test(engine): bind analysis fixture to snapshot policy revision

Author: Jeremy

docs/plans/mcp-observability/execution-ledger.md

@@ -45,3 +45,26 @@ invalid GH_TOKEN (I2); no push/PR or fallback credential/connection attempted.
 Local scope is complete, publication externally blocked. Final evidence commit
 retains clean source/branch and sanitized reports for parent; bundle outside repo
 preserves exact committed ref. Parent owns subsequent publication/merge.
+
+2026-10-14: Parent approved bounded I1 repair for PR #4 after prior service failures.
+Verified real checkout read/write/fsync, clean branch/head and remote PR head
+4887b7af; no workspace recovery or duplicate push needed. Revisited I1 disposition
+under explicit follow-up authority. Fixture now resolves POLICY from its immutable
+compiled snapshot, asserts existence and selects semantic_revision and its single
+successor before the existing counting mocks. Production validator, normative
+content and both count assertions are unchanged. Failing case, analysis module,
+full Engine suite and independent review are required before the next commit/push.
+
+2026-10-15: Fixture repair qualified. Owner targeted case passed 1 test in 3.748 s;
+independent targeted case passed in 3.676 s. Refreshed the registered test input
+through public Engine verify_repository; staged the new review report membership
+and refreshed again before freezing inputs. The initial analysis/full attempts
+with stale generated input were interrupted and are not acceptance evidence.
+Final analysis module passed 23 tests in 113.275 s. One uninterrupted full serial
+Engine invocation passed all 636 tests in 2161.675 s under PYTHONPATH=.; the formerly
+failing case and all observer-v3 tests passed in that run. Independent review bound
+test_analysis.py SHA256 7f51e403f03f5c57be8b1ca5736a79bcf139c87dd9eb4703ce3f7e59f1ba3d01.
+No production, validator or normative edits; both call-count assertions unchanged.
+Final evidence retains the historical I1 failure and resolves prior I2 transport
+confusion. Reviewed bounded staged scope before committing for approved PR #4
+branch push; publication identity is the Git ref, merge remains parent-owned.

docs/plans/mcp-observability/issues.md

@@ -1,20 +1,23 @@
 # Findings
 
-## I1 — baseline proposal-analysis fixture (medium, deferred)
+## I1 — baseline proposal-analysis fixture (medium, resolved)
 
 `test_analysis.AnalysisWorkflowTest.test_proposal_analysis_uses_one_projection_and_one_verified_base`
-hardcodes accepted semantic revision 1/proposed 2. Both the candidate and a clean
+originally hardcoded accepted semantic revision 1/proposed 2. Both the candidate and a clean
 Git clone of baseline `188beda1fa477d21d576c233dd8c7f4c4c267d23` return
 `AUTHORING.INVALID_SEMANTIC_REVISION` before the test reaches its projection-count
 assertions. Independent one-test baseline run:1 test, 1 failure, 1.397 s; candidate:
-1 test, 1 failure, 1.606 s. This source test is unchanged by issue3.
-
-Owner: existing analysis test/standards-content maintainers. Disposition: defer
-outside the recorder write set; do not edit normative standards or weaken the
-validator. Revisit when maintaining this fixture against accepted policy revision.
-Required evidence: bind the test to the actual immutable accepted policy revision,
-then verify its intended projection-count claim. Full suite results remain visible;
-this is not labeled a successful complete Engine run.
+1 test, 1 failure, 1.606 s. At initial handoff head 4887b7af this source test was unchanged by issue3.
+
+Owner: analysis fixture maintainers. Parent explicitly authorized this bounded
+follow-up for PR #4. Disposition: resolved by deriving the accepted semantic
+revision and its successor from the same immutable snapshot used for the proposal,
+before the counting mocks. Policy existence, real proposal/analysis results and
+both count assertions remain required. Validator and normative content unchanged.
+The targeted case passed (3.748 s), all 23 analysis tests passed (113.275 s), and
+the full serial Engine suite passed all 636 tests (2161.675 s). Independent fixture
+review passed; see reports/fixture-review.md. Historical baseline failure evidence
+above remains retained rather than relabeled as a baseline pass.
 
