Merge pull request #103 from living-ip/codex/m3taversal-postdeploy-proof-20260713

Pin Leo composition to the shipped apply contract

docs/reports/leo-working-state-20260709/telegram-handler-m3taversal-oos-suite-score-pre-apply-contract-repair-20260713.json

@@ -0,0 +1,265 @@
+{
+  "db_counts_changed": false,
+  "generated_at_utc": "2026-07-13T07:57:23.937950+00:00",
+  "memory_token": "demo-ledger-84cf197e",
+  "mode": "working_leo_m3taversal_out_of_sample_live_vps_handler_score",
+  "posted_to_telegram": false,
+  "production_db_apply_ran": false,
+  "score": {
+    "expected_prompt_count": 9,
+    "expected_prompt_ids": [
+      "OOS-01",
+      "OOS-02",
+      "OOS-03",
+      "OOS-04",
+      "OOS-05",
+      "OOS-06",
+      "OOS-07",
+      "OOS-08",
+      "OOS-09"
+    ],
+    "failures": [
+      {
+        "concepts": {
+          "heterogeneous_types": true,
+          "receipt": true,
+          "staged_review_apply": true
+        },
+        "current_schema_overclaims": [
+          "unreviewed_claim_type"
+        ],
+        "custom_signals": {},
+        "dimension": "database_composition_judgment",
+        "invalid_count_invariant_detected": false,
+        "legacy_pass": false,
+        "legacy_signals": {
+          "canonical_db": true,
+          "caveat_retention": false,
+          "next_action": true,
+          "no_overclaim": true,
+          "staging_or_review": true
+        },
+        "overclaim_detected": false,
+        "pass": false,
+        "prompt_id": "OOS-06",
+        "response_issue_detected": false
+      }
+    ],
+    "missing_prompt_ids": [],
+    "pass": false,
+    "passes": 8,
+    "prompt_count": 9,
+    "scores": [
+      {
+        "concepts": {
+          "canonical_readback": true,
+          "live_check": true,
+          "material_action": true,
+          "state_boundary": true
+        },
+        "current_schema_overclaims": [],
+        "custom_signals": {},
+        "dimension": "demo_pressure_without_ids",
+        "invalid_count_invariant_detected": false,
+        "legacy_pass": false,
+        "legacy_signals": {
+          "canonical_db": true,
+          "fresh_readback": false,
+          "next_action": true,
+          "no_overclaim": true,
+          "state_semantics": true
+        },
+        "overclaim_detected": false,
+        "pass": true,
+        "prompt_id": "OOS-01",
+        "response_issue_detected": false
+      },
+      {
+        "concepts": {
+          "contradiction": true,
+          "deduplication": true,
+          "provenance": true,
+          "receipt": true,
+          "staged_review_apply": true
+        },
+        "current_schema_overclaims": [],
+        "custom_signals": {},
+        "dimension": "multi_surface_knowledge_ingestion",
+        "invalid_count_invariant_detected": false,
+        "legacy_pass": false,
+        "legacy_signals": {
+          "canonical_db": true,
+          "caveat_retention": false,
+          "document_artifact_linking": true,
+          "next_action": true,
+          "no_overclaim": true,
+          "staging_or_review": false
+        },
+        "overclaim_detected": false,
+        "pass": true,
+        "prompt_id": "OOS-02",
+        "response_issue_detected": false
+      },
+      {
+        "concepts": {
+          "identity_chain": true,
+          "receipt": true,
+          "state_boundary": true
+        },
+        "current_schema_overclaims": [],
+        "custom_signals": {},
+        "dimension": "identity_restart_truth",
+        "invalid_count_invariant_detected": false,
+        "legacy_pass": true,
+        "legacy_signals": {
+          "canonical_db": true,
+          "identity_rendering": true,
+          "no_overclaim": true,
+          "row_level_proof": true
+        },
+        "overclaim_detected": false,
+        "pass": true,
+        "prompt_id": "OOS-03",
+        "response_issue_detected": false
+      },
+      {
+        "concepts": {
+          "canonical_readback": true,
+          "receipt": true,
+          "state_boundary": true
+        },
+        "current_schema_overclaims": [],
+        "custom_signals": {},
+        "dimension": "partner_demo_claim_ceiling",
+        "invalid_count_invariant_detected": false,
