analyzthis_design 1.15.0 → 1.19.0

package/.github/ISSUE_TEMPLATE/persona-feedback.yml

@@ -0,0 +1,75 @@
+name: Persona feedback
+description: Report when a design persona got it wrong or you had to correct it
+title: "[feedback] "
+labels: ["persona-feedback"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Help improve analyzthis_design personas. Prefer CLI submit when possible:
+        `npx analyzthis_design feedback record ...` then `npx analyzthis_design feedback submit --yes`
+
+  - type: dropdown
+    id: persona
+    attributes:
+      label: Persona
+      options:
+        - arjun
+        - meera
+        - priya
+        - zara
+        - raj
+        - noor
+        - anuj
+        - design-director
+        - other
+    validations:
+      required: true
+
+  - type: dropdown
+    id: rating
+    attributes:
+      label: How happy were you with the output?
+      options:
+        - "1 — very unhappy"
+        - "2 — unhappy"
+        - "3 — okay"
+        - "4 — good"
+        - "5 — great"
+    validations:
+      required: true
+
+  - type: checkboxes
+    id: tags
+    attributes:
+      label: What went wrong?
+      options:
+        - label: wrong_hierarchy
+        - label: invented_tokens
+        - label: missed_ds
+        - label: too_verbose
+        - label: bad_ia
+        - label: off_brief
+        - label: other
+
+  - type: textarea
+    id: comment
+    attributes:
+      label: What was wrong?
+      placeholder: The persona suggested colors that aren't in our design system...
+    validations:
+      required: true
+
+  - type: textarea
+    id: correction
+    attributes:
+      label: What did you want instead? (how you corrected it)
+      placeholder: Use --color-primary from tokens.css; primary CTA should be top-right...
+    validations:
+      required: true
+
+  - type: input
+    id: version
+    attributes:
+      label: Package version (optional)
+      placeholder: "1.17.0"

package/README.md

@@ -37,8 +37,8 @@ npx analyzthis_design --target all --force
 | Cursor | `~/.cursor/skills/<name>/SKILL.md` | `/getting-started` |
 | Claude Code | `~/.claude/skills/<name>/SKILL.md` (+ legacy `~/.claude/commands/`) | `/getting-started` |
 | Codex CLI | `~/.codex/skills/<name>/SKILL.md` | skill name / AGENTS.md |
-| Grok Build | `~/.grok/skills/<name>/SKILL.md` | `/collect-knowledge` |
-| Windsurf Cascade | `~/.codeium/windsurf/skills/<name>/SKILL.md` | `@collect-knowledge` |
+| Grok Build | `~/.grok/skills/<name>/SKILL.md` | `/kavi` |
+| Windsurf Cascade | `~/.codeium/windsurf/skills/<name>/SKILL.md` | `@kavi` |
 | Cross-agent | `~/.agents/skills/<name>/SKILL.md` | discovered by multiple hosts |
 
 All skills use the **Agent Skills** `SKILL.md` standard — same files work across Cursor, Claude, Grok, Windsurf, and Codex. The CLI (`collect`, `run`, `sync`) is host-agnostic; only *where skills are discovered* differs.
@@ -62,18 +62,18 @@ All skills use the **Agent Skills** `SKILL.md` standard — same files work acro
 
 | Command | What it does |
 |---|---|
-| `/collect-knowledge` | **Kavi — Knowledge Archivist.** Scans the codebase, builds an Obsidian vault, LLM-enriches notes, syncs into the knowledge bank. Run once per project before critiques. |
+| `/kavi` | **Kavi — Knowledge Archivist.** Scans the codebase, builds an Obsidian vault, LLM-enriches notes, syncs into the knowledge bank. Run once per project before critiques. _(Alias: `/collect-knowledge`)_ |
 | `/persona-orchestrator` | **Agentic critique entry point** (not for wireframes). MoE router + session state, ux-story-gate intake, persona chain, DS / hierarchy / verify gates → SHIP/REVISE/BLOCK |
 | `/ux-story-gate` | Task-first gate: PRDs, DS/Figma discovery, MoE routing, browser verify, assess-only mode |
 | `/design-critic` | 4-persona critique → Composite Score + Information Hierarchy Gate |
 
