Planner Autonomy: закрепить catalog-alignment в phase32 и AGENT-каталоге

2026-05-01 16:39:59 +03:00
parent c69a91342f
commit e13068cf4d
7 changed files with 24581 additions and 119 deletions
@@ -126,6 +126,8 @@ The following consolidation step added catalog-level chain-template scoring:
 - scenario acceptance now groups that warning under `catalog_alignment_ok`, and `final_status.md` prints the invariant alongside direct-answer, temporal, truth-gate, human-answer, meta-context, and selected-object gates.
 - truth-harness specs can now assert `expected_catalog_alignment_status`, `expected_catalog_chain_top_match`, and `expected_catalog_selected_matches_top` on each step.
 - `address_truth_harness_phase66_human_org_open_scope_dialog.json` now uses those fields to assert `value_flow`, `value_flow_comparison`, and `value_flow_ranking` top matches across the open-organization money dialog.
+- `address_truth_harness_phase32_planner_selected_chain_end_to_end.json` now uses the same assertions across selected-counterparty entity grounding, incoming/outgoing/net value-flow, document evidence, and movement evidence follow-ups.
+- `agent_semantic_pack_builder` now preserves these expected catalog-alignment fields in the reusable source catalog and adds the `planner_catalog_alignment` tag, so future mixed AGENT packs can deliberately select planner-brain regression probes instead of relying on hand-picked replay filenames.

 ## Why This Matters

@@ -281,9 +283,15 @@ Latest validation after phase66 catalog-alignment spec hardening:
 - Python replay-tooling tests: passed, `7 passed`
 - `load_truth_harness_spec` confirmed the phase66 expected top-match chain sequence: `value_flow`, `value_flow`, `value_flow`, `value_flow_comparison`, `value_flow_comparison`, `value_flow_ranking`, `value_flow_ranking`

+Latest validation after phase32 catalog-alignment spec hardening and AGENT source-catalog surfacing:
+
+- Python replay-tooling tests: passed, `9 passed`
+- `load_truth_harness_spec` confirmed the phase32 expected top-match chain sequence: `entity_resolution`, `value_flow`, `value_flow`, `value_flow_comparison`, `document_evidence`, `movement_evidence`
+- `agent_semantic_pack_builder.py inventory` regenerated `agent_semantic_source_catalog.*` with reusable `planner_catalog_alignment` coverage
+
 ## Next Step

-The next safe step is still to re-run live replay once the 1C side is actively polling the proxy. In parallel, local-only consolidation can continue by hardening additional planner-autonomy specs with expected catalog-chain assertions and by using `alignment_status`, alignment reason-code telemetry, truth-harness artifact surfacing, the soft divergence warning, `catalog_alignment_ok`, and the representative guard to find remaining manual branches where selected chains diverge from reviewed catalog-fabric intent.
+The next safe step is still to re-run live replay once the 1C side is actively polling the proxy. In parallel, local-only consolidation can continue by using the regenerated AGENT source catalog to assemble mixed planner-brain canaries, hardening additional planner-autonomy specs with expected catalog-chain assertions, and using `alignment_status`, alignment reason-code telemetry, truth-harness artifact surfacing, the soft divergence warning, `catalog_alignment_ok`, and the representative guard to find remaining manual branches where selected chains diverge from reviewed catalog-fabric intent.

 Recommended order:

@@ -89,6 +89,8 @@ It now documents a turnaround that is already operational in code, already mater
  - scenario acceptance now exposes `catalog_alignment_ok`, so planner-vs-catalog divergence is a first-class acceptance invariant instead of an ungrouped warning;
  - truth-harness specs can now assert expected catalog-alignment status/top-match/top-flag per step, so AGENT packs can validate the planner brain's selected chain against the reviewed catalog route fabric;
  - the phase66 open-scope money dialog spec now asserts expected catalog-chain top matches across value-flow totals, bidirectional comparison, and ranking follow-ups;
+  - the phase32 selected-counterparty chain spec now asserts expected catalog-chain top matches across entity grounding, incoming/outgoing/net value-flow, document evidence, and movement evidence follow-ups;
+  - AGENT semantic source catalog generation now preserves expected catalog-alignment fields and tags reusable steps as `planner_catalog_alignment`, so mixed pack construction can find planner-brain regression probes explicitly;
  - explicit-counterparty incoming-vs-outgoing data-need graphs now select the reviewed `value_flow_comparison` chain instead of falling back to generic `value_flow`;
  - live map sync: [20 - planner_autonomy_consolidation_2026-05-01.md](./20%20-%20planner_autonomy_consolidation_2026-05-01.md)