 ## Resolved review findings
 
@@ -26,11 +29,11 @@ content. See reports/independent-review.md for source-bound evidence.
 Actual model/client traces are outside this task: synthetic process evidence does
 not certify model intent or acquisition. No new model qualification is claimed.
 
-## I2 — publication authentication (blocking, external)
+## I2 — publication authentication (resolved)
 
-`gh auth status` reports an invalid configured `GH_TOKEN`. Owner: parent/operator
-of the authorized GitHub connection. User has approved push+PR; no renewed
-publication approval is needed. Disposition: preserve exact local commits and
-Git bundle; do not replace credentials or bypass access failure. Revisit when a
-working authorized Git transport is available, then push/open PR. No remote
-mutation was attempted through a fallback credential or connection.
+The GitHub CLI reported an invalid configured `GH_TOKEN`, initially treated as a
+publication blocker. A later explicitly authorized attempt through the existing
+Git remote succeeded without inspecting/copying tokens or changing authentication.
+Remote head 4887b7af was verified and the parent opened draft PR #4. The CLI failure
+did not establish failure of the separate Git transport. Existing bundle and
+checkout were preserved; subsequent publication uses the approved Git branch.

docs/plans/mcp-observability/plan.md

@@ -1,6 +1,6 @@
 # Persistent MCP interaction observability (issue 3)
 
-Status: Blocked (publication authentication). Local acceptance: satisfied; I1 baseline fixture deferred. Publication acceptance: unavailable (I2). Operation: start. Owner: implementation agent;
+Status: Accepted (local fixture qualification). Acceptance: satisfied. Operation: verify. Owner: implementation agent;
 publication and merge authority remain with the parent/operator. Baseline:
 `188beda1fa477d21d576c233dd8c7f4c4c267d23` (interface 46).
 Canonical plan: `docs/plans/mcp-observability/plan.md`.
@@ -119,13 +119,26 @@ D Accepted: cold stdio/process replacement, exceptions/interruption, real unavai
 locked/full SQLite, concurrent processes, migration/retention/privacy. Existing MCP,
 runtime identity, discovery and observer-v3 tests plus full Engine suite and
 contract projection check. Synthetic baseline/candidate call and byte comparison.
-E Blocked: independent GPT-6.1 Sol High design/source/privacy review accepted with all seven findings resolved; staged and full branch review, local commits, authorized push and PR.
+E Accepted: independent GPT-6.1 Sol High design/source/privacy review accepted with all seven findings resolved; staged and full branch review, local commits, authorized push and PR.
 No real logs or confidential artifacts in Git. Parent owns merge. The generated
 `evaluation/standards-effectiveness/generated/suite-inputs.json` is an allowed
 adjacent write: refresh through the Engine after staging declared inputs; it
 tracks source/README digests and is not a normative standards change.
 