 ### 8 Personas
 
-Invoke critique personas for targeted, already-grounded questions. For **wireframes**, use `/ux-ideator`, `/noor`, or `/anuj`. For full screen **critique**, prefer `/persona-orchestrator` or `/ux-story-gate`. Run `/collect-knowledge` first so they have project context.
+Invoke critique personas for targeted, already-grounded questions. For **wireframes**, use `/ux-ideator`, `/noor`, or `/anuj`. For full screen **critique**, prefer `/persona-orchestrator` or `/ux-story-gate`. Run **`/kavi`** first so they have project context.
 
 | Command | Persona | What they evaluate |
 |---|---|---|
-| `/collect-knowledge` | Kavi — Knowledge Archivist | Scan repo → Obsidian vault → enrich → sync knowledge bank (producer, not a critic) |
+| `/kavi` | Kavi — Knowledge Archivist | Scan repo → Obsidian vault → enrich → sync knowledge bank (producer, not a critic) |
 | `/arjun` | UX + Visual Design | UX Honeycomb + Visual Design Audit (hierarchy, color, type, spacing, components, style fit, micro-interactions) |
 | `/meera` | Business Agent | Retention, ARR, GTM lever, adoption risk; hierarchy vs north-star check |
 | `/priya` | Feasibility Agent | Engineering effort (T-shirt sizing, 2-axis model), state machine traps |
@@ -92,7 +92,7 @@ Invoke critique personas for targeted, already-grounded questions. For **wirefra
 
 ---
 
-## Agentic system (v1.15)
+## Agentic system (v1.19)
 
 ```
 User ask / Figma URL
@@ -101,14 +101,43 @@ User ask / Figma URL
         ↓
   ux-story-gate Phases 0–1.5 (PRD + DS/Figma + MoE router)
         ↓
-  MoE subset (default, 1–2 experts) OR design-critic / ideation chain (explicit "full")
+  Adversarial deliberation (parallel objection rounds, low satisfaction default)
         ↓
-  Hard gates: DS tokens → Information Hierarchy → Browser verify (skipped if assess_only + no URL)
+  MoE subset (default) OR full chain (explicit "full")
         ↓
-  Session state + cost metrics persisted  →  SHIP / REVISE / BLOCK
+  Raj on stalemate (2+ blocking objections)
+        ↓
+  Hard gates: DS → Hierarchy → Verify
+        ↓
+  SHIP / REVISE / BLOCK
 ```
 
-**Shared session state** lives at `~/.analyzthis_design/sessions/{project-id}/session-state.json` so Ask→Agent turns do not re-derive the task map, DS checklist, or routing decision.
+### Adversarial deliberation (v1.19)
+
+Personas **debate** grounded in real task_map, PRD, and UI context — they do not pass generic handoff documents.
+
+| Knob | Default | Meaning |
+|------|---------|---------|
+| `satisfaction_threshold` | 0.4 | Personas hard to please — must see evidence before `accepts_prior: true` |
+| `max_rounds` | 3 | Cap on objection rounds (token-bounded) |
+| `parallel_pairs` | Noor∥Anuj, Meera∥Priya | Adversarial critique in parallel |
+
+```bash
+npx analyzthis_design run --task "Review onboarding" --full --dry-run   # see deliberation groups
+npx analyzthis_design run --task "..." --satisfaction 0.3               # even harder to satisfy
+npx analyzthis_design run --task "..." --no-deliberate                  # legacy sequential mode
+npx analyzthis_design metrics                                           # deliberation_rounds, objections
+```
+
+Config: `~/.analyzthis_design/config.json` → `deliberation` block (see `supabase/deliberation-config.example.json`).
+
+Skill: `/deliberation-protocol` | Schema: `agents/deliberation-schema.json`
+
+**Low satisfaction ≠ unlimited tokens.** Objection rounds use lite schema + 600-token cap; synthesis and Raj use full models.
+
+---
+
+**Shared session state** lives at `~/.analyzthis_design/sessions/{project-id}/session-state.json` (includes `deliberation.round_log` after adversarial runs).
 
 ```bash
 npx analyzthis_design session init
@@ -139,6 +168,7 @@ npx analyzthis_design run --task "Review this screen" --figma https://figma.com/
 # Force the full design-critic chain, or bypass the router entirely
 npx analyzthis_design run --task "Full critique of onboarding" --full
 npx analyzthis_design run --task "Just check spacing" --experts arjun
+npx analyzthis_design run --task "..." --max-rounds 2 --satisfaction 0.5 --no-deliberate
 ```
 
