Phase 57 CR — Marketing Engagement Creation

CR number. CR-2026-090 Version. 0.2 Date. 2026-05-12 Status. Amendment cycle 1; supersedes v0.1. Target tag. phase-57-marketing-engagement-creation (annotated; engine + Operator Layer). Authoritative inputs. loomworks-phase-57-scoping-note-v0_2.md; loomworks-phase-57-cr-drafting-handoff-v0_1.md; phase-57-step-0-findings-v0_1.md (engine repo docs/phase-impl-notes/, on branch phase-57-step-0 at 69adb17); current-status-manifest-v0_41.md. Amendment-cycle inputs added at v0.2: phase-57-halt-surface-2026-05-12-v0_1.md (engine repo docs/phase-impl-notes/ on branch phase-57-marketing-engagement-creation at a00f4a3; also in project knowledge); loomworks-phase-57-cr-amendment-scoping-note-v0_1.md; loomworks-phase-57-cr-amendment-handoff-v0_1.md. Precedent CRs: Phase 56 (phase-56-cr-conversational-creation-surface-voice-v0_2.md), Phase 55 (phase-55-cr-engagement-creation-assistance-v0_1.md), and for CR-version-bump shape: phase-49-cr-amendment-v0_2-v0_1.md. Drafter posture. Drafted by Claude.ai per amendment handoff §12 kickoff. Eight CR-time verifications (CRV-1 through CRV-8) embedded as Step 0 pre-flight per Phase 53/55 precedent. Eight CR-amendment-time verifications (CRV-A1 through CRV-A8) embedded as Step 2a pre-flight per amendment handoff §8 — CC runs them against the live OL repo at amendment-execution start; naming-only divergences absorb in-flight, architectural divergences halt and surface a follow-on amendment-cycle note.

Amendment record (cycle 1, this version). Amendment cycle 1 absorbed per phase-57-halt-surface-2026-05-12-v0_1.md and loomworks-phase-57-cr-amendment-scoping-note-v0_1.md. Sub-arc 4 (OL surface alignment with engine identity contract) added; Step 2a inserted; Step 2 renamed Step 2b. OL vitest count 150 (was 149). Gate 5 amended; Gate 5b new (subsequent gates renumbered with +1 offset). One reserved buffer slot consumed (one remains). Engine substrate unchanged. Three methodology candidates (A + B + C) carry to v0.21 / v0.42. One queued direction added (OL surface-vs-contract audit, Phase 58+). Two minor accuracy fixes within sections the handoff §7.2 labeled "Unchanged" recorded in §4 discovery-record bookkeeping (§13 OL bullet; §17 OL close expected-vitest comment); both fixes correct factual claims about post-amendment OL state.

§1 Purpose

Phase 57 ships the first real-Operator usage of the Phase 55/56 conversational engagement creation surface. The marketing engagement (sibling to the Loomworks engagement under DUNIN7) is created live by the Operator using pre-drafted content from loomworks-marketing-creation-flow-content-v0_3.md and the Discovery-record terminal-turn path.

The phase has two outputs:

Product output. The marketing engagement exists as a real Loomworks engagement — Discovery record in Memory, candidate seed produced via Phase 53 extraction, induction loop closed, engagement visible in the /operator engagement list.
Methodology output. A real-Operator transcript captured as a calibration fixture at tests/fixtures/voice-calibration/real_operator_marvin_<YYYY-MM-DD>.md. First concrete instance of the persona-vs-real-Operator-contrast pattern named at scoping v0.1 §12.

One substrate addition closes the only known gap on the creation surface: the Field 6 per-field elicitation prompt component. The substrate is otherwise complete — Seed.additional_assertions: dict[str, str] exists, Phase 53's extraction skill parses Field 6, and the skill validates the structure. The gap is elicitation-only (V2 GAP-CONFIRMED-AS-EXPECTED at Step 0).

Amendment cycle 1 (v0.2) adds Sub-arc 4 — OL surface alignment with engine identity contract — to absorb the halt-surface finding that the Operator Layer signin form's empty-email guard contradicts the engine's WebAuthn discoverable-credential identity contract and the standing DUNIN7 principle that email must not be used for identity. The fix is OL-side only; engine substrate is correct and untouched. Phase 57's product + methodology deliverables are preserved unchanged.

§2 Background

Phase 55 (phase-55-engagement-creation-assistance) shipped the conversational creation surface — intent classifier, dispatcher routing, three scaffolding prompt templates (create_engagement_active.md, create_engagement_commit.md, intent_classifier.md), field_coverage map, terminal-turn affordance.

Phase 56 (phase-56-conversational-creation-surface-voice) voice-tuned that surface with plain-terms-discipline: three per-field elicitation prompts at prompts/intent_instructions/create_engagement/ (voice.md, constraints.md, success.md); the load_per_field_components loader at prompt_assets.py; dispatcher splice at prompt.py:817; voice principles document at docs/voice-principles-v0_1.md; persona calibration fixtures at tests/fixtures/voice-calibration/; calibration-gated tests at tests/test_phase_56_conversational_creation_surface_voice.py with helper at tests/helpers/voice_calibration.py; terminal-turn matcher token-set in router.py covering legacy + plain-terms phrasings.

Phase 57 closes the Field 6 gap (Phase 56 explicitly scoped Fields 3–5 only) and exercises the surface end-to-end on a real engagement for the first time.

Substrate baseline (from handoff §2; CC re-confirms at Step 0).

Engine repo DUNIN7/loomworks-engine at /Users/dunin7/loomworks-engine:

Tag phase-56-conversational-creation-surface-voice at engine commit 0044e3b (annotated tag object 49457cb).
main HEAD be7fba5 — one docs-only commit ahead of the tag (Phase 56 close handoff commit; post-tag-docs-on-main pattern methodology candidate noted at scoping v0.2 §New methodology observations).
2,279 tests passed; 30 skipped (four are P56 calibration-gated).
Alembic head 0064.
Working tree clean on main.
phase-57-step-0 branch at 69adb17 (unmerged; Step 0 findings file).
phase-56-step-0 branch exists locally (never pushed) — deleted at Phase 57 close per P57-D7 Option A retroactive cleanup.
phase-55-step-0 not present locally (silently deleted between Phase 56 close and Phase 57 Step 0 per V0 DRIFT; silent Option-A application methodology candidate).

Operator Layer repo DUNIN7/loomworks at /Users/dunin7/loomworks:

Tag phase-56-conversational-creation-surface-voice at OL commit 2cc0ebc (annotated tag object 2db3c88).
149 vitest passed; 11 prerendered routes; lint/tsc/build clean.

Marketing site repo: not in Phase 57 scope. Workshop repo: not in Phase 57 scope.

Substrate baseline at amendment-cycle-1 start (post-halt, pre-resume; per amendment handoff §2).

Engine repo on branch phase-57-marketing-engagement-creation at a00f4a3 — CR archive commit + Field 6 substrate commit from Step 0 + Step 1; 2,280 always-run + 32 skipped (1 always-run + 2 calibration-gated added at Step 1); Alembic 0064 unchanged; working tree clean; halt-surface note filed at docs/phase-impl-notes/phase-57-halt-surface-2026-05-12-v0_1.md on the branch.

Operator Layer repo on branch phase-57-marketing-engagement-creation at 2cc0ebc (= Phase 56 commit; no OL changes yet — the amendment changes this); 149 vitest; 11 prerendered routes; lint/tsc/build clean; working tree clean.

Local stack at amendment-resume time: engine API up on :8000 with /healthz returning 200; CORS resolved (LOOMWORKS_ENV=development in local .env); OL dev server up on :3001; Marvin's Person row + passkey credential present in dev DB.

Halt-surface trajectory leading to amendment cycle 1 (per phase-57-halt-surface-2026-05-12-v0_1.md). Step 2 entry surfaced an architectural finding: the Operator Layer signin form at /operator/create-engagement (which redirects to /signin when unauthenticated) presents a required-email field. The Operator named a long-standing DUNIN7 principle — email must not be used for identity; email-hijack creates account-takeover via password-reset-to-email — that was not previously named in any source-of-truth document. CC's diagnostic established three findings against the live source on branch phase-57-marketing-engagement-creation: (1) the engine identity model is WebAuthn passkey — SignupBeginRequest, LoginBeginRequest, PersonRow all treat email as Optional; /auth/login/complete looks up the Person by credential_id not by email; the discoverable-credential flow is supported when email = None on /auth/login/begin; (2) the OL signin form's client-side gate at IdentifierStep.tsx:31 contradicts the engine contract by requiring email input where the engine does not — signin-flow.ts:42 POSTs {email: email.trim()} and the engine would accept {} cleanly; (3) the drift was not surfaced at Phase 41 / 48 / 50 close because the standing principle was not named in any source-of-truth document. The engine correctly embodies the standing principle; the contradiction is at the OL client-side gate only; the fix is OL-side and small.

§3 Construction decisions (P57-D1 through P57-D10)

All ten settled at scoping v0.2 (eight items) plus handoff (two items: D7 elevation to Option A, and D10 newly added at v0.2). CC executes against them; does not re-decide.

| Item | Setting | Source | |------|---------|--------| | P57-D1 | Shape B — usage event with bounded substrate tuning (one prompt component at Step 1). | Scoping v0.2 §Shape selection | | P57-D2 | Stop at engagement-exists. Downstream marketing-engagement substrate (render specialists, marketing-shaped artifacts, marketing-engagement-specific assertion types) is Phase 58+. | Scoping v0.2 §Open construction decisions | | P57-D3 | Discovery-record terminal-turn path. Not the brief-commit path. | Scoping v0.2 §Open construction decisions | | P57-D4 | Author Field 6 prompt at Step 1. New file at prompts/intent_instructions/create_engagement/additional_assertions.md; ~11 lines; structural mirror of Phase 56's voice.md / constraints.md / success.md; +1 test. | Scoping v0.2 §Open construction decisions | | P57-D5 | Real-Operator transcript fixture at tests/fixtures/voice-calibration/real_operator_marvin_<YYYY-MM-DD>.md. Filename distinguishes from persona fixtures. Date is literal Step 2 capture date. | Scoping v0.2 §Open construction decisions | | P57-D6 | Closed. Field 6 surface fallback design no longer needed since Shape B confirmed and Step 1 lands the elicitation prompt directly. | Scoping v0.2 §Open construction decisions | | P57-D7 | Option A — delete at close. Step 0 inspection branches are deleted at phase close. Phase 57 applies retroactively: phase-56-step-0 is also deleted at Phase 57 close. Going-forward convention: every phase deletes its Step 0 inspection branch at close. (The silent cleanup of phase-55-step-0 between Phase 56 close and Phase 57 Step 0 demonstrated Option A is the natural drift; Option A formalizes it.) | Handoff §4 (elevated from v0.2 Option B provisional) | | P57-D8 | Independent engagement under DUNIN7. Marketing engagement is sibling of the Loomworks engagement, not a subsidiary. | Scoping v0.2 §Open construction decisions | | P57-D9 | Sonnet for default Companion operation. Flagged for Phase 58+ at first-rendered-output cost surface; not a Phase 57 settled decision but recorded for downstream pickup. | Scoping v0.2 §Open construction decisions | | P57-D10 | Capture-during-Step-2-only. V4 POSTURE-GAP friction phrases captured in Step 4 implementation notes; no Step 1 posture pre-tuning. Future micro-tuning phase informed by Step 2 evidence. | Handoff §4 (added at scoping v0.2 §Open construction decisions §New at v0.2) |