@@ -101,7 +103,7 @@ Current honest status:
 - open-world bounded-autonomy readiness: `~85%`
 - Post-F semantic integrity module progress: `~99%` operationally closed, with remaining risk now treated as next-slice discovery rather than an open blocker inside the closed slice
 - active inventory-stock breadth slice progress: `100%` for the declared scenario pack, not for arbitrary inventory questions
- Planner Autonomy Consolidation progress: `~92%` for the declared module, with catalog-fabric, value-flow arbitration, lifecycle bounded inference, broad-evaluation bridge, inventory catalog templates, inventory runtime-boundary honesty, exact inventory recipe bridging, unambiguous metadata-surface lane inference, catalog chain-template scoring, structured chain-match contract exposure, runtime/debug propagation, subject-aware bidirectional comparison arbitration, structured catalog-alignment verdicts, representative alignment regression guard, catalog-alignment reason-code telemetry, explicit `alignment_status` propagation, truth-harness/acceptance-matrix surfacing, soft divergence warning, `catalog_alignment_ok` acceptance invariant, step-level expected catalog-alignment assertions, and phase66 spec alignment expectations validated locally, but live replay for the new bridge is currently blocked by missing active 1C polling and broader unfamiliar 1C asks still need replay-backed growth
+- Planner Autonomy Consolidation progress: `~93%` for the declared module, with catalog-fabric, value-flow arbitration, lifecycle bounded inference, broad-evaluation bridge, inventory catalog templates, inventory runtime-boundary honesty, exact inventory recipe bridging, unambiguous metadata-surface lane inference, catalog chain-template scoring, structured chain-match contract exposure, runtime/debug propagation, subject-aware bidirectional comparison arbitration, structured catalog-alignment verdicts, representative alignment regression guard, catalog-alignment reason-code telemetry, explicit `alignment_status` propagation, truth-harness/acceptance-matrix surfacing, soft divergence warning, `catalog_alignment_ok` acceptance invariant, step-level expected catalog-alignment assertions, phase66 and phase32 spec alignment expectations, and AGENT source-catalog surfacing validated locally, but live replay for the new bridge is currently blocked by missing active 1C polling and broader unfamiliar 1C asks still need replay-backed growth
 - graph snapshot after latest rebuild: `5951 nodes`, `12926 edges`, `139 communities`
 - current breakpoint:
  - the validated hot paths are no longer structurally broken;
@@ -160,6 +162,7 @@ Latest live proof now includes:
 - catalog-alignment acceptance invariant accepted locally: Python truth-harness/acceptance tests passed `6/6`; graphify rebuilt to `5949 nodes`, `12923 edges`, `136 communities`
 - catalog-alignment spec assertions accepted locally: Python truth-harness/acceptance tests passed `7/7`; graphify rebuilt to `5951 nodes`, `12926 edges`, `139 communities`
 - phase66 planner-alignment spec hardening accepted locally: Python truth-harness/acceptance tests passed `7/7`; `load_truth_harness_spec` confirmed expected top matches `[value_flow, value_flow, value_flow, value_flow_comparison, value_flow_comparison, value_flow_ranking, value_flow_ranking]`
+- phase32 selected-counterparty planner-alignment spec hardening and AGENT source-catalog surfacing accepted locally: Python replay-tooling tests passed `9/9`; `load_truth_harness_spec` confirmed expected top matches `[entity_resolution, value_flow, value_flow, value_flow_comparison, document_evidence, movement_evidence]`; regenerated source catalog exposes `planner_catalog_alignment` as a reusable tag

 Current architectural reading: