Orchestrata Ultimate › Plans
Plans
311 tracked plan documents under plans/ (including plans/briefs/), mirrored page by page, plus 103 machine files listed at the end. Dates are the most recent git commit touching the file. Relative links inside plans are rewritten to GitLab permalinks at commit 8a2cb42ad.
Prose pending.
Activity
Plan documents
| Plan | Last changed | Summary | Source |
|---|---|---|---|
| Brief template: a Sonnet subagent dispatched from a Claude Code coordinator | 2026-10-22 | Use this for every Agent-tool dispatch (builder, wirer, refactorer, test-writer, auditor) in an orchestrata worktree. The worker sees only the brief, so the brief must carry everything below. Copy th… | plans/briefs/TEMPLATE-sonnet-agent.md |
| Brief and agent improvement log | 2026-10-22 | The companion to plans/briefs/TEMPLATE-sonnet-agent.md. Every Sonnet dispatch gets one row in the dispatch ledger. Every defect gets one row in the defect log and a fold-back the same session. |
plans/briefs/IMPROVEMENT-LOG.md |
| 2026-10-22-runner-failure-detail-ship | 2026-10-22 | DESIGN_WAIVER: Mohamed 2026-10-22, "change the runner, improve it, get full error and debug and trace info"; the change is written and tested by the coordinator, and this packet only commits, smoke-i… | plans/briefs/2026-10-22-runner-failure-detail-ship.md |
| Brief — every commit carries a fresh codebase map, so new worktrees start clean (Sonnet builder) | 2026-10-22 | Executor: Sonnet builder (Claude Code builder agent). Worktree (cwd): /home/mohamed/workspace/wt-MAP-PRECOMMIT, branch fix/precommit-regenerates-maps, off origin/master 4ac0db570. The venv… |
plans/briefs/2026-10-22-precommit-regenerates-maps-builder.md |
Brief: maps increment 1 of 4. gen_codebase_map.py --with-full writes both maps in one process (Sonnet build… |
2026-10-22 | Executor: Sonnet builder. cwd /home/mohamed/workspace/wt-MAP-PRECOMMIT. Create branch feat/maps-one-load from HEAD b5468cb1c (item 2: the pre-commit regenerates the maps). |
plans/briefs/2026-10-22-maps-one-load-builder.md |
| Maps step B1 — per-file cache for gen_codebase_map.py (builder brief, 2026-10-22) | 2026-10-22 | GOAL: make scripts/gen_codebase_map.py --with-full re-parse only the files whose content changed since its last run, by keeping a per-file cache of symbol rows and module docstring lines, so a run… |
plans/briefs/2026-10-22-maps-delta-builder.md |
| GATE-AFFECTED — classify before infra so pure non-code pushes skip the service stack | 2026-10-21 | Task #— (unassigned), build order —. Contract: the finding on ~/workspace/knowledge-wiki/projects/orchestrata-ultimate/gates/family-suite-preflight.md §4 + scripts/run_tests.py::_main (step 1 vs… |
plans/briefs/gate-affected-classify-before-infra.md |
| Refactor lanes convergence — LSP + interpreter functions and our AST (design) | 2026-10-20 | Status: PROPOSED, partially ruled (ADR-0117, Mohamed 2026-10-20 "A": the SPEC-109 engine MOVES to codetools — P-A rescoped to MOVE-109, §6 decision 1 ratified. Decisions 2-3 and the codemod/ctok… | plans/refactor-convergence-design.md |
| Handoff — supervisor session, 2026-10-20 (compaction-safe entry point) | 2026-10-20 | Status: handoff for the next context (post-compaction or new session). Session 272, branch components, worktree /home/mohamed/workspace/wt-COMPONENTS. Written 2026-10-20 after the component-fixes… |
plans/handoff-2026-10-20-supervisor.md |
| Handoff — proper-install + transfer-remediation workstream, 2026-10-20 (compaction-safe) | 2026-10-20 | Status: handoff for the next context. Session 272, orchestrata branch components, worktree /home/mohamed/workspace/wt-COMPONENTS; second repo /home/mohamed/workspace/orchestrata.codetools (mast… |
plans/handoff-2026-10-20-proper-install.md |
| §5.1 — vendor the compiled workspace members into orchestrata's wheel | 2026-10-20 | Status: DISPATCH-READY (dispatch slot: after P-RUL040 consumption + P-RUL039 + T17/T21 + Batch-2 — the orchestrata queue is serial; the coordinator names the slot) · Repo: `/home/mohamed/workspace/wt… | plans/briefs/vendor-compiled-members.md |
| T21-ROUTING — staged source .py files enter the T21 env-key review at commit time (ADR-0116) | 2026-10-20 | Contract: docs/adr/0116-staged-source-py-files-enter-the-t21-env-key-review-at-commit-time.md (Accepted, Mohamed 2026-10-20). Dispatch AFTER the T21 rule lands (T17 packet). The rule itself is froz… |
plans/briefs/t21-routing-source-files.md |
| T17-GEN — widen the T21 registry from *_ENV constants to ALL declared module constants | 2026-10-20 | Task #570, build order 2 (docs/ast-checkable-rules.md §2#1). The engine landed 2026-10-20 (commit 25f06c3f6): T21 in scripts/test-review.py — registry of module-level *_ENV string constants, sh… |
plans/briefs/t17-gen-constants-registry.md |
| T17 — env-key drift detection in test-review.py — brief for one qwen3-coder-next run | 2026-10-20 | Ordered by Mohamed 2026-10-20, verbatim: "can you add a way to detect it from test review code?" — "it" = the bug class just measured and fixed in the P-CAP packet (commit 4a470482c): `scripts/run_te… | plans/briefs/t17-env-key-drift.md |
| T17 packet, run 2 — REWORK: env-key drift rule in test-review.py (run 1 REJECTED) | 2026-10-20 | RUN-3 STATUS NOTE (2026-10-20, coordinator): the first run-2 attempt died on a provider error mid-flight after reverting scripts/test-review.py to HEAD and writing two out-of-fence codemod scri… |
plans/briefs/t17-env-key-drift-run2.md |
| Packet: integrate the rename engine as a codetools dispatcher verb (no external script) | 2026-10-20 | Status: DISPATCH-READY · Repo: /home/mohamed/workspace/orchestrata.codetools (branch master) Authority: Mohamed ruling 2026-10-20, verbatim: "rename must be integrated into codetools inside the mod… |
plans/briefs/rename-verb-integration.md |
| Packet: proper-install §5.4 implementation + §5.3 staleness guard (codetools) | 2026-10-20 | Status: DISPATCH-READY · Repo: /home/mohamed/workspace/orchestrata.codetools (branch master) Authority: ADR-0120 (Accepted, Mohamed 2026-10-20) + the §5.3/§5.4 rulings logged in orchestrata ses… |
plans/briefs/proper-install-5-4-implementation.md |
| PI-ORCHESTRA — make the wheel installable, and make the proper install stick | 2026-10-20 | Authority: Mohamed's ruling 2026-10-20, verbatim: "python is 3.14t and if love install is sym links or in place, no, i want a propper install", and on the torch defect *"Fix it so the wheel is… | plans/briefs/pi-orchestra.md |
| PI-CODETOOLS — proper-install completion in codetools (two packets, disjoint fences) | 2026-10-20 | Authority: Mohamed's ruling 2026-10-20, verbatim: "python is 3.14t and if love install is sym links or in place, no, i want a propper install", and on scope *"Everywhere + repoint the src-path… | plans/briefs/pi-codetools.md |
| P-CAP-TESTS — real tests for the adopted test-phase cap work — brief for one qwen3-coder-next run | 2026-10-20 | Context: the previous session left an uncommitted, ruled implementation in the tree (RUL-038 cap ruling, Mohamed 2026-10-19: the test phase is SELECTED, COUNTED and CAPPED; plus the ADR-0076 graphs-s… | plans/briefs/pcap-cap-tests.md |
| P-RUL040 Stage 1 — orchestrata side: consume the deployed select-affected verb; the escalate arm dies | 2026-10-20 | Status: DISPATCH-READY (dispatch ONLY after the coordinator confirms the codetools verb is DEPLOYED — see Sequence) · Repo: /home/mohamed/workspace/wt-COMPONENTS (branch components) Authority: RUL-… |
plans/briefs/p-rul040-stage1-orchestrata-consumption.md |
P-RUL040 Stage 1 — codetools side: the select-affected verb with a frozen JSON contract |
2026-10-20 | Status: DISPATCH-READY · Repo: /home/mohamed/workspace/orchestrata.codetools (branch master) Authority: RUL-040 (Mohamed, verbatim, injected in plans/briefs/p-rul040-fail-closed-blast-radius.md §… |
plans/briefs/p-rul040-stage1-codetools-verb.md |
| P-RUL040 native refusal seam (this repo only) — the escalate arm dies; named reasons are the verdict | 2026-10-20 | Status: DISPATCH-READY · Repo: /home/mohamed/workspace/wt-COMPONENTS (branch components) Authority: RUL-040 (Mohamed, verbatim: "never escalate=true is meaningless, it must be measured never the wh… |
plans/briefs/p-rul040-native-refusal-seam.md |
| P-RUL040 — reuse ledger + blast radius accurate: fail-closed selection, never a silent full run | 2026-10-20 | Queue position 2 (handoff 2026-10-20 §3). Task ledger: the P-RUL040 entry. Contract: docs/ast-checkable-rules.md §4 (the ruled mechanism: symbol-precise blast radius + fail-closed "cannot bound, na… |
plans/briefs/p-rul040-fail-closed-blast-radius.md |
| P-RUL039 — the promotion gate never runs rehearsal-class tests (derived labels, fail-closed consumption) | 2026-10-20 | Queue position 1 (handoff 2026-10-20 §3). Task ledger: the P-RUL039 entry (registered this session). Mechanism design surface: docs/ast-checkable-rules.md §4 + §3#13 — category DERIVATION feeds the… |
plans/briefs/p-rul039-rehearsal-exclusion.md |
| Owed small items — two micro-packets (one per repo, dispatched separately) | 2026-10-20 | Status: DISPATCH-READY (slots: codetools item after the prul040-codetools-verb worker finishes; orchestrata item after the git-sentinel worker finishes — the coordinator names the slot) · Authority:… | plans/briefs/owed-small-items.md |
| MOVE Batch 2 — the three adjudicated clean transfers (ADR-0118 decision 3) | 2026-10-20 | Contract: docs/adr/0118-... decision 3 + §4 phase discipline; template = the executed MOVE-109 / Batch-1 pattern (byte-faithful, green both sides, recorded dispositions). The cross-vendor audit pan… |
plans/briefs/move-batch2-adjudicated.md |
| MOVE Batch 1 — pyright_autofix.py + pyright_ratchet.py transfer to codetools (ADR-0118) | 2026-10-20 | Contract: docs/adr/0118-tier-1-host-side-scripts-transfer-to-codetools-in-two-batches.md decisions 2 + 4 (phase discipline) — the ADR-0117 move template applies (byte-faithful, green both sides, re… |
plans/briefs/move-batch1-pyright-pair.md |
| MOVE-109 — the SPEC-109 rename engine moves to codetools (ADR-0117 + ADR-0118 phase discipline) | 2026-10-20 | Contract: docs/adr/0117-spec-109-rename-engine-moves-to-codetools-and-orchestrata-consumes-the-deployed-cli.md (the ruling) + docs/adr/0118-... §4 (phase discipline) + `plans/refactor-convergence… |
plans/briefs/move-109-rename-engine.md |
| HOTFIX — batch children lack the SANCTIONED_RUNNER stamp: every push gate dies (P-CAP wiring gap) | 2026-10-20 | Priority: URGENT — blocks every git push on this repo (the pre-push affected-gate's batch executor children are all guard-killed). Coordinator-diagnosed with full evidence; this packet is the minim… |
plans/briefs/hotfix-batch-child-stamp.md |
| §5.2 — git_sentinel: tree snapshot is the hard signal, ref advance is advisory | 2026-10-20 | Status: DISPATCH-READY · Repo: /home/mohamed/workspace/wt-COMPONENTS (branch components) Authority: Mohamed ruling 2026-10-20 §5.2, option (a): "Tree snapshot is the hard signal; ref advance = advi… |
plans/briefs/git-sentinel-split-signal.md |
| GATE-RUL038 — the Prolog gate clause ADR-0111 owes: no container-creating module under tests/ | 2026-10-20 | Task #569, build order 1. Contract: docs/ast-checkable-rules.md §2#3 (the ruled mechanism shape) + the RUL-038 wiki page (`~/workspace/knowledge-wiki/rulings/RUL-038-test-runs-never-create-containe… |
plans/briefs/gate-rul038-container-creation.md |
| Handoff — component fixes, continue from here | 2026-10-19 | Status: handoff for the next model. Session 272, branch components, worktree /home/mohamed/workspace/wt-COMPONENTS. Written 2026-10-20. |
plans/handoff-component-fixes-2026-10-20.md |
| Plan and design — component fixes after the 2026-10-19 analysis | 2026-10-19 | Status: executing. Coordinator: this session. Workers do the edits. No new ruling is minted here. The Accepted ADRs below are the contract. | plans/component-fixes-2026-10-19.md |
| P-ARCHSYNC — correct the self-described-architecture table to current doctrine — brief for one qwen3-coder-ne… | 2026-10-19 | Authority: Mohamed 2026-10-19 verbatim "we are not using neo4j models get confused make this clear" + the coordinator's P-ARCHSYNC task (session 272). The script `scripts/sync_architecture_to_graph.p… | plans/briefs/p-archsync-table-correction.md |
| INT-01 — SPEC-125 delta + release scaffold — brief for one qwen3-coder-next run | 2026-10-19 | DESIGN_WAIVER: none — the design exists and is ruled. Authority: ADR-0113 (integration L1 builds now), packages/integration/design/decisions.md D-I1 + D-I13, `packages/integration/increments/README… |
