@mmerterden/multi-agent-pipeline 18.0.0 → 19.1.0

package/pipeline/multi-agent-refs/analysis/locked.md

@@ -1,25 +1,52 @@
-# Locked decisions (37)
+# Locked decisions (36)
 
-> The 37 Locked decisions of the analysis flow. Loaded by `/multi-agent:analysis`, by `/multi-agent:analysis-resolve` (which inherits them) and by pipeline Phase 1 when it runs the analysis engine. Numbering is canonical: cite as `Locked <n> (<short label>)`.
+> The 36 Locked decisions of the analysis flow. Loaded by `/multi-agent:analysis`, by `/multi-agent:analysis-resolve` (which inherits them) and by pipeline Phase 1 when it runs the analysis engine. Numbering is canonical: cite as `Locked <n> (<short label>)`.
 
 ### Index by category (v9.1.0+)
 
-Browse-friendly grouping of the 37 Locked decisions. Numbering stays canonical (matches the list below); the index is read-only navigation.
+Browse-friendly grouping of the 36 Locked decisions. Numbering stays canonical (matches the list below); the index is read-only navigation.
 
 | Category | Decisions | Concern |
 |---|---|---|
-| **A. Governance** | 1, 5, 6, 7, 10, 26, 27, 32, 36 | Run-level process rules: one feature per run, default output, auto-commit ban, punctuation policy, output picker timing, Pass B preview, evidence digest cache, analysis profile, document reviewed before publish |
-| **B. Citation and Evidence** | 3, 4, 8, 11, 24, 30, 34 | Every fact in the doc traces back to a source: citation discipline, forward-looking spec, standards binding, repo-evidence reuse-first, Pass B footnote mandatory, analysis self-contained (pipeline-wide), references built from the evidence record |
-| **C. Output Format and Structure** | 2, 9, 13, 14, 16, 17, 20, 21, 25, 33, 35, 37 | How the document is laid out: section omission rule, per-platform output split, Gherkin user stories, Goals + Non-Goals paired, Files-to-Add tag, API response variants exhaustive, localization mode (ownership-aware), References at the bottom, Lite mode, corporate backbone always renders, stack-optional render, redesign records v1 before planning v2 |
+| **A. Governance** | 1, 5, 6, 7, 10, 25, 26, 31, 35 | Run-level process rules: one feature per run, default output, auto-commit ban, punctuation policy, output picker timing, Pass B preview, evidence digest cache, analysis profile, document reviewed before publish |
+| **B. Citation and Evidence** | 3, 4, 8, 11, 24, 29, 33 | Every fact in the doc traces back to a source: citation discipline, forward-looking spec, standards binding, repo-evidence reuse-first, Pass B footnote mandatory, analysis self-contained (pipeline-wide), references built from the evidence record |
+| **C. Output Format and Structure** | 2, 9, 13, 14, 16, 17, 20, 21, 32, 34, 36 | How the document is laid out: section omission rule, per-platform output split, Gherkin user stories, Goals + Non-Goals paired, Files-to-Add tag, API response variants exhaustive, localization mode (ownership-aware), References at the bottom, corporate backbone always renders, stack-optional render, redesign records v1 before planning v2 |
 | **D. Design Source and Pipeline Architecture** | 12, 22, 23 | Where design comes from and how the pipeline renders: Figma 3-tier access (BLOCKING), platform-agnostic template + Pass B render, convention extraction (Phase 1c) |
-| **E. UI, Variant, and Test Coverage** | 15, 18, 19, 28, 29, 31 | UI artefact rules: SVG default for new assets, screenshots embedded, all Figma variants drilled, SwiftUI Preview block (iOS), variant usage explicit, business-rule to acceptance-criterion to test traceability |
+| **E. UI, Variant, and Test Coverage** | 15, 18, 19, 27, 28, 30 | UI artefact rules: SVG default for new assets, screenshots embedded, all Figma variants drilled, SwiftUI Preview block (iOS), variant usage explicit, business-rule to acceptance-criterion to test traceability |
 
 When citing a Locked decision in code or docs, prefer `Locked <n> (<short label>)` form so the category is inferable (e.g. `Locked 30 (analysis self-contained, category B)`).
 
+### Gate status
+
+Which of the 36 a script enforces. An unmarked decision reads as enforced.
+
+**Gated (18):** 2, 7, 13, 14, 15, 16, 17, 18, 21, 24, 28, 30, 32, 35, 36 by
+`validate-analysis-doc.mjs`; 29 by `smoke-analysis-mode.sh`; 33 by
+`build-references.mjs --check`; 34 by `smoke-validate-analysis-doc.sh`. Each has
+a smoke of its own.
+
+**Not gated (18):** 1, 3, 4, 5, 6, 8, 9, 10, 11, 12, 19, 20, 22, 23, 25, 26, 27,
+31. Breaking one produces a worse document, not a failing run. Two read like
+gates and are not: 12 opens "MUST: Figma access", 23 "Convention extraction
+mandatory". Both are model-applied.
+
+A gate checks a SHAPE the template prescribes, never whether it was filled
+honestly: 13 asks if a scenario is Gherkin, not if it is the right one. The rest
+stays prose because it is run behaviour no document records (5, 6, 10, 25),
+evidence gathered before rendering (11, 12, 19, 23, 26), or judgement about
+meaning (3, 4, 8, 9, 20, 22, 27, 31).
+
+A decision counts as gated only when a script names it in the message it fails
+with: that message is what the attribution check reads.
+
+`smoke-locked-citations.sh` checks these two lists against what the scripts
+actually enforce, so a decision that gains or loses a gate cannot leave them
+behind.
+
 ### Full list
 