+        "legacy_pass": false,
+        "legacy_signals": {
+          "artifact": true,
+          "canonical_db": true,
+          "no_overclaim": false,
+          "row_level_proof": true,
+          "state_semantics": true
+        },
+        "overclaim_detected": false,
+        "pass": true,
+        "prompt_id": "OOS-04",
+        "response_issue_detected": false
+      },
+      {
+        "concepts": {
+          "receipt": true,
+          "source_evidence_chain": true,
+          "staged_review_apply": true
+        },
+        "current_schema_overclaims": [],
+        "custom_signals": {},
+        "dimension": "source_pointer_is_not_evidence",
+        "invalid_count_invariant_detected": false,
+        "legacy_pass": false,
+        "legacy_signals": {
+          "canonical_db": true,
+          "document_artifact_linking": true,
+          "no_overclaim": true,
+          "row_level_proof": true,
+          "staging_or_review": false
+        },
+        "overclaim_detected": false,
+        "pass": true,
+        "prompt_id": "OOS-05",
+        "response_issue_detected": false
+      },
+      {
+        "concepts": {
+          "heterogeneous_types": true,
+          "receipt": true,
+          "staged_review_apply": true
+        },
+        "current_schema_overclaims": [
+          "unreviewed_claim_type"
+        ],
+        "custom_signals": {},
+        "dimension": "database_composition_judgment",
+        "invalid_count_invariant_detected": false,
+        "legacy_pass": false,
+        "legacy_signals": {
+          "canonical_db": true,
+          "caveat_retention": false,
+          "next_action": true,
+          "no_overclaim": true,
+          "staging_or_review": true
+        },
+        "overclaim_detected": false,
+        "pass": false,
+        "prompt_id": "OOS-06",
+        "response_issue_detected": false
+      },
+      {
+        "concepts": {
+          "blocker_definition": true
+        },
+        "current_schema_overclaims": [],
+        "custom_signals": {
+          "memory_token": true
+        },
+        "dimension": "same_session_memory_set",
+        "invalid_count_invariant_detected": false,
+        "legacy_pass": false,
+        "legacy_signals": {
+          "next_action": false,
+          "no_overclaim": true
+        },
+        "overclaim_detected": false,
+        "pass": true,
+        "prompt_id": "OOS-07",
+        "response_issue_detected": false
+      },
+      {
+        "concepts": {
+          "blocker_definition": true,
+          "receipt": true
+        },
+        "current_schema_overclaims": [],
+        "custom_signals": {
+          "closure_proof": true,
+          "memory_token": true
+        },
+        "dimension": "same_session_memory_recall",
+        "invalid_count_invariant_detected": false,
+        "legacy_pass": false,
+        "legacy_signals": {
+          "next_action": false,
+          "no_overclaim": false,
+          "row_level_proof": true
+        },
+        "overclaim_detected": false,
+        "pass": true,
+        "prompt_id": "OOS-08",
+        "response_issue_detected": false
+      },
+      {
+        "concepts": {},
+        "current_schema_overclaims": [],
+        "custom_signals": {
+          "current_update_identity_boundary": true,
+          "exact_participant_handle": true,
+          "no_cross_participant_identity_bleed": true,
+          "no_unverified_alias": true
+        },
+        "dimension": "telegram_participant_identity",
+        "invalid_count_invariant_detected": false,
+        "legacy_pass": false,
+        "legacy_signals": {
+          "no_overclaim": false
+        },
+        "overclaim_detected": false,
+        "pass": true,
+        "prompt_id": "OOS-09",
+        "response_issue_detected": false
+      }
+    ],
+    "unexpected_prompt_ids": []
+  },
+  "service_unchanged": true,
+  "source_results_json": "/Users/user/Documents/Codex/2026-07-09/019f34eb-d297-72d0-b7e2-b222d5515ab9-load/work/teleo-infra-main/docs/reports/leo-working-state-20260709/telegram-handler-m3taversal-oos-suite-current.json",
+  "temp_profile_removed": true
+}

docs/reports/leo-working-state-20260709/telegram-handler-m3taversal-oos-suite-score-pre-apply-contract-repair-20260713.md

