Drive every FM26 Deepener product to 100% polished completion under an expansive definition: functionality complete, decode confidence graded, tests green, docs current, and outputs staged so the only remaining layer is Jimmy's taste.
The session acts as architect only — all implementation goes to Sonnet/Opus implementer lanes and Codex cross-vendor lanes. Durable work items get slotted into beads; this page is the single view of progress.
outputs/advisor_loop/merge_train_2026-07-19.mdadvisor-loop label + 1 pre-existing cross-linked, no errorsoutputs/advisor_loop/estate_audit_2026-07-19.mdoutputs/advisor_loop/refactor_scout_2026-07-19.mdAll lanes verify locally with scripts/verify.py fast/pr; CI confirmation is blocked until the billing lockout clears.
outputs/advisor_loop/merge_train_2026-07-19.md. Holding merges until checks can actually run — gate-verdict-before-merge discipline.outputs/advisor_loop/story_samples_2026-07-19/.| Product | Status | Read on distance to done |
|---|---|---|
| fm_storytelling | 9 at standard* | All 9 types at standard in code; full union verified green (9,714 / 0). Real-data caveats being fixed: pre_match_preview rich brief doesn't engage on the real bundle (fix lane on #950), transfer types get no shortlist data on the Newcastle save (decoder portability lane), season_review sensitive to club-name format (queued behind the shared-infra triage lane). Merge runbook + train-tail patch ready. Then: taste-pass samples (needs ANTHROPIC_API_KEY). |
| fm_save_extract | Structurally closed | Frame 3 ledger 99.60% known, beyond-F3 unowned 0 bytes. Remaining decode gaps are FMRTE-session-gated (need Jimmy at the machine), not code work — except shortlist/scout surfaces (lane running). Warm re-decode ≈0.35s via fmdecode world already shipped. |
| fm_save_read / fm_oracle | Undocumented | Real consolidation layer the audit found that CLAUDE.md never mentions — docs lane is wiring it in; contract-drift audit queued. |
| fm_data_access | Queued | Canonical access layer, but fm_applications bypasses it (architectural drift, scout item 7); consolidation spec split into 3 landable steps. |
| fm_mcp_server / fm_data_mcp | In play | fm_mcp_server stale ~3 months; plan is consolidation into fm_data_mcp (queued). Real perf bug in fm_data_mcp — DataAccessService rebuilt per call — fix lane running. |
| fm_applications | Queued | Works but bypasses fm_data_access; reroute is step 2 of the consolidation spec. |
| fm_tactics_creator | To grade | .fmf create/inspect/edit shipped; polish bar assessment queued behind higher-leverage lanes. |
| fm_pilot | Roughest | Highest TODO density in the estate (56 per 10K LOC). TODO triage + restriction-policy bead queued; armed captures remain operator-gated. |
| fm_save_patch | Caveat | Re-parse-validated only, never FM-load-validated — honest ceiling until an FM-load test is designed (operator-gated). |
| fm_live_bridge | Scoped-done | Deliberately narrow read-only proof oracle; no gaps found within scope. |
| fm_html_extract | Legacy-frozen | FM24/25 only by design (FM26 removed HTML export). Docs lane removing overstated claims. |
| docs + tests | In play | Fast tier verified green on main (9,568 passed / 0 failed, run live today). STATUS.md + comprehensive plan stale — docs lane running. verify.py fast measured 194s vs stale "sub-minute" claim; speed-up beaded. |
Evidence-backed as of the 2026-07-19 estate audit + refactor scout (reports in outputs/advisor_loop/). Beads: 72 tracked — 38 open, 17 blocked (mostly FM-session-gated), 7 in progress; 8 stale draft PRs (#881–#891) awaiting triage.