@mindrian_os/cli 2.0.0-beta.3 → 2.0.0-beta.33

package/skills/mullins-scaffold/SKILL.md

@@ -0,0 +1,132 @@
+---
+name: mullins-scaffold
+description: >
+  Room scaffolding around the Mullins Seven Domains of Attractive Opportunities
+  (Market, Industry, Sustainable Advantage, Mission/Aspirations, Ability to
+  Execute on Critical Success Factors, Connectedness Up the Value Chain,
+  Connectedness Down the Value Chain). Use ONLY when the navigator explicitly
+  asks to scaffold a room around the Mullins Seven Domains, names Mullins or
+  the Seven Domains directly, or ignite's own front door has resolved toward
+  a market-attractiveness structure. Do NOT use for a general "let's assess
+  this opportunity" remark with no Mullins-specific ask -- that stays in
+  conversation (or routes through /mos:ignite's front door). Backed by
+  skills/mullins-scaffold/scaffold.json (the section definitions and prompts).
+license: BSL-1.1. See LICENSE for complete terms (Business Source License 1.1, Change Date 2030-04-16 to Apache License 2.0).
+# --- Phase 143.3 connector frontmatter ---
+connector:
+  connects_to_spine: true
+  sensor_triggers: []
+  reach_id: brain_consult
+  sub_mode: mullins-scaffold
+  posture: hold
+  hierarchy_rank: 13
+  filing: fileEvidenceWithReadback
+  plan_gated: false
+  web_scope: null
+  surface: F.1
+hitl_shape: "F.1"
+hitl_why: "Each of the seven domain folders is offered at an F.1 Decision Gate before creation, never auto-imposed on the room."
+---
+
+<!-- mos:firing-block v2 -->
+At this skill's Decision Gate, when the fork is genuinely unanswered and relevant to the
+current conversation, fire the AskUserQuestion card natively rather than printing a bare
+numbered menu or bullet list. Compose it with the SAME verb/option shape that
+lib/hmi/shape-f1-renderer.cjs (renderShapeF1) produces and that lib/hmi/selector-dispatcher.cjs
+(appendAskUserQuestionTrailer) fires, matching this skill's declared hitl_shape. Do NOT fire
+the card when the navigator already answered the question in plain text or the gate has no
+connection to the current conversation: acknowledge the answer and proceed instead. Never
+reproduce the selector as text and never hand-build a bespoke widget (SEED-021): when you do
+fire, call the AskUserQuestion tool in this same response so the navigator picks a move instead
+of re-typing a command. Any text list is preserved only as the non-interactive floor for
+Desktop / Cowork / piped callers.
+<!-- /mos:firing-block -->
+
+# Mullins Scaffold -- Seven Domains of Attractive Opportunities
+
+## What this scaffold is
+
+This scaffold structures a venture room around John Mullins's Seven Domains of
+Attractive Opportunities, the diagnostic at the heart of "The New Business Road
+Test." The seven domains split into two axes -- market and industry attractiveness
+(macro and micro) on one side, and the team plus its connectedness up and down
+the value chain on the other. Each domain asks a focused question: how large is
+the market today and in five years, how attractive is the industry on Porter's
+five forces, what beachhead segment will the venture win first, what mission and
+risk appetite the founding team carries, which critical success factors must go
+right, and which value-chain relationships unlock the venture. Used as a Data Room
+skeleton at the early or opportunity stage, the seven domains give the navigator a
+near-decomposable structure: each domain is a subsystem with strong internal
+cohesion and weak coupling to the others, so a finding in "Industry Dynamics" can
+be filed without disturbing "Team Mission." Generated from Mullins Seven Domains
+(Phase 84-04, v1.10.8).
+
+## The data file
+
+The canonical section list lives in `skills/mullins-scaffold/scaffold.json`. That
+file carries `version`, `generated_from`, and a `sections[]` array. Each section
+has `id`, `domain`, `title`, `prompt`, and `required`. Room-scaffolding code (and
+`/mos:scaffold`-style flows) reads this JSON to build the folder skeleton -- one
+folder per section, each with its ROOM.md identity file and the section prompt as
+the opening question. The JSON is the source of truth; this SKILL.md is the human
+and agent-facing index that points at it. When the domain list changes, edit the
+JSON; this index describes the shape, not the contents.
+
+## When Larry should reach for this
+
+- A navigator is creating a new venture room and has no structure yet.
+- An opportunity-bank deep-dive needs to assess a banked opportunity against the
+  same seven axes a venture would be tested on.
+- A market-attractiveness review is requested (Porter five forces, market sizing,
+  beachhead segment selection) and the room lacks a place to file it.
+- Two ventures need to be compared on the same axes -- the seven domains give a
+  shared coordinate system.