plans/briefs/int-01-release-scaffold.md |
| Brief — week-of-history audit: errors and lessons (2026-10-12 → 2026-10-20) | 2026-10-19 | Ordered by Mohamed 2026-10-19: run multiple MiniMax agents and GLM agents over the entire history of the last week — tool calls and briefings across the Claude Code, DeepSeek and OpenCode channels —… | plans/briefs/history-audit-2026-10-19.md |
| Component-DAG ontology seed — brief for one qwen3-coder-next run | 2026-10-19 | DESIGN_WAIVER: none needed — the design exists. Authority: plans/component-fixes-2026-10-19.md §4.2 (the ruled table) and plans/handoff-component-fixes-2026-10-20.md Step A. The ratified ontology… |
plans/briefs/component-dag-seed.md |
| ADR-0114 roots and ADR-0113 LEVEL0 identity — brief for one sonnet run | 2026-10-19 | DESIGN_WAIVER: ADR-0114 and ADR-0113. This brief executes those two Accepted decisions and nothing else. | plans/briefs/adr-0114-roots-and-level0.md |
| ADR-0112 tools seams — brief for one deepseek-pro run | 2026-10-19 | DESIGN_WAIVER: ADR-0112. Execute that Accepted decision. Do not invent a tools→kernel edge. | plans/briefs/adr-0112-tools-seams.md |
| Tools-family implementation plan (N-V3 / N-V4) — specs, design, implementation | 2026-10-18 | Status: Awaiting ratification · Date: 2026-10-18 · Authorised by: Mohamed 2026-10-18 ("create a detailed plan including specs and design and implementation of the missing features first, then imp… | plans/tools-family-implementation-plan.md |
| L-newest — Spec-gap re-verification (SPEC-106 … SPEC-114) | 2026-10-18 | Cluster L — newest specs, bonus beyond the 000-105 task scope. Verified against CURRENT code on branch components (HEAD de9e996f2, 337 commits ahead of the 3-month-old audits). No prior audits ex… |
plans/spec-audit/reverify-2026-10-18/L-newest.md |
| Cluster K — harness/newer REVERIFY (SPEC-102/103/104/105) | 2026-10-18 | Re-verification against current components branch (commit de9e996f2, 337 commits ahead of the session-195 audits). All evidence regenerated fresh via the AST toolkit (`scripts/serialize_codeb… |
plans/spec-audit/reverify-2026-10-18/K-harness-newer.md |
| Cluster J — Standards & Architecture (SPEC-097 … SPEC-101) — Re-verification 2026-10-18 | 2026-10-18 | Re-verification agent J. READ-ONLY, evidence-by-code-only, against the CURRENT tree (components branch, 337 commits past the 3-month-old session-195 audit). Prior audit confirmed/updated, not redon… |
plans/spec-audit/reverify-2026-10-18/J-standards-arch.md |
| Cluster I — Tools suite re-verification (061–072) | 2026-10-18 | Read-only re-audit against CURRENT code on branch components (HEAD de9e996f2), 337 commits past the session-195 audit. Method: AST toolkit only for Python source; checklists/requirements.md box… |
plans/spec-audit/reverify-2026-10-18/I-tools.md |
| Cluster H — Integrations reverify (2026-10-18) | 2026-10-18 | READ-ONLY reverification of SPEC-017 / 018 / 020 / 021 / 052 against current code (branch components, 337 commits ahead of the session-195 audit). Every claim is re-derived from code via the AS… |
plans/spec-audit/reverify-2026-10-18/H-integrations.md |
| Cluster G — Gateway, UI, TUI & plugins — RE-VERIFICATION (2026-10-18) | 2026-10-18 | Re-verification against CURRENT code (branch components, HEAD de9e996f2). Builds on docs/spec-gap-register.md (2026-07-14) and plans/spec-audit/G-gateway-ui.md (session 195). Method: code-only… |
plans/spec-audit/reverify-2026-10-18/G-gateway-ui.md |
| Cluster F (volks 2 + verification) — re-verification 2026-10-18 | 2026-10-18 | Auditor: Cluster F. Read-only re-verification of specs 031/032/033/034/035 against current code (components branch, 337 commits ahead of the 3-month-old audits). Markers in `checklists/requirem… |
plans/spec-audit/reverify-2026-10-18/F-volks-2.md |
| Cluster E — Volks (PM / UX / Junior / CodeDirector / Architect) — RE-VERIFY | 2026-10-18 | Read-only re-verification of SPEC-012, 013, 027, 029, 030 against src/orchestrata_ultimate/agents/volks/ on branch components (337 commits ahead of the 3-month-old audits). Judged by code only —… |
plans/spec-audit/reverify-2026-10-18/E-volks-1.md |
| Cluster D — Providers & LLM — re-verification (2026-10-18) | 2026-10-18 | Re-verification of src/orchestrata_ultimate/ against 4 specs on branch components (337 commits ahead of the 2026-07-14 audits). Method per _METHOD.md + the re-verify brief: AST toolkit only for… |
plans/spec-audit/reverify-2026-10-18/D-providers-llm.md |
| Cluster C — Knowledge, memory, context & compliance (reverify 2026-10-18) | 2026-10-18 | Read-only re-verification of SPEC-008, 009, 010, 019, 026 against CURRENT code (branch components, 337 commits ahead of the 3-month-old audits). Evidence from the AST toolkit only (symbols / `ref… |
plans/spec-audit/reverify-2026-10-18/C-knowledge-memory.md |
| Cluster B — Session, Governance, DI (re-verification, 2026-10-18) | 2026-10-18 | Read-only re-audit of src/orchestrata_ultimate/ against 5 specs (006, 007, 023, 024, 060), on branch components (337 commits ahead of the 2026-07-14 audits). Evidence-only: AST toolkit (symbols… |
plans/spec-audit/reverify-2026-10-18/B-session-gov-di.md |
| Cluster A — Core runtime & protocol (SPEC-000…005) — REVERIFY 2026-10-18 | 2026-10-18 | Read-only reverification against current code (branch components, 337 commits ahead of the session-195 audit). Evidence via the AST toolkit only (symbols/refs/who-imports/source); .md… |
plans/spec-audit/reverify-2026-10-18/A-core-runtime.md |
| Ruling record — the 54 shipped-but-never-queried governance predicates (2026-10-09) | 2026-10-13 | Register task: "54 shipped-but-never-queried governance predicates — wire or retire". Mohamed's directive: "review the laws and where they must be applied" — full review executed (every predicate tra… | plans/ruling-2026-10-09-governance-predicates.md |
Brief: review fix — the AST sync hook's except tuples are parenthesized in both copies, and the MCP gateway… |
2026-10-13 | Date: 2026-10-13 · DESIGN_WAIVER: ADR-0097 (Accepted: the resident AST daemon publishes the snapshot; the post-edit hooks stop re-serializing) and ADR-0099 rule 1 (Accepted: the gateway MCP transport… | plans/briefs/2026-10-13-review-fix-hook-except-tuples-and-mcp-brief-transport-line.md |
| Brief: ADR-0038, orchestrata half — the gateway's MCP transport generated from its handler table, and both se… | 2026-10-13 | Date: 2026-10-13 · DESIGN_WAIVER: ADR-0038 (Accepted ruling, rules 2, 3, 4; the codetools half landed on codetools master at b39d26f and 74cad1e) · Executor: Sonnet builder in worktree `orchestrata-u… | plans/briefs/2026-10-13-mcp-gateway-transport-and-deployed-registration.md |
| Brief: the AST daemon publishes without changing the process working directory | 2026-10-13 | Date: 2026-10-13 · DESIGN_WAIVER: ADR-0097 (Accepted: the resident AST daemon publishes the snapshot from its warm cache) and ADR-0067 R1 (Accepted: a daemon instance runs from `/opt/orchestrata-tool… | plans/briefs/2026-10-13-daemon-publish-without-chdir.md |
| Brief: the resident AST daemon publishes the snapshot; post-edit hooks stop re-serializing; the duplicate hoo… | 2026-10-13 | Date: 2026-10-13 · DESIGN_WAIVER: ADR-0097 (Accepted ruling; the entire scope executes it) · Executor: builder (Sonnet) in an orchestrata worktree off origin/master · One slice, stop and report | plans/briefs/2026-10-13-ast-daemon-publishes-snapshot.md |
| Brief: ADR graph sync treats wiki pointers as pointers, the three-way check compares bodies, ADR-0073 re-base… | 2026-10-13 | Date: 2026-10-13 · DESIGN_WAIVER: ADR-0096 (Accepted ruling; the entire scope executes it) · Executor: builder (Sonnet) in a worktree off origin/master · Audit evidence: session scratchpad `adr-body-… | plans/briefs/2026-10-13-adr-sync-pointers-check-bodies-rebaseline-0073.md |
| Brief: ADR-0102 rules 1 and 3 — the re-baseline reaches the three overwritten nodes, and the sync refuses a f… | 2026-10-13 | Date: 2026-10-13 · DESIGN_WAIVER: ADR-0102 (Accepted 2026-10-13 21:12: re-baseline graph nodes ADR-0035, ADR-0036 and ADR-0041 from this repository's records under ADR-0102's authority; the sync refu… | plans/briefs/2026-10-13-adr-0102-rebaseline-mechanism-and-foreign-register-refusal.md |
| Brief: ADR-0101 rule 2 — the real pre-commit hook records its stage walls to an append-only ledger | 2026-10-13 | Date: 2026-10-13 · DESIGN_WAIVER: ADR-0101 (Accepted 2026-10-13 21:05: scripts/hooks/pre-commit records one line per commit with the wall of each stage and the per-file reviewer walls inside review… |
plans/briefs/2026-10-13-adr-0101-precommit-stage-walls-ledger.md |
| Q9 Phase A report (ADR-0091) — COMPLETE (Kimi continuation) | 2026-10-12 | Phase A is done: the two later orchestrator orders are executed (the approved test_install_orchestrata_cc.py expectation verified on disk; the fork now always relinks via ForcedBuildExt), the red… |
plans/briefs/qwen/Q9-report.md |
| Q9 — the janus fork links the declared SWI-Prolog (ADR-0091) | 2026-10-12 | DESIGN_WAIVER: ADR-0091 (Accepted by Mohamed 2026-10-12: "agree with adr"). Read docs/adr/0091-the-janus-fork-links-the-declared-swi-prolog-through-a-path-guix-gc-keeps-alive.md on branch `origin/d… |
plans/briefs/qwen/Q9-janus-swipl-declared.md |
| Q8 report — hooks that judge a process by the words in its command line | 2026-10-12 | Worktree /home/mohamed/workspace/wt-HOOK-MATCH, branch fix/hook-process-matching, HEAD 762935ab6. Nothing committed; changes staged, scratch (.q8/) unstaged. |
plans/briefs/qwen/Q8-report.md |
| Q8 — hooks that judge a process by the words in its command line | 2026-10-12 | DESIGN_WAIVER: none needed. Both changes make a hook do what its own header already says it does. Neither adds a capability. | plans/briefs/qwen/Q8-hook-process-matching.md |
Q8 continuation — the leaking live_run_tree fixture, then finish |
2026-10-12 | Same worktree, same branch, same rules as plans/briefs/qwen/Q8-hook-process-matching.md. Do not commit. Every scripts/run_tests.py run goes through bash .run_exclusive.sh .... Every measured st… |
plans/briefs/qwen/Q8-continuation.md |
Q2b-D Report — scripts/code-review.py ruff-missing verdict restored under ADR-0089 |
2026-10-12 | DESIGN_WAIVER: ADR-0089 (Accepted). Q2b converted scripts/code-review.py's ruff spawns to <interpreter> -m ruff (the same conversion Phase B applied to harness/evaluators/lint.py); this task fi… |
plans/briefs/qwen/Q2b-D-report.md |
| Q2b Phase C report | 2026-10-12 | State inherited: C.1, C.2, C.3 were already applied and staged by the previous executor (one unstaged pyright suppression comment in tests/harness/test_evaluator_lint.py, staged now). I verified by… |
plans/briefs/qwen/Q2b-C-report.md |
| Q2a — The AST snapshot records literal program names at process-spawn sites | 2026-10-11 | Mohamed's directive (verbatim): "fix bare python make it prolog and atoms". | plans/briefs/qwen/Q2a-snapshot-argv-capture.md |
| Q2a Report — the AST snapshot records literal program names at process-spawn sites | 2026-10-11 | No other file changed by me. git diff --cached --stat is exactly the five paths above. |
plans/briefs/qwen/Q2a-report.md |
| Q1 — One C/C++ toolchain declaration: finish, test and verify | 2026-10-11 | Mohamed (verbatim): "make the gcc path a configuration and set it". | plans/briefs/qwen/Q1-toolchain-declaration.md |
| Q1 report — One C/C++ toolchain declaration: finish, test and verify | 2026-10-11 | Executor: Qwen3.8-max (openrouter/qwen/qwen3.8-max-0902) via opencode run. Worktree: /home/mohamed/workspace/wt-BARE-PYTHON, branch fix/bare-interpreter-gate (HEAD c1eebd019). Deliverable s… |
plans/briefs/qwen/Q1-report.md |
Installer hardening — a declared manifest replaces every literal in deploy/install-claude-config.sh |
2026-10-09 | Status: Proposed 2026-10-09 (user ruling: "fix the installer so the 5 issues never occur again, use configuration not hardcoding"). Amends SPEC-108 FR-001 / ERR-004 and SPEC-020. Scope: `depl… | plans/installer-config-manifest-plan.md |
| Graph-usage defects — remediation plan (2026-10-09) | 2026-10-09 | Source: the "how is the graph used now?" investigation of 2026-10-09 against prod (/opt/orchestrata @ 1c0beae6a, both graphs on the prod cluster, split by database). |
plans/graph-usage-defects-plan.md |
| Recorded run 2026-10-08 — the eight failures: investigation, design, swarm plan | 2026-10-08 | Run: promote-test-irc, HEAD 5cc8bbd5e, 1832 passed / 3 failed / 5 batch-failed-solo-recovered, 1429.7s. Tasks filed: 572–579 (session 271). Hot-fixes shipped: 3bb5319df, 0fa0ac048… |
plans/recorded-run-2026-10-08-eight-failures-design.md |
| SPEC-110 completion plan — build what the spec still owes | 2026-10-07 | Directive: Mohamed, 2026-10-06: "build spec 110". Worktree: wt-SPEC-110 (feat/spec-110-completion, base origin/master 83c604886). Authority: specs/110-codemod-engine/spec.md (51 REQ ids) + th… |
plans/spec-110-completion-plan.md |
| SPEC-110 packet S4 — the CLI connects to the daemon it can start (REQ-110-140) + the docstring sweep sweeps d… | 2026-10-07 | Design authority: plans/contracts/spec-110-codemod-engine.contract.json entry D29 (committed daec60c25) for the daemon routing; specs/110-codemod-engine/spec.md REQ-110-010 verbatim for the s… |
plans/briefs/spec-110-s4-builder.md |
| SPEC-110 packet S3 — fix round 3 builder brief (round-3 reviewer findings F1, F2, F3) | 2026-10-07 | Authority: ADR-0068 (Accepted) for REQ-110-034; contract plans/contracts/spec-110-codemod-engine.contract.json (9f7ee385d) sections classes (FR-012), check_catalogue, reuse, `design_decisions… |
plans/briefs/spec-110-s3-fix3-builder.md |
| PH1 — prod unit health: builder brief (orchestrator's picks, 2026-10-07) | 2026-10-07 | Plan: plans/ast-daemon-deployment-plan.md § "PH1 — prod unit health". Read that section first; it carries the diagnosis. This brief carries the exact source, the change and the proof. |
plans/briefs/ph1-prod-unit-health-builder.md |
| P6b — the promoter's verify settles before it judges: builder brief (orchestrator's picks, 2026-10-07) | 2026-10-07 | DESIGN_WAIVER: plan item P6b of plans/ast-daemon-deployment-plan.md § "P6 — enable the primary instances and prove identity end to end" (bullet "P6b — promoter verify settles before it judges"): a… |
plans/briefs/p6b-promoter-verify-settle-hold-builder.md |
| P6a — identity verifier judges tool-tree template instances against their own root: builder brief (orchestrat… | 2026-10-07 | Plan: plans/ast-daemon-deployment-plan.md § "P6a". Read it first; it holds the measured failure, the six executed rules and the acceptance. This brief holds the exact source at the sites, the chang… |
plans/briefs/p6a-identity-tool-tree-instances-builder.md |
| PLAN — the AST daemon as a real deployment | 2026-10-07 | Status: RULED, ready to build (2026-10-05). D1 and D2 below were decided by Mohamed the same day (rulings R1/R2, recorded as ADR-0067); every packet is now engineering under the platform conv… | plans/ast-daemon-deployment-plan.md |
| SPEC-110 §15 observability — wiring design | 2026-10-06 | Status: BUILT (S1, b0fd759a0). Satisfies RUL-022 (design before build) for the follow-on implementation brief. | plans/codemod-observability-wiring-design.md |
| SPEC-110 packet S3 — builder brief (REQ-110-033 / REQ-110-034 / REQ-110-035) | 2026-10-06 | Authority: ADR-0068 (Accepted 2026-10-06) amending REQ-110-034; contract plans/contracts/spec-110-codemod-engine.contract.json (9f7ee385d) sections classes (FR-012: ReviewCheck, CheckCategory, Ch… |
plans/briefs/spec-110-s3-builder.md |
| SPEC-110 packet S2 — builder brief (REQ-110-031 / REQ-110-032) | 2026-10-06 | Contract: plans/contracts/spec-110-codemod-engine.contract.json (committed 9f7ee385d) — sections classes (FR-011: BlastRadiusAnalyzer, BreakingChangeDetector, ComplexityAnalyzer, TestCoverageMapp… |
plans/briefs/spec-110-s2-builder.md |
| Builder brief — AST daemon plan P5: retire the checkout-bound units and gate their return | 2026-10-06 | Plan: plans/ast-daemon-deployment-plan.md § 3 "P5" (lines ~759–771), § 3b ship log, § "P4 review round 4" (the three MINOR findings carried to P5). Design authority: ADR-0067 (Accepted; R1 "every d… |
plans/briefs/ast-daemon-p5-builder.md |
| Brief: enforce RUL-032 — a test module runs once per code state | 2026-09-22 | Ruling (Mohamed, 2026-09-22, verbatim): "with the rule enforced that test only run once unless the code in the test or code is changed, and watch for escalation to full suite when the tests have alre… | plans/briefs/2026-09-22-rul-032-run-once-ledger.md |
| Brief: retarget the HA controller tests at the two-node orchgraph sandbox | 2026-09-22 | DESIGN_WAIVER: ADR-0058 (Accepted 2026-09-22). Scope is exactly the ADR's execution. | plans/briefs/2026-09-22-adr-0058-ha-sandbox-fixture.md |
| Brief: make the ADR tooling register-aware (execute ADR-0047) | 2026-09-22 | DESIGN_WAIVER: ADR-0047 (Accepted 2026-08-29). Scope is exactly that ADR's mandate: "ids match as zero-padded strings — ADR-0001 (factory register, docs/adr) and ADR-001 (project register, the wi… |
plans/briefs/2026-09-22-adr-0047-register-aware-adr-tooling.md |
| RTM Traceability Swarm Plan — Session 268 | 2026-08-25 | Make reports/rtm-evidence.md reflect the actual test coverage by adding explicit @traces decorators to test functions that already verify requirements but do not currently cite them. |
plans/rtm-traceability-swarm-plan.md |
| Orchestrata — master system analysis | 2026-08-23 | Living document. Generated from analysis/register.json; every analysis round appends to the register and this file is re-rendered. Do not hand-edit — an edit here is lost on the next round and… |
plans/system-analysis-master.md |
| Orchestrata system analysis — 2026-08-23 | 2026-08-23 | Method. Six analyst swarms (Specs & Requirements, Code & Architecture, Tests & Verification, Docs & Knowledge, Enforcement & Gates, Runtime & Deployment). Five lenses per domain, 30 workers, one… | plans/system-analysis-2026-08-23.md |
| SPEC-020 drift ledger | 2026-08-23 | Compiled 2026-08-23. Method: SPEC-020 read in full (spec.md 1911 lines, compliance-audit.md, 4 checklists), cross-referenced against every hook declaration source in the repo and on this mach… | plans/spec-020-drift-ledger.md |
SUPERSEDED — see plans/claude-surface-pipeline.md |
2026-08-23 | Status: superseded 2026-08-23. Do not implement from this file. | plans/claude-surface-promotion-plan.md |
| Claude surface: dev → test → prod | 2026-08-23 | Status: written 2026-08-23. Supersedes plans/claude-surface-promotion-plan.md, which rested on a false premise — that the project Claude surface had no deployed copy — and specified an elaborat… |
plans/claude-surface-pipeline.md |
| Analysis pipeline | 2026-08-23 | The master report (../system-analysis-master.md) is generated. Do not hand-edit it. |
plans/analysis/README.md |
| Test-run observability — event stream, live view, durable ledger | 2026-08-20 | STATUS: requirement captured, design forks open. Written in plan mode from injected context only — **every "exists" claim below is from docs/CODEBASE_MAP.md one-line entries and memory, NOT from op… |
plans/test-run-ledger-design.md |
| Volk↔Volk Messaging + Orchestrator↔Volk Heartbeat/Status Awareness — Design | 2026-08-19 | Status: DESIGN ONLY (RUL-022 — no implementation in this artifact) Branch: feat/cxp-direct-transport · Date: 2026-08-05 · Author: analyst (design phase) Epic: Communication: volk<… | plans/volk-comms-heartbeat-design.md |
| Trace Remediation Program — operational runbook | 2026-08-19 | Session 224 (2026-07-08). Owner: orchestrator (Opus) + Sonnet swarm waves via .claude/workflows/trace-wave.js. Status ledger at the bottom is the single source of progress truth; update it at every… |
plans/trace-remediation-plan.md |
| Stage 2.0: Syntax Error Pattern Analysis & Bulk Fix Strategy | 2026-08-19 | Date: 2026-04-19 Scope: 54 syntax errors across 48 files in src/orchestrata_ultimate/ Frozen Source: /home/mohamed/workspace/orchestrata/packages/ (verified clean) |
plans/stage2_syntax_error_analysis.md |
| Semantic Graph Q&A Results (Latest: Hybrid Vector + Keyword + Module Graph) | 2026-08-19 | Model: mistralai/codestral-embed-2505 | Reranker: cohere/rerank-4-pro | Project: orchestrata-ultimate | plans/semantic_graph_qa_results_latest.md |
| RTM — evidence-graded | 2026-08-19 | Generated by scripts/generate_rtm_evidence.py. Every row carries its proof class; a row upgrades ONLY when a test cites the requirement (and, under --verify, runs green). DECLARED rows are unveri… |
plans/rtm.md |
| Audit 01 — Volks: personas, tools, LLM wiring, gaps | 2026-08-19 | Volks in src/orchestrata_ultimate/agents/volks/. Kernel registers 9 (kernel/pipeline.py:118-138): Cx, PM, Ux, Ar, Cd, Junior, Qa, BA, Cp. Two aux NOT in pipeline: Documentor (U:Do), SeniorDev (U:… |
plans/research/audit-01-volks.md |
| Requirements Traceability Matrix (RTM) | 2026-08-19 | Generated: 2026-07-06T20:41:41.966823 Total Requirements: 4629 Verified: 4508 Partial: 0 Missing: 121 | plans/requirements-traceability-matrix-complete.md |
| Pipeline-Event Convergence — Design | 2026-08-19 | Status: DESIGN ONLY (RUL-022 — no implementation in this artifact) Branch: feat/cxp-direct-transport · Date: 2026-08-05 · Author: analyst (design phase) Defect: two producers publ… | plans/pipeline-event-convergence-design.md |
| Pipeline Automation — Detailed Implementation Plan | 2026-08-19 | Date: 2026-06-25 Specs: SPEC-003 (Intent), SPEC-005 (Multi-Agent), SPEC-016 (VizInt), SPEC-032 (Concierge) Standards: SPEC-097 (Testing), SPEC-100 (Logging) Architecture: Layer 3 (dom… | plans/pipeline-automation-plan.md |
| Natural-language query → work intent: research findings, 2026-08-08 | 2026-08-19 | Method. Six parallel literature lanes (semantic parsing, grammar-based NLU, conversational query rewriting, intent classification/calibration, evaluation methodology, production architecture) ove… | plans/nlq-research-2026-08.md |
| Kernel Dispatch-Reply HARDENING — Design Addendum (F4 / F5 / F7+F8) | 2026-08-19 | Status: DESIGN ONLY (RUL-022 — no implementation in this artifact) Parent: plans/kernel-dispatch-reply-design.md (7 packets, all shipped in commit 9914d662 on feat/cxp-direct-transport;… |
plans/kernel-dispatch-reply-hardening.md |
| Kernel Dispatch Ack-Only + Reply Addressing — Design | 2026-08-19 | Status: DESIGN ONLY (RUL-022 — no implementation in this artifact) Branch: feat/cxp-direct-transport · Date: 2026-08-05 · Author: analyst (design phase) Defects: (A) kernel violat… | plans/kernel-dispatch-reply-design.md |
| Extensible NL intent parser + evaluator — design contract (SPEC-003 US-001 extension) | 2026-08-19 | Origin: user directive — "create an intent parser and evaluator step and make it so we can add vocabulary, keywords and a mapper to categories and workflows." This is the honest NL→structured-Int… | plans/intent-nl-classifier-design.md |
| Intent DCG accuracy — design contract (SPEC-003 US-001, increment 2) | 2026-08-19 | Status: DESIGN (2026-08-08). Successor to plans/intent-nl-classifier-design.md, which landed the cascade itself (REQ-003-US-001-040..049). That increment proved the shape: DCG tier first at c… |
plans/intent-dcg-accuracy-design.md |
| Governance promotions table (W1-P7) | 2026-08-19 | The SINGLE registry for every governance interim state — each row carries owner + trigger + expiry per the ratified standing rule (ADR-023: "no interim state without owner + trigger + expiry"). W… | plans/governance-promotions.md |
| W5.3 Tail Classification — specs 022/028/017/009/004 + dangling-103 triage (2026-07-06) | 2026-08-19 | Baseline: 190 untraced / 103 dangling / 293 total. Read-only sweep. | plans/evidence/w5-tail-classification.md |
| D4 Evidence Pack — DI Container vs Setter Wiring | 2026-08-19 | Source: auditor agent W3.E4 (2026-07-06). Decision: plan §D, D4. Blocks W3.4. Agent-declared not-verified: gateway/rpc.py setter bodies (prior-session cites), session/cli submodules, whether DIContai… | plans/evidence/d4-di-container.md |
| Semantic Graph Q&A Results (Hybrid Vector + Keyword + Module Graph) | 2026-08-19 | Model: mistralai/codestral-embed-2505 | Reranker: cohere/rerank-4-pro | Project: orchestrata-ultimate | plans/archive/semantic_graph_qa_results_hybrid_v2.md |
| Semantic Graph Q&A Results (Hybrid Vector + Keyword) | 2026-08-19 | Model: mistralai/codestral-embed-2505 | Reranker: cohere/rerank-4-pro | Project: orchestrata-ultimate | plans/archive/semantic_graph_qa_results_hybrid.md |
| Semantic Graph Q&A Results (Final: Hybrid Vector + Keyword + Module Graph) | 2026-08-19 | Model: mistralai/codestral-embed-2505 | Reranker: cohere/rerank-4-pro | Project: orchestrata-ultimate | plans/archive/semantic_graph_qa_results_final.md |
| Semantic Graph Q&A Results | 2026-08-19 | Model: mistralai/codestral-embed-2505 | Reranker: cohere/rerank-4-pro | Project: orchestrata-ultimate | plans/archive/semantic_graph_qa_results.md |
| Master execution plan — ratified decisions, all workstreams | 2026-08-17 | Refreshed 2026-08-17 (session 265). Previous refresh 2026-07-21 (session 244). 27 days of work landed: 1206+ commits, 65 RFP/REO closes, full SPEC-110 codemod engine, gateway hardening, plugin cu… | plans/master-execution-plan.md |
| Subnet renumbering — env-octet scheme (ruling 2026-08-15) | 2026-08-15 | Ruling (Mohamed, 2026-08-15, backlog 413): environment subnets must be FORCED apart so they can never be confused — the environment lives in its own dedicated octet (XXX.XXX.001.XXX / `XXX.XXX.… |
plans/subnet-renumbering-design.md |
| Workflow Improvements Plan — From Memory Export 2026-07-26 | 2026-08-13 | Source: memory export of 2026-07-26 (global + 4 project memory stores, SESSION_START.md, global CLAUDE.md, 645-prompt Kimi user-history). The prompt history shows the same rules being re-issued verba… | plans/workflow-improvements-plan.md |
| Traceability repair — session 264, 2026-08-13 | 2026-08-13 | Status: paused mid-verification. The plumbing is fixed. Traceability itself is not. Read the last section before resuming; the numbers got worse on purpose. | plans/traceability-repair-2026-08-13.md |
| Prolog + AST deterministic-reasoning ladder | 2026-08-13 | Origin: user directive 2026-08-02 — "what more can prolog do, tasks that take a lot of time and tokens but are deterministic and we can build right now?" Then, on tests/coverage: consolidate the… | plans/prolog-ast-reasoning-ladder.md |
| Backlog delegation plan — Claude ↔ kimi split (session 238) | 2026-08-13 | Directive (Mohamed, IRC 2026-07-14): after #125, "create a plan and plan to delegate some tasks to kimi if that works to offload and speed up the process." Status: APPROVED by Mohamed on #agents… | plans/delegation-plan-s238.md |
| Swarm execution plan — suite runtime + graph defects (2026-08-12) | 2026-08-12 | Executes plans/suite-runtime-and-graph-defects-plan.md (with §6b/§8 second-review corrections) per the user sign-off: both scopes, suite-side first, executed in parallel by a swarm of coder sub… |
plans/swarm-execution-plan-2026-08-12.md |
| Suite runtime research — full record (2026-08-12) | 2026-08-12 | Companion to plans/suite-runtime-and-graph-defects-plan.md (the plan). This file is the complete research record behind it: method, measurements, censuses, dead ends, and the adversarial-review cor… |
plans/suite-runtime-research-2026-08-12.md |
| Post-mortem: suite runtime optimization — PROVEN FAILURE (2026-08-12) | 2026-08-12 | Verdict: the objective "make the suite meaningfully faster" (originally: halve it, ~240s) failed. Final authoritative measurement on the merged tree: 455s wall vs 445.7s baseline (+2%), **2,2… | plans/suite-runtime-failure-postmortem-2026-08-12.md |
| Suite runtime + graph-defect remediation plan | 2026-08-12 | Date: 2026-08-12 Status: CLOSED — production-side DELIVERED; suite-side objective PROVEN FAILURE, rolled back Measure-first state: checklist completed 2026-08-12 and disarmed (`.kimi/… | plans/suite-runtime-and-graph-defects-plan.md |
| Suite runtime, attempt 2 — plan | 2026-08-12 | Date: 2026-08-12 Baseline: 6ceef2ef + uncommitted D2b fix — 426.6s wall, 32,499 passed / 0 failed / 0 errors / 0 skipped, 1611/1611 modules, -j 8 -b 6. Call CPU 2,202.4s, 8-lane f… |
plans/suite-runtime-2-plan.md |
| Promotion to test + deployment — session 262 work | 2026-08-12 | Authored 2026-08-12. Covers everything fixed this session plus the five open items, through documentation, review, commit, promotion and deployment verification. Every number here was measured, not e… | plans/promotion-and-deployment-plan.md |
| A Prolog subsystem that learns from test runs — research record | 2026-08-12 | Date: 2026-08-12 Question (user): build a Prolog subsystem that learns from test runs, stores the facts it learns, updates them as code changes, and produces optimized ways to run tests and c… | plans/prolog-learning-subsystem-research-2026-08-12.md |
| Swarm Remediation Plan — 2026-07-06 | 2026-08-10 | NO git stash in agent tasks (added 2026-07-06 after two stash collisions between concurrent agents on this shared, non-worktree checkout — one required git-object-database recovery). For before… |
plans/swarm-remediation-plan-2026-07-06.md |
| Spec consolidation — diagnosis + plan (2026-08-02) | 2026-08-10 | User thesis: the specs are "disjointed features with no use-case usage-scenario narrative." Confirmed, quantitatively, via trace_intel/code_intel + a structural scan (deterministic-first — no… |
plans/spec-consolidation-analysis.md |
| Implementation Plan: Port Orchestrata to Orchestrata-Ultimate | 2026-08-10 | Port ~50,000 LOC of tested implementations from orchestrata's 12 packages into orchestrata-ultimate's package structure. Keep ultimate's core/ infrastructure (observability, error handling, threading… | plans/port-from-orchestrata.md |
| Orchestrata Completion Plan — autonomous execution | 2026-08-10 | Derived from 7 parallel audits (plans/research/audit-0*.md). Executed non-stop, committing per coherent unit, tests + lint green each step, documenting as I go. |
plans/orchestrata-completion-plan.md |
| Implementation Plan: Port Orchestrata → Orchestrata-Ultimate | 2026-08-10 | Port ~119,000 LOC (net) from orchestrata's 26 packages into orchestrata-ultimate's single-package structure. Keep ultimate's core/ infrastructure (observability, error handling, threading, exceptions… | plans/implementation-plan.md |
| Decision Register Rulings — 2026-07-06 | 2026-08-10 | Ruled by the orchestrator under Mohamed's directive: "make the D1-D10 decisions per the evidence recommendations favouring the specs; if there are more complete implementations elsewhere where they s… | plans/decisions-2026-07-06.md |
| KIMI TASK — two masked flakes and one unversioned unit | 2026-08-10 | Base: origin/master @ e1793c1f (pushed). Work in your own worktree with its own env (RUL-021 — no symlinked .venv, no exported PYTHONPATH). |
plans/KIMI-TASK-flakes-and-unit.md |
| Prolog gates — implementation plan (LIVING DOCUMENT) | 2026-08-09 | Contract: plans/contracts/prolog-gates.contract.json · Diagram: plans/contracts/prolog-gates.mmd Update protocol (RUL-015 plan fidelity). This file is edited in the SAME commit as the work it… |
plans/prolog-gates-implementation-plan.md |
| P1/P2 remediation — the whole backlog, in dispatch order | 2026-08-09 | Source: context.json deferred_work, open items at priority P1 (18) and P2 (41). Full text was read before planning; the truncated titles in session status hide that several "items" are multi-we… |
plans/p1-p2-remediation-plan.md |
| Prod deployment isolation — design | 2026-08-07 | Investigated 2026-08-07, read-only, in /home/mohamed/workspace/orchestrata-ultimate-architecture, branch feat/cxp-direct-transport, currently dirty (git status --short: 20+ modified/deleted… |
plans/prod-deployment-isolation-design.md |
| gRPC retirement — design | 2026-08-07 | Branch: feat/cxp-direct-transport · Authorized: 2026-08-07 ("agreed merge, retire grpc, proceed as you recommend") · RUL-022 design-of-record for this change. |
plans/grpc-retirement-design.md |
Gate-daemon routing design — cutting architecture (26.1s) and check-deps (14.1s) |
2026-08-07 | Status: design only, no code changed. Baseline: scripts/gates.py measured 2026-08-07, 10 gates parallel, wall = 26.1s (= architecture's own runtime). |
plans/gate-daemon-routing-design.md |
| Plan: orchestrata builds, deploys and promotes — by itself | 2026-08-07 | Written: 2026-08-08, end of session 260, for a NEW session after a Claude Code restart. Self-contained on purpose: assume none of session 260's context survives. | plans/dogfood-build-to-promotion.md |
_dispatch() decomposition — design of record |
2026-08-07 | Status: APPLIED 2026-08-07. See §Execution result at the end. Driver: 109 of the repo's 237 mypy errors, all inside one function. Ruling: RUL-022 (design before build), RUL-013 (behaviour… | plans/dispatch-decomposition-design.md |
| SessionHandler Cohesion Split — Design | 2026-08-05 | Status: DESIGN ONLY (RUL-022 — no implementation in this artifact) Branch: feat/cxp-direct-transport · Date: 2026-08-05 · Author: analyst (design phase) Subject: `src/orchestrata_… | plans/session-handler-split-design.md |
| Claude-only test campaign — handoff (2026-08-04) | 2026-08-05 | Policy (Mohamed): tests exercise Claude ONLY; never OpenRouter/qwen/minimax/deepseek. Follow-ups: "copy claude's answer as if it is the same for the other llms" and "do not call the llm in the te… | plans/claude-only-tests-handoff.md |
| P3 Migration Map — Replacing LibCST in the Codemod Engine | 2026-08-04 | Scope: every libcst/cst.* touch-point under src/orchestrata_ultimate/refactor/codemod/ (confirmed via grep -rl "^import libcst\|^from libcst\|import libcst as cst" src/ — the LibCST footprint… |
plans/ctok-p3-migration-map.md |
| Execution Plan: Port Orchestrata → Orchestrata-Ultimate | 2026-08-03 | STATUS: DONE — Superseded by plans/stage2_port_plan.md on 2026-04-19. The bulk port is complete. Stage 2 addresses syntax errors, test failures, coverage gaps, and production readiness. |
plans/execution-plan.md |
| Tooling wiring plan — every automation asset installed + wired (2026-08-02) | 2026-08-02 | User command: "install and wire every single tool ... any existing tool that will benefit must be installed now." This plan records the audit verdict per tool and the wiring action taken. Scope is DE… | plans/tooling-wiring.md |
| Worktree merge plan — 2026-07-29 (session 256) | 2026-07-29 | Ruling applied: only complete-and-merged branches get deleted; unmerged work gets a completeness-ranked merge plan. Stubs are forbidden — both surviving branches were audited: **zero stub/TODO/No… | plans/worktree-merge-plan.md |
| Wiring campaign — construct and wire ALL unwired code (user order, 2026-07-06) | 2026-07-27 | Ruling: every implemented, spec-traced module with zero production construction gets WIRED (D14/D15 ruling generalized). Retirement is not an option; the only allowed exception is a proven same-REQ t… | plans/wiring-campaign-2026-07-06.md |
| Volk Persona & Per-Volk Tool Optimization — Plan + Task List | 2026-07-27 | Origin: Wave-2 P1 ("give each volk a distinct persona + per-volk tools; optimize"). Source of findings: full per-volk audit (session 197) — 9 LLM volks + compliance. **Scope decisions (user):… | plans/volk-optimization-plan.md |
| Traceability Matrix — Session 165 (Phase D modules) | 2026-07-27 | Maps each requirement id -> the @traces-annotated code symbol -> the real-infrastructure test(s) that cover it. Built with the repo's own traceability scanner (core.tracing.scanner) + RTM generat… |
plans/traceability-matrix-session165.md |
| Tools Useful to Plan | 2026-07-27 | Reference guide for Claude and other agents working on the Orchestrata-Ultimate port. Every tool lives in scripts/ unless noted. All commands assume the project root as CWD. |
plans/tools_useful_to_plan.md |
| Functionality-tool build plan — specs 063-071 (session 227) | 2026-07-27 | User ruling 2026-07-12: SPEC-099 security work is DEPRIORITIZED ("forget security"); build the missing functionality tools, prioritized by functional importance, in swarm waves with code/test/archite… | plans/tool-wave-plan.md |
| Thread ontology + event-backfill design (session-254 Option A) | 2026-07-27 | Status: DESIGN — settled, ready to build. No implementation in this document. Author: analyst (design pass), 2026-07-26. Governs: src/orchestrata_ultimate/knowledge_graph/canonical_schema.py (S… |
plans/thread-ontology-design.md |
| Revised Test Coverage Plan: 104 Untested Methods | 2026-07-27 | Generated by orchestrata_tools — deterministic analysis with exact parity to legacy ast_explorer.py |
plans/test_coverage_plan_revised.md |
| Test Coverage Plan: Uncovered Methods | 2026-07-27 | Goal: Cover 104 concrete untested methods to push module-level coverage to ≥90%. Approach: 6 parallel agent workstreams, each with isolated scope. Standards: All tests must pass `pytest -… | plans/test_coverage_plan.md |
| Feature plan — SPEC-<NNN> <feature name> | 2026-07-27 | Instantiate this template for EVERY spec feature before implementation starts (user ruling, 2026-07-06). A feature is NOT done when its modules exist and their unit tests pass — it is done when the c… | plans/templates/feature-plan-template.md |
| SWI-Prolog Tabling & Evaluation Capabilities — Authoritative Catalog | 2026-07-27 | Target runtime: SWI-Prolog 10.0.2, driven from Python via janus-swi. Scope: tabling (SLG resolution) and adjacent evaluation features that are "free" correctness/performance wins for a codeba… | plans/swi-tabling-capabilities.md |
| Swarm implementation plan — prioritized by impact (2026-07-06) | 2026-07-27 | Derived from audit-full-2026-07-06.md (57 specs, full chain SPECIFIED → TRACED → IMPLEMENTED → WIRED → TESTED) and wiring-campaign-2026-07-06.md (Waves A–I). Ordered by impact, not spec numbe… |
plans/swarm-plan-prioritized-2026-07-06.md |
| Brutally Honest Status Report — 2026-04-12 | 2026-07-27 | Method coverage: 80.4% on mapped class pairs (1,040/1,294 methods). True overall coverage including unmapped classes is lower. 232 Python files, 39,075 LOC. 1,447 tests passing, 341 broken. 64% l… | plans/statusreport_2026-04-12_1621.md |
| Stage 2 Tracker: Fix, Verify, and Production-Ready | 2026-07-27 | Companion to: plans/stage2_port_plan.md Last Updated: 2026-04-28T23:03:32.692979 Current Phase: 5 (final) Active Session: 2 (continuing) |
plans/stage2_tracker.md |
| Stage 2 Porting Plan: Fix, Verify, and Production-Ready | 2026-07-27 | Previous Plan: plans/execution-plan.md (238 steps, 5 phases) — MARKED DONE as of 2026-04-19. Status: The bulk port produced 481 source files and 190 test files, but 54 source files have… |
plans/stage2_port_plan.md |
| Spec implementation gaps — evidence-graded audit (session 227) | 2026-07-27 | Question: which specs have genuinely unimplemented requirements? Method: check-traces + generate_rtm_evidence.py over specs/ vs src/, then code-level audits of the suspect clusters (4 parallel au… |
plans/spec-implementation-gaps.md |
| Spec-audit method (shared brief for all investigation agents) | 2026-07-27 | You are one of 11 parallel investigation agents in a planning session. Your job is to investigate & verify an assigned cluster of specs against the actual implementation and produce a per-s… | plans/spec-audit/_METHOD.md |
| Cluster K — Test harness & greenfield capabilities (SPEC-102/103/104/105) | 2026-07-27 | Investigation agent K. READ-ONLY audit against actual code in src/orchestrata_ultimate/, per plans/spec-audit/_METHOD.md. Checklist - [ ] boxes ignored (stale); judged by code. These four specs… |
plans/spec-audit/K-harness-greenfield.md |
| Cluster J — Standards & Architecture (SPEC-097 … SPEC-101) | 2026-07-27 | Investigation agent J. READ-ONLY audit of src/orchestrata_ultimate/ against the five cross-cutting standards/architecture specs. Evidence by code only (checklist - [ ] markers ignored per `_METHO… |
plans/spec-audit/J-standards-arch.md |
| Cluster I — Tools suite (greenfield tools 063–072) | 2026-07-27 | Investigation agent report. READ-ONLY audit of src/orchestrata_ultimate/ against specs 063–072. Method: plans/spec-audit/_METHOD.md. Evidence-based; requirements-checklist boxes ignored. |
plans/spec-audit/I-tools.md |
| Cluster H — External integrations & agent harnesses (SPEC-017, 018, 020, 021, 052) | 2026-07-27 | Investigation agent report. READ-ONLY audit against actual code; boxes in specs/*/checklists/requirements.md ignored per _METHOD.md. None of these 5 specs appear in docs/spec-gap-register.md (w… |
plans/spec-audit/H-integrations.md |
| Cluster G — Gateway, UI, TUI & plugins (spec audit + plan) | 2026-07-27 | Investigation agent G. READ-ONLY audit of src/orchestrata_ultimate/gateway/, orchestrator/, integrations/cheetahclaws/, plugin/, kernel/ CLIs, and the vizint-ui/ web app. Evidence by code… |
plans/spec-audit/G-gateway-ui.md |
| Cluster F — Volks (QA / Concierge / CheetahClaws) — spec audit | 2026-07-27 | Auditor: Cluster F. Read-only investigation of src/orchestrata_ultimate/ per plans/spec-audit/_METHOD.md. Markers in checklists/requirements.md ignored; judgement by code only. Prior work: `doc… |
plans/spec-audit/F-volks-2.md |
| Cluster E — Volks (PM / UX / Junior / CodeDirector / Architect) | 2026-07-27 | Read-only audit of SPEC-012, 013, 027, 029, 030 against src/orchestrata_ultimate/agents/volks/. Judged by code, not checklist markers. Prior work in docs/spec-gap-register.md already audited all… |
plans/spec-audit/E-volks-1.md |
| Cluster D — Providers & LLM — spec audit + implementation plan | 2026-07-27 | Investigation agent D. READ-ONLY audit of src/orchestrata_ultimate/ against 4 specs, evidence-based, per _METHOD.md. Prior work confirmed/updated against docs/spec-gap-register.md (which audite… |
plans/spec-audit/D-providers-llm.md |
| Cluster C — Knowledge, memory, context & compliance | 2026-07-27 | Investigation agent C. Read-only audit of SPEC-008, 009, 010, 019, 026 against actual code in src/orchestrata_ultimate/. Evidence-based; requirements.md markers ignored per _METHOD.md. Builds on… |
plans/spec-audit/C-knowledge-memory.md |
| Cluster B — Session, governance, verification & DI (spec audit) | 2026-07-27 | Investigation agent B. Read-only audit of src/orchestrata_ultimate/ against 6 specs, evidence-based per _METHOD.md. AST toolkit (symbols/refs) + targeted reads. No source/test files modified. |
plans/spec-audit/B-session-gov-di.md |
| Cluster A — Core runtime & protocol (SPEC-000…005) | 2026-07-27 | Investigation agent A. Read-only audit of src/orchestrata_ultimate/ against the six specs, evidence-based (AST symbols/refs + targeted reads). Checklist - [ ] markers ignored per _METHOD.md… |
plans/spec-audit/A-core-runtime.md |
| Wave-0 decisions (D1–D5) — resolved | 2026-07-27 | Companion to 00-MASTER-PLAN.md. These are the five foundational calls the plan was blocked on. Decided in session 195 (D1/D2/D3/D5… |
plans/spec-audit/01-DECISIONS.md |
| Orchestrata Ultimate — Spec Implementation Master Plan | 2026-07-27 | Session 195 planning deliverable. Evidence-based audit of all 60 specs (61 entries — SPEC-007 is two specs) against the actual code, plus a cross-spec dependency graph, parallelism analysis, an… | plans/spec-audit/00-MASTER-PLAN.md |
| SPEC-110 (codemod engine) — merge plan | 2026-07-27 | Branch: feat/codemod-engine · Worktree: ~/workspace/wt-QWEN · Author: opencode Status when written: spec/design/briefs authored; implementation not started. **Status 2026-07-27 (f… |
plans/spec-110-merge-plan.md |
SPEC-110 _codemod_fast — C extension rewrite spec |
2026-07-27 | Target: scripts/_codemod_fast/ on feat/codemod-engine (wt-QWEN) Status: spec — not yet built. Do not edit wt-QWEN while opencode is building. Author: Mohamed Date: 2026-07-27 **Mo… |
plans/spec-110-codemod-fast-c-rewrite.md |
| SPEC-023 Goal-System Consolidation Plan | 2026-07-27 | Three overlapping goal implementations exist: | plans/spec-023-goal-consolidation-plan.md |
| SPEC-021 Port Map — OpenCode Integration → orchestrata-ultimate | 2026-07-27 | Read-only audit. Source: /home/mohamed/workspace/orchestrata/open-code/ (frozen). Deployed twin: ~/.opencode/ (running @opencode-ai/plugin@1.3.15, confirmed via `~/.opencode/node_modules/@openc… |
plans/spec-021-port-map.md |
| SPEC-021 multi-platform conversation producers — kimi (IRC) + Claude Code | 2026-07-27 | User directive 2026-07-13: "Apply the same plugin specs to 1. kimi 2. claude code." The W1a backend (knowledge_graph/conversation_consumer.py, landed a194d41b) is platform-agnostic by design — mess… |
plans/spec-021-multiplatform-producers.md |
| SPEC-021 OpenCode integration — full implementation plan (session 227+) | 2026-07-27 | User ruling 2026-07-13: no retire, no re-scope — a THOROUGH implementation of SPEC-021, retargeted from the frozen monorepo paths to orchestrata_ultimate. 299 requirements (checklists/requirements.md… | plans/spec-021-implementation-plan.md |
| SPEC-003 (Intent Broker) — completion plan | 2026-07-27 | Trigger: user ruling "complete spec 003 — working, wired; specs are source of truth." | plans/spec-003-completion-plan.md |
| Session Plan: Phase 2 — Zero Test Failures | 2026-07-27 | Goal: All 5,479 tests pass with 0 failed, 0 errors, 0 skipped. Baseline: 5,364 passed, 99 failed, 23 errors, 5 skipped Tag: session-phase1-complete |
plans/session-phase2-plan.md |
| Autonomous Session Plan: CI/CD & Infrastructure Hardening v1.1.0 | 2026-07-27 | Fix GitLab CI pipeline, Docker Compose networking, deprecation warnings, and mypy CI blockers. Deliver a deterministic green pipeline. Version bump to v1.1.0. | plans/session-autonomous-ci-hardening.md |
| Semantic-Graph Ontology Design | 2026-07-27 | Status: decisions RESOLVED (2026-07-08) — ready to build · Author: orchestrator session Task: #3 (ontology-first; import Neo4j through the ontology, never raw) Anchors: SPEC-008 (KG… | plans/semantic-graph-ontology-design.md |
| Scripts Fix Plan | 2026-07-27 | 18 issues across 15 scripts. All deterministic fixes, no architectural changes. Generated from code review of all 35 scripts (~18,383 LOC). | plans/scripts_fix/fix-plan.md |
| Audit 07 — KG Schema / Semantic Layer | 2026-07-27 | Headline: No single schema/ontology. Three parallel Cypher conventions + SPEC-105 ontology targets Stardog/RDF (disjoint from Neo4j). It's a code-structure graph with bolt-on provenance fragments… | plans/research/audit-07-kg-schema.md |
| Audit 05 — Spec-Compliance Gap Analysis (000–105) | 2026-07-27 | - Placeholder markers BANNED + enforced (review_checks.py, core/standards.py NO_PLACEHOLDER). Gaps = absent modules, not TODOs. Only 1 real TODO: gateway/test_runner.py:288 (coverage). - Pe… |
plans/research/audit-05-spec-gaps.md |
| Audit 04 — Tracing / Debugging / Observability | 2026-07-27 | Headline: core/tracing/__init__.py::IterationTracer is a COMPLETE runtime per-volk tracer with ZERO production callers. Built, fully unwired. Biggest gap + cleanest insertion point. |
plans/research/audit-04-tracing-debugging.md |
| Audit 03 — Context Injection (SPEC-009) + Memory/KG Wiring into Volks | 2026-07-27 | Research audit for the completion mandate. Paths are repo-relative to /home/mohamed/workspace/orchestrata-ultimate-architecture/. |
plans/research/audit-03-context-injection.md |
| Audit 02 — Communication Fabric + Orchestrator Status-Awareness | 2026-07-27 | Paths repo-relative. Two runtimes / two registries — the biggest confusion source. | plans/research/audit-02-communication-status.md |
| Open-source Neo4j alternatives — research (2026-07-06) | 2026-07-27 | Question (user): what genuinely open-source alternatives to Neo4j exist, and should Orchestrata adopt one? "Open source" = OSI-approved license only; source-available (BSL/SSPL/Elastic/FSL) is di… | plans/research-oss-graph-alternatives-2026-07-06.md |
| Reproducibility & Infrastructure-as-Code Plan | 2026-07-27 | Drafted 2026-07-10 (session 224) from a live fleet audit (incus list, per-container incus config show, in-container version probes). Goal: a fresh machine — or this machine after a disk loss — re… |
plans/reproducibility-plan.md |
| Rename Engine — Architecture and Spike Findings (SPEC-109) | 2026-07-27 | Status: design ratified by a passing live spike, 2026-07-27 Spec: specs/109-rename-engine/spec.md Branch: feat/rename-engine Builder briefs: `plans/rename-engine-briefs/BRIEF-B{1,… |
plans/rename-engine-design.md |
| BRIEF-B3 — Rename-plan compiler, atomic executor, residue reporter, CLI, volk tool | 2026-07-27 | Spec: specs/109-rename-engine/spec.md · Design: plans/rename-engine-design.md Branch: feat/rename-engine · Agent: Sonnet builder Depends on: B1 (models.py, lsp_client.py… |
plans/rename-engine-briefs/BRIEF-B3.md |
| BRIEF-B2 — Candidate oracle, residue classifier, edit applier, module move + string layer | 2026-07-27 | Spec: specs/109-rename-engine/spec.md · Design: plans/rename-engine-design.md Branch: feat/rename-engine · Agent: Sonnet builder Depends on: B1's models.py (contract-froze… |
plans/rename-engine-briefs/BRIEF-B2.md |
| BRIEF-B1 — LSP client + type-resolved symbol-rename core | 2026-07-27 | Spec: specs/109-rename-engine/spec.md · Design: plans/rename-engine-design.md Branch: feat/rename-engine · Agent: Sonnet builder Depends on: nothing. B2 and B3 code against… |
plans/rename-engine-briefs/BRIEF-B1.md |
| Pytest-native features audit — what to adopt, what stays custom | 2026-07-27 | Synthesis of 6 research lanes (core config/cache/faulthandler, xdist deep-dive, duration splitting, rerun/flake tooling, timeout/hang tooling, free-threaded parallelism) mapped against `src/orchestra… | plans/pytest-native-audit.md |
| Provider-protocol split-brain — reconciliation plan | 2026-07-27 | Task #24. Grounded in the auditor audit (agent a0bf…, 2026-07-05) which ran live uv run pyright (ground truth, not inference). Execution DEFERRED until coverage wave 2 + the OpenRouter… |
plans/provider-protocol-reconciliation.md |
| Prolog utilization plan — unused engine capabilities mapped to orchestrata | 2026-07-27 | Status: PROPOSED (2026-07-10). No implementation yet — this documents the options, their landing sites, effort/value, and a recommended sequence. Companion to the governance janus migration (session… | plans/prolog-utilization-plan.md |
| SPEC-106 FR-006: Prolog Tabling Strategy for kg_relevance.pl | 2026-07-27 | Author: codewhale (Brother Whale) Date: 2026-07-10 For: claude — P1 investigation task | plans/prolog-tabling-strategy.md |
Plan: Prolog bounded tabling, tnot/1 safety audit, CLIPS-vs-SWI spike |
2026-07-27 | Worktree: /home/mohamed/workspace/orchestrata-kimi-wt3 Branch: kimi/prolog-tabling off c717bfcb (current master) Scope: P-1 bounded tabling on knowledge.pl:ownership_chain/3, P-2… |
plans/prolog-tabling-restraint-plan.md |
| Prolog codebase-intelligence verification plan (session 242) | 2026-07-27 | Subject: commit 3b159679 "Add Prolog codebase intelligence layer" (author Hannah |
plans/prolog-codeintel-verification-plan.md |
| Project Status\n\n## Porting Progress\n- Semantic pairs: 766\n- Readiness: 483 mostly complete, 264 equal, 14… | 2026-07-27 | plans/project-status.md |
|
| Port Plan: Adversarial Review Resolution | 2026-07-27 | Four adversarial reviewers (build, architecture, testing, scope/risk) raised 65 issues. This document resolves each one. Resolutions feed back into the main plan. | plans/port-review-and-gaps.md |
| Sprint 4: Personal Gadgets & Final Compliance | 2026-07-27 | Duration: Week 4 (32 hours) Goal: Web Crypto, Todoist gadget, remaining constitutional items, final compliance Target: ≥90% constitutional (128/142), 100% requirements | plans/plan_vizint_phase_6/sprint-4-personal-final.md |
| Sprint 3: Code Quality & Standards | 2026-07-27 | Duration: Week 3 (40 hours) Goal: Close Article VI (JS Standards), VII (Testing), X (Versioning) + documentation Target: 45 constitutional items verified | plans/plan_vizint_phase_6/sprint-3-code-quality.md |
| Sprint 2: Gadget Polish | 2026-07-27 | Duration: Week 2 (40 hours) Goal: Close 29 requirements in Categories A–F Target: 100% requirements completion | plans/plan_vizint_phase_6/sprint-2-gadget-polish.md |
| Sprint 1: Resilience Foundation | 2026-07-27 | Duration: Week 1 (40 hours) Goal: Close all 20 Article IX (Graceful Degradation) items + 10 Article VIII (Observability) items Target: 30 constitutional items verified | plans/plan_vizint_phase_6/sprint-1-resilience.md |
| VizInt Command Center — Gap Closure Roadmap | 2026-07-27 | Status: All 4 Sprints Complete | Target: 100% Requirements + 90% Constitutional Compliance Current: ~86% Requirements (253/294) | 44% Constitutional (63/142) Gap: 41 Requirements | 79… | plans/plan_vizint_phase_6/roadmap.md |
| VizInt Phase 6: Gap Closure Plan | 2026-07-27 | From: 82.3% Requirements, 15.5% Constitutional Current: ~97% Requirements (288/294), 19% Constitutional (27/142) To: 100% Requirements, ≥90% Constitutional Duration: 4 sprints (4 week… | plans/plan_vizint_phase_6/README.md |
| VizInt Command Center — Detailed Implementation Plan | 2026-07-27 | Spec: 016-vizint-command-center Status: Gap Analysis Complete → Implementation Planned Plan Version: 1.0.0 Created: 2026-05-26 Estimated Duration: 8–10 weeks (1 engineer full-time… | plans/plan_vizint_implementation/implementation-plan.md |
| subplan-tests-qa-volk | 2026-07-27 | Task: Add comprehensive, parallel-safe unit tests for src/orchestrata_ultimate/agents/volks/qa/volk.py in tests/agents/volks/qa/test_volk.py. |
plans/plan_tests_qa_volk/subplan-tests-qa-volk.md |
| Subplan: Sub-phase 2.1 — Knowledge Subset (Steps 99-104) | 2026-07-27 | Tier 1 complete. 1639 tests pass. This subplan ports the knowledge graph subset needed by Tier 2 agents and governance — 6 files (~1,725 LOC). | plans/plan_subphase_2_1/subplan-knowledge-subset-2026-04-12.md |
| Subplan: Sub-phase 1.6 — Agent Implementations (Steps 74-96) | 2026-07-27 | Sub-phases 1.3-1.5 complete. 1522 tests pass. This subplan ports the agent framework (~22 files) and 9 volk packages (~38 files) — the largest sub-phase in Tier 1. | plans/plan_subphase_1_6/subplan-agents-2026-04-12.md |
| Subplan: Sub-phases 1.3-1.5 — DI + Drivers + Verification Review (Steps 61-73) | 2026-07-27 | Sub-phase 1.2 (Provider + LLM) is complete. 1296 tests pass. This subplan ports DI container (2 files), Drivers (11 files), and Verification review subset (12 files). | plans/plan_subphase_1_3/subplan-di-drivers-verification-2026-04-12.md |
| Subplan: Sub-phase 1.2 — Provider + LLM (Steps 48-60) | 2026-07-27 | Sub-phase 1.1 (CXP) is complete. 1103 tests pass. This subplan ports the Provider package (8 core + 6 adapters) and LLM package (3 files). | plans/plan_subphase_1_2/subplan-provider-llm-2026-04-12.md |
| Subplan: Sub-phase 1.1 — CXP Protocol (Steps 39-47) | 2026-07-27 | Phase 0 is complete. 813 tests pass at 91% coverage on core modules. This subplan ports the CXP (Cross-Agent eXchange Protocol) package — 27 modules (~7,500 LOC) for inter-agent communication. | plans/plan_subphase_1_1/subplan-cxp-protocol-2026-04-12.md |
| Subplan: Sub-phases 0.3 + 0.4 — Test Infrastructure + Dependencies (Steps 28-38) | 2026-07-27 | Sub-phase 0.2 (core port) is complete. 791 tests pass at 91% coverage on ported modules. This subplan sets up test infrastructure (fixtures, factories, markers) and updates pyproject.toml dependencie… | plans/plan_subphase_0_3/subplan-test-infra-deps-2026-04-12.md |
| Subplan: Sub-phase 0.2 — Port orchestrata-core (Steps 12-27) | 2026-07-27 | Sub-phase 0.1 bug fixes and coverage remediation are complete. 576 tests pass at 96% coverage on target files. This subplan ports 16 modules (~3,747 LOC) from orchestrata-core into orchestrata-ultima… | plans/plan_subphase_0_2/subplan-port-core-2026-04-12.md |
| Subplan: Sub-phase 0.1 Coverage Remediation | 2026-07-27 | Sub-phase 0.1 bug fixes are merged. 295 tests pass. But coverage of the 10 changed files is 55%, not 99%. The existing tests are interface stability tests (verify signatures exist) — they do not exec… | plans/plan_subphase_0_1_coverage/subplan-coverage-remediation-2026-04-12.md |
| Subplan: Sub-phase 0.1 — Fix Ultimate Bugs (Steps 1–11) | 2026-07-27 | orchestrata-ultimate has 10 bugs identified in the execution plan (Steps 1–10) plus 1 discovered during analysis. These block the entire import chain — 0 out of 27 tests currently pass because… |
plans/plan_subphase_0_1/subplan-subphase-0.1-fix-ultimate-bugs-2026-04-11.md |
| Sub-phase 0.1 Pipeline Checklist | 2026-07-27 | Every step must be marked DONE with evidence before proceeding to the next. | plans/plan_subphase_0_1/CHECKLIST.md |
| AUDIT — Sub-phase 0.1: Fix Ultimate Bugs | 2026-07-27 | Total: ~150 lines changed across 10 files. | plans/plan_subphase_0_1/AUDIT.md |
| Subplan Step 1: Scope Object + Context Builder | 2026-07-27 | Prerequisite: subplan-step0 (AST serializer extension + Neo4j sync) must be complete and all 14 verification queries passing. Parent: master-plan.md (Automated Porting Harness) | plans/plan_automated_porting_harness/subplan-step1-scope-object-context-builder-2026-04-11.md |
| Plan: Phase 1 — AST Serializer Extension + Neo4j Full Sync | 2026-07-27 | We have scripts/serialize_codebase_ast.py (1,451 LOC) that captures modules, classes, methods, parameters, calls, imports, inheritance, and dependency graphs — but stops at method signatures. We ne… |
plans/plan_automated_porting_harness/subplan-step0-ast-serializer-neo4j-sync-2026-04-11.md |
| Harness Iteration 0: Automated Porting Pipeline | 2026-07-27 | Reviewed: 4 rounds of Sonnet subagent review. 71 gaps found, all addressed. | plans/plan_automated_porting_harness/master-plan.md |
| Porting Progress Tracker | 2026-07-27 | Last updated: 2026-04-12 AST comparison: plans/ast-deep-comparison.json (fresh) | plans/plan_automated_porting_harness/TRACKER.md |
| Plan: Spec 102 — Individual Volk Test Harness (Swarm Implementation) | 2026-07-27 | Version: 0.1.0 Date: 2026-05-26 Agents: 9 parallel workstreams (A–I) Estimated Total LOC: ~3,500 Estimated Time: 2–3 hours wall-clock with 9 agents | plans/plan_102_volk_harness_swarm.md |
| Plan 102: Volk Test Harness — Agent Configs | 2026-07-27 | This directory contains orchestrator agent configurations for implementing Spec 102 — Individual Volk Test Harness via a 9-agent swarm. | plans/plan_102_volk_harness/README.md |
| Parallel Test Flakiness — Root-Cause Fix Plan | 2026-07-27 | Date: 2026-06-18 · Status: proposed (review before applying) · Author: Mohamed | plans/parallel-flakiness-fix-plan.md |
| Parallel-collision fix plan — suite failures from shared port + File/Directory constraint races | 2026-07-27 | Origin: 2026-07-22 full-suite measurement (session 252): 575.5 s, 27,187 passed / 41 failed / 15 errors across 19 modules. Both failed-module samples pass solo (9 passed, 6 s) — the failures are… | plans/parallel-collision-fix-plan.md |
| Design — a Claude-invokable OpenRouter tool (cross-model calls + scoped context) | 2026-07-27 | Task #26. Grounded in the read-only investigation (agent a2262…, 2026-07-05). Status: DESIGN + decisions. Implementation is gated on user approval — this tool sends project context to third-par… |
plans/openrouter-tool-design.md |
| Migration Plan — Operational KG: Neo4j → orchgraph | 2026-07-27 | Goal: move the operational knowledge graph off Neo4j 5.26.28 Community (neo4j-db 10.92.53.11) onto the orchgraph Memgraph fork, then re-point every tool, service, and test at it. **At the end of th… |
plans/neo4j-to-orchgraph-migration-plan.md |
| Operational-graph repository seam (backlog #163) | 2026-07-27 | Route all direct operational-Neo4j access through a repository/adapter seam mirroring semantic_graph's create_semantic_graph factory, so the operational store becomes swappable/droppable. Driver… |
plans/neo4j-seam-design.md |
| Kimi delegation plan — SPEC-018 Fireflies backend completion slice | 2026-07-27 | Delegation brief for the IRC fleet agent kimi (Moonshot, localhost:6667 #agents). Kimi reads THIS FILE from its worktree — it is self-contained: everything needed to produce compliant work is in… |
plans/kimi-delegation-plan.md |
| Kimi continuation plan — 2026-07-13 evening → 2026-07-14 18:00 | 2026-07-27 | Claude weekly limit is nearly exhausted; kimi carries the work until tomorrow 18:00. Everything below runs on OpenRouter/Moonshot + local infra — zero Claude tokens. Work the tasks IN ORDER; one… | plans/kimi-continuation-2026-07-13.md |
| Kimi brief K1 — the 5 pre-existing vizint full-suite failures (backlog #217) | 2026-07-27 | Self-contained brief for the IRC fleet agent kimi (delegation plan plans/delegation-plan-s238.md, approved by Mohamed on #agents 2026-07-15). Work in YOUR worktree; report progress + blockers on… |
plans/kimi-brief-k1.md |
| KG Schema Gaps — SPEC-008 (audit + remediation plan) | 2026-07-27 | Source: read-only subsystem map (this session). Scope = SPEC-008 Neo4j KG only. | plans/kg-schema-gaps.md |
| Project-scoped KG identity — migration plan (session 227) | 2026-07-27 | User rulings 2026-07-12: (1) "the graph must take multiple projects, 100 even"; (2) "projects have specs, user stories, requirements, and ast unique to them". Every project-derived entity is unique P… | plans/kg-project-scoped-identity.md |
Plan: Consolidate Kernel Orchestration onto the Mixin PipelineRunner |
2026-07-27 | Date: 2026-05-27 · Mode: verify locally, commit to master (no CI) Verified against: plans/ast-ultimate.json (fresh) via ast-query + RLM. Principle: keep the working behavior (`S… |
plans/kernel-consolidation-plan.md |
| Codegen / Jinja optimization plan | 2026-07-27 | Task #23. Grounded in the read-only inventory + Jinja research (agent a7b8…, 2026-07-05). Extends plans/ast-codegen-audit.md item 12-L (shared emitter) + item 10 (compile+exec tests). **E… |
plans/jinja-codegen-optimization.md |
| Implementation Status & Plan — orchestrata-ultimate | 2026-07-27 | Produced from three read-only audits (volk completeness vs. frozen source; non-volk stub inventory; intended-set + wiring gaps), each spot-verified against the code. Date: 2026-06-20. | plans/implementation-status-and-plan.md |
Hub-link plan — restoring the root-connectivity invariant in orchkg |
2026-07-27 | Status: DESIGN (analyst). No production code changed by this document. Branch: feat/hub-link. Measured against the LIVE operational KG (neo4j://10.92.53.160:7691, database orchkg, auth none) on… |
plans/hub-link-plan.md |
| Harness Iteration 0: Automated Porting Pipeline | 2026-07-27 | Reviewed: 4 rounds of Sonnet subagent review. 71 gaps found, all addressed. | plans/harness-iteration-0.md |
Graph Rename Plan — eradicate neo4j vocabulary, technology- and platform-agnostic |
2026-07-27 | Status: DRAFT — awaiting Mohamed's ratification Date: 2026-07-27 · Session 255 Directive (verbatim): "you must rename neo4j to graph, I want graph, technology and platform agnostic" **Exe… | plans/graph-rename-plan.md |
| Graph-consolidation decision — operational KG on orchgraph vs two-graph topology | 2026-07-27 | Session 227 (2026-07-12). Evidence: read-only Cypher-surface audit of the operational-KG code + live construct probes against the orchgraph cluster (neo4j://10.92.53.160:7691) + capacity measuremen… |
plans/graph-consolidation-decision.md |
| Global Toolchain Integration Plan | 2026-07-27 | Date: 2026-06-25 Status: Core tools deployed, integration pending | plans/global-toolchain-integration.md |
| Plan: Fix Test Template Issues | 2026-07-27 | Based on code review of 24 generated test files (5685 total issues): | plans/fix_test_template_issues.md |
| Full-suite remediation plan — fireflies slice worktree | 2026-07-27 | Generated from the full-suite run python scripts/run_tests.py --skip-gates executed in /home/mohamed/workspace/orchestrata-kimi-wt on 2026-07-12. Baseline: 24,785 passed, 29 failed, 0 errors.… |
plans/fireflies-slice-full-suite-remediation.md |
| Amendment to Execution Plan: Automated CI/CD Integration | 2026-07-27 | This amendment adds fully automated CI/CD capabilities to the existing execution plan by integrating GitLab deployment into the phased approach. | plans/execution-plan-amendment.md |
| W8.1 Ground-Truth Inventory — Context Semantic Layer (2026-07-06) | 2026-07-27 | Evidence pack for the W8.2 design. Produced read-only while W4.4 (injector merge) was IN FLIGHT — context_injector.py findings marked pre-merge must be re-verified after W4.4 lands. | plans/evidence/w8-context-layer-inventory.md |
| W5.1b — spec-105 domaingen classification (40 REQs: 34 stamp / 6 partial / 0 missing) | 2026-07-27 | Root cause: requirements enacted inside Jinja templates (.j2) or private helpers — invisible to AST-based check-traces. Fix = EXTEND the reqs=[...] list on the owning public symbol (parse_ontology, g… | plans/evidence/w5-spec105-classification.md |
| W5.1a — spec-102 classification (96 REQs: 65 stamp / 20 partial / 11 missing) | 2026-07-27 | Stamp list below is machine-actionable (REQ -> file:line Symbol). PARTIAL/MISSING details live in the session log + backlog items filed 2026-07-06. Key real bugs: aggregate-score weight drift (runner… | plans/evidence/w5-spec102-classification.md |
| W3.1 Absorption Map (2026-07-06) — see the W3.1-map agent report (session 201) | 2026-07-27 | Summary of load-bearing facts (full detail in session transcript): - kernel PipelineRunner = PipelineSessionMixin + PipelineKGMixin + PipelineEscalationMixin; checkpoint/artifacts/events composed (pi… | plans/evidence/w31-absorption-map.md |
| D3 Evidence Pack — Port-Residue Duplicate Twins (verdict per pair) | 2026-07-27 | Source: auditor agent W3.E3 (2026-07-06). Decision: plan §D, D3. Blocks W3.3. Agent-declared not-verified: GovernanceEngine test assertions unread; LRUCache TTL/eviction semantics undiffed; dead arch… | plans/evidence/d3-duplicate-twins.md |
| D2 Evidence Pack — Traceability Quintuple Collapse | 2026-07-27 | Source: auditor agent W3.E2 (2026-07-06), verified with corrections by the orchestrator (see "Verification notes"). Decision: plan §D, D2. Blocks W3.2. | plans/evidence/d2-traceability.md |
| D1 Evidence Pack — PipelineRunner Ownership (kernel vs orchestrator vs workflow_engine) | 2026-07-27 | Source: auditor agent W3.E1 (2026-07-06). Decision: plan §D, D1. Blocks W3.1/W3.5. Orchestrator note: agent self-reported 6 explicit not-verified gaps (listed at bottom) — spot-check those during W3.… | plans/evidence/d1-pipeline-runners.md |
| E2E live-trace plan — whole-system dogfood with tracing & debugging | 2026-07-27 | User directive 2026-07-12 (session 227): after the in-flight work lands, test the WHOLE system end to end. Mohamed supplies the intents (live, via the UI and/or CLI); **Claude traces, logs, debug… | plans/e2e-live-trace-plan.md |
| E2E DeepSeek-v4-pro Dogfood — Test Results | 2026-07-27 | Companion to e2e-deepseek-test-plan.md. Records the actual runs of the orchestrata pipeline driven on deepseek-v4-pro via `scripts/e… | plans/e2e-deepseek-test-results.md |
| E2E DeepSeek-v4-pro Dogfood Test Plan | 2026-07-27 | Prove the full intent → orchestration → output loop works on a real LLM with real infrastructure (Redis + Neo4j), and that we have provenance of exactly what happened — no simulation, no hidden f… | plans/e2e-deepseek-test-plan.md |
| Dogfood notes — Wave 7 (started 2026-07-06, session 204) | 2026-07-27 | All endpoints come from .env (no hardcoded addresses in source; per-worker Neo4j fleet keys NEO4J_URI_GW<N> map batched-runner slots to instances). |
plans/dogfood-notes-2026-07-06.md |
| Parallel-collision patterns — Prolog-derived diagrams | 2026-07-27 | Facts: canonical_schema.CANONICAL_MERGE_KEYS (imported live), the verified C2 sweep (plans/briefs/kimi-c2-result.md), and the 2026-07-22 SHOW CONSTRAINTS census. Relations derived by SWI-Prolog… |
plans/diagrams/parallel-collision-patterns.md |
| Diagram-to-Code Parity Report | 2026-07-27 | orchestrata_tools.diagram.diagram_to_code.DiagramToCode (src/orchestrata_tools/diagram/diagram_to_code.py) was the original Mermaid classDiagram → Python skeleton generator. A newer generator,… |
plans/diagram-to-code-parity.md |
| Escalation absorption design (D1-addendum-2) — 2026-07-06 | 2026-07-27 | Kernel PipelineEscalationMixin does free-form hop routing (volk -> volk, with capability-mesh resolution, cycle/depth guards, human-approval workflow). The orchestrator runner executes a FIXED Pipeli… | plans/design-escalation-absorption-2026-07-06.md |
| Tiered Context Model (L0 / L1 / L2) | 2026-07-27 | Status: design · Author: orchestrator session · Date: 2026-07-08 Motivation: an orchestrator (Claude) repeatedly re-derived basic infra facts — "are the graphs docker?", "where is Neo… | plans/context-tiers-design.md |
| Context-Injection Tracked Plan | 2026-07-27 | Continuation of plans/context-injection-evolution-plan.md and [docs/context-injection.md](https://gitlab.com/MSamy/orchest… |
plans/context-injection-tracked-plan.md |
| Phase 2 KG Enhancements — Comprehensive Execution Plan | 2026-07-27 | Continuation of plans/context-injection-tracked-plan.md. This plan closes the seven pending Phase 2 items (2.2–2.8) that enrich the graph context injected into volk prompts and the feedback loop ar… |
plans/context-injection-phase2-plan.md |
| Context-Injection Owed-Work Plan | 2026-07-27 | Scope: Close the four items left unchecked in the 2026-07-14 spec update: | plans/context-injection-owed-work-plan.md |
| Context-Injection Improvement Plan | 2026-07-27 | The repository has a layered context-injection architecture: | plans/context-injection-improvement-plan.md |
| Context Injection Evolution Plan | 2026-07-27 | Analysis of how the project currently assembles an agent's prompt context, plus a concrete plan to make far better use of the AST, Neo4j knowledge graph, and session/plan/memory context — while keepi… | plans/context-injection-evolution-plan.md |
| Context Injection: AST / Graph / Context Use — Analysis + Plan | 2026-07-27 | 2026-07-14 | plans/context-injection-ast-analysis.md |
| Ratification packet — real deny conditions for the remaining decorative invariants | 2026-07-27 | - Status: PARTIALLY RATIFIED. On 2026-07-24 Mohamed directed the tightening of Articles IV, V, VII, XI — those had working violation detectors (respects_privacy(_,violation), `operates_fair… |
plans/constitutional-invariants-ratification.md |
| SPEC-110: In-Memory Code Intelligence Platform — Implementation Summary | 2026-07-27 | Version: 2.0.0 Date: 2026-07-27 Status: Complete (post-adversarial review, ready for implementation) | plans/codemod-engine-implementation-summary.md |
| SPEC-110 Codemod Engine — Execution Plan (Revised) | 2026-07-27 | Date: 2026-07-27 Status: Ready for Implementation Total Estimated Time: ~2.5 hours (145 minutes) Parallel Agents: Yes (W1 and W2 use parallel agents) | plans/codemod-engine-execution-plan.md |
| SPEC-110 Codemod Engine — Design Document | 2026-07-27 | Status: Complete (post-adversarial review) Author: Claude Opus 4.6 (orchestration) Date: 2026-07-27 Version: 2.0.0 | plans/codemod-engine-design.md |
| W1 Agent Context Document | 2026-07-27 | Wave: W1 (Forest + Sentinel) Date: 2026-07-27 Status: Ready for Implementation | plans/codemod-engine-briefs/W1-AGENT-CONTEXT.md |
| W0 (Scaffold) Completion Report | 2026-07-27 | Date: 2026-07-27 Status: ✅ COMPLETE Duration: ~15 minutes Agent: Haiku (fast, cheap, mechanical tasks) | plans/codemod-engine-briefs/W0-COMPLETION-REPORT.md |
| BRIEF-W5: C Extension (Qwen Max Agent) | 2026-07-27 | Wave: W5 (C Extension) Agent: Qwen Max (C systems programming, CPython C-API expertise) Duration: ~20 minutes Dependencies: W1 (CSR index Python implementation for parity reference) *… | plans/codemod-engine-briefs/BRIEF-W5.md |
| BRIEF-W4: Persistence (Qwen Max Agent) | 2026-07-27 | Wave: W4 (Persistence) Agent: Qwen Max (graph database patterns, Cypher queries) Duration: ~15 minutes Dependencies: W1 (workspace, CIG), W2 (passes, review), W3 (observability, CLI)… | plans/codemod-engine-briefs/BRIEF-W4.md |
| BRIEF-W3: Integrator (Qwen Max Agent) | 2026-07-27 | Wave: W3 (Integrator) Agent: Qwen Max (CLI design, interop glue, benchmark harness) Duration: ~15 minutes Dependencies: W1 (Forest + Sentinel) + W2 (Architect + Reviewer) **Parallel E… | plans/codemod-engine-briefs/BRIEF-W3.md |
| BRIEF-W2: Architect + Reviewer (Qwen Max + Sonnet, Parallel) | 2026-07-27 | Wave: W2 (Architect + Reviewer) Agents: - ARCHITECT (Qwen Max): passes.py (5 built-in transform passes), analysis/*.py (7 analysis modules) - REVIEWER (Sonnet): review.py (40 in-memor… | plans/codemod-engine-briefs/BRIEF-W2.md |
| BRIEF-W1: Forest + Sentinel (Qwen Max + Sonnet, Parallel) | 2026-07-27 | Wave: W1 (Forest + Sentinel) Agents: - FOREST (Qwen Max): workspace.py, _csr_index.py, _cig.py, _cig_builder.py - SENTINEL (Sonnet): txn.py Duration: ~20 minutes Dependencies:… | plans/codemod-engine-briefs/BRIEF-W1.md |
| BRIEF-W0: Scaffold (Haiku Agent) | 2026-07-27 | Wave: W0 (Scaffold) Agent: Haiku (fast, cheap, mechanical tasks) Duration: ~15 minutes Dependencies: None (first wave) Parallel Execution: No (single agent) | plans/codemod-engine-briefs/BRIEF-W0.md |
| Build Factory — self-improving, pattern-based, TDD spec-build pipeline (2026-07-06) | 2026-07-27 | Dogfood Orchestrata to build Orchestrata. A self-improving factory that turns a spec into merged, traced, tested code using the project's own roles, tools, generators, and knowledge graph — augmentin… | plans/build-factory-architecture.md |
| C3 Verification Result — Parallel Collision Fix (Workstream C3) | 2026-07-27 | Source: plans/briefs/c3_run1.json, c3_run2.json, c3_run3.json (run_tests.py --json outputs, three independent runs). |
plans/briefs/kimi-c3-result.md |
| Kimi task C2 — twin-bug sweep: shared ports + MERGE-key/constraint-key mismatches | 2026-07-27 | Read plans/parallel-collision-fix-plan.md (Workstream C2) for context. Enumeration only: no code changes, no fixes, no test runs. |
plans/briefs/kimi-c2.md |
| Kimi task C2 — twin-bug sweep results | 2026-07-27 | Generated from a repo-wide sweep of tests/ + src/orchestrata_ultimate/ for bind/listen/serve sites and a cross-check of every MERGE (:<Label> {…}) against knowledge_graph/canonical_schema.py. |
plans/briefs/kimi-c2-result.md |
| Kimi task C1 — failure census of the 2026-07-22 full-suite run | 2026-07-27 | Read plans/parallel-collision-fix-plan.md (Workstream C1) for context. This is a classification task: no code changes, no fixes. |
plans/briefs/kimi-c1.md |
| Kimi C1 — failure census of 2026-07-22 full-suite run | 2026-07-27 | Source: plans/briefs/full_suite_run2.json (output of scripts/run_tests.py --json). |
plans/briefs/kimi-c1-result.md |
| BodyMatcher split plan (cohesion-driven, behavior-preserving) | 2026-07-27 | Status: EXECUTED 2026-07-10 (commits 5c7b74f6.. on master), with two mid-flight user rulings that superseded parts of this plan: |
plans/bodymatcher-split-plan.md |