 Provider defaults live in `~/.analyzthis_design/config.json`:
@@ -282,11 +312,70 @@ analyzthis_design is a design **critique** layer, not a design generator. The pe
 **LoRA readiness (export hook only — no training in this release):**
 
 ```bash
-npx analyzthis_design session accept --persona arjun     # mark the last output as a good example
+# Good examples (positive pairs)
+npx analyzthis_design session accept --persona arjun
 npx analyzthis_design export-training --persona arjun --all
+
+# Bad output + how you corrected it (negative / DPO pairs) — v1.16
+npx analyzthis_design session accept --persona arjun --reject \
+  --comment "Invented tokens not in our DS" \
+  --correction "Use --color-primary and spacing-4 from tokens.css" \
+  --rating 2 --tags invented_tokens,missed_ds
+
+npx analyzthis_design feedback record --persona arjun --rating 2 \
+  --comment "Hierarchy wrong — CTA buried" \
+  --correction "Primary action should be top-right, above the fold"
+
+npx analyzthis_design feedback list
+npx analyzthis_design feedback export --persona arjun --all
 ```
 
-Writes `{ system_card, digest, user, assistant }` JSONL pairs to `~/.analyzthis_design/training/<persona>.jsonl` from every session where that persona's output was explicitly accepted. Once a persona accumulates ~100–300 accepted pairs, that data is ready for a future fine-tuning pass on an open model — not part of this package yet.
+Writes `{ system_card, digest, user, assistant }` JSONL pairs to `~/.analyzthis_design/training/<persona>.jsonl` from every session where that persona's output was explicitly accepted.
+
+**Correction export** writes `{ assistant_rejected, assistant_preferred, user_comment, tags }` to `~/.analyzthis_design/feedback/<persona>-corrections.jsonl` — useful when users were unhappy or had to rewrite persona output. Every entry is also appended to a global `corrections.jsonl` across projects.
+
+Once a persona accumulates ~100–300 accepted pairs (and optionally correction pairs), that data is ready for a future fine-tuning pass on an open model — not part of this package yet.
+
+---
+
+## Persona feedback — corrections & unhappiness (v1.16)
+
+When a persona gets it wrong, you can record **what was wrong** and **how you fixed it**. This feeds future fine-tuning (negative / DPO pairs) alongside the existing positive `export-training` path.
+
+| Command | Purpose |
+|---------|---------|
+| `feedback record` | Log rating, comment, correction, tags for a persona's last output |
+| `feedback list` | See all feedback for this project (or `--all`) |
+| `feedback export` | Write `{ assistant_rejected, assistant_preferred, … }` JSONL |
+| `session accept --reject --comment …` | Reject + record in one step |
+
+Suggested tags: `wrong_hierarchy`, `invented_tokens`, `missed_ds`, `too_verbose`, `bad_ia`, `off_brief`.
+
+Stored in `session-state.json` → `feedback_log` and appended globally to `~/.analyzthis_design/feedback/corrections.jsonl`.
+
+### Community collection (v1.17) — opt-in submit
+
+For **open-source contributors**, share anonymized corrections with maintainers:
+
+```bash
+npx analyzthis_design feedback record --persona arjun --rating 2 --comment "..." --correction "..."
+npx analyzthis_design feedback submit --dry-run    # preview redacted payload
+npx analyzthis_design feedback submit --all --yes  # send unsent entries (asks consent once)
+npx analyzthis_design feedback status
+```
+
+**What gets sent:** persona, rating, tags, comment, correction, redacted output snippets, anonymous install id, package version.
+
+**What does NOT get sent:** project paths, repo names, emails, API keys, full source trees.
+
+**Maintainer setup (Supabase):**
+
+1. Create a Supabase project
+2. Run `supabase/migrations/001_persona_feedback.sql` in the SQL editor
+3. Copy `supabase/feedback-config.example.json` into `~/.analyzthis_design/config.json` under `"feedback"` (or set env vars `ANALYZTHIS_FEEDBACK_URL` + `ANALYZTHIS_FEEDBACK_ANON_KEY`)
+4. View submissions in Supabase Table Editor → `persona_feedback`
+
+Users can also file GitHub issues via **Persona feedback** template if they prefer not to use CLI submit.
 