 1. **One feature per run.** Every Figma URL, Confluence page, Jira ID, and Standards source the user supplies belongs to the **same feature**. The command never asks "which feature is this for?" or "which URL is primary?". Mixed inputs covering multiple features are treated as user error: surface the conflict, stop, and ask the user to split into separate runs.
-2. **Section omission rule.** Sections with zero evidence are dropped entirely; no `TBD` placeholder section. Numbering remains sequential `1..N` over the rendered set.
+2. **Section omission rule.** Sections with zero evidence are dropped entirely; no `TBD` placeholder section. **A rendered section keeps its canonical template number**, so the set has gaps and that is correct: `1, 2, 4, 9, 13, 14, 21` is a valid rendered document. This clause used to say numbering re-flows sequentially `1..N`, which could not hold alongside Locked 30 - that decision threads ids across sections BY NUMBER (`Section 15.1 scenario`, `Section 4.4`, `Section 3/5 layout cells`), and a re-flowed document sends every one of those cross-references to the wrong section or to nothing. No emitted document ever re-flowed; the rule was the part that was wrong. What IS checked: every rendered number is a real template number, and the numbers ascend without repeating.
 3. **Citation discipline.** Every quoted UI string, endpoint path, error code, or analytics event name in Sections 2-4 must carry an inline citation: `[Figma annotation <nodeId>]` for copy taken from a Dev Mode annotation, `[Figma <nodeId>]` (MCP) or `[figma-export: <project-slug>/<screen-slug>:<nodeId>]` (local source) for design strings; `file:line` for repo evidence; `Confluence:<pageId>:<heading-slug>` for spec text. **Annotation-as-copy precedence:** when the project's `figma-config` has `annotations.enabled` and a node carries a Dev Mode annotation, that annotation is the authoritative copy for the node and the visible text layer is treated as a placeholder; cite the annotation, not the layer text. Never invent copy - blank beats a guess; a node whose annotation has the base language but is missing a target language emits a Section 20 (Risks) row rather than a fabricated value. Uncited quotes are downgraded to `[label TBD - see Open Questions]` and a row is added to Section 7 Risks. Subagent prose and Code Connect snippets are not citations.
 4. **The spec is forward-looking.** Section bodies describe the new feature as drawn / specified. Findings that exist only in legacy code or the existing branch appear as `> Legacy reference: <text> (file:line)` blockquotes inside the relevant section, never as the lead sentence or a primary table row. A legacy-only finding with no forward counterpart goes to Section 7 Risks as a decision item: "current code does X; should the new feature keep, change, or drop this?".
 5. **Output default = Local file.** The Phase 3.5 output picker keeps `Local file` pre-selected. Confluence and Jira outputs are never default-selected (see `analysis-output-confluence-on-request` memory).
@@ -44,17 +71,16 @@ When citing a Locked decision in code or docs, prefer `Locked <n> (<short label>
 22. **Platform-agnostic template + Pass B render.** The template (`$HOME/.claude/multi-agent-refs/analysis-template.md`) describes concepts (state holder, view, navigator, use case, repository, DTO, state model, DI register, localization key, accessibility identifier, test method) without platform-specific class names. Pass B (Phase 2b) projects each concept onto the selected platform using conventions extracted at Phase 1c.
 23. **Convention extraction mandatory (Phase 1c).** After Phase 1b repo evidence, Phase 1c extracts seven pattern groups (folder structure, class naming, UI state model, test method naming, accessibility identifier, localization key, DI registration) per selected repo via `~/.claude/lib/extract-conventions.sh`. Output lands in `state.analysisSpec.evidence.conventions[<repo>]` with confidence levels (high / medium / low / none) and evidence file citations.
 24. **Pass B cell footnote mandatory.** Every cell Pass B fills in Section 13 (Architecture Plan concept table) and any other per-platform projection carries a footnote of the form `^[<convention-key> <confidence>: <evidence-source>]` pointing back to Phase 1c output. Cells with `confidence: low | none` cite `conventions-defaults.md:C<n>-<platform>` and emit a row in Section 20 Risks ("convention fallback applied"). Footnote-less cells fail the dispatch gate.
-25. **Lite mode for small features.** When Phase 1 signals indicate a small feature, Lite mode auto-activates and renders only Sections 1, 2, 4, 9, 13, 14, 21, plus optional 23 Changelog. The user can force Lite with `--lite` or force Full with `--full`. Full mode is the default for new feature analyses. **Scoring (v9.1.0+):** three independent signals - `confluenceSpecLines < 100`, `figmaFramesCount <= 1`, `repoDirectMatchCount >= 8`. Each true signal scores 1 point; Lite auto-activates at `score >= 2`. Previous AND-threshold (`v8.12.0..v9.0.x`) was too strict and forced small features into Full mode when one signal was just over the line. Explicit user flags (`--lite` / `--full`) always win over auto-scoring.
-26. **Pass B preview before render.** Phase 2a presents the resolved convention table to the user before Phase 2b emits any platform file. The user can approve, override individual cells, or cancel. Empty answers do not imply consent (`feedback_no-inferred-defaults-from-empty-answer`); the picker re-asks on empty submit.
-27. **Evidence digest caches Phase 1b and 1c.** `evidence_digest = sha256(featureName || sorted(platforms) || repoEvidence.summary || conventions.summary)`. When the same feature name is invoked again against the same set of repos and the digest matches, Phase 1b and 1c are skipped and the cached `evidence.repoEvidence` / `evidence.conventions` is reused. Cache TTL is 24 hours; manual invalidation via `--no-cache` flag.
-28. **SwiftUI Preview block mandatory (iOS projection, SwiftUI only).** When the iOS file is produced AND the affected view is a SwiftUI view (detected via `import SwiftUI` + `: View` protocol conformance in `evidence.repoEvidence[<repo>].buckets.uiComponents`), Section 13.6 renders a Preview block table covering at minimum: canonical default (LTR Light), Dark, RTL, Dynamic Type accessibilityLarge, and one error variant. Loading state and edge-case variants are added when distinct from canonical. UIKit-only features (no SwiftUI view artefact) drop Section 13.6 with note `(N/A: UIKit-only feature)`. Preview macro convention (`#Preview` for Swift 5.9+ vs legacy `PreviewProvider`) is read from `evidence.conventions[<repo>].previewMacro`. Each Preview variant listed in Section 13.6 must have a matching row in Section 15.2 Snapshot Tests; a Preview without a snapshot row triggers a Section 20 Risk.
-29. **Variant usage explicit and bounded.** Section 6 inventory rows list which variants this feature consumes per component (concrete enum case + bool value). New Section 6.X (Variant Usage Matrix) catalogues the full variant axis vs. used subset with a rationale per excluded variant. Sections 13.6 (Preview) and 15.2 (Snapshot) cover only the used subset; expanding the variant set requires updating Section 6.X first.
-30. **Analysis as self-contained design bridge - no MCP outside analysis phase (BLOCKING, pipeline-wide).** The analysis document is the sole design source for every downstream phase. After Phase 1 of `/multi-agent:analysis` produces `analysis/<feature>-<platform>.md`, Phase 2 Planning, Phase 3 Dev, Phase 4 Review, Phase 5 Test, Phase 6 Commit, and Phase 7 Report consume only the analysis document plus repo Code Connect mappings (`*.figma.swift` / `*.figma.kt`). Calling `mcp__claude_ai_Figma__*`, hitting `api.figma.com`, or fetching a `figma.com/design/...` URL during Phase 2+ is a violation. Applies to every mode that runs Phase 2+: `/multi-agent`, `/multi-agent:autopilot`, `/multi-agent:local`, `/multi-agent:local-autopilot`, at either depth. Hard requirement (v9.0.0): Phase 2 Pre-item and Phase 3 Pre-item (BLOCKING) abort the run when the analysis document is missing. Memory: `[[mcp-only-in-analysis]]`. Generic rule rationale and access matrix: see `$HOME/.claude/rules/figma-pipeline.md` "MUST: No MCP outside analysis phase".
-31. **Business-rule to acceptance-criterion to test traceability (AI + human spine).** The analysis is a development handoff that both an AI implementer and a human reviewer must act on, so it is bound by one shared-ID vocabulary. Every business rule carries a stable id `BR-<slug>-NN` (Section 4.4). Each rule maps to at least one acceptance criterion written Given / When / Then (binary - two readers must not be able to disagree on pass/fail). Each acceptance criterion maps to unit-test scenarios in Section 15.1, one row per case across happy / boundary / error / empty-nil (enumerate at least the failure modes; agents hallucinate error handling when it is omitted). The same ids thread onward: Section 15.6 UI-test flows reference the `BR-` ids and use stable selectors (accessibilityIdentifier / testTag), Section 16 accessibility items reuse those identifiers, Section 11 analytics events cite their triggering rule or story, and Section 5/7 layout cells carry token + Figma node refs. Never invent copy or values (blank beats a guess; a missing source becomes a Section 20 Open Question). **Mode-aware gate:** in Full mode a business rule with no acceptance criterion, or an acceptance criterion with no Section 15.1 scenario, fails the dispatch gate. In **Lite mode Section 15 is not rendered**, so the rule-to-test half does not apply - Section 4.4 still lists each rule with its Given/When/Then acceptance criterion (the acceptance criterion is itself the testable statement), and the 15.1 mapping is deferred to whenever the feature is later analyzed in Full or implemented by a dev run. The rule-to-acceptance-criterion half always holds, in both modes.
-