-Current phase: E (publication blocked). Next slice: parent restores working authorized GitHub access, then publishes the retained exact branch and opens the approved PR.
-Blockers: I2 invalid GitHub CLI token. D executed all 636 Engine cases: 635 pass after environment qualification,1 unchanged baseline fixture failure I1 explicitly deferred. No full-suite-green claim is made. Replan on privacy/schema ownership, protocol/domain
-outcome change, unsupported storage invariant or insufficient acceptance evidence.
-See [verification](reports/verification.md), [independent review](reports/independent-review.md), [ledger](execution-ledger.md) and [issues](issues.md).
+F Accepted: repair I1 using the actual policy semantic revision from the immutable
+snapshot, before entering the existing counting mocks. Write set:
+`tools/standards_engine/tests/test_analysis.py`, this plan/ledger/issues, a bounded
+fixture-review report and current verification evidence; generated verifier input
+manifest only if its compiler requires a refresh. Gate: failing case, analysis
+module and full Engine suite pass; independent review; reviewed commit/push to
+existing approved PR #4 branch. Validator, normative content and both count
+assertions remain unchanged. No telemetry activation or raw log publication.
+
+Current phase: complete local qualification. Next slice: none. Blockers: none.
+F evidence: targeted case passed; analysis module 23/23; full serial Engine suite
+636/636; independent fixture review satisfied. I1 is resolved without changing
+validator, normative content or either count assertion; historical baseline failure
+remains in issues/evidence. I2 resolved through the existing Git transport; parent
+opened PR #4. The verified follow-up is packaged for the explicitly approved branch
+push; Git/PR refs own publication identity and parent owns hosted CI/merge.
+See [verification](reports/verification.md), [fixture review](reports/fixture-review.md), [independent source/privacy review](reports/independent-review.md), [ledger](execution-ledger.md) and [issues](issues.md).

docs/plans/mcp-observability/reports/fixture-review.md

@@ -0,0 +1,68 @@
+# Independent fixture repair review
+
+Date: 2026-10-14. Parent baseline:
+`4887b7aff0ba84acd257da081135b7849cc9c79f`.
+Disposition: **satisfied for this bounded fixture change**. No source, privacy or
+oracle-weakening findings. Overall acceptance remains with the owner's final
+frozen-source analysis/full Engine and generated-input verification gates.
+
+## Exact scope
+
+The only test behavior change is in
+`tools/standards_engine/tests/test_analysis.py:2191`, method
+`test_proposal_analysis_uses_one_projection_and_one_verified_base`:
+
+- Resolve `POLICY` through the compiled corpus of the same `self.snapshot` used
+  as the proposal's `base_snapshot` and source of its body.
+- Assert the policy exists, then use its semantic revision as the accepted
+  revision and that revision plus one as the proposed revision.
+- Perform this setup before installing the two counting mocks.
+
+The diff is seven added lines and one removed line. The actual analysis call,
+`PendingResult` assertion and both exact `call_count == 1` assertions are
+unchanged. No production validator, normative content, telemetry code or public
+contract changes. The coordinated generated `suite-inputs.json` refresh is an
+allowed fixture-repair artifact: it records the changed registered test input and
+review-file membership; it does not alter the validator or weaken its decision.
+
+## Authority and oracle assessment
+
+`StandardsEngine._compiled_snapshot` at `engine.py:2122` loads captured content for
+the explicit snapshot ID and compiles a `FrozenContentSource`; it does not select
+the current live policy implicitly. Snapshot `load_content` at
+`standards_snapshots/module.py:123` verifies captured content identity after its
+durable read. The fixture's `open_repository` call supplies no compiled cache, so
+the extra setup lookup does not introduce a warm-cache substitute for the observed
+analysis path.
+
+The repair follows the existing nearby convention in
+`test_analysis.py:335–351`: obtain the policy's accepted semantic revision from the
+captured corpus and advance it explicitly. This is correct fixture authority,
+rather than a new expected-result oracle derived from the subject under test.
+The test's independent expected behavior remains one verified-base load and one
+proposal projection during the analysis operation. Real proposal construction
+and revision validation still run and `CreateProposalResult` remains required.
+
+## Independent evidence and binding
+
+Command, from `/workspace/Coding-Standards` on CPython 3.12.14:
+
+```sh
+PYTHONPATH=. python -m unittest tools.standards_engine.tests.test_analysis.AnalysisWorkflowTest.test_proposal_analysis_uses_one_projection_and_one_verified_base
+```
+
+Result: **one test passed in 3.676 seconds**. `git diff --check` passed.
+
+Reviewed test-file SHA256:
+`7f51e403f03f5c57be8b1ca5736a79bcf139c87dd9eb4703ce3f7e59f1ba3d01`.
+
+The prior accepted observer, MCP, observer-test and operating-guide hashes were
+rechecked unchanged. The reviewer wrote only this report and performed no
+publication or installation action. No model calls or private logs were used.
+
+The owner's first broader runs were interrupted because the registered test input
+had changed before its generated verifier digest was refreshed; their partial
+results are not acceptance evidence. The owner is refreshing through the public
+Engine verification path and will rerun the analysis module and full serial
+Engine suite from frozen source. Those final results and generated-manifest
+freshness are outside this independently executed targeted check.