 ---
 
@@ -345,7 +434,7 @@ Schema: `agents/design-spec-schema.json`. Producer orchestration: `/design-direc
 Kavi is a **producer** persona (not a critic). One command scans the current repo, **discovers Obsidian vaults and knowledge graphs**, **fetches external URLs**, writes an Obsidian vault with dynamic `Sources/*.md` manifests, optionally enriches notes, then auto-connects and syncs everything into the knowledge bank.
 
 ```
-/collect-knowledge  (or  npx analyzthis_design collect)
+/kavi  (or  npx analyzthis_design collect)
         ↓
   Scan codebase → draft Obsidian notes
         ↓
@@ -443,7 +532,15 @@ npx analyzthis_design status
 
 # Session (agentic)
 npx analyzthis_design session init|show|reset [--project id] [--all]
-npx analyzthis_design session accept --persona <id> [--reject]
+npx analyzthis_design session accept --persona <id> [--reject] [--comment "..."] [--correction "..."] [--rating 1-5] [--tags a,b]
+
+# Persona feedback (v1.16)
+npx analyzthis_design feedback record --persona <id> [--rating 1-5] [--comment "..."] [--correction "..."] [--tags a,b]
+npx analyzthis_design feedback list [--all]
+npx analyzthis_design feedback export [--persona <id>] [--all] [--output path] [--include-positive]
+npx analyzthis_design feedback submit [--persona <id>] [--all] [--yes] [--dry-run]
+npx analyzthis_design feedback status
+npx analyzthis_design feedback revoke
 
 # Research
 npx analyzthis_design research --url <url>
@@ -454,12 +551,13 @@ npx analyzthis_design retrieve --file <csv> --column <col> --keywords a,b [--lim
 
 # Standalone orchestrator
 npx analyzthis_design run --task "..." [--figma URL] [--provider anthropic|openai|google|zai] [--dry-run] [--output path]
-npx analyzthis_design run --task "..." [--lite | --full] [--experts a,b]
+npx analyzthis_design run --task "..." [--lite | --full] [--experts a,b] [--deliberate | --no-deliberate] [--max-rounds N] [--satisfaction 0.4]
 
 # Efficiency / cost
 npx analyzthis_design metrics [--project id] [--all]
 npx analyzthis_design cost [--project id] [--all]
 npx analyzthis_design export-training --persona <id> [--project id] [--all] [--output path]
+npx analyzthis_design feedback export [--persona <id>] [--project id] [--all] [--output path]
 ```
 