+- A team-readiness check is needed (mission, aspirations, propensity for risk,
+  critical success factors).
+
+## Brain-driven cross-framework folders (additive)
+
+Beyond the seven fixed Mullins domains, the scaffold proposes a small set of
+complementary folders drawn from the frameworks Mullins FEEDS_INTO. These live in
+`scaffold.json` under `brain_folders[]` and today number three: Value Proposition
+(the precise value the offering delivers to the beachhead segment), Disruptive vs
+Sustaining Posture (whether the venture sustains an incumbent trajectory or
+disrupts from a new-market or low-end foothold), and Systems Map (the feedback
+loops, stocks, and leverage points that govern the venture as a nested system).
+Each folder carries its source framework name, a domain label, an opening prompt,
+the literal `feeds_into_source` origin "Mullins Seven Domains", and `offered: true`.
+
+These folders are OFFERED at a Decision Gate, never auto-imposed. The navigator
+approves which frameworks' folders to add (per Canon Part 3, GUIDED default); the
+`offered: true` flag tells consumers to route the proposal through that gate rather
+than materializing the folder silently. The Brain supplies only the framework names
+and domain labels for the proposal -- generic methodology handles, never user
+artifacts, meetings, decisions, or content (Canon Part 8). The Part-8-clean query
+that asks the Brain for these neighbors carries only the framework handle "Mullins
+Seven Domains" plus a problem-type enum; see `buildBrainFolderQuery` in
+`lib/core/mullins-scaffold.cjs`.
+
+## Ackoff bidirectional traversal
+
+The scaffold also renders the Ackoff DIKW traversal that structures how the seven
+domains fill and validate. It lives in `scaffold.json` under `ackoff_traversal`,
+with `ascent[]`, `descent[]`, a `brain_chain` (Systems Thinking, MAP THE HIERARCHY),
+and a `validation_center` ("Validation"). The ASCENT fills the domains toward
+Validation-at-center: Data in the domain folders rises through Information and
+Knowledge to Wisdom (a validated decision) at the center. The DESCENT is the New
+Business Road Test validation loop: Validation decomposes back down to re-test each
+domain's connections, structure, and underlying data and assumptions.
+
+This is additive doctrine, not a new one. The ascent/descent labels reuse the
+"bidirectional Ackoff ascent" already carried in `skills/larry-personality`: the
+ascent earns evidence up the levels (push_forward when Validation holds), and the
+descent re-tests assumptions (pull_back when a gap surfaces). The traversal here
+does not contradict that doctrine -- it renders it as scaffold structure.
+
+## Relationship to other scaffolds
+
+This is one of several room scaffolds; it is the market-attractiveness lens,
+complementary to the PWS section structure (`skills/pws-methodology`). PWS organizes
+a room around the venture-design pipeline; the Mullins scaffold organizes it around
+the opportunity-attractiveness diagnostic. A room can carry both -- they answer
+different questions.

package/skills/mullins-scaffold/scaffold.json

@@ -0,0 +1,223 @@
+{
+  "version": 2,
+  "generated_from": "Mullins Seven Domains of Attractive Opportunities (Phase 84-04, v1.10.8)",
+  "sections": [
+    {
+      "id": "market-size-now",
+      "domain": "market",
+      "title": "Market Size Today",
+      "prompt": "How large is the addressable market right now in units, customers, and dollars?",
+      "required": false
+    },
+    {
+      "id": "market-size-five-years",
+      "domain": "market",
+      "title": "Market Size in Five Years",
+      "prompt": "How large will the addressable market be five years out, and what drives that growth?",
+      "required": false
+    },
+    {
+      "id": "market-benefits",
+      "domain": "market",
+      "title": "Market-Level Benefits",
+      "prompt": "What benefits does this market deliver that customers cannot easily get elsewhere?",
+      "required": false
+    },
+    {
+      "id": "macro-trends",
+      "domain": "market-attractiveness",
+      "title": "Macro Trends",
+      "prompt": "Which macro trends make this market more or less attractive over the planning horizon?",
+      "required": false
+    },
+    {
+      "id": "political-regulatory",
+      "domain": "market-attractiveness",
+      "title": "Political and Regulatory Climate",
+      "prompt": "What political, legal, and regulatory forces shape this market's attractiveness?",
+      "required": false
+    },
+    {
+      "id": "economic-cycles",
+      "domain": "market-attractiveness",
+      "title": "Economic Cycles",
+      "prompt": "How sensitive is this market to economic cycles, interest rates, and capital availability?",
+      "required": false
+    },
+    {
+      "id": "social-cultural",
