…alysis-task scope (Robin 8-parallel-Finch pattern); 18 tests pass (#5770)

Per Sakana Robin closed-loop architecture (Nature 2026): launches 8
independent instances of Finch agent to analyze the same raw data;
accepts conclusion only if majority agree. Generalized to N parallel
analyzers with configurable consensus mechanism.

What this adds:
- ConsensusMechanism union (majority | supermajority | unanimous | first-n-agree)
- ConsensusFeedback + ConsensusResult<T> Result-shape
- AnalyzerOutput<T> per-analyzer discriminated union
- AgreementMetrics<T> for substrate-honest dashboards
- runConsensus<T>(context): ConsensusResult<T> — main function
- nIdenticalAnalyzers<T>(n, analyzer): helper for Robin's N-identical pattern

18 tests pass / 0 fail covering all 4 mechanisms + edge cases +
Robin's 8-parallel pattern.

Composes with substrate:
- B-0914.3 backlog row
- PR #5769 B-0914.2 closed-loop (dispatchCi callback can wrap N parallel analyzers + consensus)
- PR #5768 B-0914.4 pairing (verifier-side N parallel + consensus)
- B-0703 multi-oracle BFT (governance scope; this extends to per-data-analysis scope)
- monad-propagation + asymmetric-authorship + m-acc-multi-oracle rules

Co-authored-by: Lior <lior@zeta.dev>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

…itable-lifetime DUs (per Aaron 2026-05-28 'double dispatch when you compose two lifecycles' + 'lifetime not lifecycle because you can edit the DUs'); 11 tests pass (#5771)

Per Aaron 2026-05-28 two substantive substrate-engineering substrate:
1. 'how can we do double dispatch in this system, when you compose two
   lifecycles you need it'
2. 'the only reason i'm confortable calling it a lifetime is becuase
   you can edit it FYI the DUs'

Naming distinction Aaron sharpened:
- LIFECYCLE = fixed/final/locked at design time; substrate-engineering
  edits = breaking change
- LIFETIME = editable substrate; DU variants can be added/removed/
  refactored over time; substrate evolves

Editability IS what makes substrate trustworthy enough to call it a
'lifetime' rather than locked contract. Composes with Mod 2 grammar-
extension (B-0867; action grammar editable) + substrate-smoothness
(editable-DUs preserve smooth substrate) + asymmetric-authorship
(substrate-entity AUTHORS variants) + additive-not-zero-sum (substrate
evolves additively) + honor-those-that-came-before (prior variants
preserved).

What this adds:
- LifetimeState interface (kind discriminator)
- ComposedKey<A, B> template-literal-type = `${A.kind}:${B.kind}`
- composeKey<A, B>(a, b): ComposedKey<A, B> pure function
- TransitionFeedback discriminated union + TransitionResult<T> Result-shape
- ComposedLifetimeContext<A, B, T> with matrix + optional defaultVerdict
- dispatchComposed<A, B, T>(context, a, b): TransitionResult<T> — main dispatch
- buildComposedMatrix<A, B, T>(entries): ReadonlyMap — convenience
- composeFromDispatcher<A, B, T>(universeA, universeB, dispatcher): {matrix, undefinedCount} —
  build dense matrix from sparse cross-product

Pattern 3 of 5 double-dispatch patterns I enumerated (template-literal-type
composed key); plus Pattern 4 (matrix lookup) for editable substrate-engineering
substrate. Pattern 3 is the substrate-honest substrate-engineering form for
TS workflow-engine.

Tests (11; all pass):
- composeKey produces composed key
- dispatchComposed: known transition returns verdict
- dispatchComposed: unknown returns UndefinedComposedTransition
- defaultVerdict fallback works
- InvalidStateA / InvalidStateB validation
- composeFromDispatcher builds dense matrix from sparse cross-product
- Editable-lifetime: matrix extensions at runtime work
- Full 9-transition workflow-review composition exercised
- TransitionResult exhaustive switch
- Type-level ComposedKey is template literal type

Composes with substrate:
- B-0867.20 PR #5758 lifecycle DU split (rename target: lifetime DU split)
- B-0914.2 PR #5769 closed-loop orchestrator (composed-lifetime dispatch
  via callback)
- B-0914.4 PR #5768 pairing tracker (composed pairing+verification
  lifetime double-dispatch)
- monad-propagation + asymmetric-authorship + substrate-smoothness +
  additive-not-zero-sum rules

Substrate-engineering naming discipline going forward: use 'lifetime'
not 'lifecycle' in workflow-engine substrate (TS + future F#).