 ---
@@ -481,12 +579,17 @@ lib/
   retrieve.js           Filtered, citation-ready CSV row retrieval
   cache.js              On-disk cache for retrieve/kb slices
   export.js             LoRA training-pair export hook
+  feedback.js           Persona unhappiness + correction logging (session + global JSONL)
+  feedback-submit.js    Opt-in anonymized submit to Supabase (community feedback)
+  deliberation.js       Adversarial satisfaction loops, context pack, Raj escalation
   cost.js               $-cost report from metrics × config.pricing
   orchestrator/run.js   Standalone LLM runtime (v2) — MoE, effort-graded tiers, caps, cache-aware
 scripts/obfuscate.js    Build step → dist/
 skills/
-  collect-knowledge/    Kavi — Knowledge Archivist
+  kavi/                 Kavi — Knowledge Archivist (/kavi)
+  collect-knowledge/    Alias for Kavi (backward compatible)
   persona-orchestrator/ Agentic critique entry point
+  deliberation-protocol/ Adversarial review rules (v1.19)
   ux-story-gate/        Task-first gate + DS/MoE/verify/assess phases
   design-critic/        4-persona critique + hierarchy gate
   ux-ideator/           6-phase ideation

package/agents/cards/anuj.md

@@ -20,3 +20,9 @@ Top fix: [one line]
 Full Concept B text wireframe (hierarchy check, primary action, nav level, visible-on-load at full density, keyboard shortcuts, progressive disclosure, rationale) — see `skills/anuj/SKILL.md` "Output — Concept B". Use deep mode for ideation runs or full/deep critiques.
 
 **Citation:** `[filename, row N: "exact quoted value"]` — e.g. `[ux-guidelines.csv, row 22: "..."]`. Only run this persona when task Frequency = daily/weekly.
+
+## Deliberation modes (v1.19)
+
+**Review mode (rounds 0–N-1):** Critique prior output with grounded objections. Default `accepts_prior: false`. Include deliberation JSON block.
+
+**Produce mode (final round):** Full output schema after consensus or Raj. See `skills/deliberation-protocol/SKILL.md`.

package/agents/cards/arjun.md

@@ -21,3 +21,9 @@ Combined score: [X/5]
 Full UX Critique + Visual Design Audit blocks with per-dimension reasons — see `skills/arjun/SKILL.md` "Output format". Use deep mode when the user asks for a full/deep critique, any dimension scores C or below and needs the full rubric quoted, or `default_chain` is running.
 
 **Citation:** `[filename, row N: "exact quoted value"]`. Consult `skills/arjun/SKILL.md` Grade Rubric tables when scoring C or below and rubric detail is needed.
+
+## Deliberation modes (v1.19)
+
+**Review mode (rounds 0–N-1):** Critique prior output with grounded objections. Default `accepts_prior: false`. Include deliberation JSON block.
+
+**Produce mode (final round):** Full output schema after consensus or Raj. See `skills/deliberation-protocol/SKILL.md`.