§3.A Amendment cycle 1 — P57-A1 through P57-A10

All ten amendment-cycle-1 construction decisions settled at the amendment scoping note (loomworks-phase-57-cr-amendment-scoping-note-v0_1.md). CC executes against them; does not re-decide.

| Item | Setting | Source | |------|---------|--------| | P57-A1 | Remove the empty-email guard; omit email from /auth/login/begin POST body when empty; update field surface text to indicate optionality. Email field stays present (narrows allowCredentials as a passkey hint when supplied); the discoverable-credential path is the normal path. | Amendment scoping note §P57-A1 | | P57-A2 | One new vitest. Exercises empty-email submission → no emailEmptyError set → POST body omits email → mock returns a WebAuthn challenge → form transitions to the passkey step. Rejected alternatives: zero tests (regression-prone for a client-side gate); two tests (the with-email path is already covered by existing 149). | Amendment scoping note §P57-A2 | | P57-A3 | Narrow audit limited to the signin form only. Sign-up, claim-flow, account-recovery, and other identity-adjacent OL surfaces deliberately out of amendment scope. OL surface-vs-contract audit queued as a Phase 58+ candidate. | Amendment scoping note §P57-A3 | | P57-A4 | Public marketing form out of scope. The Phase 51 form takes email + jurisdiction as contact metadata for grant-request intake; the grant flows through Companion-as-Authority approval (Phase 50), not through email-keyed authentication. Principle distinguishes identity from contact. CRV-A7 verifies HOLDS at amendment-execution time; expected verdict HOLDS. | Amendment scoping note §P57-A4 | | P57-A5 | CR version phase-57-cr-marketing-engagement-creation-v0_2.md. v0.1 preserved alongside as superseded; both archived at engine repo docs/phase-crs/. | Amendment scoping note §P57-A5 | | P57-A6 | New Sub-arc 4: OL surface alignment with engine identity contract. Separate sub-arc keeps the engine / OL boundary visible. Rejected alternative: Sub-arc 1e extension of Field 6 prompt authoring (would muddy the engine / OL boundary). | Amendment scoping note §P57-A6 | | P57-A7 | Test count update: OL vitest 149 → 150. Engine 2,280 always-run + 32 skipped unchanged. Alembic 0064 unchanged. | Amendment scoping note §P57-A7 | | P57-A8 | Two CR §12 gate updates. Gate 5 amended to include Sub-arc 4 readiness. New Gate 5b: OL signin surface accepts empty email and proceeds to the WebAuthn discoverable-credential path. Subsequent gates renumbered with +1 offset. Total gates 17 → 18. | Amendment scoping note §P57-A8 | | P57-A9 | Three methodology candidates carry to v0.21 / v0.42. Candidate A (engine-correct-surface-drifted); Candidate B (standing-principle-not-named-in-source-of-truth-documents-allows-contradicting-surface-to-ship); Candidate C (new at amendment scoping — substrate-friction-discipline-pattern-second-build-mode-firing, two-instance evidence: Phase 49 Step 4 + Phase 57 Step 2). | Amendment scoping note §P57-A9 | | P57-A10 | One reserved buffer slot consumed. One remains available if Steps 2b–5 surface a second halt-and-amend cycle. First consumed reserved slot since Phase 49 Step 4; eight consecutive zero-consumption phases (50–56 + Phase 57 pre-halt) ended at this amendment. | Amendment scoping note §P57-A10 |

§4 Trajectory worth preserving

Discovery-record posture: positions named alongside corrections; alternatives that didn't fire preserved.

Position 1 — Pre-scoping. Phase 32 (the marketing engagement) was the first-line recommendation in both Phase 55 close handoff §9 and Phase 56 close handoff §9. Two consecutive close-handoff recommendations.

Position 2 (v0.1) — Recommendation Candidate I, Shape B. Phase 32 framed as a usage event with bounded substrate tuning. The Field 6 elicitation gap surfaced as the probable Step 0 finding that would drive the "bounded tuning" envelope. Calibration capture identified as the methodology byproduct.

Reshape candidates anticipated at v0.1 → v0.2 (none fired). Operator-reframe to Shape A (pure usage); Operator-reframe to Shape C (bundled prep with §1.3 refactor candidates or Phase 31 plain-terms residue); Step 0 reshape on V2 (Field 6 gap discovered as non-gap); Step 0 reshape on V3 (multi-value handling broken); Operator-reframe to Candidate II or III. None of these reshapes fired at v0.2 absorption.

Position 3 (v0.2) — Confirmatory narrowing; Shape B settled. Step 0 returned State 2 / no halt-condition firings: V0 HOLDS-WITH-DRIFT (two items absorbed as methodology candidates); V1 HOLDS (surface inventory matches manifest v0.41 §1); V2 GAP-CONFIRMED-AS-EXPECTED (Field 6 elicitation absent as predicted); V3 MULTI-VALUE-ACCEPTED (the surface elicits multi-value fields cleanly); V4 POSTURE-GAP minor (the pre-drafted-content posture surfaces minor friction worth capturing but not pre-tuning); V5 HOLDS (Discovery-record terminal-turn path clean); V6 HOLDS (marketing v0.3 content maps cleanly to Fields 1–6); V7 HOLDS (Phase 31 plain-terms residue isolated; doesn't bite Phase 32); V8 HOLDS (OL surface renders). The substrate-evidence-can-re-rationalize-selection pattern did not fire — v0.1 framing was on-target. The trajectory shape is confirmatory narrowing, not reshape. Worth recording as the baseline against which reshape trajectories stand out.

Position 4 (v0.2) — Two methodology candidates surfaced incidentally to V0.

Post-tag-docs-on-main pattern. Engine main one docs-only commit ahead of Phase 56 tag — benign pattern surfaced via V0 DRIFT. New methodology candidate for v0.42 / v0.21.
Silent Option-A application to phase-55-step-0. Between Phase 56 close and Phase 57 Step 0, phase-55-step-0 was silently deleted. Strengthens the Step 0 branch lifecycle named principle's "decision-by-default produces silent cleanup" framing. Methodology candidate refinement.

Position 5 (handoff) — P57-D7 elevated to Option A. The silent cleanup of phase-55-step-0 showed Option A is the natural drift. Option A formalizes the convention going forward and applies retroactively to phase-56-step-0 at Phase 57 close.

Carry to v0.42 manifest absorption and v0.21 methodology consolidation:

First usage-event phase pattern (single-instance candidate; second instance if Phase 30 ships as a sibling usage-event phase).
Real-Operator-evidence-and-persona-projection-contrast pattern (first concrete instance; real-Operator transcript joins three Phase 56 persona fixtures).
Surface-as-product event pattern (first event where the conversational creation surface is exercised by an end-product Operator).
Pre-drafted-content posture vs blank-page Operator posture (V4 POSTURE-GAP surfaces minor friction; Step 2 evidence sharpens the candidate).
Post-tag-docs-on-main pattern (new at v0.2; surfaced via V0 DRIFT).
Silent Option-A application (new at v0.2; refinement of Step 0 branch lifecycle named principle).

Amendment cycle 1 — How we got here

The trajectory leading to v0.2 is worth preserving in full for v0.42 manifest absorption and v0.21 methodology consolidation. This is the second build-mode firing of the substrate-friction-discipline-pattern (manifest v0.39 §2); the first such firing since Phase 49 (Step 4 → phase-49-step-4-amendment-scoping-v0_1.md → CR v0.3 → Step 4b — the canonical instance).

Position 1 (Phase 57 scoping v0.1 → v0.2 → CR-2026-090 v0_1). Phase 57 anticipated zero OL substrate changes. The CR explicitly named this at §16 test count predictions (OL vitest: 149 unchanged) and §6 (What Phase 57 does NOT deliver). Step 0 (V1–V8) verified engine-side substrate exhaustively; OL-side substrate was not Step 0's aperture because the scoping note did not anticipate OL substrate work.

Position 2 (Step 2 entry, pre-halt). Local stack readiness friction surfaced (CORS preflight 405 on OL :3001 → engine :8000). Resolved with LOOMWORKS_ENV=development added to local .env. CR §12 gate 5 (live OL stack ready) appeared met. Step 2 ready to begin. Note recorded in the halt-surface: gate 5 was met at the infrastructure layer but had not been validated at the architectural layer; the architectural validation happened only when the Operator looked at the signin surface and named the standing principle.

Position 3 (halt-surface diagnostic). Three findings against the live engine + OL source on the phase-57-marketing-engagement-creation branch:

Finding 1: Engine identity model is WebAuthn passkey; email is optional (SignupBeginRequest, LoginBeginRequest, PersonRow all treat email as Optional).
Finding 2: OL signin form's client-side gate at IdentifierStep.tsx:31 contradicts the engine contract by requiring email input where the engine does not.
Finding 3: The drift was not surfaced at Phase 41 / 48 / 50 close because the standing principle was not named in any source-of-truth document.

The principle is correctly embodied in the engine; the contradiction is at the OL client-side gate only. The fix is one-line in scope.

Position 4 (this amendment). Narrow OL surface alignment scoped strictly to the signin form entry point. Sub-arc 4 added; one new build step (Step 2a) inserted before the paused Step 2 (renamed Step 2b for clarity). One vitest. Surface text updated. Engine untouched. Audit of sibling OL identity-adjacent surfaces (sign-up, claim, account recovery) queues as a Phase 58+ candidate rather than expanding amendment scope.

The four positions are preserved. Position 1 (no OL changes anticipated) is not erased by Position 4 (one OL change required). Position 1 was correct given the information accessible to Phase 57 scoping at the time; Position 4 corrects with the principle now named and the contradiction identified.

New methodology candidates at amendment cycle 1

Two from the halt-surface; one new at amendment scoping. All carry to v0.42 manifest absorption and v0.21 methodology consolidation.