+      "domain": "market-attractiveness",
+      "title": "Social and Cultural Forces",
+      "prompt": "Which social and cultural shifts pull customers toward or away from this market?",
+      "required": false
+    },
+    {
+      "id": "beachhead-segment",
+      "domain": "target-segment",
+      "title": "Beachhead Segment",
+      "prompt": "Which narrowly defined customer segment will the venture win first, and why them?",
+      "required": false
+    },
+    {
+      "id": "segment-benefits",
+      "domain": "target-segment",
+      "title": "Segment-Specific Benefits",
+      "prompt": "What unique benefits does this segment receive that no incumbent currently delivers?",
+      "required": false
+    },
+    {
+      "id": "segment-reachability",
+      "domain": "target-segment",
+      "title": "Segment Reachability",
+      "prompt": "How will the venture reach this segment economically and at scale?",
+      "required": false
+    },
+    {
+      "id": "porter-rivalry",
+      "domain": "industry-dynamics",
+      "title": "Competitive Rivalry",
+      "prompt": "How intense is rivalry among existing competitors in this industry?",
+      "required": false
+    },
+    {
+      "id": "porter-suppliers",
+      "domain": "industry-dynamics",
+      "title": "Supplier Power",
+      "prompt": "How much bargaining power do suppliers hold over participants in this industry?",
+      "required": false
+    },
+    {
+      "id": "porter-buyers",
+      "domain": "industry-dynamics",
+      "title": "Buyer Power",
+      "prompt": "How much bargaining power do buyers hold, and how price-sensitive are they?",
+      "required": false
+    },
+    {
+      "id": "porter-barriers-to-entry",
+      "domain": "industry-dynamics",
+      "title": "Barriers to Entry",
+      "prompt": "What barriers protect insiders from new entrants, and which ones can the venture build?",
+      "required": false
+    },
+    {
+      "id": "porter-substitutes",
+      "domain": "industry-dynamics",
+      "title": "Substitute Threats",
+      "prompt": "What substitutes could replace this industry's offering and at what cost?",
+      "required": false
+    },
+    {
+      "id": "team-mission",
+      "domain": "mission",
+      "title": "Team Mission",
+      "prompt": "What is the founding team's mission and why is this team the one to pursue it?",
+      "required": false
+    },
+    {
+      "id": "team-aspirations",
+      "domain": "mission",
+      "title": "Team Aspirations",
+      "prompt": "What outcomes does the team aspire to over the next three to seven years?",
+      "required": false
+    },
+    {
+      "id": "team-propensity-for-risk",
+      "domain": "mission",
+      "title": "Propensity for Risk",
+      "prompt": "How much risk is the team willing and able to absorb, and across which dimensions?",
+      "required": false
+    },
+    {
+      "id": "execution-critical-success-factors",
+      "domain": "ability-to-execute",
+      "title": "Critical Success Factors",
+      "prompt": "Which few things must go right for this venture to succeed, and how will the team ensure them?",
+      "required": false
+    },
+    {
+      "id": "value-chain-connections",
+      "domain": "connectedness",
+      "title": "Value Chain Connections",
+      "prompt": "Which upstream, downstream, and lateral relationships in the value chain unlock this venture?",
+      "required": false
+    }
+  ],
+  "brain_folders": [
+    {
+      "id": "value-proposition",
+      "framework": "Value Proposition",
+      "domain": "value-proposition",
+      "title": "Value Proposition",
+      "prompt": "What precise value does the offering deliver to the beachhead segment, and how is it worth paying for?",
+      "feeds_into_source": "Mullins Seven Domains",
+      "offered": true
+    },
+    {
+      "id": "disruptive-innovation",
+      "framework": "Disruptive Innovation",
+      "domain": "disruption-posture",
+      "title": "Disruptive vs Sustaining Posture",
+      "prompt": "Is this venture sustaining an incumbent trajectory or disrupting from a new-market or low-end foothold?",
+      "feeds_into_source": "Mullins Seven Domains",
+      "offered": true
+    },
+    {
+      "id": "systems-thinking",
+      "framework": "Systems Thinking",
+      "domain": "systems-map",
+      "title": "Systems Map",
+      "prompt": "Which feedback loops, stocks, and leverage points govern this venture as a nested system?",
+      "feeds_into_source": "Mullins Seven Domains",
+      "offered": true
+    }
+  ],
+  "ackoff_traversal": {
+    "validation_center": "Validation",
+    "brain_chain": ["Systems Thinking", "MAP THE HIERARCHY"],
+    "ascent": [
+      {
+        "level": "Data",
+        "label": "Domain data gathered",