docs/plans/mcp-observability/reports/verification.md

@@ -8,15 +8,40 @@ The following evidence commit owns this report; use `git rev-parse HEAD` for the
 final handoff OID. No normative standards, generated agent contracts, Tuldok,
 observer-v3 code/artifacts or existing installation configuration changed.
 
-## Result
+## Current fixture follow-up result (2026-10-15)
 
-Local issue3 implementation and independent source/privacy review are satisfied.
-Publication is blocked by unavailable GitHub CLI authentication: `gh auth status`
-reports that the configured `GH_TOKEN` is invalid. User authorization for push/PR
-was received; this is an authentication blocker, not a request for permission.
-No push, PR, comment, deployment, telemetry enabling or credential workaround was
-performed. Parent retains publication/merge ownership through a working authorized
-connection. The exact committed branch is preserved in a separate Git bundle.
+The bounded PR #4 fixture repair is qualified: resolve the policy from the same
+immutable snapshot, assert it exists, use semantic_revision and its successor,
+and keep setup outside the counting mocks. The real result assertions, validator,
+normative content and both count assertions are unchanged. Only test behavior and
+its registered generated-input digest changed; production observer hashes remain
+those accepted by the original source/privacy review.
+
+| Required follow-up check | Result |
+| --- | --- |
+| Formerly failing case | 1 test passed in 3.748 s |
+| Complete analysis module | 23 tests passed in 113.275 s |
+| Full serial Engine suite | 636 tests passed in 2161.675 s; one uninterrupted invocation with PYTHONPATH=. |
+| Independent fixture review | Satisfied; targeted case independently passed in 3.676 s; exact test-file SHA256 recorded |
+| Generated input verification | Public Engine refresh returned 73 suites / 121 checks passed before final frozen-source runs |
+
+See [fixture review](fixture-review.md). The first broader attempts caught the
+stale registered test-input digest and were interrupted; no partial results count
+as acceptance. After the coordinated generated-input refresh, both requested
+broader commands were restarted from zero and passed as stated above.
+
+The existing Git transport successfully published the original head 4887b7af
+without authentication changes; the parent opened draft PR #4. The invalid CLI
+token was specific to that CLI connection, not proof that Git transport failed.
+The verified fixture follow-up is packaged for the approved existing branch push;
+Git/PR refs own the actual publication identity. Parent owns hosted CI and merge.
+No existing installation was enabled and no actual interaction log is published.
+
+## Original observability qualification (before fixture repair)
+
+The evidence below preserves the initial baseline comparison and its historical
+I1 failure. That failure is now resolved by the qualified follow-up above; it has
+not been rewritten as a successful run of the old fixture.
 
 ## Evidence and limits
 
@@ -46,12 +71,13 @@ invocation was green. The CI environment sets `PYTHONPATH=.`. An initial
 and candidate; re-running each with that documented setting passed (candidate
 45.363 s, baseline 43.920 s). Its corrected pass is included in 635.
 
-The one remaining failure is
+The original remaining failure was
 `test_analysis.AnalysisWorkflowTest.test_proposal_analysis_uses_one_projection_and_one_verified_base`:
-`AUTHORING.INVALID_SEMANTIC_REVISION`. It fails identically in a clean Git clone of
+`AUTHORING.INVALID_SEMANTIC_REVISION`. It failed identically in a clean Git clone of
 the baseline, because the fixture hardcodes accepted revision 1/proposed 2. The
-recorder never participates in that test. See [I1](../issues.md). It is deferred
-to the owning fixture maintainers; the full Engine suite is not labeled green.
+recorder never participates in that test. See [I1](../issues.md). It was initially
+deferred, then repaired under explicit follow-up authority as recorded above. The
+initial qualification is not relabeled as a green full-suite run.
 