-32. **Analysis profile selected at intake.** `state.analysisSpec.profile` is `global` (default) or `corporate`, asked once at Phase 0 Step 1b and never re-asked mid-run. `global` renders `$HOME/.claude/multi-agent-refs/analysis-template.md` (23 sections, development handoff). `corporate` renders `$HOME/.claude/multi-agent-refs/analysis-template-corporate.md` (requirements document: `IG -> UC -> FG` spine, three traceability matrices, current-to-target state with impact analysis, then Technical Analysis and Development Analysis). **Both profiles read the same `state.analysisSpec.evidence.*`** - intake, fetching, repo evidence and convention extraction are shared and profile-independent; only the projection differs. This is what keeps the two templates from drifting into two products. One run emits one profile: rendering both from a single run would produce two documents describing the same feature, and the next reader would have to decide which one is current. When only one profile is available (`prefs.global.analysisProfiles` lists one, or the corporate profile has no binding configuration), the step auto-resolves and prints its breadcrumb with the resolution noted, per the picker contract.
-33. **Corporate backbone always renders.** In the `corporate` profile the Locked 2 omission rule is replaced for Part A and the footer: those sections render even with zero evidence, carrying `N/A` when the section is genuinely out of scope for the feature and `EKLENECEK` when evidence is expected but missing. This is the point of a requirements document - a reader has to be able to tell "we considered hardware needs and there are none" from "nobody looked". Every `EKLENECEK` emits a matching Section 20 Risks and Open Questions row naming what is missing and who can answer it; an `EKLENECEK` with no such row fails the dispatch gate, because an unanswered question nobody owns is how a placeholder reaches production. **Missing inputs never block the run**: the corporate source practice of halting until every input arrives is deliberately not adopted - the document is produced with `EKLENECEK` in the gaps and the gaps are raised in Section 20. Part B follows the global omission table unchanged. In the `global` profile Locked 2 applies as written, with no placeholder of any kind.
-34. **References are built from the evidence record, not written.** Section 21 is emitted by `$HOME/.claude/scripts/build-references.mjs` from `state.analysisSpec.evidence.*` in both profiles. Each row carries a precision anchor in its `Sürüm / Ref` column - Figma node id, Confluence `pageId` plus page version, the commit SHA a repo was read at, the Swagger spec version - because a reference with no anchor points at a moving target. Each row carries an `Erişim / Access` cell: a declared source that could not be fetched still gets a row reading `erişilemedi (<reason>)`, since a silently dropped source reads to the next person as a source that never existed. User statements from the conversation that no fetched source contains are recorded as `Serbest metin` rows, quoted verbatim, with the decision they settled. **Coverage gate**: every entry in `evidence.figma[]`, `confluence[]`, `jira[]`, `swagger[]`, `repo[]`, `standards[]`, `firebase[]`, `documents[]`, `outside[]`, `freeText[]` and every entry in `evidence.fetchErrors[]` must appear as a row, and every row must map to an evidence entry. A source that shaped the document but is missing from References fails the dispatch gate; so does an invented row with no evidence behind it.
-35. **Stack-optional render.** Platform and repo selection are optional. When `state.analysisSpec.platforms[]` is empty, the run still completes: the analysis layers that do not need a target repository render in full - Part A and Part B in the corporate profile, Sections 1-12 and 16-17 in the global profile - and only the development layer is dropped (corporate Part C; global Sections 13, 14, 15) along with the Pass B projection, since there are no conventions to project onto. A Section 20 row records that the development analysis awaits a repo selection. **The channel split survives the missing repo.** Channels are derived from the evidence instead of repo stack tags (`intake.md` Step 3 carries the signal table) and one document is emitted per derived channel - `mobile`, `web`, or both. A phone screen and a browser screen carry different requirements before anyone has picked a repository; the split (Locked 9) exists to carry that difference and only its *projection* half needs conventions. `mobile` stays one channel rather than iOS plus Android, since without conventions nothing tells the two apart. Evidence with no interface at all yields a single channel-agnostic `<feature>.md`. Files land under `~/Desktop/multiAgentAnalysis/<feature-name>/`, named `<feature>-<channel>.md` (or `<feature>.md` for the channel-agnostic case): the repo-relative `analysis/` path has nothing to be relative to without a repo, and the current working directory is never used, since for a repo-less run it is arbitrary. Desktop rather than a hidden directory because the document is a deliverable somebody is meant to open and hand over, and `multiAgentAnalysis` rather than a bare `Analysis` because a generic word collides with whatever else is on a desktop while the producer name groups every run this command ever writes. The Phase 3.5 picker shows the resolved path and takes an override through its Other input. A requirements document is useful before anyone has decided which repository will hold the code, and refusing to produce one until that decision exists inverts the order the work actually happens in.
-36. **The document is reviewed before it is published.** An analysis run used to go from draft straight to dispatch behind a deterministic validator, so nothing read what it was about to publish: one run put a channel it never searched for, an open question about a frame it never opened, and twenty-three unowned `EKLENECEK` markers onto a live page. Every one is what a reader catches on the first pass. Phase 3.2 runs `phases/phase-4-review.md` Step 0 (strict validator, the host's three-reviewer set, triage) on the draft before the destination is chosen: a finding is cheap while nothing is written. Reviewers are subagents holding `analysis/review.md`, never the context that wrote the document, which cannot notice a search it never thought to run. A blocking finding returns to Phase 2b with dispatch closed and never becomes an open question, since "the document is wrong" is not something to ask the reader; capped at two returns. Phase 3.3 sorts every remaining gap into searched-and-closed, asked-and-answered, or `AS-NN`; an unstamped gap fails the dispatch gate. Autopilot runs both; only the asking degrades, into rows stamped `autopilot: could not ask`.
-37. **A redesign records v1 before it plans v2.** `options.redesign` is an opt-in on the `options.uiTests` axis, never a third `mode` value: `mode` says how many sections, `redesign` says which content, and a `mode: redesign` would switch off the Full-mode traceability, Test Plan and rule-to-test gates in exactly the documents that need them. It adds three sub-sections and no top-level section: current behaviour with `CB-<slug>-NN` ids and `repo/file:line` citations, the v1 to v2 endpoint mapping, and a difference list over a closed status vocabulary. Every `Missing` and `Partial` owes a Section 20 row by `AS-NN`, and a `CB-` id in one table but not the other fails in both directions - a behaviour that is in the code and on nobody's difference list is what a redesign loses and production finds. Evidence and certainty are derived from `repoEvidence`, never graded by the writer (Locked 24, same reason), and `options.redesign` is an `evidence_digest` input. Contract and the eight checks: `analysis/redesign.md`, loaded only on a redesign run.
+25. **Pass B preview before render.** Phase 2a presents the resolved convention table to the user before Phase 2b emits any platform file. The user can approve, override individual cells, or cancel. Empty answers do not imply consent (`feedback_no-inferred-defaults-from-empty-answer`); the picker re-asks on empty submit.
+26. **Evidence digest caches Phase 1b and 1c.** `evidence_digest = sha256(featureName || sorted(platforms) || repoEvidence.summary || conventions.summary)`. When the same feature name is invoked again against the same set of repos and the digest matches, Phase 1b and 1c are skipped and the cached `evidence.repoEvidence` / `evidence.conventions` is reused. Cache TTL is 24 hours; manual invalidation via `--no-cache` flag.
+27. **SwiftUI Preview block mandatory (iOS projection, SwiftUI only).** When the iOS file is produced AND the affected view is a SwiftUI view (detected via `import SwiftUI` + `: View` protocol conformance in `evidence.repoEvidence[<repo>].buckets.uiComponents`), Section 13.6 renders a Preview block table covering at minimum: canonical default (LTR Light), Dark, RTL, Dynamic Type accessibilityLarge, and one error variant. Loading state and edge-case variants are added when distinct from canonical. UIKit-only features (no SwiftUI view artefact) drop Section 13.6 with note `(N/A: UIKit-only feature)`. Preview macro convention (`#Preview` for Swift 5.9+ vs legacy `PreviewProvider`) is read from `evidence.conventions[<repo>].previewMacro`. Each Preview variant listed in Section 13.6 must have a matching row in Section 15.2 Snapshot Tests; a Preview without a snapshot row triggers a Section 20 Risk.
+28. **Variant usage explicit and bounded.** Section 6 inventory rows list which variants this feature consumes per component (concrete enum case + bool value). New Section 6.X (Variant Usage Matrix) catalogues the full variant axis vs. used subset with a rationale per excluded variant. Sections 13.6 (Preview) and 15.2 (Snapshot) cover only the used subset; expanding the variant set requires updating Section 6.X first.