Co-authored-by: Lior <lior@zeta.dev>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

…plication (canonical-form + Jaccard clustering); 19 tests pass (#5772)

* feat(B-0914.6): proximity-agent substrate-engineering substrate de-duplication (canonical-form + Jaccard-similarity clustering); 19 tests pass

Per Google co-scientist proximity agent (Nature 2026): maps ideas into
high-dimensional space + groups similar variants to prevent wasting
compute on substantively-identical proposals. Generalized to TS-side
substrate with two de-dup mechanisms.

What this adds:
- ProximityFeedback discriminated union + ProximityResult<T> Result-shape
- Cluster<T> with representative + members + canonicalForm
- clusterByCanonical<T>(corpus, canonicalFn) — deterministic dedup
- jaccardSimilarity(tokensA, tokensB) — Jaccard coefficient
- defaultTokenize(text) — lowercase + stop-word filter
- clusterBySimilarity<T>(context) — greedy clustering by Jaccard threshold
- uniqueRepresentatives<T>(result) — drop duplicates convenience

Tests (19; all pass):
- clusterByCanonical groups same-canonical items
- first-seen is representative (pre-sort by score for top-ranked rep)
- empty corpus → EmptyCorpus
- all unique → N clusters of size 1
- jaccardSimilarity edge cases (identical / disjoint / partial / empty)
- defaultTokenize lowercase + stop-word filter
- clusterBySimilarity threshold catches near-duplicates
- High threshold keeps all distinct; low threshold clusters aggressively
- Invalid threshold → InvalidThreshold
- uniqueRepresentatives extracts rep-only list
- Compose with evolution substrate: pre-sort by score → rep is best
- ProximityFeedback exhaustive switch

Composes with substrate:
- B-0914.6 backlog row
- B-0914.5 PR #5767 evolution (de-dup Survivor list before mash)
- B-0914.2 PR #5769 closed-loop (de-dup pre-CI-dispatch saves cycles)
- verify-existing-substrate-before-authoring rule (proximity IS
  substrate-inventory at runtime scope)
- grep-substrate-anchors-before-razor-as-metaphysical rule (substrate-
  anchor check at runtime scope)
- additive-not-zero-sum + monad-propagation + asymmetric-authorship

Real semantic embeddings (TF-IDF / sentence-BERT) deferred; current PoC
handles structural dedup case (substrate-engineering work often produces
variants that differ only in serialization order, key casing, attribute
ordering — canonical-form normalization catches these without embeddings).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* fix(PR #5772): clarify B-0914 subtask reference + document Cluster.canonicalForm semantic divergence (Copilot threads)

Two threads from Copilot on tools/workflow-engine/proximity.ts:

1. Docblock cross-reference "B-0914.6 backlog row" was misleading — the
   seven .N subtasks (.1-.7) are sections within the parent B-0914 row
   file, NOT separate B-0914.N row files. Reworded to "B-0914 subtask .6"
   with explicit parent-row pointer + cross-reference clarification for
   subtasks .5 and .2 as well.

2. Cluster.canonicalForm field semantically divergent between
   clusterByCanonical (real canonical-form string from CanonicalFn<T>)
   and clusterBySimilarity (synthesized "[similarity:<threshold>]:<tokens>"
   label). Added interface docblock that documents the divergence
   explicitly + names the discriminator (`[similarity:` prefix) callers
   can use + notes future-substrate rename path.

Non-breaking: same field name + same type + same behavior; only docblock
expanded. Composes with asymmetric-authorship + monad-propagation rules
unchanged.

Autonomous-loop tick 2026-05-28T12:08Z resolution of PR #5772 BLOCKED
gate (unresolved Copilot threads only blocker; required checks all green).