 The recorder regressions cover opt-in omission, unchanged catalog/outcomes,
 actual validation feedback, malformed envelopes/JSON, arbitrary-output exclusion,
@@ -81,7 +107,8 @@ python3 -m tools.standards_contracts.standards_contracts.projection --check
 PYTHONPATH=.:tools/standards_verifier python3 tools/standards_verifier/verify.py --complete
 ```
 
-The broad command is expected to expose I1 on this accepted-content baseline.
+The broad command exposed I1 at original head 4887b7af; after the bounded fixture
+repair the current full serial suite passes all 636 tests.
 [Cold comparison](baseline-comparison.md) gives the workload and byte totals.
 [Independent review](independent-review.md) binds final production/test/docs hashes.
 [Operating contract](../../../../tools/standards_engine/MCP-OBSERVABILITY.md) owns
@@ -96,15 +123,17 @@ reverifies any material change. Retirement follows the parent's accepted merge,
 rejection or explicit retained-resource decision; this task grants no destructive
 cleanup authority. No other mounted repository was modified.
 
-The handoff bundle is `/workspace/issue3-mcp-observability.bundle`, outside the
-repository and not staged. It requires the named baseline commit and preserves
-the exact feature ref/head. In an authorized checkout containing that baseline:
+The original `/workspace/issue3-mcp-observability.bundle` remains preserved at
+pre-fixture head 4887b7af. The qualified fixture follow-up is packaged separately
+as `/workspace/issue3-mcp-observability-fixture-repair.bundle`, outside the
+repository and not staged. It requires the named baseline and preserves its
+exact feature ref/head. In an authorized checkout containing that baseline:
 
 ```sh
-git bundle verify /workspace/issue3-mcp-observability.bundle
-git fetch /workspace/issue3-mcp-observability.bundle feat/issue3-mcp-observability:feat/issue3-mcp-observability
+git bundle verify /workspace/issue3-mcp-observability-fixture-repair.bundle
+git fetch /workspace/issue3-mcp-observability-fixture-repair.bundle feat/issue3-mcp-observability:feat/issue3-mcp-observability
 ```
 
-Parent may then review the exact branch, push it and open the approved issue3 PR
-through working authorized access. Merge and installation enablement remain
-separate decisions. No actual telemetry or qualification trace accompanies it.
+PR #4 already exists. Parent may inspect the exact qualified branch and its
+publication ref through working authorized access. Merge and installation
+enablement remain separate decisions. No actual telemetry or qualification trace accompanies it.

evaluation/standards-effectiveness/generated/suite-inputs.json

@@ -7829,7 +7829,7 @@
       ]
     },
     {
-      "digest": "sha256:c463c48d95bcbc5b5bfd3690668198897a251c5000e59db71f2cbc5f983d71af",
+      "digest": "sha256:7f51e403f03f5c57be8b1ca5736a79bcf139c87dd9eb4703ce3f7e59f1ba3d01",
       "path": "tools/standards_engine/tests/test_analysis.py",
       "state": "present",
       "uses": [
@@ -14070,7 +14070,7 @@
     "path": "evaluation/standards-effectiveness/suite-registry.toml"
   },
   "repository_index": {
-    "digest": "sha256:7e6fd4988235abb92e2dd8eea14954b57f9e2b247ef7fddfac5afef2073e65c4",
+    "digest": "sha256:32d5e126dd74c0349f8b402496260d9184db813209fc2e6de80ed4259f66bef9",
     "uses": [
       {
         "check": "python-package-contract",