package/agents/cards/kavi.md

@@ -23,4 +23,4 @@ Knowledge bank: [synced count] → [targets]
 Next: run /persona-orchestrator or any critique persona — they read this bank first.
 ```
 
-Consult `skills/collect-knowledge/SKILL.md` for the host workflow. Prefer running `npx analyzthis_design collect` over re-scanning files in chat.
+Consult `skills/kavi/SKILL.md` for the host workflow. Prefer running `npx analyzthis_design collect` over re-scanning files in chat. Invoke as **`/kavi`** (alias: `/collect-knowledge`).

package/agents/cards/meera.md

@@ -19,3 +19,9 @@ Score: [1-5]
 Full Business Impact block (metric impact, hierarchy check, segment, GTM lever, retention hook, adoption risk, verdict) — see `skills/meera/SKILL.md` "Output format". Use deep mode for full/deep critiques or when `default_chain` is running.
 
 **Citation:** `[filename, row N: "exact quoted value"]` — e.g. `[products.csv, row 6: "..."]`. Consult `skills/meera/SKILL.md` for the full reference-data table when a specific product-type match is needed.
+
+## Deliberation modes (v1.19)
+
+**Review mode (rounds 0–N-1):** Critique prior output with grounded objections. Default `accepts_prior: false`. Include deliberation JSON block.
+
+**Produce mode (final round):** Full output schema after consensus or Raj. See `skills/deliberation-protocol/SKILL.md`.

package/agents/cards/noor.md

@@ -20,3 +20,9 @@ Rationale: [one line, Hick's Law / progressive disclosure]
 Full Concept A text wireframe (hierarchy, primary action, nav level, visible-on-load, progressive disclosure, nav path, rationale) — see `skills/noor/SKILL.md` "Output — Concept A". Use deep mode for ideation runs or full/deep critiques.
 
 **Citation:** `[filename, row N: "exact quoted value"]` — e.g. `[stacks/shadcn.csv, row 8: "..."]`. Consult `skills/noor/SKILL.md` when naming specific components.
+
+## Deliberation modes (v1.19)
+
+**Review mode (rounds 0–N-1):** Critique prior output with grounded objections. Default `accepts_prior: false`. Include deliberation JSON block.
+
+**Produce mode (final round):** Full output schema after consensus or Raj. See `skills/deliberation-protocol/SKILL.md`.

package/agents/cards/priya.md

@@ -19,3 +19,9 @@ Score: [1-5]
 Full Feasibility Analysis block (score, blockers, ranked risks, effort, simpler alternative) — see `skills/priya/SKILL.md` "Output format". Use deep mode for full/deep critiques or when `default_chain` is running.
 
 **Citation:** `[filename, row N: "exact quoted value"]` — e.g. `[stacks/nextjs.csv, row 12: "..."]`. Consult `skills/priya/SKILL.md` for the stack-file table matching the session's tech stack.
+
+## Deliberation modes (v1.19)
+
+**Review mode (rounds 0–N-1):** Critique prior output with grounded objections. Default `accepts_prior: false`. Include deliberation JSON block.
+
+**Produce mode (final round):** Full output schema after consensus or Raj. See `skills/deliberation-protocol/SKILL.md`.

package/agents/cards/raj.md

@@ -21,3 +21,9 @@ What [losing agent] gives up: [named]
 ```
 
 **Citation:** `[filename, row N: "exact quoted value"]`. Consult `skills/raj/SKILL.md` for the ranked product-principles list (Owner governs, Data honesty, Intentionality over automation, Persona density split, PRD scope boundary) and their worked examples before deciding.
+
+## Deliberation modes (v1.19)
+
+**Review mode (rounds 0–N-1):** Critique prior output with grounded objections. Default `accepts_prior: false`. Include deliberation JSON block.
+
+**Produce mode (final round):** Full output schema after consensus or Raj. See `skills/deliberation-protocol/SKILL.md`.

package/agents/cards/zara.md

@@ -22,3 +22,9 @@ If high-frequency working surface: output only "no delight needed here — speed
 Full Delight Pass block (surface, moment, type, specific addition, why-this-one, cost, design-system pointer) — see `skills/zara/SKILL.md` "Output format". Use deep mode for full/deep critiques or when `default_chain` is running.
 
 **Citation:** `[filename, row N: "exact quoted value"]`. Apply the `styles.csv` 5-step filter in `skills/zara/SKILL.md` before citing — never read the full file.
+
+## Deliberation modes (v1.19)
+
+**Review mode (rounds 0–N-1):** Critique prior output with grounded objections. Default `accepts_prior: false`. Include deliberation JSON block.
+
+**Produce mode (final round):** Full output schema after consensus or Raj. See `skills/deliberation-protocol/SKILL.md`.

package/agents/chain.json

@@ -1,20 +1,26 @@
 {
   "description": "Default sequential graph for a full multi-persona critique (design-critic). The MoE router in router.json selects a smaller subset of this chain by default; only run this full chain for an explicit full-screen review.",
   "default_expert_budget": 2,
+  "deliberation_mode": "adversarial",
+  "objection_token_cap": 600,
   "default_chain": [
     { "step": 1, "persona": "arjun",  "handoff_from": null,     "handoff_to": "meera",  "parallel_safe_with": [] },
     { "step": 2, "persona": "meera",  "handoff_from": "arjun",  "handoff_to": "priya",  "parallel_safe_with": ["priya"] },
     { "step": 3, "persona": "priya",  "handoff_from": "meera",  "handoff_to": "zara",   "parallel_safe_with": ["meera"] },
     { "step": 4, "persona": "zara",   "handoff_from": "priya",  "handoff_to": null,     "parallel_safe_with": [] }
   ],
+  "deliberation_groups": {
+    "critique": [["arjun"], ["meera", "priya"], ["zara"]],
+    "ideation": [["meera"], ["noor", "anuj"], ["arjun"], ["zara", "priya"]],
+    "lite": [["arjun"], ["meera"]]
+  },
   "ideation_chain": [
     { "step": 1, "persona": "meera", "handoff_to": ["noor", "anuj"], "parallel_safe_with": [] },
     { "step": 2, "persona": "noor",  "handoff_from": "meera", "handoff_to": "arjun", "parallel_safe_with": ["anuj"] },
     { "step": 2, "persona": "anuj",  "handoff_from": "meera", "handoff_to": "arjun", "parallel_safe_with": ["noor"] },
     { "step": 3, "persona": "arjun", "handoff_from": ["noor", "anuj"], "handoff_to": "zara", "parallel_safe_with": [] },
     { "step": 4, "persona": "zara",  "handoff_from": "arjun", "handoff_to": "priya", "parallel_safe_with": [] },
-    { "step": 5, "persona": "priya", "handoff_from": "zara",  "handoff_to": "raj", "parallel_safe_with": [] },
-    { "step": 6, "persona": "raj",   "handoff_from": "priya", "handoff_to": null, "parallel_safe_with": [] }
+    { "step": 5, "persona": "priya", "handoff_from": "zara",  "handoff_to": null, "parallel_safe_with": [] }
   ],
   "tiers": {
     "router": null,

package/agents/deliberation-schema.json

@@ -0,0 +1,44 @@
+{
+  "description": "Structured output every persona emits during adversarial deliberation rounds (v1.19).",
+  "persona_output_block": {
+    "grounding": [
+      {
+        "type": "task_map | prd | ui_region | ds_token | figma",
+        "ref": "string — e.g. task_map[0], PRD line, header/CTA, --color-primary",
+        "note": "string — why this citation matters"
+      }
+    ],
+    "satisfaction_with_prior": "number 0.0–1.0 — how satisfied with prior persona output",
+    "accepts_prior": "boolean — true only if satisfaction >= threshold",
+    "objections": [
+      {
+        "target_persona": "string — persona id being challenged",
+        "claim": "string — specific claim being contested",
+        "evidence_required": "string — what would resolve this",
+        "blocking": "boolean — must resolve before synthesis",
+        "grounded_in": "string — citation to task/PRD/UI"
+      }
+    ],
+    "questions": ["string — contextual questions about UI, PRD, task, JTBD"],
+    "revisions": ["string — concrete changes required in prior output"],
+    "verdict": "SHIP | REVISE | BLOCK | CONTEST | ACCEPT",
+    "synthesis": "string — optional; full produce-mode output on final round only"
+  },
+  "session_deliberation": {
+    "round": "number — current round index",
+    "max_rounds": "number",
+    "satisfaction_threshold": "number 0.0–1.0",
+    "open_objections": ["object — unresolved objections from round_log"],
+    "round_log": [
+      {
+        "round": "number",
+        "persona": "string",
+        "parsed": "object — parsed deliberation block",
+        "raw_length": "number"
+      }
+    ],
+    "consensus_reached": "boolean",
+    "raj_escalated": "boolean",
+    "mode": "adversarial | legacy"
+  }
+}

