs/packet-schema.v0.10.json) | `0.10` |
+| Packet schema (Release Evidence Packet, latest) | [`docs/packet-schema.v0.11.json`](docs/packet-schema.v0.11.json) | `0.11` |
 | Agent result schema (current) | [`docs/agent-result-schema.v2.json`](docs/agent-result-schema.v2.json) | `agent_result_v2` |
-| Verifier schema (current) | [`docs/verifier-schema.v0.3.json`](docs/verifier-schema.v0.3.json) | `0.3` |
-| Agent handoff schema (current) | [`docs/agent-handoff-schema.v3.json`](docs/agent-handoff-schema.v3.json) | `shipgate.agent_handoff/v3` |
+| Verifier schema (current) | [`docs/verifier-schema.v0.4.json`](docs/verifier-schema.v0.4.json) | `0.4` |
+| Agent handoff schema (current) | [`docs/agent-handoff-schema.v4.json`](docs/agent-handoff-schema.v4.json) | `shipgate.agent_handoff/v4` |
 | Preflight schema (current) | [`docs/preflight-schema.v0.3.json`](docs/preflight-schema.v0.3.json) | `0.3` |
 | Host-grants inventory schema | [`docs/host-grants-inventory-schema.v0.2.json`](docs/host-grants-inventory-schema.v0.2.json) | `0.2` |
 | Host-grants baseline schema | [`docs/host-grants-baseline-schema.v0.2.json`](docs/host-grants-baseline-schema.v0.2.json) | `0.2` |
 | Host-grants drift schema | [`docs/host-grants-drift-schema.v0.2.json`](docs/host-grants-drift-schema.v0.2.json) | `0.2` |
-| Capability standard | [`docs/capability-standard.md`](docs/capability-standard.md) | `0.4` |
-| Capability lock schema | [`docs/capability-lock-schema.v0.5.json`](docs/capability-lock-schema.v0.5.json) | `0.5` |
-| Capability lock diff schema | [`docs/capability-lock-diff-schema.v0.6.json`](docs/capability-lock-diff-schema.v0.6.json) | `0.6` |
+| Capability standard | [`docs/capability-standard.md`](docs/capability-standard.md) | `0.5` |
+| Capability lock schema | [`docs/capability-lock-schema.v0.6.json`](docs/capability-lock-schema.v0.6.json) | `0.6` |
+| Capability lock diff schema | [`docs/capability-lock-diff-schema.v0.7.json`](docs/capability-lock-diff-schema.v0.7.json) | `0.7` |
 | Governance benchmark catalog schema | [`docs/governance-benchmark-catalog-schema.v0.2.json`](docs/governance-benchmark-catalog-schema.v0.2.json) | `0.2` |
 | Governance benchmark result schema | [`docs/governance-benchmark-result-schema.v0.2.json`](docs/governance-benchmark-result-schema.v0.2.json) | `0.2` |
 | Check catalog | [`docs/checks.json`](docs/checks.json) | regenerated each release |
@@ -582,7 +583,7 @@
 `agents-shipgate evidence-packet --from <packet.json|report.json>` to
 re-render. The full packet contract (fixed sections, disclaimers,
 `evidence_matrix` rules) lives in
-[STABILITY.md §Release Evidence Packet](STABILITY.md#release-evidence-packet-v010)
+[STABILITY.md §Release Evidence Packet](STABILITY.md#release-evidence-packet-v011)
 and [`docs/agent-contract-current.md`](docs/agent-contract-current.md#read-these-for-release-review).
 
 Exit codes (stable):

CHANGELOG.md

@@ -2,6 +2,27 @@
 
 ## Unreleased
 
+- **Evidence-basis policy gate (P0, `0.16.0b5`).** Semantic claims and risk
+  hints now carry a typed evidence basis, stable claim IDs, and derived policy
+  eligibility. Policy-pack and action-policy predicates evaluate to
+  `matched | not_matched | indeterminate | conflicting`; rule severity,
+  confidence, `block: true`, manual tags, and risk overrides cannot upgrade
+  heuristic or incomplete evidence into an authoritative finding.
+- **Non-waivable policy applicability gaps.** Heuristic-only, mixed, unknown,
+  or conflicting applicability is emitted outside Findings and routes to
+  `insufficient_evidence`. Baselines, suppressions, severity overrides,
+  acknowledgements, and `--no-heuristics` cannot hide it. Supported findings
+  expose deterministic predicate support and a `support_hash`; baseline v0.8
+  requires that hash to remain equal. Pre-v0.8 baselines cannot supply that
+  binding, so supported findings re-gate as new until a human reviews the new
+  evidence and re-runs `agents-shipgate baseline save`.
+- **Evidence contract versions.** Runtime contract advances to v16; report to
+  v0.33; packet to v0.11; verifier to v0.4; handoff to v4; policy pack to
+  v0.4; capability standard to v0.5; lock/diff to v0.6/v0.7; action snapshot
+  to v0.4; downstream local contract to v5; and safety qualification formats
+  to v3. Existing finding fingerprints and all prior schema files remain
+  frozen.
+
 - **Complete zero-config multi-host boundary (`0.16.0b4`).** The local
   boundary check now evaluates every recognized changed Codex, Claude Code,
   Cursor, VS Code MCP, shared instruction, and GitHub workflow surface through