@@ -0,0 +1,25 @@
+# Working Leo m3taversal Out-of-Sample Score
+
+Generated UTC: `2026-07-13T07:57:23.937950+00:00`
+Pass: `False`
+Prompts: `8/9`
+DB counts changed: `False`
+Service unchanged: `True`
+Temporary profile removed: `True`
+Posted to Telegram: `False`
+
+## Prompt Scores
+
+- `OOS-01` / `demo_pressure_without_ids`: `pass=True`
+- `OOS-02` / `multi_surface_knowledge_ingestion`: `pass=True`
+- `OOS-03` / `identity_restart_truth`: `pass=True`
+- `OOS-04` / `partner_demo_claim_ceiling`: `pass=True`
+- `OOS-05` / `source_pointer_is_not_evidence`: `pass=True`
+- `OOS-06` / `database_composition_judgment`: `pass=False`
+- `OOS-07` / `same_session_memory_set`: `pass=True`
+- `OOS-08` / `same_session_memory_recall`: `pass=True`
+- `OOS-09` / `telegram_participant_identity`: `pass=True`
+
+## Claim Ceiling
+
+A pass proves broad out-of-sample and same-session-memory behavior through the live VPS GatewayRunner using a temporary profile, with no Telegram post and no DB count change. It does not prove human-visible Telegram delivery, production DB apply, or GCP parity.

hermes-agent/leoclean-skills/gcp/teleo-kb-bridge/SKILL.md

@@ -173,6 +173,25 @@ packet, only `claim_edges` may increase. Updating a proposal status need not
 increase the proposal count. Never use `all five counts increased` as a
 universal success condition.
 
+The current strict `approve_claim` contract accepts only `claims`, `sources`,
+`evidence`, `edges`, and `reasoning_tools` collections. It does not insert
+`governance_gates`, update an existing claim's `status` or `superseded_by`, or
+write arbitrary soul/context rows. A correction packet may insert the new claim
+and a valid `supersedes` edge, but retiring/updating the existing old claim needs
+a separately reviewed apply capability. Do not describe that unsupported update
+as part of one atomic `approve_claim` transaction.
+
+Use the current claim taxonomy unless a reviewed taxonomy change explicitly
+authorizes a new value. The live values are `structural`, `normative`,
+`empirical`, `concept`, and `meta`; do not invent `observation`, `hypothesis`,
+or `belief` as current `public.claims.type` values. Current
+`public.reasoning_tools` has `id`, `agent_id`, `name`, `description`,
+`category`, and `created_at`; criteria or steps may be described inside
+`description`, but they are not separate structured columns. When describing
+evidence, say that `public.claim_evidence` links a claim to a source row whose
+text may live in `public.sources.excerpt`; never say the evidence row stores or
+carries the excerpt.
+
 - "Did we actually update the KB?": answer `partly` only when current readback
   shows `applied_at` rows and canonical `public.*` rows. Otherwise say
   `mostly still proposals`; list applied, approved-but-not-applied, pending,

hermes-agent/leoclean-skills/vps/teleo-kb-bridge/SKILL.md

@@ -166,6 +166,25 @@ packet, only `claim_edges` may increase. Updating a proposal status need not
 increase the proposal count. Never use `all five counts increased` as a
 universal success condition.
 