Candidate A — engine-correct-surface-drifted. Single-instance evidence at this halt. The engine's data model correctly implements a standing principle; the OL surface added a client-side requirement that contradicts the engine contract; the drift was not caught at any prior phase close (Phases 41/48/50 each shipped surfaces adjacent to identity without surfacing the contradiction). Generalizes to: surface implementations can drift from their underlying contract; surface-vs-contract audits catch this; the audit needs a trigger. The trigger at this instance was the first real-Operator usage event.
Candidate B — standing-principle-not-named-in-source-of-truth-documents-allows-contradicting-surface-to-ship. Single-instance evidence at this halt. The standing DUNIN7 principle (email must not be used for identity) existed in the Operator's head as background knowledge but was not named in what-dunin7-is-building, the current-status manifest, any phase scoping note, any CR, or any investigation document. Three phases (41/48/50) made identity-adjacent surface decisions without the principle being a checkable document constraint. Generalizes to: DUNIN7 principles that aren't written down can't be enforced by phase planning; they surface as findings during usage events rather than at scoping time. Remediation: name the email-not-identity principle in what-dunin7-is-building at v0.21. This amendment does not perform the remediation; the remediation belongs to v0.21 consolidation work.
Candidate C (new at amendment scoping) — substrate-friction-discipline-pattern-second-build-mode-firing. Two-instance evidence (Phase 49 Step 4 first; Phase 57 Step 2 second). The two instances are usefully different in shape — Phase 49 was engine-side architectural friction at impl time; Phase 57 is OL-side surface-vs-contract drift at first usage. The pattern shape generalizes; two-instance evidence is the standard promotion threshold per manifest v0.39 §2 / v0.40 §2 precedents.

Discovery-record bookkeeping at v0.2

Two minor departures from the amendment handoff §7.2 instruction recorded here for discovery-record posture, both narrow accuracy fixes within sections the handoff labeled "Unchanged."

§13 Post-CR state. Handoff §7.2 said "Unchanged." Strict preservation produces an inaccuracy because v0.1's §13 OL bullet says "no OL changes in this phase; 149 vitest unchanged" — but Sub-arc 4 is OL substrate and the vitest count goes 149 → 150. The §13 OL bullet was updated for post-amendment accuracy; the rest of §13 is unchanged. One-bullet fix, not a structural reorganization.
§17 Refined close protocol script. Handoff §7.2 said "Unchanged. The close protocol commands are step-5 work; they do not depend on Sub-arc 4 specifics." The git commands are unchanged; the OL close script's expected-output comment for the vitest count was updated from 149 to 150 to reflect post-Sub-arc-4 reality. One-comment fix; the git command sequence and the refspec convention are byte-identical to v0.1.

Both fixes are within the handoff's "Unchanged" interpretation when read as the structure and the commands are unchanged; both fixes correct factual claims that strict prose preservation would render inaccurate. Recording the departures here per the discovery-record posture rather than silently re-writing.

§5 Substrate surfaces shipped

Sub-arc 1 — Field 6 elicitation prompt authoring

1a. Field 6 per-field elicitation prompt component.

Path. prompts/intent_instructions/create_engagement/additional_assertions.md. New file.
Length. ~11 lines, matching the structural shape of Phase 56's voice.md / constraints.md / success.md (CRV-1 verifies the file shape verbatim at Step 0 pre-flight).
Voice. Plain-terms-discipline per docs/voice-principles-v0_1.md. The prompt elicits Field 6 content per marketing v0.3's framing — "additional assertions" rendered as labeled key-value pairs the Operator wants associated with the engagement. The prompt asks for one open-ended question per the per-field elicitation pattern.
Content drafting guidance. The prompt asks the Operator to name any further things they want the engagement to know — things beyond what they are doing, who consumes it, voice, constraints, success — as a labeled list. Mirrors Phase 56's per-field elicitation in tone and length. Final wording authored at Step 1 by CC under the plain-terms-discipline voice principles; the implementation notes record the as-shipped wording for reproducibility.

1b. field_coverage map extension.

Where. Wherever the existing field_coverage map is constructed (CRV-2 confirms the construction site and verifies the key convention).
Phase 56 baseline. Map covers Fields 3–5 with keys matching the prompt component filenames (voice / constraints / success per V1).
Phase 57 addition. New entry for Field 6. Key convention: additional_assertions (matching the prompt filename; aligns with Phase 56's filename-to-key convention). CRV-2 verifies the existing keys verbatim — if Phase 56 used numeric keys (field_3 etc.) instead, CR absorbs in-flight as naming-only divergence and uses field_6.

1c. Active-template scaffolding update.

Path. prompts/create_engagement_active.md.
Change. Companion-judgement site that populates operation_data["field_coverage"] is extended to include the Field 6 entry. Insertion point is after the existing Field 5 (success) entry, following the existing ordering convention. CRV-3 verifies the exact insertion point and ordering at Step 0 pre-flight.
Other content unchanged. Phase 56's plain-terms-discipline applies to existing scaffolding; Phase 57 only adds the Field 6 line.

1d. Test exercising new prompt component loading.

Path. tests/test_phase_57_marketing_engagement_creation.py (new test module following the Phase 56 naming pattern).
What it exercises. The load_per_field_components loader successfully loads the new additional_assertions.md component as part of the per-field prompt assembly. Always-run test.
Helper. Uses the existing prompt_assets.py loader API (no loader changes per CRV-4).

1e. (Not anticipated.) Loader extension. Only required if CRV-4 reveals the loader is hardcoded to specific keys. Default expectation per V1: loader handles arbitrary keys; no loader change needed.

Sub-arc 2 — Usage event (live conversation)

Not substrate work; Operator-paced. Documented here for CR completeness.

2a. Operator opens /operator/create-engagement on the running stack (local OL against local engine).
2b. Operator conducts the marketing engagement creation conversation, providing marketing v0.3 content piece-by-piece (some pasted multi-value per V3 evidence; some elicited per V1 enumeration).
2c. Companion produces Discovery markdown at terminal turn (Discovery-record path per P57-D3).
2d. Phase 16 upload + Phase 53 extract_discovery_to_seed_skill + induct_seed cascade runs (CRV-7 confirms signatures at pre-flight; V5 HOLDS at Step 0).
2e. Marketing engagement appears in /operator engagement list with induction pass clean.

Sub-arc 3 — Calibration capture + observation capture

3a. Real-Operator transcript fixture.

Path. tests/fixtures/voice-calibration/real_operator_marvin_<YYYY-MM-DD>.md where date is the literal Step 2 capture date.
Format. Mirrors the three Phase 56 persona fixtures (CRV-5 verifies persona fixture format verbatim — structured format with conversation turns, speaker labels, optional metadata header).
Filename convention. Distinguishes from persona fixtures (persona_*.md) by the real_operator_marvin_ prefix.

3b. Calibration-gated tests.

Path. Extensions to tests/test_phase_57_marketing_engagement_creation.py.
Count. ~1–2 tests exercising the new real-Operator fixture.
Gating. LOOMWORKS_RUN_CALIBRATION=1 environment variable per Phase 56 P56-D7 precedent. Skip in CI; pass locally with env var set. CRV-6 verifies the gating pattern, skipif decorator usage, and helper invocation against tests/test_phase_56_conversational_creation_surface_voice.py + tests/helpers/voice_calibration.py.

3c. Implementation notes document.

Path. docs/phase-impl-notes/phase-57-implementation-notes-v0_1.md.
Contents. Conversation trajectory; comprehension-gap observations (input to loomworks-explain-affordance-investigation-v0_1.md §6.4 candidate selection downstream); V4 POSTURE-GAP friction phrases captured during the live conversation (input to future micro-tuning phase per P57-D10); persona-vs-real-Operator delta notes (input to v0.21 methodology consolidation); any Step 1 substrate refinement made; as-shipped wording of the Field 6 prompt for reproducibility. At v0.2: amendment cycle 1 trajectory captured alongside the original Sub-arc 3c content — second build-mode firing of substrate-friction-discipline-pattern; Sub-arc 4 components as-shipped; any Step 2a refinements made; the standing DUNIN7 principle named in §3 of the halt-surface note (the first naming in a Loomworks document; awaiting v0.21 canonical naming in what-dunin7-is-building).

Sub-arc 4 — OL surface alignment with engine identity contract (new at amendment cycle 1)

Three substantive components plus one new vitest. All OL-side. Engine substrate is correct and untouched. The work resolves the halt-surface finding: the OL signin form's client-side empty-email guard contradicts the engine's WebAuthn discoverable-credential identity contract and the standing DUNIN7 principle that email must not be used for identity.

CR-amendment-time verifications CRV-A1 through CRV-A8 (specified in §10 Step 2a pre-flight) supply exact paths, line numbers, constant locations, and existing test conventions at execution time. Where paths or constants are cited below, CC verifies them live before edits; naming-only divergences absorb in-flight; architectural divergences halt and surface a follow-on amendment-cycle note in docs/phase-impl-notes/.

4a. Signin form empty-email guard removal.

File. IdentifierStep.tsx (halt-surface §2 Finding 2 cites IdentifierStep.tsx:31; CRV-A1 confirms exact path and current line at amendment-execution time — likely under src/components/signin/ or analogous).
Change. Remove the empty-email guard:

``` if (!email.trim()) { setLocalError(SIGNIN.emailEmptyError); return; } ``` Replace with: proceed to submission unconditionally (no email-required gate at the client). The engine accepts the empty-email POST cleanly per halt-surface Finding 1 and runs the WebAuthn discoverable-credential path.

Constant cleanup. SIGNIN.emailEmptyError likely becomes orphaned. CRV-A2 verifies the constant's location and other call-sites at amendment-execution time. If no other call-sites: delete the constant. If orphaned but otherwise harmless: leave with a one-line comment noting Phase 57 amendment cycle 1 removed the sole caller. Recommended: delete.

4b. POST body construction.

File. signin-flow.ts (halt-surface §2 Finding 2 cites signin-flow.ts:42; CRV-A3 confirms exact path and POST body construction line at amendment-execution time).
Change. POST body to /auth/login/begin currently constructed as { email: email.trim() }. Change to omit the email field when empty. Idiomatic TypeScript shape:

```ts const body = email.trim() ? { email: email.trim() } : {}; ``` Exact TypeScript idiom selected at execution time within the existing file's style. Engine accepts {} cleanly per halt-surface Finding 1 — LoginBeginRequest.email: str | None = None, so an absent field and a null field are equivalent under Pydantic.

4c. Field surface text — optionality indication.

File(s). Likely IdentifierStep.tsx (label) plus any helper-text component the form composes (CRV-A4 verifies). The strings probably live in a strings constants module such as SIGNIN.identifierLabel / SIGNIN.identifierPlaceholder / SIGNIN.identifierHelper (exact constants verified at execution time).
Change. Update copy to indicate the field is optional. Recommended shape (plain-terms-discipline per Phase 56's voice principles):
Label: Email (unchanged) or Email (optional) — execution-time pick.
Placeholder: Email (optional) if not already.
Helper text near the field: short, plain. Example: "Leave blank to sign in with any passkey." CC selects final copy at execution time within plain-terms-discipline.
Plain-terms-discipline applies. The helper copy is user-facing; methodology vocabulary stays out. Do NOT write "discoverable credential," "WebAuthn," "passkey hint," or "Companion" in the helper copy. The implementation notes record the as-shipped copy for reproducibility.

4d. Vitest pinning the corrected discoverable-credential path.

Placement. Existing OL vitest convention for signin tests — likely under tests/components/signin/ or analogous (CRV-A5 verifies exact placement and naming convention against current 149-test surface).
Behavior pinned. Empty email submit → localError does NOT get set to emailEmptyError → POST body to /auth/login/begin is {} (or omits the email field equivalently) → mocked /auth/login/begin returns a WebAuthn challenge → form transitions to the passkey step. The test mocks the engine boundary at the fetch / API layer; does not exercise live engine.
Test name shape. Suggested: submits empty email to discoverable-credential path or proceeds to passkey step without requiring email input. CC selects final name at execution time within existing test-naming conventions on the branch.
Count delta. OL vitest 149 → 150.

Unchanged substrate surfaces

Cited verbatim for clarity; CR does not modify these:

prompt.py:817 — dispatcher splice (CRV-1 confirms line at pre-flight).
prompt_assets.py — load_per_field_components loader (CRV-4 confirms arbitrary-key handling).
router.py — terminal-turn matcher token-set.
classifier.py / routing.py — IntentLabel literals (18 per manifest v0.41).
All existing per-field elicitation prompts at prompts/intent_instructions/create_engagement/ (voice.md, constraints.md, success.md).
All existing scaffolding templates (create_engagement_active.md, create_engagement_commit.md, intent_classifier.md) — except for the single field_coverage line addition per 1c.

Engine substrate is unchanged at amendment cycle 1. Sub-arc 4 is OL-only. No engine endpoint, no engine schema, no Memory event, no _ANCHOR_PRIORITY entry, no Alembic migration. SignupBeginRequest, LoginBeginRequest, PersonRow, begin_signup, and the /auth/login/complete lookup-by-credential_id path all stay as halt-surface Finding 1 documented them.

§6 What Phase 57 does NOT deliver

Per scoping v0.2 §What Phase 57 does NOT deliver:

Phase 31 create_project.md plain-terms revision. V7 SURFACED-TO-OPERATOR "constraints" leak in the older creation path. Phase 31 is the Phase-31-path; marketing engagement runs the Phase-55-path; V7 residue isolated. Phase 58+ carry-forward.
§1.3 refactor candidates. Split draft_engagement; raw-Markdown variant of extract_discovery_to_seed_skill. Non-urgent; remain queued.
Voice work on the 22 other voice templates outside the creation flow (6 credit_voice + 14 non-creation Tier-2 + 2 standing instructions). Carry beyond Phase 57.
§1.4 Phase 31 / Phase 53 unification verdict. Phase 58+ clarification-scoping candidate; verdict-able with full evidence after Phase 32 closes.
§6.4 explain affordance (button-mode or audible-mode). Phase 58+ candidate informed by Phase 32 calibration evidence; design space scoped in loomworks-explain-affordance-investigation-v0_1.md.
Option C — Discovery-trajectory + Discovery-record render specialists. Phase 58+ candidate informed by Phase 32 producing the first real Discovery record.
Downstream marketing-engagement substrate. Per P57-D2 — marketing-engagement-specific render specialists, Shaping rules for marketing-shaped artifacts, marketing-engagement-specific assertion types. All Phase 58+.
Posture-awareness pre-tuning at Step 1. Per P57-D10. V4 POSTURE-GAP friction phrases captured during Step 2 only; future micro-tuning phase reads the implementation notes.
Captcha for the public form; threshold-driven Companion autonomy; modify-the-proposal action; multi-Companion cross-checking; real-LLM e2e cadence formalization; Phase 42 reconciler coverage; reactivation in-session chrome; mobile presence; quick-capture substrate; multi-instance fleet groundwork. All carry beyond Phase 57.
Methodology v0.21 consolidation. Pressure compounds (ten phases plus Discovery arc plus investigations); worth scheduling before Phase 60; not a Phase 57 blocker.
Operational hygiene cluster beyond P57-D7 retroactive cleanup: the 7 stale origin/phase-* refs from pre-Phase-55 backfill remain out-of-scope (separate Operator-elective).

Added at amendment cycle 1:

Broader OL surface-vs-contract audit. Per P57-A3 — sign-up, claim-flow, account-recovery, and other identity-adjacent OL surfaces beyond the signin form. Queued as a Phase 58+ candidate (OL surface-vs-contract audit) at loomworks-queued-directions-and-deferred-work-v0_12.md (next version bump from v0.11) at Phase 57 close. The Phase 57 amendment fixes the signin entry point Marvin uses; the broader audit is well-shaped as a dedicated future phase with its own scoping arc and its own Step 0 inspection brief.
what-dunin7-is-building v0.21 absorption. Per amendment scoping note settled item 5 (inheriting halt-surface §5 settled item 5): the standing DUNIN7 principle (email must not be used for identity) is named in the halt-surface §3 for the first-time-in-a-Loomworks-document record; canonical naming in what-dunin7-is-building is downstream v0.21 consolidation work, not Phase 57 scope.

§7 Test strategy

Always-run. +1 engine test exercising the new Field 6 prompt component loading (sub-arc 1d). Path: tests/test_phase_57_marketing_engagement_creation.py.
Calibration-gated. +1–2 engine tests exercising the new real-Operator transcript fixture (sub-arc 3b). Same test module; LOOMWORKS_RUN_CALIBRATION=1 gating.
OL vitest — updated at amendment cycle 1. +1 OL vitest exercising the empty-email discoverable-credential path (sub-arc 4d). Path under tests/components/signin/ or analogous (CRV-A5 verifies). Test behavior: empty email submit → no emailEmptyError set → POST body to /auth/login/begin omits the email field → mocked engine returns a WebAuthn challenge → form transitions to the passkey step. Existing 149 OL vitest stay green. Post-Sub-arc-4 OL count: 150.
No e2e fixture. The Step 2b live usage event is the e2e exercise itself; not a recorded test.

Tests must pass at Checkpoint A (substrate gate, extended at amendment cycle 1 to cover Step 2a OL substrate) and Checkpoint B (final gate). The calibration-gated tests are confirmed to pass locally with LOOMWORKS_RUN_CALIBRATION=1 and confirmed to skip without it before close.

§8 Backwards-compatibility

Existing 2,279 substrate tests stay green through Step 0 / Step 1; existing 2,280 always-run + 32 skipped at amendment-cycle-1 start stay green through Steps 2a–5. No edits to existing prompt files (voice.md / constraints.md / success.md); no edits to the load_per_field_components loader; no edits to the dispatcher splice at prompt.py:817; no schema or migration change. The Field 6 addition is purely additive (new prompt file + new map entry + new active-template line).
Existing 149 OL vitest stay green through Steps 0–2 entry. At amendment cycle 1, sub-arc 4 adds +1 vitest (149 → 150) without modifying any existing vitest. No existing OL component is removed or renamed; the signin form's component shape stays; only the empty-email guard, the POST body construction, the field surface text, and (probably) the SIGNIN.emailEmptyError constant change. Existing imports and call-sites of the signin form continue to work.
Existing 30 skipped tests count adjusts to 31–32 depending on whether 1 or 2 calibration-gated tests land (P56's 4 gated remain; P57 adds 1–2 more).
Alembic head unchanged at 0064. Eighth consecutive phase of typed-MemoryObject-without-migration (Phase 57 adds no MemoryObject subclass, no _ANCHOR_PRIORITY entry, no endpoint). Sub-arc 4 does not touch the engine; backwards-compat at the engine layer is total.
No FORAY surface changes. See §9.
No IntentLabel additions. Creation-flow labels carried from Phase 55/56; no Phase 57 additions.
No router matcher additions. Phase 56's terminal-turn matcher token-set covers the existing creation flow; Phase 57 doesn't change termination logic.

Amendment cycle 1 backwards-compat summary. Existing 149 OL vitest stay green; the new vitest pins the corrected behavior; engine substrate is untouched so all engine backwards-compat carries. The OL signin form remains functionally compatible with previously-registered passkey credentials — narrowing allowCredentials via a supplied email continues to work, and the new empty-email path activates the engine's existing discoverable-credential branch. No data migration, no client-side state migration, no API contract change.

§9 FORAY hooks

No new surfaces. No new MemoryObject subclass; no new _ANCHOR_PRIORITY entry; no new endpoint. Existing FORAY surfaces (Phase 16 upload anchors; Phase 53 discovery_to_seed_extracted anchor at priority "standard"; standard induct_seed anchor) carry the Discovery-record path unchanged.

Amendment cycle 1 touches no Memory event, no _ANCHOR_PRIORITY entry, no engine endpoint, no FORAY hook. The signin path is the WebAuthn flow at the auth boundary; it does not write Memory events of its own. FORAY surfaces are unchanged at v0.2.

§10 Build steps

Six active steps + two reserved buffer slots (one consumed at amendment cycle 1; one remains). Reserved-slot-as-halt-condition-pre-commitment per manifest v0.39 §2; the eighth-consecutive zero-consumption observation projected at v0.1 is superseded — Phase 57 consumed one slot via Sub-arc 4 (Step 2a). Methodology candidate C captures this trajectory (substrate-friction-discipline-pattern-second-build-mode-firing).

Auto-mode posture: Step 0 + Step 1 auto-proceed. Checkpoint A halts before Step 2 and extends at amendment cycle 1 to cover Step 2a completion — Operator confirms substrate (Field 6) AND Sub-arc 4 fix before Step 2b live usage proceeds. Steps 2b–4 are Operator-paced (Step 2b is the live conversation; Steps 3/4 are CC capture). Checkpoint B (final) halts before tagging.

Step 0 — Pre-flight + CR archival + build branch

Status at amendment cycle 1. DONE pre-halt. CR archival path updates from v0_1 to v0_2 at amendment-execution time (CC re-archives the amended CR; preserves v0_1 alongside).

What. Standard pre-flight. CC archives this CR to engine repo at docs/phase-crs/phase-57-cr-marketing-engagement-creation-v0_2.md (preserves phase-57-cr-marketing-engagement-creation-v0_1.md alongside as superseded). Confirms baseline tags, test counts, Alembic head. Creates branch phase-57-marketing-engagement-creation from main on engine and OL repos. (Branch already exists pre-amendment-resume; CC re-archives the CR on the existing branch.)

Pre-flight reads. CR-time deltas — exact strings, file paths, signatures, naming conventions that scoping-time Step 0 didn't enumerate and that the CR drafter could not verify from Claude.ai. CC runs these against the live engine repo. Naming-only divergences absorb in-flight; architectural divergences halt and surface a phase-57-halt-surface-<timestamp>-v0_1.md note in docs/phase-impl-notes/.

CRV-1. Per-field elicitation prompt file shape. Read prompts/intent_instructions/create_engagement/voice.md (or constraints.md or success.md) verbatim. Confirms structural shape Phase 57's additional_assertions.md mirrors. Expected: ~11 lines; plain-terms-discipline applied; one elicitation question per prompt; format aligned with Phase 56 precedent.
CRV-2. field_coverage map key convention. Verify existing keys and their construction site. Expected: keys match prompt component filenames per V1 (so voice, constraints, success — Phase 57 adds additional_assertions). If numeric keys are used instead (field_3/field_4/field_5), Phase 57 uses field_6 per the same convention.
CRV-3. Active-template Companion-judgement site for field_coverage. Locate the site in prompts/create_engagement_active.md where the Companion populates operation_data["field_coverage"]. Phase 56 added entries for Fields 3–5; Phase 57 adds the Field 6 entry at the same construction site, following existing ordering convention (Field 6 entry inserted after the Field 5 entry).
CRV-4. load_per_field_components loader signature and key handling. Read the loader at prompt_assets.py. Confirm it handles arbitrary keys (per V1). Expected: no loader change required. Failure mode: loader is hardcoded to specific keys → Sub-arc 1e activated (loader extension).
CRV-5. Persona fixture format. Read one persona file at tests/fixtures/voice-calibration/persona_*.md. Confirm the format Phase 57's real-Operator transcript fixture mirrors. Expected: structured format with conversation turns; speaker labels; optional metadata header. Format settled by Phase 56 P56-D2.
CRV-6. Calibration-gated test pattern. Read tests/test_phase_56_conversational_creation_surface_voice.py for the four P56 calibration-gated tests. Confirm the LOOMWORKS_RUN_CALIBRATION=1 env-var gating pattern, the skipif decorator usage, and the test-helper invocation at tests/helpers/voice_calibration.py. Phase 57's gated tests mirror this pattern exactly.
CRV-7. Discovery-record path end-to-end function signatures. Read function signatures for the Phase 16 upload entry point, Phase 53 extract_discovery_to_seed_skill, and induct_seed. Confirm path Step 2b exercises is unchanged from Phase 56 close. V5 HOLDS at Step 0; CRV-7 is the drafting-time confirmation.
CRV-8. Refined close protocol invocation pattern. Read docs/voice-principles-v0_1.md and the Phase 56 close session handoff for the explicit-refspec convention promoted at manifest v0.41 §2. Confirm the close commands Phase 57 uses verbatim. P57-D7 Option A retroactive cleanup added as Step 5 actions.

CR archival. Copy this CR file to engine repo docs/phase-crs/phase-57-cr-marketing-engagement-creation-v0_2.md (preserving v0_1 alongside as superseded).

Branch creation. git checkout -b phase-57-marketing-engagement-creation on engine and OL (already in place at amendment-cycle-1 resume).

Mode posture. Auto-proceed.

Acceptance gate. All eight CRV verdicts captured. Branch present on both repos. CR archived (v0_2 alongside v0_1). Baseline tag + test counts + Alembic head confirmed against handoff §2.

Halt threshold. Any CRV produces an architectural divergence (not naming-only) → halt-surface note + Operator-elective amendment cycle in a fresh Claude.ai chat. Baseline divergence (test count off by more than ±2 routine noise; Alembic head different; working tree dirty; tag missing) → halt before any further work.

Time. ~10 min.

Step 1 — Field 6 prompt authoring (sub-arc 1)

Status at amendment cycle 1. DONE pre-halt. Engine substrate at a00f4a3 on the build branch; +1 always-run test added (2,280 always-run total); +1 calibration-gated and +1 additional gated test (32 skipped total) per the halt-surface §6 state-at-halt record.

What. Author additional_assertions.md per 1a. Extend field_coverage map per 1b. Update active-template per 1c. Add +1 test per 1d.

Build.

Create prompts/intent_instructions/create_engagement/additional_assertions.md (~11 lines).
Edit the field_coverage map construction site (per CRV-2/3) to add the additional_assertions entry (or field_6 if numeric convention).
Edit prompts/create_engagement_active.md to add the Field 6 entry to the Companion-judgement site (per CRV-3 insertion point and ordering).
Create tests/test_phase_57_marketing_engagement_creation.py with one always-run test exercising the new prompt component loading.

Tests. +1 always-run.

Mode posture. Auto-proceed.

Acceptance gate. New prompt file present at the specified path with ~11 lines following Phase 56 structural shape. field_coverage map carries the new entry. Active-template Companion-judgement site references Field 6. New test green. Existing 2,279 tests still green. Lint clean.

Halt threshold.

The Field 6 prompt naming convention (CRV-2) reveals a structural divergence from Phase 56's per-field key pattern. (Low probability — V1 enumerated the surface; convention is settled.)
Adding the Field 6 entry to field_coverage requires a loader change beyond the simple extension (CRV-4 failure). (Low probability — V1 confirms the loader handles arbitrary keys.)
Test count divergence from the +1 estimate greater than +3.

Checkpoint A (extended at amendment cycle 1). Originally halted before Step 2 live usage to confirm Field 6 substrate. At amendment cycle 1 the checkpoint extends to also cover Step 2a (Sub-arc 4 fix). Live OL stack readied for Step 2b entry: /operator/create-engagement accessible; banner revision (Phase 56 ChatView.tsx:254) present; Sub-arc 4 fix landed; lint/tsc/build/test clean on OL including the new sign-in vitest at OL count 150.

Time. ~30 min.

Step 2a — OL signin alignment (sub-arc 4 — new at amendment cycle 1)

What. Remove the empty-email guard at the OL signin form (per Sub-arc 4a); omit the email field from the /auth/login/begin POST body when empty (per Sub-arc 4b); update field surface text (label / placeholder / helper) to indicate optionality (per Sub-arc 4c); add one vitest pinning the corrected discoverable-credential path (per Sub-arc 4d). Delete the now-orphan SIGNIN.emailEmptyError constant if no other call-sites remain.

Pre-flight reads. CR-amendment-time verifications CRV-A1 through CRV-A8 per amendment handoff §8. CC runs these against the live OL repo on branch phase-57-marketing-engagement-creation at 2cc0ebc. Naming-only divergences absorb in-flight; architectural divergences halt and surface a follow-on phase-57-halt-surface-<timestamp>-v0_1.md note in engine repo docs/phase-impl-notes/ (the OL repo does not carry impl-notes; engine repo is the methodology home).

CRV-A1. IdentifierStep.tsx exact path and current line numbers. Halt-surface cites IdentifierStep.tsx:31. Verify the file's location in the OL repo's tree (likely under src/components/signin/ or analogous) and confirm the empty-email-guard block's current line range. Path the CR's Sub-arc 4a edit at the verified location.
CRV-A2. SIGNIN.emailEmptyError constant — location and all call-sites. Determine the strings file/module (likely src/strings/signin.ts or analogous). Determine whether removing the sole caller (Sub-arc 4a) orphans the constant. Plan: delete if orphaned, leave with a one-line comment if any other caller remains. Record the decision in implementation notes.
CRV-A3. signin-flow.ts exact path and POST body construction at the cited line. Halt-surface cites signin-flow.ts:42. Verify the current shape of the body construction and any surrounding TypeScript style conventions; specify the new idiomatic conditional body in TypeScript within the existing file's style.
CRV-A4. Field surface text constants. Likely SIGNIN.identifierLabel, SIGNIN.identifierPlaceholder, SIGNIN.identifierHelper (or whatever the exact constants are). Verify the actual constant names and current values. Specify new copy values per Sub-arc 4c within plain-terms-discipline; capture the as-shipped strings in the implementation notes for reproducibility.
CRV-A5. Existing vitest convention for signin tests. Read the existing vitest files under whatever signin-related test folder exists (likely tests/components/signin/ or analogous). Confirm naming convention (file names, describe-block style, test-name style, mock patterns for the /auth/login/begin boundary). The new Sub-arc 4d vitest matches the existing convention.
CRV-A6. /auth/login/begin POST body absent-email engine behavior. Halt-surface Finding 1 establishes this. Re-read the engine LoginBeginRequest schema and the route handler to triple-confirm at the time of execution. Expected verdict: engine accepts email: None cleanly via Pydantic optional default; absent field and null field are equivalent. If verdict shifts, halt and surface.
CRV-A7. Phase 51 marketing form signature. Per P57-A4: verify the public marketing form's submission handler keys off the form-event Memory write, not an email-based auth lookup. Expected verdict: HOLDS (the form is contact intake, not identity). If CONTRADICTED, the amendment scope re-opens — surface to Operator before proceeding with Sub-arc 4.
CRV-A8. Existing OL vitest count baseline. Halt-surface §6 cites 149 OL vitest at OL commit 2cc0ebc. Re-confirm on the OL repo's phase-57-marketing-engagement-creation branch at amendment-execution time. Expected: 149.

Build.

Edit IdentifierStep.tsx at the location CRV-A1 verifies — remove the empty-email guard block (4a).
Edit signin-flow.ts at the location CRV-A3 verifies — change the POST body construction to omit email when empty (4b).
Edit the surface-text constants (likely a strings module per CRV-A4) — update label / placeholder / helper to indicate field optionality (4c).
Delete the SIGNIN.emailEmptyError constant if CRV-A2 confirms no other call-sites; otherwise leave with a one-line comment.
Add one new vitest exercising the empty-email discoverable-credential path under the location CRV-A5 verifies (4d).

Tests. +1 OL vitest. OL vitest count 149 → 150.

Mode posture. Auto-proceed.

Acceptance gate. All four Sub-arc 4 components landed at the verified file locations. The new vitest passes; existing 149 OL vitest still pass; lint/tsc/build clean on OL. OL vitest count 150 (was 149). Implementation notes capture the as-shipped surface-text strings and the SIGNIN.emailEmptyError constant disposition.

Halt threshold.

Any CRV-A verification produces an architectural divergence (not naming-only) — e.g., the strings file is structured differently than expected; LoginBeginRequest has shifted shape since the halt-surface diagnostic; the Phase 51 marketing form submission handler keys off email-as-identity. → halt and surface a follow-on phase-57-halt-surface-<timestamp>-v0_1.md note.
Any of the four Sub-arc 4 components (4a/4b/4c/4d) surfaces unexpected drift from CR specification.
OL vitest count diverges beyond ±1 from the predicted 150.
IdentifierStep.tsx or signin-flow.ts already changed since halt-surface diagnostic time (the OL branch may have been edited between halt-surface filing and amendment-execution resumption). CC re-reads the halt-surface findings against current branch state; if findings still HOLD, proceed; if findings have shifted, surface to Operator before proceeding.

Checkpoint A extends. Operator confirms Sub-arc 4 fix before Step 2b live usage proceeds. Gate 5 + new Gate 5b together cover the extended Checkpoint A acceptance condition.

Time. ~30 min.

Step 2b — Live usage event (sub-arc 2; was Step 2 in v0.1)

What. Operator runs the marketing engagement creation. CC ensures local stack ready, observes the conversation, captures the live conversation log for fixture creation at Step 3.

Build (Operator-paced).

2a. Operator opens /operator/create-engagement on the running stack (local OL against local engine). With the Sub-arc 4 fix landed, the redirect to /signin accepts an empty-email submission and proceeds to the WebAuthn discoverable-credential flow; the browser presents the registered passkey; /auth/login/complete resolves identity by credential_id; the Operator is signed in.
2b. Operator conducts the conversation, providing marketing v0.3 content piece-by-piece.
2c. Companion produces Discovery markdown at terminal turn (Discovery-record path per P57-D3).
2d. Phase 16 upload + Phase 53 extract_discovery_to_seed_skill + induct_seed cascade runs.
2e. Marketing engagement appears in /operator engagement list with induction pass clean.

Tests. 0 new (the live event is the exercise).

Mode posture. Operator-paced.

Acceptance gate. Marketing engagement live in the local engine database. Engagement appears in /operator engagement list. Discovery record visible in Memory. Candidate seed produced. Induction pass clean. Marketing v0.3 content (Fields 1–6 with eight Field-6 entries) fully reflected in the inducted seed.

Halt threshold.

Signin still fails despite Sub-arc 4. (Would indicate a deeper engine-side issue the halt-surface diagnostic missed; halt and re-diagnose. Low probability — halt-surface Finding 1 established the engine's discoverable-credential path is supported and accepts empty-email POST bodies.)
Operator's live conversation surfaces friction the Field 6 prompt can't resolve (e.g., Companion doesn't elicit Field 6 despite the prompt being present and field_coverage correctly populated). Halt for diagnosis; Step 1 substrate may need amendment.
Discovery-record terminal-turn cascade fails (Phase 16 upload error; Phase 53 extract error; induct_seed error). V5 HOLDS at Step 0, so this is low probability — but Step 2b is the live exercise; halt and diagnose if it fails.
Marketing v0.3 content reveals a Field-mapping mismatch V6 didn't catch (e.g., a Field 6 entry whose semantic shape doesn't fit dict[str, str] cleanly — e.g., a key collision between two entries with the same Label).

Time. ~30–60 min wall time (depends on Operator pace).

Step 3 — Calibration capture (sub-arcs 3a + 3b)

What. CC files the real-Operator transcript fixture. Adds calibration-gated tests. Runs the gated tests with LOOMWORKS_RUN_CALIBRATION=1 to confirm they pass; confirms they skip without the env var.

Build.

Create tests/fixtures/voice-calibration/real_operator_marvin_<YYYY-MM-DD>.md with the Step 2b conversation captured per Phase 56 persona fixture format (CRV-5).
Add ~1–2 calibration-gated tests to tests/test_phase_57_marketing_engagement_creation.py exercising the new fixture. Pattern mirrors CRV-6 evidence: LOOMWORKS_RUN_CALIBRATION=1 skipif decorator; helper invocation at tests/helpers/voice_calibration.py.
Run gated tests with env var set → confirm pass.
Run gated tests without env var → confirm skip.

Tests. +1–2 calibration-gated.

Mode posture. Auto-proceed.

Acceptance gate. Fixture file present at the dated path; format mirrors persona fixtures. Gated tests green with LOOMWORKS_RUN_CALIBRATION=1. Gated tests skip in CI default mode. Total skipped count adjusts from 30 to 31–32.

Halt threshold. Real-Operator transcript capture reveals a format incompatibility with Phase 56's persona fixture format (CRV-5 failure). Halt for diagnosis.

Time. ~20 min.

Step 4 — Observation capture (sub-arc 3c)

What. CC files docs/phase-impl-notes/phase-57-implementation-notes-v0_1.md capturing trajectory, comprehension gaps, V4 friction phrases, persona-vs-real-Operator deltas, and amendment-cycle-1 observations.

Build.

Create docs/phase-impl-notes/phase-57-implementation-notes-v0_1.md.
Sections: conversation trajectory; comprehension-gap observations; V4 POSTURE-GAP friction phrases captured during Step 2b; persona-vs-real-Operator delta notes; as-shipped wording of the Field 6 prompt (for reproducibility); any Step 1 substrate refinement made; methodology candidates carry-forward (first usage-event phase pattern; real-Operator-evidence-and-persona-projection-contrast pattern; surface-as-product event pattern; pre-drafted-content posture vs blank-page Operator posture; post-tag-docs-on-main pattern; silent Option-A application).
At v0.2: additional amendment-cycle-1 sections — Sub-arc 4 as-shipped surface (file paths, line ranges, exact strings for the new helper copy, SIGNIN.emailEmptyError disposition); Sub-arc 4 vitest as-shipped (path, test name, mocked boundaries); the second build-mode firing of substrate-friction-discipline-pattern (methodology candidate C); the halt-surface trajectory (Position 1 → Position 4); the standing DUNIN7 principle naming as the first-time-in-a-Loomworks-document record per halt-surface §3.

Tests. 0 new.

Mode posture. Auto-proceed.

Acceptance gate. Document present at the specified path. All required sections populated, including amendment-cycle-1 sections. Carry-forward methodology candidates named (six from v0.1 + three new at v0.2: candidate A, candidate B, candidate C).

Halt threshold. None expected.

Time. ~15–20 min.

Step 5 — Close

What. Apply refined close protocol with explicit refspecs per manifest v0.41 §2. Tag phase-57-marketing-engagement-creation on both repos (annotated). Apply P57-D7 Option A retroactive cleanup: delete phase-56-step-0 locally; delete phase-57-step-0 locally after merging Step 0 findings into the build branch context.

Build (refined close protocol, both repos where applicable). See §17 for the full command sequence. Summary:

Fast-forward main to phase-57-marketing-engagement-creation head.
Push main to origin via git push origin refs/heads/main.
Delete local build branch: git branch -d phase-57-marketing-engagement-creation.
Delete remote build branch: git push origin :refs/heads/phase-57-marketing-engagement-creation (only if pushed during build).
Prune remote-tracking refs: git remote prune origin.
Verify Step 0 findings file present on main at docs/phase-impl-notes/phase-57-step-0-findings-v0_1.md. Then apply P57-D7 Option A:

Delete phase-56-step-0 locally: git branch -D phase-56-step-0 (force; never pushed).
Delete phase-57-step-0 locally: git branch -D phase-57-step-0 (force; never pushed).

Annotate-tag: git tag -a phase-57-marketing-engagement-creation -m "Phase 57 close: marketing engagement creation" on both engine and OL repos.
Push tags via explicit refspecs: git push origin refs/tags/phase-57-marketing-engagement-creation (separate invocation per repo).
Verify tag landed: git ls-remote origin 'refs/tags/phase-57-marketing-engagement-creation' (separate invocation per repo).

Tests. 0 new. Final test sweep confirms all tests still green before Checkpoint B halt.

Mode posture. Auto-proceed through close-protocol mechanics; Checkpoint B halts before tagging. Operator final-confirms before tags land.

Acceptance gate. All Step 1 / Step 2a / Step 2b / Step 3 / Step 4 acceptance gates green. Working tree clean on main for both repos. Tags landed and verified on origin. phase-56-step-0 and phase-57-step-0 branches deleted locally (per P57-D7 Option A). Refined close protocol fired correctly via explicit refspecs.

Halt threshold.

Test-count divergence from estimates greater than 50% (smaller absolute count makes the percentage more sensitive; tighter tolerance than larger phases).
Refined close protocol command sequence produces unexpected errors.
Working tree dirty unexpectedly.

Time. ~15 min.

Step 6 — Reserved buffer (consumed at amendment cycle 1)

(reserved — consumed by Sub-arc 4 work / Step 2a per P57-A10)

Phase 57's two reserved buffer slots: Step 6 consumed at amendment cycle 1 by the Sub-arc 4 budget; Step 7 remains available. Not literally a position in the build sequence — the consumption is at the budget layer; Step 2a sits earlier in the sequence chronologically. First consumed reserved slot since Phase 49 Step 4 (the canonical instance of substrate-friction-discipline-pattern); eight consecutive zero-consumption phases (50/51/52/53/54/55/56 + Phase 57 pre-halt) ended at this amendment. Per manifest v0.41 §1's observation that the no-mid-build-amendment pattern is "structural rather than coincidental," the consumption is now logged as the design intent firing correctly — slots exist to absorb mid-build amendment without derailing the phase. Methodology candidate C captures the cadence (seven-and-then-one-consumed-by-design).

Step 7 — Reserved buffer (remaining)

(reserved — buffer for any further mid-build amendment arising from steps 2b–5)

One reserved buffer slot remains, available if Steps 2b–5 surface a second halt-and-amend cycle. None anticipated. Reserved-not-skipped principle preserved; the slot's value is its presence, not its consumption.

§11 Halt conditions

Per friction-discipline-pattern-family mid-build boundary. CC halts and writes a phase-57-halt-surface-<timestamp>-v0_1.md note in engine repo docs/phase-impl-notes/ on any of:

Step 0. Any CRV produces an architectural divergence (not naming-only). Baseline divergence on test count / Alembic head / working tree / tag missing.
Step 1. Field 6 prompt naming convention (CRV-2) reveals a structural divergence from Phase 56's per-field key pattern. (Low probability.) Adding the Field 6 entry to field_coverage map requires a loader change beyond simple extension. (Low probability — V1 confirms loader handles arbitrary keys.)
Step 2a (new at amendment cycle 1). Any CRV-A verification produces an architectural divergence (not naming-only) — e.g., the strings file is structured differently than expected; LoginBeginRequest has shifted shape since the halt-surface diagnostic; the Phase 51 marketing form submission handler keys off email-as-identity (CRV-A7 CONTRADICTED, scope re-opens). Any Sub-arc 4 component (4a/4b/4c/4d) surfaces unexpected drift from CR specification. OL vitest count diverges beyond ±1 from the predicted 150. IdentifierStep.tsx or signin-flow.ts already changed since halt-surface diagnostic time in a way that invalidates the findings.
Step 2b. Signin still fails despite Sub-arc 4 (would indicate a deeper engine-side issue the halt-surface diagnostic missed; halt and re-diagnose). Operator's live conversation surfaces friction the Field 6 prompt can't resolve. Discovery-record terminal-turn cascade fails. Marketing v0.3 content reveals a Field-mapping mismatch V6 didn't catch.
Step 3. Real-Operator transcript capture reveals a format incompatibility with Phase 56's persona fixture format (CRV-5 failure).
Any step. Test-count divergence from estimates greater than 50%.

Mid-build amendment scoping runs in a separate Claude.ai chat per the standard pattern (substrate-friction-discipline-pattern from manifest v0.39 §2 — note-first; Operator-elective amendment cycle). Amendment cycle 1 is the active instance at v0.2; further amendment cycles would consume the remaining reserved slot (Step 7) if needed.

§12 Acceptance gates

Eighteen items per scoping v0.2 §Acceptance gates plus amendment-cycle-1 amendments per P57-A8 (Gate 5 amended; new Gate 5b inserted; subsequent gates renumbered with +1 offset from old 6→7 onwards).

| # | Gate | Where verified | |---|------|---------------| | 1 | Step 0 findings absorbed; v0.2 produced; CR drafting handoff filed (already met by this CR's existence); amendment scoping note absorbed (already met by this CR's existence at v0.2). | Pre-existing | | 2 | Field 6 per-field elicitation prompt component landed at prompts/intent_instructions/create_engagement/additional_assertions.md (or final filename per CRV resolution); +1 test green. (Satisfied pre-amendment-resume at engine a00f4a3.) | Step 1 | | 3 | field_coverage map extended to include the Field 6 entry; dispatcher splice route exercised. (Satisfied pre-amendment-resume.) | Step 1 | | 4 | Active-template scaffolding at prompts/create_engagement_active.md updated for Field 6 elicitation; existing tests still green. (Satisfied pre-amendment-resume.) | Step 1 | | 5 | (Amended at amendment cycle 1.) Live OL stack ready at Step 2 entry: /operator/create-engagement accessible; banner revision present; Sub-arc 4 fix landed (see Gate 5b); lint/tsc/build/test clean on OL including the new sign-in vitest at OL count 150. | Checkpoint A (extended) | | 5b | (New at amendment cycle 1.) OL signin surface accepts empty email and proceeds to the WebAuthn discoverable-credential path. IdentifierStep.tsx empty-email guard removed; signin-flow.ts POST body omits the email field when empty; field label / placeholder / helper text indicate optionality (plain-terms-discipline, no methodology vocabulary in user-facing copy); SIGNIN.emailEmptyError constant deleted or orphaned-but-harmless per CRV-A2 resolution; new vitest pins the corrected behavior at the OL count-150 boundary. | Step 2a | | 7 | Marketing engagement created live in the local engine database via /operator/create-engagement. Engagement appears in /operator engagement list. (Was Gate 6 in v0.1; renumbered +1.) | Step 2b | | 8 | Discovery record produced and uploaded via Phase 16 pipeline; visible in Memory. (Was Gate 7 in v0.1.) | Step 2b | | 9 | Phase 53 extract_discovery_to_seed_skill produced a candidate seed against the Discovery record. (Was Gate 8 in v0.1.) | Step 2b | | 10 | induct_seed produced an induction-pass-clean Status on the marketing engagement. (Was Gate 9 in v0.1.) | Step 2b | | 11 | Marketing v0.3 content (Fields 1–6 with eight Field-6 entries) fully reflected in the inducted seed. (Was Gate 10 in v0.1.) | Step 2b | | 12 | Real-Operator transcript captured as tests/fixtures/voice-calibration/real_operator_marvin_<date>.md. Distinguished from persona fixtures by filename. (Was Gate 11 in v0.1.) | Step 3 | | 13 | ~1–2 calibration-gated tests added exercising the new fixture; gates green with LOOMWORKS_RUN_CALIBRATION=1; skip in CI by default. (Was Gate 12 in v0.1.) | Step 3 | | 14 | Phase 57 implementation notes document filed at docs/phase-impl-notes/phase-57-implementation-notes-v0_1.md carrying trajectory, comprehension-gap observations, V4 POSTURE-GAP friction phrases, persona-vs-real-Operator deltas, and amendment-cycle-1 observations (Sub-arc 4 as-shipped surface; methodology candidates A + B + C; standing-principle first-time-in-Loomworks-document record). (Was Gate 13 in v0.1.) | Step 4 | | 15 | Engine test count within v0.2 estimate (~2,280 always-run + 31–32 skipped); OL vitest count 150; lint/tsc/build clean on OL; Alembic head unchanged at 0064. (Was Gate 14 in v0.1; OL count updated at amendment cycle 1.) | Checkpoint B | | 16 | P57-D7 Option A retroactive cleanup applied: phase-56-step-0 deleted locally; phase-57-step-0 deleted locally (after findings merged forward). (Was Gate 15 in v0.1.) | Step 5 | | 17 | Refined close protocol firing on both repos via explicit refspecs (refs/heads/..., refs/tags/...). (Was Gate 16 in v0.1.) | Step 5 | | 18 | Tags phase-57-marketing-engagement-creation landed on both engine and OL repos; pushed; verified via git ls-remote origin 'refs/tags/...'. (Was Gate 17 in v0.1.) | Step 5 / Checkpoint B |

Total: 18 items (was 17 at v0.1). Gate 5b inserted between Gate 5 and old Gate 6 (now Gate 7) per the handoff §7.2 explicit instruction.

§13 Post-CR state

After Phase 57 close:

Engine repo. Tag phase-57-marketing-engagement-creation at the post-Step-4 engine commit. Substrate: 2,280 always-run tests + 31–32 skipped; Alembic 0064 unchanged. New prompt file at prompts/intent_instructions/create_engagement/additional_assertions.md. New test module at tests/test_phase_57_marketing_engagement_creation.py. New fixture at tests/fixtures/voice-calibration/real_operator_marvin_<YYYY-MM-DD>.md. New implementation notes at docs/phase-impl-notes/phase-57-implementation-notes-v0_1.md. Halt-surface note at docs/phase-impl-notes/phase-57-halt-surface-2026-05-12-v0_1.md. Existing surfaces at prompts/create_engagement_active.md, the field_coverage map site, and prompt_assets.py / prompt.py:817 unchanged in shape, with the single Field 6 entry added. phase-56-step-0 and phase-57-step-0 deleted locally.

Operator Layer repo (updated at amendment cycle 1). Tag phase-57-marketing-engagement-creation at the post-Step-2a OL commit. 150 vitest (was 149 at v0.1; +1 from Sub-arc 4d); 11 prerendered routes unchanged. Sub-arc 4 surface changes landed: IdentifierStep.tsx empty-email guard removed; signin-flow.ts POST body construction conditioned on email presence; field surface text (label / placeholder / helper) indicates optionality; SIGNIN.emailEmptyError constant deleted (or orphaned-but-harmless per CRV-A2 disposition); new vitest under tests/components/signin/ (or analogous per CRV-A5) pins the corrected discoverable-credential path. (v0.1 said "no OL changes in this phase; 149 vitest unchanged" — corrected at amendment cycle 1 per the discovery-record bookkeeping note in §4; the amendment handoff §7.2 instructed §13 as "Unchanged" but strict preservation produced an inaccuracy that the one-bullet fix resolves.)

Marketing site repo. Untouched.

Database. Marketing engagement exists as a row in the engagements table under DUNIN7, sibling to the Loomworks engagement. Discovery record stored in Memory. Candidate seed produced and inducted. Status reflects induction-pass-clean.

Methodology. Nine methodology candidates carried forward to v0.42 manifest absorption and v0.21 consolidation: first usage-event phase pattern; real-Operator-evidence-and-persona-projection-contrast pattern; surface-as-product event pattern; pre-drafted-content posture vs blank-page Operator posture; post-tag-docs-on-main pattern; silent Option-A application (Step 0 branch lifecycle refinement); candidate A engine-correct-surface-drifted (new at amendment cycle 1); candidate B standing-principle-not-named-in-source-of-truth-documents-allows-contradicting-surface-to-ship (new at amendment cycle 1; remediation: name email-not-identity in what-dunin7-is-building at v0.21); candidate C substrate-friction-discipline-pattern-second-build-mode-firing (new at amendment cycle 1; two-instance evidence).

Phase 58 first-line candidates. §6.4 explain affordance (button-mode) informed by Phase 57 comprehension-gap observations; future micro-tuning phase for V4 POSTURE-GAP friction phrases captured at Step 2b; marketing-engagement substrate (render specialists, Shaping rules for marketing-shaped artifacts); OL surface-vs-contract audit (new at amendment cycle 1; per P57-A3 / queued direction added at Phase 57 close).

§14 Carry-forward

Per scoping v0.2 §Carry-forward inventory:

Out-of-scope (carry beyond Phase 57):

Voice work on the 22 other voice templates outside the creation flow.
§1.4 Phase 31 / Phase 53 unification verdict.
§6.4 explain affordance (button-mode + audible-mode).
Option C — Discovery-trajectory + Discovery-record render specialists.
Mobile presence + quick-capture (voice-modality substrate).
Multi-instance fleet groundwork.
Captcha for the public form.
Threshold-driven Companion autonomy.
Modify-the-proposal action.
Multi-Companion-instance cross-checking.
Real-LLM e2e cadence formalization.
Phase 42 reconciler coverage.
Reactivation in-session chrome.
Methodology v0.21 consolidation.
§1.3 refactor candidates (split draft_engagement; raw-Markdown variant of extract_discovery_to_seed_skill).
Phase 31 create_project.md plain-terms revision.
The 7 stale origin/phase-* refs from pre-Phase-55 backfill (out-of-scope cleanup; separate Operator-elective).
instruction-refinement-during-absorption minor candidate.
P57-D9 marketing engagement first Companion model identity (flag for Phase 58+ at first-rendered-output cost surface).
Posture-awareness pre-tuning (per P57-D10; informed by Phase 57 Step 2b evidence).

Newly enabled by Phase 57:

First real Discovery record exists in Memory — Discovery-record render specialist work (Option C) now has a concrete reference.
First real-Operator calibration fixture exists — persona-vs-real-Operator delta methodology comparison can begin.
Marketing engagement substrate work (Phase 58+) — render specialists for marketing content; Shaping rules for marketing-shaped artifacts; marketing-engagement-specific assertion types.

Added at amendment cycle 1:

Three methodology candidates per P57-A9, all carrying to v0.42 manifest absorption and v0.21 methodology consolidation:
Candidate A — engine-correct-surface-drifted. Single-instance evidence at the Phase 57 halt-surface. Generalization: surface implementations can drift from their underlying contract; the drift surfaces at first real usage; the audit needs a trigger.
Candidate B — standing-principle-not-named-in-source-of-truth-documents-allows-contradicting-surface-to-ship. Single-instance evidence at the Phase 57 halt-surface. Remediation: name the email-not-identity principle in what-dunin7-is-building at v0.21. This amendment does not perform the remediation; v0.21 consolidation does.
Candidate C — substrate-friction-discipline-pattern-second-build-mode-firing. Two-instance evidence (Phase 49 Step 4 + Phase 57 Step 2). Pattern shape reliable; carries as the standard mid-build resolution shape.
One new queued direction per P57-A3: OL surface-vs-contract audit — a Phase 58+ candidate phase reading every OL surface that touches identity, contact, or any other engine-side data contract; verifying each surface against the engine contract; correcting any drift surfaced. Filed for inclusion in loomworks-queued-directions-and-deferred-work-v0_12.md (next version bump from v0.11) at Phase 57 close. Phase 57 amendment candidates A + B feed the eventual phase's scoping.

§15 Kickoff prompt — paste-ready for CC (resuming at amendment cycle 1)


Resume Phase 57 build at amendment cycle 1 per CR-2026-090 v0.2
(phase-57-cr-marketing-engagement-creation-v0_2.md). v0.1 is
superseded; both are archived at engine repo docs/phase-crs/.

Baseline confirmation at amendment-cycle-1 start (post-halt, pre-resume):
- Engine repo /Users/dunin7/loomworks-engine on branch
  phase-57-marketing-engagement-creation at commit a00f4a3.
  Tests: 2,280 always-run + 32 skipped (+1 always-run / +2 calibration-gated
  added at Step 1 vs the Phase 56 baseline 2,279 / 30).
  Alembic head 0064 unchanged. Working tree clean.
  Halt-surface note present at
  docs/phase-impl-notes/phase-57-halt-surface-2026-05-12-v0_1.md.
  Step 0 findings present at
  docs/phase-impl-notes/phase-57-step-0-findings-v0_1.md.
  Step 1 substrate present at
  prompts/intent_instructions/create_engagement/additional_assertions.md.
  phase-57-step-0 branch at 69adb17 (unmerged; for P57-D7 retroactive cleanup
  at Step 5). phase-56-step-0 branch exists locally (never pushed;
  scheduled for P57-D7 Option A retroactive cleanup at Step 5).
- Operator Layer repo /Users/dunin7/loomworks on branch
  phase-57-marketing-engagement-creation at commit 2cc0ebc
  (= Phase 56 commit; no Phase 57 changes yet — Step 2a changes this).
  149 vitest passed; 11 prerendered routes; lint/tsc/build clean.
- Local stack ready (engine API up on :8000, /healthz 200, CORS resolved
  via LOOMWORKS_ENV=development in local .env; OL dev server up on :3001;
  Marvin's Person row + passkey credential present in dev DB).

Per CR §10 Step 0: re-archive this CR (v0.2) to engine repo
docs/phase-crs/phase-57-cr-marketing-engagement-creation-v0_2.md
(preserving v0_1 alongside as superseded). CRV-1 through CRV-8 ran
pre-halt at Step 0 of the original build cycle; their verdicts hold.

Per CR §10 Step 2a (new at amendment cycle 1): run CRV-A1 through
CRV-A8 as Step 2a pre-flight reads against the live OL repo on
branch phase-57-marketing-engagement-creation at 2cc0ebc.
Naming-only divergences absorb in-flight; architectural divergences
halt and surface a follow-on phase-57-halt-surface-<timestamp>-v0_1.md
note in engine repo docs/phase-impl-notes/.

Per CR §10: six active build steps (Step 0 + Step 1 done pre-halt;
Step 2a is the resumption point at amendment cycle 1; Step 2b
follows the live signin fix; Steps 3–5 unchanged from v0.1) + two
reserved buffer slots (Step 6 consumed at amendment cycle 1 by
Sub-arc 4 work; Step 7 remains available if Steps 2b–5 surface
a second halt-and-amend cycle).

Per CR §10: auto-mode posture — Step 2a auto-proceeds; Checkpoint A
extends to cover Step 2a (Operator confirms Sub-arc 4 fix before
Step 2b proceeds); Steps 2b–4 are Operator-paced (Step 2b is the
live conversation; Steps 3/4 are CC capture); Checkpoint B (final)
halts before tagging.

Per CR §3 + §3.A: ten construction decisions P57-D1 through P57-D10
plus ten amendment-cycle-1 decisions P57-A1 through P57-A10 are
settled. CC executes against them; does not re-decide.

Per CR §11: halt-and-surface is preferred to draft-and-hope. Halt
thresholds at amendment cycle 1: CRV-A architectural divergence at
Step 2a; any Sub-arc 4 component (4a/4b/4c/4d) surfaces unexpected
drift; OL vitest count diverges beyond ±1 from 150; IdentifierStep.tsx
or signin-flow.ts already changed since halt-surface diagnostic time;
CRV-A7 CONTRADICTED (Phase 51 marketing form keys off email-as-identity,
which would re-open amendment scope); signin still fails despite
Sub-arc 4 at Step 2b (would indicate deeper engine-side issue);
Operator's live conversation surfaces friction the Field 6 prompt
can't resolve; Discovery-record terminal-turn cascade fails; marketing
v0.3 content reveals a Field-mapping mismatch; persona fixture format
incompatibility at Step 3; test-count divergence greater than 50%.

Per CR §17: refined close protocol with explicit refspecs (manifest
v0.41 §2). P57-D7 Option A retroactive cleanup applied at Step 5
(delete phase-56-step-0 + phase-57-step-0 locally after findings
merged forward).

Tag name: phase-57-marketing-engagement-creation. Annotated. Lands
on both engine and OL repos at Checkpoint B (final).

Begin at Step 2a (Sub-arc 4 OL signin alignment). CRV-A1 through
CRV-A8 first, then the four Sub-arc 4 components (4a/4b/4c/4d),
then await Operator confirmation at the extended Checkpoint A
before Step 2b live usage.

§16 Test count predictions

| Surface | Pre-Phase-57 | Phase-57 delta (v0.1) | Phase-57 delta (v0.2 amendment) | Post-Phase-57 | |---------|-------------|----------------------|--------------------------------|--------------| | Engine always-run | 2,279 | +1 | 0 | ~2,280 | | Engine skipped (calibration-gated) | 30 (= 26 pre-P56 + 4 P56-gated) | +1 to +2 | 0 | 31–32 | | OL vitest | 149 | 0 | +1 (Sub-arc 4d) | 150 | | Alembic migration head | 0064 | 0 | 0 | 0064 | | Prerendered OL routes | 11 | 0 | 0 | 11 |

Existing 2,279 substrate tests stay green throughout build. Calibration-gated tests pass with LOOMWORKS_RUN_CALIBRATION=1; skip in CI by default per P56-D7 precedent. Amendment cycle 1 adds +1 OL vitest exercising the empty-email discoverable-credential path; all 149 existing OL vitest stay green.

§17 Refined close protocol script

Aligned with Phase 56 CR-2026-080 v0.2 §3.1 close-protocol refinement and manifest v0.41 §2 named principle (explicit refspecs). Executed at Step 5 by CC; Checkpoint B halts before tag-push for Operator final confirmation. Unchanged at amendment cycle 1 — the close-protocol commands are step-5 work; they do not depend on Sub-arc 4 specifics.

Engine repo close


cd /Users/dunin7/loomworks-engine

# 1. Confirm Step 0 findings present on main before Step 0 branch deletion
test -f docs/phase-impl-notes/phase-57-step-0-findings-v0_1.md \
  && echo "Step 0 findings present on main" \
  || { echo "ERROR: Step 0 findings missing"; exit 1; }

# 2. Confirm build branch is up-to-date with main (assuming build commits
#    were made directly on main, or were merged forward)
git status
git log --oneline -5

# 3. Confirm tests green at close
.venv/bin/pytest -q
# Expected: ~2,280 passed, 31-32 skipped

# 4. Confirm working tree clean
git status --porcelain
# Expected: empty

# 5. Push main to origin via explicit refspec
git push origin refs/heads/main

# 6. Delete local build branch (if it exists as a separate branch)
git branch | grep phase-57-marketing-engagement-creation \
  && git branch -d phase-57-marketing-engagement-creation \
  || echo "Build branch already merged or not separate"

# 7. Delete remote build branch via explicit refspec (only if pushed during build)
git ls-remote origin 'refs/heads/phase-57-marketing-engagement-creation' \
  && git push origin :refs/heads/phase-57-marketing-engagement-creation \
  || echo "Build branch not on origin; skip remote delete"

# 8. Prune remote-tracking refs
git remote prune origin

# 9. P57-D7 Option A retroactive cleanup
git branch -D phase-56-step-0
git branch -D phase-57-step-0

# 10. [CHECKPOINT B HALT — Operator final-confirms before tags land]

# 11. Create annotated tag
git tag -a phase-57-marketing-engagement-creation \
  -m "Phase 57 close: marketing engagement creation"

# 12. Push tag via explicit refspec
git push origin refs/tags/phase-57-marketing-engagement-creation

# 13. Verify tag landed on origin
git ls-remote origin 'refs/tags/phase-57-marketing-engagement-creation'

Operator Layer repo close


cd /Users/dunin7/loomworks

# 1. Confirm working tree clean (Sub-arc 4 changes already committed)
git status --porcelain
# Expected: empty

# 2. Confirm tests green
npm test -- --run
# Expected: 150 vitest passed (was 149 pre-amendment-cycle-1; +1 from Sub-arc 4d)
npm run lint
npm run tsc
npm run build
# Expected: all clean

# 3. Push main to origin via explicit refspec
git push origin refs/heads/main

# 4. [CHECKPOINT B HALT — Operator final-confirms before tags land]

# 5. Create annotated tag at the post-Step-2a OL commit
git tag -a phase-57-marketing-engagement-creation \
  -m "Phase 57 close: marketing engagement creation"

# 6. Push tag via explicit refspec
git push origin refs/tags/phase-57-marketing-engagement-creation

# 7. Verify tag landed on origin
git ls-remote origin 'refs/tags/phase-57-marketing-engagement-creation'

Explicit-refspec convention reminders (per manifest v0.41 §2)

git push origin refs/heads/<branch> — not git push origin <branch>.
git push origin :refs/heads/<branch> — not git push origin --delete <branch>.
git push origin refs/tags/<tag> — not git push origin <tag>.
git ls-remote origin 'refs/heads/<name>' and git ls-remote origin 'refs/tags/<name>' — separate invocations.

The convention prevents the error: src refspec ... matches more than one failure mode that Phase 56 encountered and resolved in-session.

DUNIN7 — Done In Seven LLC — Miami, Florida Loomworks Phase 57 CR — Marketing Engagement Creation — v0.2 — 2026-05-12