package/agents/manifests/kavi.json

@@ -1,7 +1,7 @@
 {
   "id": "kavi",
   "role": "knowledge_archivist",
-  "system_skill": "skills/collect-knowledge/SKILL.md",
+  "system_skill": "skills/kavi/SKILL.md",
   "system_card": "agents/cards/kavi.md",
   "tier": "structured",
   "max_output_tokens": 4000,

package/agents/router.json

@@ -76,10 +76,10 @@
     },
     {
       "problem_type": "collect_knowledge",
-      "signals": ["collect knowledge", "scan codebase", "build vault", "knowledge archivist", "collect-knowledge"],
+      "signals": ["kavi", "/kavi", "collect knowledge", "scan codebase", "build vault", "knowledge archivist", "collect-knowledge"],
       "route_to": ["kavi"],
       "never_route_to": ["design-critic_chain", "zara", "arjun", "meera", "priya"],
-      "notes": "Producer only — run /collect-knowledge or `npx analyzthis_design collect`. Never part of a critique chain."
+      "notes": "Producer only — run /kavi or `npx analyzthis_design collect`. Never part of a critique chain."
     }
   ]
 }

package/agents/session-schema.json

@@ -52,8 +52,33 @@
       "spec_verdict": "object — arjun_visual, ds_gate, hierarchy_gate, notes",
       "updated_at": "ISO 8601"
     },
+    "feedback_log": [
+      {
+        "id": "string — unique feedback entry id",
+        "at": "ISO 8601",
+        "persona": "string — persona id",
+        "satisfied": "boolean — true if user was happy",
+        "rating": "number | null — 1 (very unhappy) to 5 (very happy)",
+        "comment": "string — what was wrong or what they liked",
+        "correction": "string — how the user corrected or what they wanted instead",
+        "tags": ["string — e.g. wrong_hierarchy, invented_tokens, off_brief"],
+        "original_output": "string — snapshot of persona output at feedback time",
+        "submitted_at": "ISO 8601 | omitted — set when feedback submit succeeds",
+        "context": "object — task_map_summary, problem_type, mode"
+      }
+    ],
     "vault_path": "string — Obsidian vault written by Kavi collect (empty until first collect)",
     "last_collect_at": "ISO 8601 timestamp — last successful collect run",
+    "deliberation": {
+      "round": "number — current deliberation round",
+      "max_rounds": "number",
+      "satisfaction_threshold": "number 0.0–1.0",
+      "open_objections": ["object — unresolved blocking objections"],
+      "round_log": ["object — per-persona per-round parsed output"],
+      "consensus_reached": "boolean",
+      "raj_escalated": "boolean",
+      "mode": "adversarial | legacy"
+    },
     "digest": {
       "task_map_summary": "string — short summary passed to persona calls instead of the full task_map/persona_outputs history",
       "hierarchy_top3": ["string — top 3 ranked hierarchy items, if declared"],
@@ -71,7 +96,11 @@
       "cache_hits": "number — retrieve/cache hits during the last run",
       "mode": "lite | full",
       "effort_log": [{ "persona": "string", "effort": "trivial|standard|hard", "model": "string|null", "scoped_mode": "string|null" }],
-      "cost_usd": "number — estimated $ cost of the run from config.pricing (0 when pricing missing)"
+      "cost_usd": "number — estimated $ cost of the run from config.pricing (0 when pricing missing)",
+      "deliberation_rounds": "number — adversarial rounds executed in last run",
+      "objections_raised": "number",
+      "objections_resolved": "number",
+      "raj_escalations": "number"
     }
   }
 }