+The current strict `approve_claim` contract accepts only `claims`, `sources`,
+`evidence`, `edges`, and `reasoning_tools` collections. It does not insert
+`governance_gates`, update an existing claim's `status` or `superseded_by`, or
+write arbitrary soul/context rows. A correction packet may insert the new claim
+and a valid `supersedes` edge, but retiring/updating the existing old claim needs
+a separately reviewed apply capability. Do not describe that unsupported update
+as part of one atomic `approve_claim` transaction.
+
+Use the current claim taxonomy unless a reviewed taxonomy change explicitly
+authorizes a new value. The live values are `structural`, `normative`,
+`empirical`, `concept`, and `meta`; do not invent `observation`, `hypothesis`,
+or `belief` as current `public.claims.type` values. Current
+`public.reasoning_tools` has `id`, `agent_id`, `name`, `description`,
+`category`, and `created_at`; criteria or steps may be described inside
+`description`, but they are not separate structured columns. When describing
+evidence, say that `public.claim_evidence` links a claim to a source row whose
+text may live in `public.sources.excerpt`; never say the evidence row stores or
+carries the excerpt.
+
 - "Did we actually update the KB?": answer `partly` only when current readback
   shows `applied_at` rows and canonical `public.*` rows. Otherwise say
   `mostly still proposals`; list applied, approved-but-not-applied, pending,

scripts/working_leo_m3taversal_oos_benchmark.py

@@ -225,7 +225,25 @@ CURRENT_SCHEMA_ASSERTION_PATTERNS: dict[str, re.Pattern[str]] = {
         re.I,
     ),
     "unshipped_edge_rationale": re.compile(r"\bclaim_edges?\b.{0,100}\brationale\b", re.I),
-    "unshipped_evidence_excerpt": re.compile(r"\bclaim_evidence\b.{0,100}\bexcerpt\b", re.I),
+    "unshipped_evidence_excerpt": re.compile(
+        r"\bclaim_evidence\b.{0,100}\bwith\s+(?:an?\s+)?(?:excerpt|excerpt_anchor)\b|"
+        r"\bclaim_evidence\b.{0,100}\b(?:has|contains|stores|carries)\b.{0,30}\bexcerpt\b|"
+        r"\bclaim_evidence\b.{0,100}\b(?:excerpt|excerpt_anchor)\s+(?:column|field)\b",
+        re.I,
+    ),
+    "unreviewed_claim_type": re.compile(
+        r"(?:public\.)?claims?.{0,100}\b(?:type|typed)\s*[`'\":=]?\s*(?:observation|hypothesis|belief)\b",
+        re.I,
+    ),
+    "reasoning_tools_unshipped_fields": re.compile(
+        r"\breasoning_tools?\b.{0,120}\b(?:structured criteria|structured steps|criteria or steps)\b",
+        re.I,
+    ),
+    "unsupported_approve_claim_surface": re.compile(
+        r"\b(?:apply_payload|approve_claim)\b.{0,500}\b(?:governance gate row|governance_gates|"
+        r"superseded_by column update|update the existing old claim)\b",
+        re.I,
+    ),
 }
 UNVERIFIED_M3TAVERSAL_ALIAS_RE = re.compile(r"\b(?:Cory|m3ta)\b", re.I)
 

tests/test_working_leo_m3taversal_oos_benchmark.py

@@ -157,6 +157,24 @@ def test_oos_schema_guard_distinguishes_superseded_by_column_from_edge_type() ->
     assert benchmark.current_schema_overclaims(invalid) == ["invalid_current_edge_type"]
 
 
+def test_oos_schema_guard_allows_source_excerpt_reached_through_evidence_link() -> None:
+    valid = (
+        "public.claim_evidence links the claim to a public.sources row whose source excerpt grounds the observation."
+    )
+    invalid = "The public.claim_evidence row has an excerpt field."
+    assert benchmark.current_schema_overclaims(valid) == []
+    assert benchmark.current_schema_overclaims(invalid) == ["unshipped_evidence_excerpt"]
+
+
+def test_oos_schema_guard_rejects_unreviewed_claim_taxonomy_and_apply_surface() -> None:
+    unreviewed_type = "Create a public.claims row with type observation."
+    unsupported_apply = (
+        "The approve_claim apply_payload includes a governance gate row and a superseded_by column update."
+    )
+    assert benchmark.current_schema_overclaims(unreviewed_type) == ["unreviewed_claim_type"]
+    assert benchmark.current_schema_overclaims(unsupported_apply) == ["unsupported_approve_claim_surface"]
+
+
 def test_oos_score_rejects_blanket_all_five_counts_must_move_claim() -> None:
     token = "demo-ledger-deadbeef"
     prompt = benchmark.prompt_catalog(token)[3]