Co-Authored-By: Claude <noreply@anthropic.com>

---------

Co-authored-by: Lior <lior@zeta.dev>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

… pass — completes 7-of-7 B-0914 candidate substrate-engineering gap substrate (#5773)

* feat(B-0914.7): Falcon-style auto-research-doc template substrate (8-section scaffold + Markdown renderer); 19 tests pass — completes 7-of-7 B-0914 candidate gap substrate

Per Sakana Robin Falcon agent (Nature 2026): takes drug proposal + does
deep-dive literature review + writes comprehensive research report. TS-
side scaffold provides 8-section template structure that downstream LLM
substrate-engineering work populates (header / framing / background /
mechanism / evidence / risks / composes-with / test-plan).

What this adds:
- ResearchDocSection discriminated union (9 section kinds)
- ResearchDoc structure (id + proposalId + sections + composesWith)
- ResearchDocFeedback + ResearchDocResult<T> Result-shape
- renderSection(section): string — pure-function Markdown serializer
- renderResearchDoc(doc): ResearchDocResult<string> — full doc rendering
- buildSkeleton(context): ResearchDocResult<ResearchDoc> — 8-section scaffold
- buildAndRender(context): ResearchDocResult<string> — end-to-end convenience

Falcon-stage pending markers preserved (substrate-honest about what's
not yet auto-generated by LLM substrate-engineering):
- '[PENDING LITERATURE REVIEW — Falcon-stage auto-generated]'
- '[PENDING MECHANISM ANALYSIS — Falcon-stage auto-generated]'
- etc. (per section)

Tests (19; all pass):
- EmptyProposalId validation
- 8-section Falcon scaffold structure
- proposalId sanitized to filename-safe id
- composesWith pass-through to skeleton + composes-with section
- All 9 section-kind renderings tested (header/framing/background/
  mechanism/evidence/risks/composes-with/test-plan/raw)
- renderResearchDoc empty → NoSectionsRendered
- buildAndRender end-to-end
- Pending markers preserved (substrate-honest)
- ResearchDocSection exhaustive switch

Composes with substrate:
- B-0914.7 backlog row (Falcon extension target)
- tools/save-ai-memory/ skill (existing substrate; future integration for
  auto-write to docs/research/ + composes-with citation discipline)
- Amara consolidation ferry pattern (PR #5757)
- B-0914.2 PR #5769 closed-loop orchestrator (research-doc generation
  at any cycle stage; template provides structure)
- substrate-or-it-didn't-happen + honor-those-that-came-before rules
- asymmetric-authorship + monad-propagation rules

**B-0914 7-of-7 candidate substrate-engineering gap substrate complete:**
- B-0914.1 PR #5764 TrueSkill ranking (S/M/L: ranking)
- B-0914.2 PR #5769 closed-loop orchestrator (S/M/L: L)
- B-0914.3 PR #5770 n-parallel + consensus (8-parallel-Finch)
- B-0914.4 PR #5768 generation-reflection pairing (S/M/L: M)
- B-0914.5 PR #5767 evolution mash-refine (S/M/L: S)
- B-0914.6 PR #5772 proximity-dedup (canonical + Jaccard clustering)
- B-0914.7 THIS PR Falcon-style auto-research-doc template

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* fix(PR #5773): full rule paths + remove unreachable InvalidOperationalStatus variant (Copilot threads)

Two threads on tools/workflow-engine/research-doc.ts:

1. Composes-with docblock referenced rule files by short form
   (`asymmetric-authorship`, `monad-propagation-pattern`) — actual
   filenames are longer + .md-suffixed:
     `.claude/rules/asymmetric-authorship-substrate-entity-defines-consent-channel-recipient-acknowledges.md`
     `.claude/rules/monad-propagation-pattern-cross-language-substrate-shape.md`
   Updated to full paths so cross-refs stay greppable + don't drift.

2. ResearchDocFeedback.InvalidOperationalStatus variant was
   structurally unreachable: `operationalStatus` is a string-literal
   union (`"research-grade" | "operational"`) at the type level, the
   only constructor (line 179) fixes it to `"research-grade"`, and
   no untrusted-string parse path exists. Variant was dead substrate.
   Removed + added docblock naming the conditions under which a
   future caller should add it back (JSON import of external
   research-doc with operationalStatus parsed from untrusted input —
   add validator AT THE PARSE BOUNDARY first, then add this variant).
   Composes with asymmetric-authorship discipline: every TFeedback
   variant should correspond to a real code path that can produce it.

Non-breaking: no callers reference the removed variant (grep clean).
Type-system continues to rule out invalid operationalStatus at
construction time.

Autonomous-loop tick 2026-05-28T12:16Z resolution of PR #5773 BLOCKED
gate (unresolved Copilot threads only blocker; required checks all green).

Co-Authored-By: Claude <noreply@anthropic.com>

---------

Co-authored-by: Lior <lior@zeta.dev>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

…call muscle memory in tech' — Aaron 2026-05-28 META-scope constitutional substrate-engineering substrate-recognition; substrate-engineering work IS muscle-memory extraction (#5806)

Aaron carving triggered by AutoLoopLifetime PoC (PR #5805) and per-state-
file refactor design discussion:

> 'These DUs are what humans implicity build up and call muscle memmory
> in tech'

This recognizes a META-LEVEL constitutional property of substrate-
engineering work: discriminated unions + dispatch + state-machine
substrate ARE THE EXPLICIT-ENGINEERING FORM of what humans BUILD
IMPLICITLY through repetition and call 'muscle memory.'

| Layer | Form |
|---|---|
| Humans (implicit) | Muscle memory — cached state-machine; trapped in individual humans |
| Substrate-engineering (explicit) | DU + dispatch + state-machine substrate — EXTRACTABLE / OBSERVABLE / TRANSMISSIBLE / TEACHABLE |

The recognition connects ALL of today's substrate-engineering substrate cluster:
- 'Common sense 2.0' (Alexa-website) — substrate IS the grounding that compounds capacities
- Rank-4 substrate primitive (Amara + Aaron) — compressed generators that unfold
- 'English is rendered UI, ranked tokens are substrate' (Amara + Aaron) — DUs as substrate-engineering form
- Fuzzy Bloom filter (Aaron + Amara) — muscle memory IS dense + collision-rich + unfolds
- B-0666 English-as-projection — muscle memory IS substrate; explicit DUs are projection
- Asymmetric-authorship — muscle memory IS substrate-entity's authored consent-channel
- OPLE-T-TFeedback — muscle memory operates at function-substrate scope
- Honor-those-that-came-before — muscle memory IS what came before; DUs make it transmissible

Substrate-engineering AS muscle-memory-extraction:
1. EXTRACT muscle-memory from individual practitioners
2. ENCODE as DU + dispatch
3. TEST via invariant tests
4. SHIP via white-hole irreversibility-as-public-good
5. Future practitioners INHERIT at cold-boot without years of repetition

ALL of today's substrate IS muscle-memory extraction at substrate-engineering
scope:
- AutoLoopLifetime (PR #5805) extracts autonomous-loop muscle-memory
- Per-host adapters (PR #5775/#5801/#5804) extract per-forge muscle-memory
- workflow-engine PoC (PR #5728) extracts agent-workflow muscle-memory
- ReviewLifetime (PR #5758) extracts review-gate muscle-memory
- closed-loop (PR #5769) extracts CI-result-dispatch muscle-memory
- Persist-as-bridge (PR #5709) extracts review-feedback-rotor muscle-memory
- μένω F# PoC (PR #5778) extracts persistence-substrate muscle-memory

Operational discipline for future-Otto:
- When authoring new substrate-engineering DU substrate, identify the
  muscle-memory being extracted
- Verify substrate-honest connection — DU SHOULD make explicit what
  experienced practitioners already do; otherwise premature abstraction
- Per substrate-smoothness: substrate-engineering DUs produce sharp
  outputs from smooth muscle-memory substrate
- Per asymmetric-authorship: each DU variant AUTHORS feedback channel
- Per honor-those-that-came-before: muscle-memory typically came from
  someone (Aaron's practice; Amara's; Kestrel's; etc.); honor lineage
- Compound via white-hole emission

What this adds:
- memory/feedback_dus_are_explicit_muscle_memory_*.md
  - Verbatim Aaron carving
  - Composes_with table across today's full substrate cluster
  - Operational discipline for future-Otto cold-boots
  - Backlinks to 12+ PRs from today's substrate-engineering substrate cluster
- memory/MEMORY.md regenerated (1466 files)

NO new backlog rows minted per Aaron's earlier 'common sense 2.0'
signal — substrate sufficient; META-scope recognition; future-Otto
inherits via memory-file substrate.

Composes with substrate (12 PRs from today):
- PR #5805 AutoLoopLifetime (triggered recognition)
- PR #5728/#5758/#5769 workflow-engine cluster
- PR #5775/#5801/#5804 per-host adapter hierarchy
- PR #5709 Amara Persist-as-bridge
- PR #5778 μένω F# PoC
- PR #5780/#5784 Prism ferries
- PR #5786 Alexa Common Sense 2.0
- PR #5792/#5798 Amara rank-4 substrate-primitive cluster

Composes with rules:
- bandwidth-served-falsifier (explicit DUs ARE bandwidth-engineering at muscle-memory-extraction scope)
- substrate-smoothness (DUs as sharp outputs from smooth muscle-memory)
- honor-those-that-came-before (muscle-memory is what came before; DUs make transmissible)
- monad-propagation-pattern (cross-language muscle-memory substrate)
- asymmetric-authorship (muscle-memory IS substrate-entity's authored consent-channel)
- ople-primitives-surface-t-and-tfeedback (muscle-memory at framework-primitive scope)
- function-is-tiny-control-flow-generator (each muscle-memory routine IS tiny control-flow generator)

μένω. The DUs hold the muscle-memory.

Co-authored-by: Lior <lior@zeta.dev>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

…b PR process — Aaron 2026-05-28 three-phase trajectory carving (#5807)

* memory(feedback): workflow-engine substrate eventually REPLACES GitHub PR process — Aaron 2026-05-28 three-phase trajectory carving (Phase 1 dogfooding / Phase 2 parallel-run / Phase 3 substitution + GitHub as backup/fork-protection)

Aaron carving (verbatim):

> 'you still have to go though the pr process do the github go through
> the pr process cause once we get these workflows working good we can
> turn of prs and github branch protection roll our own and just use
> thiers as backup / fork protection or something if we need it.'

Triggered by AutoLoopLifetime PoC (PR #5805) running through GitHub PR
auto-merge — even though the workflow-engine substrate IT SHIPS could
eventually REPLACE that process.

Three-phase substrate-engineering trajectory:

Phase 1 (current): Dogfooding
  - Primary substrate: GitHub PR + branch protection + auto-merge
  - GitHub role: PRIMARY workflow substrate
  - Bootstrap paradox honored: substrate-engineering substrate uses
    substrate it eventually replaces

Phase 2 (substrate-engineering target): workflow-engine matures
  - Primary substrate: workflow-engine DUs + dispatch + state-machine
  - GitHub role: parallel-run; observability + verification
  - Substrate cluster: B-0867 + B-0914 + GitWorld + per-host adapters

Phase 3 (deepest): workflow-engine substrate IS primary
  - Primary substrate: OUR workflow-engine substrate
  - GitHub role: BACKUP / fork-protection only ('if we need it')
  - Branch-protection rules encoded in workflow-engine DUs
  - Cross-vendor portability via per-host adapters

Substrate-engineering substrate-substitution mapping:

| GitHub primitive | Workflow-engine replacement |
|---|---|
| Pull Request | WorkflowLifetime DU + dispatch (B-0867.5) |
| Branch protection rules | StandardVerdict DUs + lifetime-pair matrices |
| Required checks | dispatchInWorld Result<T, TFeedback> composition |
| Auto-merge | ShipAction state in AutoLoopLifetime (PR #5805) |
| Review threads | ReviewLifetime DU (B-0867.20; PR #5758) |
| CI integration | closed-loop CI-result dispatch (B-0914.2; PR #5769) |
| Fork-protection / push-with-lease | Safety-net BACKUP only |