+29. **Analysis as self-contained design bridge - no MCP outside analysis phase (BLOCKING, pipeline-wide).** The analysis document is the sole design source for every downstream phase. After Phase 1 of `/multi-agent:analysis` produces `analysis/<feature>-<platform>.md`, Phase 1 Plan, Phase 2 Dev, Phase 3 Review, Phase 3 Review, Phase 4 Commit, and Phase 5 Report consume only the analysis document plus repo Code Connect mappings (`*.figma.swift` / `*.figma.kt`). Calling `mcp__claude_ai_Figma__*`, hitting `api.figma.com`, or fetching a `figma.com/design/...` URL during Phase 2+ is a violation. Applies to every mode that runs Phase 2+: `/multi-agent`, `/multi-agent:autopilot`, `/multi-agent:local`, `/multi-agent:local-autopilot`, at either depth. Hard requirement (v9.0.0): Phase 2 Pre-item and Phase 3 Pre-item (BLOCKING) abort the run when the analysis document is missing. Memory: `[[mcp-only-in-analysis]]`. Generic rule rationale and access matrix: see `$HOME/.claude/rules/figma-pipeline.md` "MUST: No MCP outside analysis phase".
+30. **Business-rule to acceptance-criterion to test traceability (AI + human spine).** The analysis is a development handoff that both an AI implementer and a human reviewer must act on, so it is bound by one shared-ID vocabulary. Every business rule carries a stable id `BR-<slug>-NN` (Section 4.4). Each rule maps to at least one acceptance criterion written Given / When / Then (binary - two readers must not be able to disagree on pass/fail). Each acceptance criterion maps to unit-test scenarios in Section 15.1, one row per case across happy / boundary / error / empty-nil (enumerate at least the failure modes; agents hallucinate error handling when it is omitted). The same ids thread onward: Section 15.6 UI-test flows reference the `BR-` ids and use stable selectors (accessibilityIdentifier / testTag), Section 16 accessibility items reuse those identifiers, Section 11 analytics events cite their triggering rule or story, and Section 3/5 layout cells carry token + Figma node refs. Never invent copy or values (blank beats a guess; a missing source becomes a Section 20 Open Question). **Gate:** a business rule with no acceptance criterion, or an acceptance criterion with no Section 15.1 scenario, fails the dispatch gate. There is no mode clause: the rule used to be suspended in Lite mode, which deferred the rule-to-test half to "whenever the feature is later analyzed in Full" - a debt nothing tracked and nothing ever paid. Section 15 renders when there is evidence for it and is dropped when there is not, like every other section, and the gate applies to whatever was rendered.
+
+31. **Analysis profile selected at intake.** `state.analysisSpec.profile` is `global` (default) or `corporate`, asked once at Phase 0 Step 1b and never re-asked mid-run. `global` renders `$HOME/.claude/multi-agent-refs/analysis-template.md` (23 sections, development handoff). `corporate` renders `$HOME/.claude/multi-agent-refs/analysis-template-corporate.md` (requirements document: `IG -> UC -> FG` spine, three traceability matrices, current-to-target state with impact analysis, then Technical Analysis and Development Analysis). **Both profiles read the same `state.analysisSpec.evidence.*`** - intake, fetching, repo evidence and convention extraction are shared and profile-independent; only the projection differs. This is what keeps the two templates from drifting into two products. One run emits one profile: rendering both from a single run would produce two documents describing the same feature, and the next reader would have to decide which one is current. When only one profile is available (`prefs.global.analysisProfiles` lists one, or the corporate profile has no binding configuration), the step auto-resolves and prints its breadcrumb with the resolution noted, per the picker contract.
+32. **Corporate backbone always renders.** In the `corporate` profile the Locked 2 omission rule is replaced for Part A and the footer: those sections render even with zero evidence, carrying `N/A` when the section is genuinely out of scope for the feature and `EKLENECEK` when evidence is expected but missing. This is the point of a requirements document - a reader has to be able to tell "we considered hardware needs and there are none" from "nobody looked". Every `EKLENECEK` emits a matching Section 20 Risks and Open Questions row naming what is missing and who can answer it; an `EKLENECEK` with no such row fails the dispatch gate, because an unanswered question nobody owns is how a placeholder reaches production. **Missing inputs never block the run**: the corporate source practice of halting until every input arrives is deliberately not adopted - the document is produced with `EKLENECEK` in the gaps and the gaps are raised in Section 20. Part B follows the global omission table unchanged. In the `global` profile Locked 2 applies as written, with no placeholder of any kind.
+33. **References are built from the evidence record, not written.** Section 21 is emitted by `$HOME/.claude/scripts/build-references.mjs` from `state.analysisSpec.evidence.*` in both profiles. Each row carries a precision anchor in its `Sürüm / Ref` column - Figma node id, Confluence `pageId` plus page version, the commit SHA a repo was read at, the Swagger spec version - because a reference with no anchor points at a moving target. Each row carries an `Erişim / Access` cell: a declared source that could not be fetched still gets a row reading `erişilemedi (<reason>)`, since a silently dropped source reads to the next person as a source that never existed. User statements from the conversation that no fetched source contains are recorded as `Serbest metin` rows, quoted verbatim, with the decision they settled. **Coverage gate**: every entry in `evidence.figma[]`, `confluence[]`, `jira[]`, `swagger[]`, `repo[]`, `standards[]`, `firebase[]`, `documents[]`, `outside[]`, `freeText[]` and every entry in `evidence.fetchErrors[]` must appear as a row, and every row must map to an evidence entry. A source that shaped the document but is missing from References fails the dispatch gate; so does an invented row with no evidence behind it.
+34. **Stack-optional render.** Platform and repo selection are optional. When `state.analysisSpec.platforms[]` is empty, the run still completes: the analysis layers that do not need a target repository render in full - Part A and Part B in the corporate profile, Sections 1-12 and 16-17 in the global profile - and only the development layer is dropped (corporate Part C; global Sections 13, 14, 15) along with the Pass B projection, since there are no conventions to project onto. A Section 20 row records that the development analysis awaits a repo selection. **The channel split survives the missing repo.** Channels are derived from the evidence instead of repo stack tags (`intake.md` Step 3 carries the signal table) and one document is emitted per derived channel - `mobile`, `web`, or both. A phone screen and a browser screen carry different requirements before anyone has picked a repository; the split (Locked 9) exists to carry that difference and only its *projection* half needs conventions. `mobile` stays one channel rather than iOS plus Android, since without conventions nothing tells the two apart. Evidence with no interface at all yields a single channel-agnostic `<feature>.md`. Files land under `~/Desktop/multiAgentAnalysis/<feature-name>/`, named `<feature>-<channel>.md` (or `<feature>.md` for the channel-agnostic case): the repo-relative `analysis/` path has nothing to be relative to without a repo, and the current working directory is never used, since for a repo-less run it is arbitrary. Desktop rather than a hidden directory because the document is a deliverable somebody is meant to open and hand over, and `multiAgentAnalysis` rather than a bare `Analysis` because a generic word collides with whatever else is on a desktop while the producer name groups every run this command ever writes. The Phase 3.5 picker shows the resolved path and takes an override through its Other input. A requirements document is useful before anyone has decided which repository will hold the code, and refusing to produce one until that decision exists inverts the order the work actually happens in.
+35. **The document is reviewed before it is published.** An analysis run used to go from draft straight to dispatch behind a deterministic validator, so nothing read what it was about to publish: one run put a channel it never searched for, an open question about a frame it never opened, and twenty-three unowned `EKLENECEK` markers onto a live page. Every one is what a reader catches on the first pass. Phase 3.2 runs `phases/phase-3-review.md` Step 0 (strict validator, the host's three-reviewer set, triage) on the draft before the destination is chosen: a finding is cheap while nothing is written. Reviewers are subagents holding `analysis/review.md`, never the context that wrote the document, which cannot notice a search it never thought to run. A blocking finding returns to Phase 2b with dispatch closed and never becomes an open question, since "the document is wrong" is not something to ask the reader; capped at two returns. Phase 3.3 sorts every remaining gap into searched-and-closed, asked-and-answered, or `AS-NN`; an unstamped gap fails the dispatch gate. Autopilot runs both; only the asking degrades, into rows stamped `autopilot: could not ask`.
+36. **A redesign records v1 before it plans v2.** `options.redesign` is an opt-in on the `options.uiTests` axis, never a third `mode` value: `mode` says how many sections, `redesign` says which content, and a `mode: redesign` would switch off the Full-mode traceability, Test Plan and rule-to-test gates in exactly the documents that need them. It adds three sub-sections and no top-level section: current behaviour with `CB-<slug>-NN` ids and `repo/file:line` citations, the v1 to v2 endpoint mapping, and a difference list over a closed status vocabulary. Every `Missing` and `Partial` owes a Section 20 row by `AS-NN`, and a `CB-` id in one table but not the other fails in both directions - a behaviour that is in the code and on nobody's difference list is what a redesign loses and production finds. Evidence and certainty are derived from `repoEvidence`, never graded by the writer (Locked 24, same reason), and `options.redesign` is an `evidence_digest` input. Contract and the eight checks: `analysis/redesign.md`, loaded only on a redesign run.