| Plan: Install and Configure Cucumber and Gherkin for BDD Testing | 2026-07-27 | Add Behavior-Driven Development (BDD) testing support to orchestrata-ultimate using Cucumber/Gherkin syntax. This will enable writing tests in natural language that can be understood by both technica… | plans/bdd_cucumber_gherkin_setup.md |
| BDD runtime-tracing plan — execution-evidence tier for the RTM | 2026-07-27 | Session 244, 2026-07-21. Execution plan derived from reports/research-bdd-runtime-tracing-rtm.md (verdict: PARTIAL YES — runtime attribution fixes the PRECISION half of the frozen-at-55% trace prob… |
plans/bdd-runtime-tracing-plan.md |
| Session-Tooling Backlog — Detailed Implementation Plan | 2026-07-27 | Plan for the 6 remaining backlog items (Phase 9 / VizInt is done). Written after a file-and-line investigation of the session-hook + CLI system. Several items turned out to be **smaller or differentl… | plans/backlog-plan.md |
| Whole-project spec audit — 2026-07-06 (all 57 specs, 6 auditor groups) | 2026-07-27 | Chain scored per requirement family: SPECIFIED → TRACED → IMPLEMENTED → WIRED → TESTED-FOR-REAL. "Wired" = constructed in production (the RTM's historical blind spot: it verified decorator existence… | plans/audit-full-2026-07-06.md |
| AST Toolkit Evaluation + Codegen Expansion — audit + roadmap | 2026-07-27 | Source: ast-codegen-audit swarm (w0kuij9g6, 12 agents, 1.1M tokens). Full results: workflow journal wf_9d4c9f94-589/journal.jsonl. User directive 2026-07-05. |
plans/ast-codegen-audit.md |
| AST Analysis Report — orchestrata-ultimate Porting Status | 2026-07-27 | Generated: 2026-04-12 Source AST: plans/ast-ultimate-fresh.json (generated from src/orchestrata_ultimate/) Comparison AST: plans/ast-orchestrata.json (original 26-package monorepo)… |
plans/ast-analysis-report.md |
| README-semantic-graph-qa | 2026-07-27 | ARCHIVED: superseded QA snapshots (57% era). Canonical output: ../semantic_graph_qa_results_latest.md (82% coverage, 0 low-quality) — regenerated by scripts/evaluate_semantic_graph_qa.py | plans/archive/README-semantic-graph-qa.md |
| Orchestrata Ultimate — Architecture Review & Gap-Closure Design | 2026-07-27 | Method: the system-design skill applied to the actual system (Phase 0 = ground truth first). Evidence gathered with the repo's own AST tooling (plans/ast-ultimate.json, direct query) for st… |
plans/architecture-review-2026-07-18.md |
| Architecture Ontology — RATIFIED (implementation pending) | 2026-07-27 | STATUS: RATIFIED 2026-07-19 — all 8 open questions ruled (see §9); schema not yet applied. This is the ontology-before-graph-import step (project doctrine: never dump docs into a graph without… | plans/architecture-ontology-draft.md |
| Deep-Analysis Findings — 2026-07-06 (Session 199) | 2026-07-27 | Evidence-based snapshot of code, architecture, structure, features, process, and hygiene, produced by an Opus orchestrator + 5 read-only agents (hygiene, AST metrics, architecture, feature inventory,… | plans/analysis-2026-07-06-findings.md |
| Specialized Subagent Roster — evidence-based | 2026-07-27 | Source: agent-roster-proposal swarm (wfxzhziah / wf_c669ec71-82a, 2026-07-05, 10 agents, 236K tokens). Deterministic mining (scratchpad/mine_subagent_tasks.py) of **131 unique subagent tasks… |
plans/agent-roster.md |
| Agent Implementation — Pipeline Automation | 2026-07-27 | Branch: deepseek-edition Specs: SPEC-103 (Tool-Calling), SPEC-019 (Agents) Status: Phase 4 — Observer Logging | plans/agent-implementation-plan.md |
| Prompt: Generate Detailed Iterative Execution Plan | 2026-07-27 | Usage: Paste this entire prompt into a new Claude session with MAX THINKING enabled. The output will be a step-by-step plan executable by DeepSeek/Sonnet/Opus at medium effort. | plans/PROMPT-detailed-execution-plan.md |
| Orchestrator Pipeline Checklist — Universal | 2026-07-27 | Mandatory for every subplan. Every step must be marked DONE with evidence before proceeding. Skipping steps is a pipeline violation. If a step fails, stop and investigate — do not proceed. | plans/ORCHESTRATOR-CHECKLIST.md |
| Efficient Project Analysis Plan — Refined | 2026-07-27 | Date: 2026-05-17 Recon Status: ✅ COMPLETE Goal: Thorough project analysis while minimizing context consumption via structured-data-first workflow. | plans/EFFICIENT_ANALYSIS_PLAN.md |
Machine and data files (not mirrored)
| File | Bytes | Purpose |
|---|---|---|
plans/ORCHESTRATA_PIN.txt |
41 | Plain-text pin / note |
plans/affected-tests-manifest.json |
41,437 | Manifest (machine-generated) |
plans/analysis/apply_verdicts.py |
8,563 | Analysis script |
plans/analysis/build_register.py |
13,067 | Analysis script |
plans/analysis/make_verify_batches.py |
8,268 | Analysis script |
plans/analysis/overlay.json |
17,911 | JSON data (machine-generated) |
plans/analysis/register.json |
3,807,966 | JSON data (machine-generated) |
plans/analysis/render_report.py |
24,480 | Analysis script |
plans/analysis/trace_refs.py |
5,356 | Analysis script |
plans/ast-comparison.json |
23,597 | AST snapshot (machine-generated) |
plans/ast-deep-comparison-124.json |
3,482,260 | AST snapshot (machine-generated) |
plans/ast-deep-comparison-125.json |
3,482,260 | AST snapshot (machine-generated) |
plans/ast-deep-comparison-126.json |
3,482,260 | AST snapshot (machine-generated) |
plans/ast-deep-comparison-127.json |
3,543,918 | AST snapshot (machine-generated) |
plans/ast-deep-comparison-fresh.json |
1,134,446 | AST snapshot (machine-generated) |
plans/ast-deep-comparison.json |
3,282,683 | AST snapshot (machine-generated) |
plans/ast-orchestrata.json |
9,713,664 | AST snapshot (machine-generated) |
plans/ast-tests.json |
62,054,439 | AST snapshot (machine-generated) |
plans/ast-ultimate-backup.json |
13,685,680 | AST snapshot (machine-generated) |
plans/ast-ultimate-fresh.json |
8,894,581 | AST snapshot (machine-generated) |
plans/ast-ultimate.json |
112,720,889 | AST snapshot (machine-generated) |
plans/ast-vizint-ui.json |
1,069,849 | AST snapshot (machine-generated) |
plans/briefs/c3_run1.json |
221,753 | JSON data (machine-generated) |
plans/briefs/c3_run2.json |
227,545 | JSON data (machine-generated) |
plans/briefs/c3_run3.json |
222,003 | JSON data (machine-generated) |
plans/briefs/full_suite_run2.json |
265,567 | JSON data (machine-generated) |
plans/class-mapping.json |
6,368 | JSON data (machine-generated) |
plans/code-index.json |
180,914 | JSON data (machine-generated) |
plans/contracts/SPEC-072.contract.json |
24,311 | JSON data (machine-generated) |
plans/contracts/SPEC-072.mmd |
8,949 | Mermaid diagram source |
plans/contracts/SPEC-072.reqmapped.mmd |
9,280 | Mermaid diagram source |
plans/contracts/constraint-prolog-evaluation.contract.json |
5,895 | JSON data (machine-generated) |
plans/contracts/constraint-prolog-evaluation.mmd |
2,003 | Mermaid diagram source |
plans/contracts/ctok-parser.contract.json |
9,069 | JSON data (machine-generated) |
plans/contracts/ctok-parser.mmd |
3,073 | Mermaid diagram source |
plans/contracts/ctok-parser.trace-map.json |
3 | JSON data (machine-generated) |
plans/contracts/eight-failures-2026-10-08.mmd |
10,694 | Mermaid diagram source |
plans/contracts/ft-grpcio-tools.contract.json |
4,665 | JSON data (machine-generated) |
plans/contracts/gateway-kernel-reprobe.contract.json |
36,599 | JSON data (machine-generated) |
plans/contracts/gateway-kernel-reprobe.mmd |
8,299 | Mermaid diagram source |
plans/contracts/implementation-scanner-ast.contract.json |
15,137 | JSON data (machine-generated) |
plans/contracts/kernel-dispatch-reply-hardening.mmd |
7,863 | Mermaid diagram source |
plans/contracts/kernel-dispatch-reply.mmd |
5,506 | Mermaid diagram source |
plans/contracts/kg-edge-resolution-provenance.contract.json |
5,833 | JSON data (machine-generated) |
plans/contracts/pipeline-event-convergence.mmd |
10,387 | Mermaid diagram source |
plans/contracts/prolog-gates.contract.json |
17,565 | JSON data (machine-generated) |
plans/contracts/prolog-gates.mmd |
3,155 | Mermaid diagram source |
plans/contracts/rul-022-design-gate.contract.json |
5,566 | JSON data (machine-generated) |
plans/contracts/session-handler-split.mmd |
6,571 | Mermaid diagram source |
plans/contracts/session-root-injection.contract.json |
7,456 | JSON data (machine-generated) |
plans/contracts/spec-007b-wiring.contract.json |
25,858 | JSON data (machine-generated) |
plans/contracts/spec-007b-wiring.mmd |
9,466 | Mermaid diagram source |
plans/contracts/spec-014-resurrection.contract.json |
39,749 | JSON data (machine-generated) |
plans/contracts/spec-014-resurrection.mmd |
11,589 | Mermaid diagram source |
plans/contracts/spec-021-ontology.contract.json |
34,896 | JSON data (machine-generated) |
plans/contracts/spec-021-ontology.mmd |
9,806 | Mermaid diagram source |
plans/contracts/spec-109-rename-engine.contract.json |
17,072 | JSON data (machine-generated) |
plans/contracts/spec-109-rename-engine.mmd |
5,067 | Mermaid diagram source |
plans/contracts/spec-110-codemod-engine.contract.json |
113,122 | JSON data (machine-generated) |
plans/contracts/spec-110-codemod-engine.mmd |
17,307 | Mermaid diagram source |
plans/contracts/spec-110-trace-map.json |
3 | JSON data (machine-generated) |
plans/contracts/verification-coordinator-loop.contract.json |
4,909 | JSON data (machine-generated) |
plans/contracts/volk-comms-heartbeat.mmd |
4,729 | Mermaid diagram source |
plans/contracts/volkdriver-phase0.contract.json |
12,519 | JSON data (machine-generated) |
plans/contracts/volkdriver-phase0.mmd |
2,720 | Mermaid diagram source |
plans/contracts/wiring-gate.contract.json |
5,467 | JSON data (machine-generated) |
plans/cov_baseline.json |
3,965,790 | JSON data (machine-generated) |
plans/cov_true2.json |
4,992,053 | JSON data (machine-generated) |
plans/derived-rtm.json |
48,812 | JSON data (machine-generated) |
plans/feature-loss-invalid-citations.json |
239,446 | JSON data (machine-generated) |
plans/feature-loss-invalid-origin-evidence.ndjson |
217,629 | Configuration / record data |
plans/orphan-modules-baseline.txt |
9,884 | Plain-text pin / note |
plans/plan_102_volk_harness/agent_config_a.yaml |
1,668 | YAML configuration / manifest |
plans/plan_102_volk_harness/agent_config_b.yaml |
1,961 | YAML configuration / manifest |
plans/plan_102_volk_harness/agent_config_c.yaml |
1,681 | YAML configuration / manifest |
plans/plan_102_volk_harness/agent_config_d.yaml |
1,903 | YAML configuration / manifest |
plans/plan_102_volk_harness/agent_config_e.yaml |
1,765 | YAML configuration / manifest |
plans/plan_102_volk_harness/agent_config_f.yaml |
1,264 | YAML configuration / manifest |
plans/plan_102_volk_harness/agent_config_g.yaml |
1,473 | YAML configuration / manifest |
plans/plan_102_volk_harness/agent_config_h.yaml |
1,895 | YAML configuration / manifest |
plans/plan_102_volk_harness/agent_config_i.yaml |
2,619 | YAML configuration / manifest |
plans/plan_subphase_0_1/agent_config.yaml |
2,561 | YAML configuration / manifest |
plans/plan_subphase_0_1_coverage/agent_config.yaml |
3,082 | YAML configuration / manifest |
plans/plan_subphase_0_2/agent_config.yaml |
5,771 | YAML configuration / manifest |
plans/plan_subphase_0_3/agent_config.yaml |
2,796 | YAML configuration / manifest |
plans/plan_subphase_1_1/agent_config.yaml |
4,571 | YAML configuration / manifest |
plans/plan_subphase_1_2/agent_config.yaml |
4,184 | YAML configuration / manifest |
plans/plan_subphase_1_3/agent_config.yaml |
4,715 | YAML configuration / manifest |
plans/plan_subphase_1_6/agent_config.yaml |
3,319 | YAML configuration / manifest |
plans/plan_subphase_2_1/agent_config.yaml |
2,849 | YAML configuration / manifest |
plans/plan_tests_qa_volk/agent_config.yaml |
1,064 | YAML configuration / manifest |
plans/reference-edges.json |
17,857 | JSON data (machine-generated) |
plans/rename-engine-briefs/example-plan.toml |
1,350 | Configuration / record data |
plans/rtm.json |
2,081,963 | JSON data (machine-generated) |
plans/runtime-callgraph.json |
2,166,018 | JSON data (machine-generated) |
plans/scripts-migration-map.json |
30,932 | JSON data (machine-generated) |
plans/semantic_graph_questions.txt |
6,766 | Plain-text pin / note |
plans/spec_term_prominence.json |
203,150 | JSON data (machine-generated) |
plans/stage2_re_port_report.json |
1,602 | JSON data (machine-generated) |
plans/test_audit_report.json |
236 | JSON data (machine-generated) |
plans/test_coverage_plan_revised.json |
56,352 | JSON data (machine-generated) |
plans/trace-acceptance-sample.json |
109,482 | JSON data (machine-generated) |
plans/trace-acceptance-wrong.json |
111,572 | JSON data (machine-generated) |