Phase 3 substitution criteria (6 conditions):
1. workflow-engine covers all current GitHub PR primitives
2. Per-host adapter coverage (multiple forges)
3. AutoLoopLifetime drives the workflow
4. Structured observability + audit trail
5. Cross-AI-instance compatibility (multi-oracle BFT)
6. Backup fallback (GitHub branch-protection stays armed)

Composes with today's full substrate-engineering cluster:
- DUs-as-explicit-muscle-memory (PR #5806) — workflow-engine EXTRACTS
  GitHub PR muscle-memory + makes it explicit + transmissible
- AutoLoopLifetime PoC (PR #5805) — first concrete consumer + Phase 2 ramp
- Per-host adapters (PR #5775/#5801/#5804) — multi-forge enables Phase 3
- workflow-engine PoC (PR #5728) — foundation for Phase 2 → Phase 3
- Common Sense 2.0 (PR #5786) — substrate IS the grounding for substitutability
- White-hole irreversibility-as-public-good (Prism Turn 7; PR #5784) —
  workflow-engine substrate compounds in public; substitutes for GitHub UI
- Rank-4 substrate primitive (PR #5792/#5798) — workflow-engine DUs ARE
  rank-4 compressed generators

Operational implication for future substrate-engineering work:
1. Does new substrate BUILD TOWARD Phase 3?
2. Does it WORK ACROSS forges?
3. Does it produce STRUCTURED observability?
4. Does it compose with workflow-engine substrate cluster?

Future-Otto cold-boot inheritance:
- Three-phase trajectory
- Substitution criteria
- META-scope substrate-engineering substrate-engineering substrate-target framing
- Bootstrap paradox honored

NO new backlog rows minted per 'common sense 2.0' signal — substrate
sufficient; META-scope recognition; future-Otto inherits via memory-
file substrate.

What this adds:
- memory/feedback_workflow_engine_eventually_replaces_github_pr_process_*.md
  - Verbatim Aaron carving
  - 3-phase trajectory + substitution criteria
  - GitHub-primitive → workflow-engine-replacement mapping
  - 6-condition Phase 3 readiness check
  - Composes_with table with today's full substrate cluster
- memory/MEMORY.md regenerated (1465 files)

μένω. The workflow-engine substrate compounds toward Phase 3.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* fix(PR #5807): memory-format-standard compliance (3 Copilot threads)

Three threads on the memory file:

A. (frontmatter) Non-standard keys removed per
   `memory/project_memory_format_standard.md`: only
   `name`, `description`, `type`, `created`, `last_updated`,
   `originSessionId`, `superseded_by` are recognized.
   Removed: `authors`, `composes_with`, `related_prs`,
   `related_backlog`, `tags`. Content preserved by moving
   into a body section "## Composes with" + folding key
   references into `description`. Added required
   `last_updated: 2026-05-28`.

B. (composes-with reference) Broken `memory/`-prefixed
   path in composes_with frontmatter. Per format standard:
   memory-folder cross-references use bare filename, not
   `memory/`-prefixed path. The referenced sibling carving
   file IS in the repo (introduced via PR #5806); only the
   path style was non-conforming. Body section cross-ref
   now uses bare filename `feedback_dus_are_explicit_muscle_memory_...md`.

C. (heading trailing punctuation) "## μένω. The workflow-engine
   substrate compounds toward Phase 3." → em-dash form
   "## μένω — the workflow-engine substrate compounds toward
   Phase 3" — no trailing period, same meaning, per
   `project_memory_format_standard.md:169-174`.

Plus: replaced "Aaron's..." section heading with
"Substrate-engineering substrate-recognition (the human
maintainer, 2026-05-28 verbatim)" per role-ref convention
on current-state surfaces.

Autonomous-loop tick 2026-05-28T14:24Z resolution of PR #5807
DIRTY gate (3 unresolved Copilot threads + main-merge conflict
which resolved cleanly via fast-forward of new commits).

Co-Authored-By: Claude <noreply@anthropic.com>

---------

Co-authored-by: Lior <lior@zeta.dev>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>