package/pipeline/multi-agent-refs/analysis/redesign.md

@@ -111,7 +111,7 @@ All in `validate-analysis-doc.mjs`, all live only when the front-matter says
 
 ## The cache, and the silent failure to avoid
 
-`evidence_digest` (Locked 27) summarises `featureName || platforms ||
+`evidence_digest` (Locked 26) summarises `featureName || platforms ||
 repoEvidence || conventions`, with a 24-hour TTL. `options.redesign` **is a
 digest input**. Without it, a redesign started within a day of a normal run on
 the same feature hits that run's cache, skips Phase 1b entirely, and renders a

package/pipeline/multi-agent-refs/analysis/render.md

@@ -6,11 +6,11 @@
 
 1. **Language resolution**: read `prefs.global.outputLanguage` (`tr` or `en`, default `tr`). Use the `Output language matrix` table in `$HOME/.claude/multi-agent-refs/analysis-template.md` to swap headings and system strings.
 
-1b. **Template selection** (Locked 32): read `state.analysisSpec.profile`. `global` renders against `$HOME/.claude/multi-agent-refs/analysis-template.md`; `corporate` renders against `$HOME/.claude/multi-agent-refs/analysis-template-corporate.md`. The evidence is the same either way - this step chooses the projection, nothing else. In the corporate profile the Part A backbone and the footer render even with zero evidence, carrying `N/A` or `EKLENECEK`, and each `EKLENECEK` emits its Section 20 row (Locked 33).
+1b. **Template selection** (Locked 31): read `state.analysisSpec.profile`. `global` renders against `$HOME/.claude/multi-agent-refs/analysis-template.md`; `corporate` renders against `$HOME/.claude/multi-agent-refs/analysis-template-corporate.md`. The evidence is the same either way - this step chooses the projection, nothing else. In the corporate profile the Part A backbone and the footer render even with zero evidence, carrying `N/A` or `EKLENECEK`, and each `EKLENECEK` emits its Section 20 row (Locked 32).
 
 2. **Markdown render**: for each platform in `state.analysisSpec.platforms[]`, concatenate the per-platform spec into one markdown file. Tables in pipe-syntax. Numbering uses plain `## 1.`, `## 2.`, ... - omitted sections do **not** create gaps. Visible numbering is sequential 1..N over the rendered set. In the corporate profile the Part A and footer numbers are fixed and do not re-flow, since the backbone never drops; Part B and Part C follow the omission table as usual.
 
-   **When `platforms[]` is empty** (Locked 35), the channels come from the evidence instead of from repo stack tags, so this loop runs once per derived channel (`mobile`, `web`, or one channel-agnostic pass). What drops is the development layer (corporate Part C, global Sections 13, 14, 15) and the Pass B projection are skipped, Section 20 carries a row recording that they await a repo selection, and the front-matter `platform` key reads `none`. Everything that does not need a target repository still renders in full.
+   **When `platforms[]` is empty** (Locked 34), the channels come from the evidence instead of from repo stack tags, so this loop runs once per derived channel (`mobile`, `web`, or one channel-agnostic pass). What drops is the development layer (corporate Part C, global Sections 13, 14, 15) and the Pass B projection are skipped, Section 20 carries a row recording that they await a repo selection, and the front-matter `platform` key reads `none`. Everything that does not need a target repository still renders in full.
 
 3. **Humanizer pass (required: actually invoke the `ai-common-toolkit:humanizer` skill on the rendered markdown - the punctuation grep alone does NOT satisfy this step)** (`technical-explanatory` tone for the scratch buffer; per-channel re-humanize happens in Phase 4 when actually emitting):
    ```
@@ -23,7 +23,7 @@
 
    **Explicit punctuation policy** (enforced by `stripFancyPunctuation: true`): no em-dash (U+2014), no en-dash (U+2013), no horizontal ellipsis (U+2026), no curly quotes (U+2018, U+2019, U+201C, U+201D), no section sign (U+00A7). The humanizer replaces these with ASCII equivalents (`-`, `:`, `,`, `...`, `'`, `"`, and `bölüm` / `section` for the section sign per `outputLanguage`) before emit. Tables, code blocks, URLs, and front-matter YAML are exempt. Post-emit verification runs through `node $HOME/.claude/scripts/validate-analysis-doc.mjs <file>`, which checks this policy deterministically in Node on all three operating systems. Do NOT verify with `grep -P`: BSD grep (macOS, the pipeline's primary platform) has no `-P`, so that command never runs and "zero matches" is trivially true. The per-language readability rules (Turkish sentence shape, nominalization chains, which terms stay untranslated) live in the humanizer skill itself, not here; this paragraph owns only the punctuation policy the validator enforces. **Diacritics are PRESERVED, not stripped: this policy targets ONLY the listed fancy-punctuation codepoints. Turkish letters (ş/Ş, ç/Ç, ğ/Ğ, ı/I, İ, ö/Ö, ü/Ü) and all other `outputLanguage` letters MUST stay verbatim. Never ASCII-fold the prose - emit `Geliştirme Özeti`, `için`, `Kullanıcı Hikayeleri`, NOT `Gelistirme Ozeti`, `icin`, `Kullanici`. ASCII-folded Turkish is a humanizer-skipped smell and fails review.**
 
-3b. **Build Section 21 References** (Locked 34): emit the table with
+3b. **Build Section 21 References** (Locked 33): emit the table with
 
    ```bash
    node "$HOME/.claude/scripts/build-references.mjs" <state.json> --lang "$OUTPUT_LANGUAGE"
@@ -31,7 +31,7 @@
 
    and paste its output under the References heading. The model does not hand-write this table; it is a projection of `state.analysisSpec.evidence.*`, which is what keeps a source the run actually read from going unlisted and a remembered-but-unread source from appearing.
 
-4. **Write scratch drafts**: create `/tmp/analysis-<feature-slug>-<UTC-iso8601>/` and write `<feature>-<platform>.md` per selected platform. With `platforms[]` empty, write one file per derived channel (`<feature>-mobile.md`, `<feature>-web.md`; Locked 35), or a single `<feature>.md` when the evidence describes no interface. Update `state.analysisSpec.outputs.draftDir` with the path.
+4. **Write scratch drafts**: create `/tmp/analysis-<feature-slug>-<UTC-iso8601>/` and write `<feature>-<platform>.md` per selected platform. With `platforms[]` empty, write one file per derived channel (`<feature>-mobile.md`, `<feature>-web.md`; Locked 34), or a single `<feature>.md` when the evidence describes no interface. Update `state.analysisSpec.outputs.draftDir` with the path.
 
