conductor(campaign): metadata_ssdl_defusing_20260624 - 3-child SSDL defusing campaign

Campaign: address the parent code_path_audit_20260607 Finding 1 (CRITICAL)
Metadata 4.01e22 effective codepaths via 3 SSDL techniques.

3 children, sequential, with budget gates:
1. metadata_nil_sentinel_20260624 (>= 10% drop): introduce
   NIL_METADATA sentinel + migrate 6 nil-check functions.
2. metadata_generational_handle_20260624 (>= 20% drop,
   BLOCKED_BY 1): wrap Metadata in (index, generation) handle;
   collapse lifetime branches to 1 lookup + 1 cmp.
3. metadata_field_cache_20260624 (>= 30% drop, BLOCKED_BY 2):
   MetadataFieldCache keyed by (handle.index, field_name);
   123 string-keyed entry.get('key', default) sites become
   cache lookups.

Each child has its own spec/plan/metadata/state. Budget gate
after each child: re-measure effective codepaths; if drop < threshold,
PAUSE the campaign and report to user.

End-of-campaign TRACK_COMPLETION captures the cumulative reduction
vs the 4.01e22 baseline. Deferred follow-up: apply the same
3 SSDL primitives to the 4 other dict[str, Any] aliases
(FileItem, CommsLogEntry, HistoryMessage, ToolDefinition, ToolCall).

16 files committed: 4 directories x 4 files each (spec, plan,
metadata, state).

conductor/tracks/metadata_field_cache_20260624/plan.md

@@ -0,0 +1,86 @@
+# Plan: metadata_field_cache_20260624
+
+3 tasks, 3 atomic commits. Same pattern as children 1 and 2.
+
+## Phase 1: Behavioral Test (1 task)
+
+- [ ] Task 1.1: Write `tests/test_metadata_field_cache.py`.
+  - WHERE: New file `tests/test_metadata_field_cache.py`
+  - WHAT: 4 tests (per spec FR3)
+  - HOW: Use 1-space indentation
+  - SAFETY: Test imports `MetadataFieldCache` + `MetadataHandle` from their production locations
+  - COMMIT: `test(metadata): behavioral test for field cache (MetadataFieldCache)`
+  - GIT NOTE: 4 tests; will be RED until Phase 2 ships
+  - VERIFY: `uv run pytest tests/test_metadata_field_cache.py -v` shows 4/4 FAIL (expected)
+
+## Phase 2: Implementation (1 task)
+
+- [ ] Task 2.1: Add `MetadataFieldCache` + migrate the 123 field-access sites.
+  - WHERE: `src/aggregate.py` (cache type) + the 123 field-access sites across `src/`
+  - WHAT:
+    - Add `class MetadataFieldCache` with `get`, `set`, `invalidate` methods
+    - Migrate the 123 `entry.get('key', default)` and `entry['key']` sites to use the cache
+  - HOW: Use `manual-slop_py_add_def` for the cache type; `manual-slop_edit_file` for the migration sites
+  - SAFETY: Verify with `ast.parse`; run the 4 tests + the child-1 + child-2 tests + the 14 previously-failing tests
+  - COMMIT: `feat(metadata): MetadataFieldCache + 123 field-access site migrations`
+  - GIT NOTE: 123 sites now use cache; cache invalidation on generation bump (child 2's registry)
+  - VERIFY: `uv run pytest tests/test_metadata_field_cache.py tests/test_metadata_generational_handle.py tests/test_metadata_nil_sentinel.py -v` shows all PASS
+
+## Phase 3: Verification + Budget Gate (1 task)
+
+- [ ] Task 3.1: Run all 6 VCs; capture the budget gate measurement; write end-of-campaign TRACK_COMPLETION.
+  - WHERE: All audit gates + test suite + SSDL measurement + campaign umbrella
+  - WHAT:
+    - Run VC1-VC6 for the child
+    - Compute the new effective-codepaths number
+    - Compare to post-child-2 measurement; require drop ≥ 30%
+    - Write the child's TRACK_COMPLETION report
+    - Update this track's `state.toml` to `status = "completed"`, all 3 phases completed
+    - Append to campaign_measurements_20260624.md
+    - Update conductor/tracks.md
+    - ALSO: write the campaign's end-of-campaign TRACK_COMPLETION at `docs/reports/TRACK_COMPLETION_metadata_ssdl_defusing_20260624.md`
+    - Update the campaign umbrella's `state.toml` to `status = "completed"`, all 4 phases completed
+  - HOW: Run each VC command, capture output, write the report.
+  - SAFETY: Same as children 1 and 2
+  - COMMIT: 3 child commits (state, TRACK_COMPLETION, tracks.md) + 3 campaign commits (state, TRACK_COMPLETION, tracks.md)
+  - GIT NOTE: Per workflow.md
+  - VERIFY: All 6 VCs pass; budget gate met; campaign umbrella SHIPPED
+
+## Commit Log (Expected)
+
+1. `test(metadata): behavioral test for field cache` (Task 1.1)
+2. `feat(metadata): MetadataFieldCache + 123 field-access site migrations` (Task 2.1)
+3. `conductor(state): metadata_field_cache_20260624 SHIPPED` (Task 3.1)
+4. `docs(reports): TRACK_COMPLETION for metadata_field_cache_20260624` (Task 3.1)
+5. `conductor(tracks): add metadata_field_cache_20260624 row` (Task 3.1)
+6. `docs(reports): TRACK_COMPLETION for metadata_ssdl_defusing_20260624` (Task 3.1)
+7. `conductor(state): metadata_ssdl_defusing_20260624 SHIPPED` (Task 3.1)
+8. `conductor(tracks): add metadata_ssdl_defusing_20260624 row + 3 child rows` (Task 3.1)
+
+## Verification Commands
+
+```bash
+# VC1: cache type exists
+grep -rn "class MetadataFieldCache" src/
+
+# VC2: production uses cache
+grep -rn "field_cache.get\|field_cache.set" src/
+
+# VC3: tests pass
+uv run pytest tests/test_metadata_field_cache.py -v
+
+# VC4: budget gate (final measurement)
+uv run python -c "from src.code_path_audit_ssdl import compute_effective_codepaths; ...; print(compute_effective_codepaths(metadata_profile, 'src'))"
+
+# VC5: full test suite
+uv run python scripts/run_tests_batched.py
+
+# VC6: 4 audit gates
+uv run python scripts/audit_weak_types.py --strict
+uv run python scripts/generate_type_registry.py --check
+uv run python scripts/audit_main_thread_imports.py
+uv run python scripts/audit_no_models_config_io.py
+
+# Campaign-wide
+cat docs/reports/TRACK_COMPLETION_metadata_ssdl_defusing_20260624.md
+```