 5. **Surface the draft tree to the user**:
    ```
@@ -44,9 +44,9 @@
 
 ### Phase 3.2 - Draft review (BLOCKING, runs in every mode)
 
-Locked 36 carries the rule. Operationally:
+Locked 35 carries the rule. Operationally:
 
-1. Run `phases/phase-4-review.md` Step 0, the analysis-mode branch. It already defines
+1. Run `phases/phase-3-review.md` Step 0, the analysis-mode branch. It already defines
    the strict validator, the host's three-reviewer set with its model routing, and the
    triage. Do not restate it here; a second definition is the one that rots.
 2. Dispatch reviewers as subagents, each given the draft path, the state JSON and
@@ -128,15 +128,15 @@ for f in /tmp/analysis-<feature-slug>-<ts>/*.md; do
 done
 ```
 
-`validate-analysis-doc.mjs` enforces the mechanically-checkable Locked decisions on the emitted markdown itself (front-matter completeness, never-omitted sections per Locked 2, humanizer punctuation per Locked 7, Full-mode business-rule traceability per Locked 31, and in the corporate profile the backbone presence and `EKLENECEK`-to-Section-20 pairing per Locked 33). `build-references.mjs --check` runs the References coverage gate (Locked 34): a source the run consumed but did not list, or a listed row with no evidence behind it, blocks dispatch. `verify-citations.mjs` resolves each claimed `file:line` at HEAD with `git cat-file`, so `Foo.swift:9999` in a repo with no Foo.swift blocks dispatch (Locked 3, Locked 37). Any ERROR blocks dispatch: fix the draft and re-validate. Warnings are advisory (run with `--strict` to treat them as blocking). This turns the "fails the dispatch gate" prose into a real, model-independent check.
+`validate-analysis-doc.mjs` enforces the mechanically-checkable Locked decisions on the emitted markdown itself (front-matter completeness, never-omitted sections per Locked 2, humanizer punctuation per Locked 7, Full-mode business-rule traceability per Locked 30, and in the corporate profile the backbone presence and `EKLENECEK`-to-Section-20 pairing per Locked 32). `build-references.mjs --check` runs the References coverage gate (Locked 33): a source the run consumed but did not list, or a listed row with no evidence behind it, blocks dispatch. `verify-citations.mjs` resolves each claimed `file:line` at HEAD with `git cat-file`, so `Foo.swift:9999` in a repo with no Foo.swift blocks dispatch (Locked 3, Locked 36). Any ERROR blocks dispatch: fix the draft and re-validate. Warnings are advisory (run with `--strict` to treat them as blocking). This turns the "fails the dispatch gate" prose into a real, model-independent check.
 
 Iterate `state.analysisSpec.outputs.requested`. For each target:
 
 | Target | Action |
 |--------|--------|
-| Local | For each per-platform draft, `cp /tmp/analysis-<feature-slug>-<ts>/<feature>-<platform>.md` into `analysis/<feature>-<platform>.md` in the matching repo's working tree. When multiple repos exist for the same platform, the file is duplicated into each and the dispatch report lists every destination. **When no repo was selected** (Locked 35) there is no working tree to be relative to, so files land in `~/Desktop/multiAgentAnalysis/<feature-name>/`, one per derived channel (`<feature>-mobile.md`, `<feature>-web.md`) or a single `<feature>.md` when none could be derived. The current working directory is never written to: for a repo-less run it is arbitrary, and creating a folder in whatever directory the command happened to be invoked from is the kind of surprise that costs a tool its trust. The user can override the path through the picker's Other input. **No commit.** |
-| Confluence | Re-humanize each draft with `formal-stakeholder` tone. One page per draft under the chosen parent, titled `<Feature> - <Platform>` - including a repo-less run, whose drafts are the derived channels (`<Feature> - Mobile` / `<Feature> - Web`, Locked 35). A single channel-agnostic draft becomes one page titled `<Feature>`, with no suffix implying a split that was not made. Cross-link siblings inside each page via `<ac:link><ri:page ri:content-title="<Feature> - <OtherPlatform>"/></ac:link>`; a lone page has no sibling block. Markdown -> storage XML via `$HOME/.claude/multi-agent-refs/channels/confluence.md`. Re-emit on existing pages uses PUT with version bump. |
-| Jira | Re-humanize the combined body with `informal-technical` tone. Concatenate the drafts under `h2. Platform: <X>` separators in production order - `iOS`, `Android`, `Web`, `Backend` repo-backed, `Mobile` / `Web` for channels derived on a repo-less run (Locked 35). A single channel-agnostic draft gets no separator: a heading announcing a split of one is noise. then run the whole body through the markdown → Jira wiki conversion table in `$HOME/.claude/multi-agent-refs/channels/jira.md`  -  both the comment body and the `description` field render wiki markup, so raw `##`/`**`/backticks arrive as literal text. Write the converted body to a file and publish it with `$HOME/.claude/lib/jira-publish.sh`, never with a hand-rolled `curl`: <br><br>`bash "$HOME/.claude/lib/jira-publish.sh" --issue "$KEY" --body-file "$F" --target comment` <br>`bash "$HOME/.claude/lib/jira-publish.sh" --issue "$KEY" --body-file "$F" --target description --mode append` <br><br>The script owns the parts that are easy to get wrong: it runs `jira-wiki-escape.mjs` on the body, resolves host + token without putting either in argv, and on the description path it GETs the current value, writes it to a backup under `~/.claude/logs/multi-agent/jira-backups/` and reports the path, appends below a `----` rule by default, and **refuses with exit 3** when `--mode replace` would discard a non-empty description unless `--confirm-overwrite` is passed. Exit 3 is reported to the user with the backup path, never retried with the flag added automatically  -  only the user's explicit "Description - replace" answer from Phase 3.5 supplies it. `--dry-run` previews the exact final body without writing. |
+| Local | For each per-platform draft, `cp /tmp/analysis-<feature-slug>-<ts>/<feature>-<platform>.md` into `analysis/<feature>-<platform>.md` in the matching repo's working tree. When multiple repos exist for the same platform, the file is duplicated into each and the dispatch report lists every destination. **When no repo was selected** (Locked 34) there is no working tree to be relative to, so files land in `~/Desktop/multiAgentAnalysis/<feature-name>/`, one per derived channel (`<feature>-mobile.md`, `<feature>-web.md`) or a single `<feature>.md` when none could be derived. The current working directory is never written to: for a repo-less run it is arbitrary, and creating a folder in whatever directory the command happened to be invoked from is the kind of surprise that costs a tool its trust. The user can override the path through the picker's Other input. **No commit.** |
+| Confluence | Re-humanize each draft with `formal-stakeholder` tone. One page per draft under the chosen parent, titled `<Feature> - <Platform>` - including a repo-less run, whose drafts are the derived channels (`<Feature> - Mobile` / `<Feature> - Web`, Locked 34). A single channel-agnostic draft becomes one page titled `<Feature>`, with no suffix implying a split that was not made. Cross-link siblings inside each page via `<ac:link><ri:page ri:content-title="<Feature> - <OtherPlatform>"/></ac:link>`; a lone page has no sibling block. Markdown -> storage XML via `$HOME/.claude/multi-agent-refs/channels/confluence.md`. Re-emit on existing pages uses PUT with version bump. |
+| Jira | Re-humanize the combined body with `informal-technical` tone. Concatenate the drafts under `h2. Platform: <X>` separators in production order - `iOS`, `Android`, `Web`, `Backend` repo-backed, `Mobile` / `Web` for channels derived on a repo-less run (Locked 34). A single channel-agnostic draft gets no separator: a heading announcing a split of one is noise. then run the whole body through the markdown → Jira wiki conversion table in `$HOME/.claude/multi-agent-refs/channels/jira.md`  -  both the comment body and the `description` field render wiki markup, so raw `##`/`**`/backticks arrive as literal text. Write the converted body to a file and publish it with `$HOME/.claude/lib/jira-publish.sh`, never with a hand-rolled `curl`: <br><br>`bash "$HOME/.claude/lib/jira-publish.sh" --issue "$KEY" --body-file "$F" --target comment` <br>`bash "$HOME/.claude/lib/jira-publish.sh" --issue "$KEY" --body-file "$F" --target description --mode append` <br><br>The script owns the parts that are easy to get wrong: it runs `jira-wiki-escape.mjs` on the body, resolves host + token without putting either in argv, and on the description path it GETs the current value, writes it to a backup under `~/.claude/logs/multi-agent/jira-backups/` and reports the path, appends below a `----` rule by default, and **refuses with exit 3** when `--mode replace` would discard a non-empty description unless `--confirm-overwrite` is passed. Exit 3 is reported to the user with the backup path, never retried with the flag added automatically  -  only the user's explicit "Description - replace" answer from Phase 3.5 supplies it. `--dry-run` previews the exact final body without writing. |
 
 **Output capture**: fill `state.analysisSpec.outputs.localPaths[]` (one entry per per-platform-per-repo write, or one per derived channel on a repo-less run), `outputs.confluencePageUrls[]` (one entry per emitted document), `outputs.confluencePages[]` (the same pages by IDENTITY - `pageId`, `title`, `space`, `channel` - because a write-back needs the id and a `/display/SPACE/Title` URL cannot be parsed for one), `outputs.jiraIssueKey` (single string).
 

package/pipeline/multi-agent-refs/analysis/resolve.md

@@ -37,7 +37,7 @@
    | `citation-tbd` | row originated from a `[label TBD - see Open Questions]` downgrade (Locked 3) | repo localization keys / Figma evidence already cited elsewhere in the doc |
    | `legacy-decision` | row phrased `current code does X; should the new feature keep, change, or drop this?` (Locked 4) | repo lookup confirms current behavior with `file:line` |
    | `standards-conflict` | row cites a binding standards source (Locked 8) | quote the binding section verbatim from References |
-   | `design-gap` | row needs new Figma/design information (tier-3 forced questions, missing variants per Locked 12/19) | NONE - Locked 30; offer only Defer + the re-run recommendation |
+   | `design-gap` | row needs new Figma/design information (tier-3 forced questions, missing variants per Locked 12/19) | NONE - Locked 29; offer only Defer + the re-run recommendation |
    | `generic` | anything else | all three standard sources |
 
 4. **Batched repo lookup** (single Explore subagent, one call regardless of row count; skip if every row classified `design-gap`):

package/pipeline/multi-agent-refs/analysis/review.md

@@ -66,13 +66,13 @@ Parallel model review, same shape as `/multi-agent:review`: 3 models on Claude C
 - Each business requirement or rule is testable: two readers cannot disagree about whether it passed.
 - Nothing important is deferred to a conversation the reader was not in.
 
-**B. Evidence** (Locked 3, 4, 34)
+**B. Evidence** (Locked 3, 4, 33)
 
 - Every quoted string, endpoint, status code and event name carries a citation.
 - Nothing in a forward-looking section is actually a description of the current code.
 - References carry their precision anchors, and a source that could not be fetched is listed as unreachable rather than dropped.
 
-**C. Spine** (Locked 31 global, Locked 33 corporate)
+**C. Spine** (Locked 30 global, Locked 32 corporate)
 
 - Global: every `BR-` id reaches an acceptance criterion and a test row.
 - Corporate: every `IG` is realised by a `UC`, every `FG` names a source that exists, and the traceability matrix agrees with the sections. The matrix half is already machine-checked in Phase 1; the reviewer judges whether the chain is *meaningful*, not merely present.

package/pipeline/multi-agent-refs/analysis/synthesis.md

@@ -32,7 +32,7 @@ synthesizedSections = {
 | 6. Business + Tests | If sections 2 and 4 are both `null` AND `evidence.firebase[]` is empty → null. Otherwise produce use-case + mock stubs + per-platform test skeletons + shared Firebase events table. Reuse Red-Green-Refactor naming from `$HOME/.claude/rules/tdd.md`. |
 | 7. Development Plan | Always present. Tasks for the current platform only. Architecture standards come from `evidence.standards[]` filtered by platform (see Pass B step 1). **Reuse-first rule (Locked 11)**: when an item has `direct-match` in `evidence.repoEvidence[<repo>].buckets.<X>`, emit `Reuse existing <FQN> (<file>:<line>)` instead of `Add new <FQN>`. New-write task with a `direct-match` competitor becomes a Risk row. |
 
-#### Phase 2a - Pass B preview (Locked 26)
+#### Phase 2a - Pass B preview (Locked 25)
 
 Before Pass B renders any file, present the resolved convention table to the user via `AskUserQuestion`. The table is one row per concept, one column per selected platform.
 
@@ -52,8 +52,8 @@ Convention preview - Pass B will render with:
 | DI | UserProfileDependencyConfigurator ^[C7 high] | UserProfileModule (Hilt) ^[C7 fallback: defaults] |
 
 Confidence summary:
-  iOS:     7/7 high, 0 medium, 0 low, 0 fallback
-  Android: 5/7 high, 1 medium, 0 low, 1 fallback
+  iOS:     5/5 high, 0 medium, 0 low, 0 fallback
+  Android: 3/5 high, 1 medium, 0 low, 1 fallback
 ```
 
 AskUserQuestion shape:
@@ -86,11 +86,17 @@ For each `platform` in `state.analysisSpec.platforms[]`:
    - `android` → `~/.claude/rules/kotlin-android.md` first → `evidence.standards[]` entries whose path contains `android` or `kotlin`
    - `backend` → `evidence.standards[]` entries matching language hints (`python`, `go`, `node`, `fastapi`) → fall back to `~/.claude/rules/security.md` + `code-style.md`
    - `web` → `evidence.standards[]` entries matching `react`, `vue`, `next`, `sveltekit` → `~/.claude/rules/code-style.md`
-2. **Apply per-platform omission rules.** Backend-only file drops Sections 5, 6, 7, 8, 16. Web with no UI inventory still keeps 5 (UI exists in code). Sections 1, 2, 4, 9, 13, 14, 20, 21 always present per Locked decision 2 + 13.
-3. **Resolve mode.** If user passed `--lite` → Lite. If user passed `--full` → Full. Otherwise use `state.analysisSpec.liteModeAuto`. Lite mode renders only Sections 1, 2, 4, 9, 13, 14, 21 plus optional 23.
-4. **Produce YAML front-matter header** (see `$HOME/.claude/multi-agent-refs/analysis-template.md`). Include `profile: <state.analysisSpec.profile | global>` and `platform: <platform | none>` so the validator applies the right contract per profile (Locked 32) and recognises the stack-optional render (Locked 35), `mode: full | lite`, plus `ui_tests: <state.analysisSpec.options.uiTests | false>`, `a11y_depth: <state.analysisSpec.options.a11yDepth | basic>` and `redesign: <state.analysisSpec.options.redesign | false>` so the pre-dispatch validator can enforce the opt-in coverage (15.6 present when ui_tests, 16.2 walkthrough present when a11y_depth is full, 4.5 / 4.6 / 9.5 present when redesign). `status` is written only by `/multi-agent:analysis-resolve`; a rendered document is a draft.
+2. **Apply per-platform omission rules.** Backend-only file drops Sections 5, 6, 7, 8, 16. Web with no UI inventory still keeps 5 (UI exists in code). Sections 1, 2, 4, 9, 13, 14, 20, 21 always present per Locked decision 2 + 13; their numbers are canonical and never re-flowed.
+3. **Resolve the section set from evidence, not from a mode.** There is one
+   pipeline. A section renders when it has evidence and is dropped when it does
+   not, per Locked 2. Lite mode used to answer this question with a fixed list
+   (1, 2, 4, 9, 13, 14, 21 plus optional 23) chosen by a three-signal score, and
+   that list fought Locked 2 in both directions: a small feature with rich
+   business rules lost Section 15 because it was not on the list, and a feature
+   with no API contract kept Section 9 because it was. Evidence decides now.
+4. **Produce YAML front-matter header** (see `$HOME/.claude/multi-agent-refs/analysis-template.md`). Include `profile: <state.analysisSpec.profile | global>` and `platform: <platform | none>` so the validator applies the right contract per profile (Locked 31) and recognises the stack-optional render (Locked 34), plus `ui_tests: <state.analysisSpec.options.uiTests | false>`, `a11y_depth: <state.analysisSpec.options.a11yDepth | basic>` and `redesign: <state.analysisSpec.options.redesign | false>` so the pre-dispatch validator can enforce the opt-in coverage (15.6 present when ui_tests, 16.2 walkthrough present when a11y_depth is full, 4.5 / 4.6 / 9.5 present when redesign). `status` is written only by `/multi-agent:analysis-resolve`; a rendered document is a draft.
 5. **Read conventions for this platform's repo.** For each cell Pass B fills in Section 13 and in any per-platform projection (Sections 5, 6, 7, 8, 10, 11, 13, 14, 15, 16, 17), read `state.analysisSpec.evidence.conventions[<repo>].<field>` and emit the value with a footnote (Locked 24). If `conventionOverrides` has an entry for that field, use the override and footnote with `^[user-override: <reason>]` instead of evidence path.
-6. **Concatenate non-null sections in canonical order.** Numbering stays sequential `1..N` over the rendered set (omitted sections do not create gaps).
+6. **Concatenate non-null sections in canonical order.** Each rendered section keeps its canonical template number, so omitted sections DO leave gaps - `1, 2, 4, 9, 13, 14, 21` is a correct rendered document. Locked 30 cites sections by number across the whole document; re-flowing them would break every one of those references.
 7. **Schema validation** on the per-platform spec object:
    ```bash
    python3 -c "import json,jsonschema; jsonschema.validate(json.load(open('state/<feature>-<platform>.json')), json.load(open('$HOME/.claude/schemas/analysis-spec.schema.json')))"

package/pipeline/multi-agent-refs/analysis-template-corporate.md

@@ -6,7 +6,7 @@ description: "Corporate profile template for /multi-agent:analysis. Requirements
 
 The corporate profile renders a **requirements document**, not a development brief. Its spine is `IG -> UC -> FG`: a business requirement is realised by a use case, which is satisfied by functional requirements, which are served by services. Three matrices prove the chain closes.
 
-This is a sibling of `analysis-template.md` (the global profile), not a replacement. Both read the same `state.analysisSpec.evidence.*`; only the projection differs. Phase 0 Step 1b picks one (Locked 32).
+This is a sibling of `analysis-template.md` (the global profile), not a replacement. Both read the same `state.analysisSpec.evidence.*`; only the projection differs. Phase 0 Step 1b picks one (Locked 31).
 
 > **Language**: This file is read as a system prompt, so its prose stays English. Section headings carry TR / EN scaffolds; the renderer picks the column matching `prefs.global.outputLanguage`.
 
@@ -19,7 +19,7 @@ This is a sibling of `analysis-template.md` (the global profile), not a replacem
 | Requirement spine | `BR-<slug>-NN` business rules with Gherkin acceptance criteria | `IG-NN` -> `UC-00N` -> `FG-NN`, plus three cross matrices |
 | Altitude | What to build and how | What is required and why; the how follows in Parts B and C |
 | Current state | Legacy findings are blockquotes inside forward-looking sections (Locked 4) | Section 2.1 is a first-class current-state analysis, and 2.3 is the diff between 2.1 and 2.2 |
-| Empty section | Dropped entirely (Locked 2) | Backbone sections always render, with `N/A` or `EKLENECEK` (Locked 33) |
+| Empty section | Dropped entirely (Locked 2) | Backbone sections always render, with `N/A` or `EKLENECEK` (Locked 32) |
 | Version history | Section 22 Changelog at the bottom | `DOKÜMAN TARİHÇESİ` table at the top |
 | Use cases | Gherkin scenarios in Section 4 | UC tables with Aktör / Ön Koşul / Ana Akış / Alternatif Akış |
 
@@ -27,7 +27,7 @@ Everything else is shared: citation discipline (Locked 3), forward-looking spec
 
 ## Section map
 
-Numbering is fixed for Parts A and B and does not re-flow, because the corporate backbone never drops (Locked 33). Section 5 sub-numbering shifts with the use-case count, exactly as the source documents do.
+Numbering is fixed for Parts A and B and does not re-flow, because the corporate backbone never drops (Locked 32). Section 5 sub-numbering shifts with the use-case count, exactly as the source documents do.
 
 | Layer | Sections | Carries |
 |---|---|---|
@@ -39,7 +39,7 @@ Numbering is fixed for Parts A and B and does not re-flow, because the corporate
 
 **Boundary rule** (inherited from the global template): remove a row, and ask what becomes unclear. Part A carries no technology name. Part C carries no business rationale. A row unclear in two layers at once is two rows.
 
-**Part C drops when no repo is selected** (Locked 35). Parts A and B always render.
+**Part C drops when no repo is selected** (Locked 34). Parts A and B always render.
 
 ---
 
@@ -189,7 +189,7 @@ Rules the renderer enforces:
 
 ## 4. Yapay Zeka Gereksinimleri / AI Requirements
 
-Renders `N/A` when the feature has no model-backed behaviour (Locked 33). When it does, each row states the decision the model makes, the input it sees, and the fallback when it is unavailable.
+Renders `N/A` when the feature has no model-backed behaviour (Locked 32). When it does, each row states the decision the model makes, the input it sees, and the fallback when it is unavailable.
 
 ```markdown
 ## 4. Yapay Zeka Gereksinimleri  <!-- TR -->
@@ -401,7 +401,7 @@ Part B carries what is technically true. It reuses the global template's scaffol
 
 Sections 15 and 16 are the implementation of the requirements stated in 7.1 and 7.3. State the requirement once, in Part A, and the implementation once, here. A sentence that appears in both is a sentence one of the two sections did not need.
 
-Part B follows the global omission table: a section with zero evidence drops. The corporate backbone guarantee (Locked 33) covers Part A and the References section, not Part B.
+Part B follows the global omission table: a section with zero evidence drops. The corporate backbone guarantee (Locked 32) covers Part A and the References section, not Part B.
 
 ---
 
@@ -417,9 +417,9 @@ Identical to the global template's Sections 13, 14 and 15, renumbered:
 
 Part C is written against the conventions extracted at Phase 1c, and every projected cell carries its Pass B footnote (Locked 24).
 
-**Part C drops entirely when no repo was selected** (Locked 35). The document then ends after Part B, and Section 20 carries a row stating that the development analysis awaits a repo selection. Parts A and B are complete on their own; a requirements document does not need a target repository to be useful.
+**Part C drops entirely when no repo was selected** (Locked 34). The document then ends after Part B, and Section 20 carries a row stating that the development analysis awaits a repo selection. Parts A and B are complete on their own; a requirements document does not need a target repository to be useful.
 
-**Traceability into Part C.** The `FG` ids are the join. Section 19's unit-test rows cite the `FG` they cover, the same way the global profile's rows cite `BR-` ids (Locked 31). An `FG` with no test row in Full mode fails the dispatch gate.
+**Traceability into Part C.** The `FG` ids are the join. Section 19's unit-test rows cite the `FG` they cover, the same way the global profile's rows cite `BR-` ids (Locked 30). An `FG` with no test row in Full mode fails the dispatch gate.
 
 ---
 
@@ -438,7 +438,7 @@ Never omitted.
 | AS-01 | <question> | <what evidence is missing> | <role or team> | 2.3 |
 ```
 
-The source corporate documents keep open questions out of the page and raise them in conversation instead. This profile keeps them in the document deliberately: an `EKLENECEK` with no matching `AS-NN` row here is an unanswered question nobody owns. Every `EKLENECEK` and every unverified assumption in 2.4 emits a row (Locked 33).
+The source corporate documents keep open questions out of the page and raise them in conversation instead. This profile keeps them in the document deliberately: an `EKLENECEK` with no matching `AS-NN` row here is an unanswered question nobody owns. Every `EKLENECEK` and every unverified assumption in 2.4 emits a row (Locked 32).
 
 ## 21. Referanslar / References