+        "movement": "Fill each Mullins domain folder with raw facts, figures, and observations toward Validation-at-center"
+      },
+      {
+        "level": "Information",
+        "label": "Domains structured",
+        "movement": "Relate the domain data into patterns and answered prompts, climbing toward Validation"
+      },
+      {
+        "level": "Knowledge",
+        "label": "Cross-domain connections earned",
+        "movement": "Connect the structured domains into a coherent opportunity read, earning evidence up the levels toward Validation"
+      },
+      {
+        "level": "Wisdom",
+        "label": "Validation at center",
+        "movement": "Resolve the connected domains into a validated go decision at the Validation center -- the ascent confirms confidence is backed"
+      }
+    ],
+    "descent": [
+      {
+        "level": "Wisdom",
+        "label": "Validation decomposes",
+        "movement": "Begin the New Business Road Test loop: Validation decomposes back to interrogate the validated read"
+      },
+      {
+        "level": "Knowledge",
+        "label": "Re-test connections",
+        "movement": "Re-test each cross-domain connection against fresh evidence, pulling back to expose weak couplings"
+      },
+      {
+        "level": "Information",
+        "label": "Re-test structure",
+        "movement": "Re-test the structured domains, surfacing assumptions that no longer hold"
+      },
+      {
+        "level": "Data",
+        "label": "Re-test domain data",
+        "movement": "Decompose down to re-test each domain's underlying data and assumptions -- the descent re-tests what the ascent earned"
+      }
+    ]
+  }
+}

package/skills/mva-brief/SKILL.md

@@ -0,0 +1,87 @@
+---
+name: mva-brief
+description: Run the 30-second MVA pipeline for the user's current venture sentence
+license: BSL-1.1. See LICENSE for complete terms (Business Source License 1.1, Change Date 2030-04-16 to Apache License 2.0).
+help_jtbd: "Build a Minimum Viable Argument brief from your room."
+body_shape: E
+hitl_shape: "F.1"
+hitl_why: "The 30-second brief closes with a numbered option or free-text choice, the canonical F.1 Next Move."
+argument-hint: (no args -- reads pending state from UserPromptSubmit detection)
+serves_jtbd: ["explore"]
+teaching: "When you have just typed a venture sentence and want a brief in under a minute, /mos:mva-brief runs the 6-agent fan-out and deploys a shareable deck. The reward-before-investment surface of Phase 118."
+allowed-tools: Bash, AskUserQuestion
+interactive_first_reward: instant_brief
+# --- Phase 144.1 connector frontmatter ---
+connector:
+  connects_to_spine: true
+  sensor_triggers: []
+  reach_id: deep_research
+  sub_mode: mva-brief
+  framework: null
+  posture: push_forward
+  hierarchy_rank: 10
+  filing: none
+  plan_gated: false
+  web_scope: null
+---
+
+<!-- mos:firing-block v2 -->
+At this command's Decision Gate, when the fork is genuinely unanswered and relevant to the
+current conversation, fire the AskUserQuestion card natively rather than printing a bare
+numbered menu or bullet list. Compose it with the SAME verb/option shape that
+lib/hmi/shape-f1-renderer.cjs (renderShapeF1) produces and that lib/hmi/selector-dispatcher.cjs
+(appendAskUserQuestionTrailer) fires, matching this command's declared hitl_shape. Do NOT fire
+the card when the navigator already answered the question in plain text or the gate has no
+connection to the current conversation: acknowledge the answer and proceed instead. Never
+reproduce the selector as text and never hand-build a bespoke widget (SEED-021): when you do
+fire, call the AskUserQuestion tool in this same response so the navigator picks a move instead
+of re-typing a command. Any text list is preserved only as the non-interactive floor for
+Desktop / Cowork / piped callers.
+<!-- /mos:firing-block -->
+
+# /mos:mva-brief
+
+Run the 30-second MVA pipeline against the pending venture sentence detected by
+the UserPromptSubmit hook (Plan 118-00).
+
+## What this does
+
+1. Reads pending state from `~/.mindrian/mva/<session-id>.json` (written by
+   Plan 118-00 detection hook).
+2. Fires 6 parallel agents (Brain similar + Brain cross-domain + Brain classic
+   traps + Tavily funding + Six-hats red/black + Dashboard graph) under the
+   45-second hard budget.
+3. Streams agent results as they return -- each one rendered in Larry's
+   GUIDED voice (per feedback_larry_pedagogical_guided_first.md).
+4. Closes with the 3-option footer:
+   - [1] Just tell me what's new (stay in "tell me" mode)
+   - [2] Build a room around this (invest)
+   - [3] Challenge me -- Devil's Advocate (go deeper cognitively)
+
+## Instructions for the model
+
+Invoke `node "${MINDRIAN_OS_ROOT:-${CLAUDE_PLUGIN_ROOT:?MindrianOS install root not found. Set MINDRIAN_OS_ROOT (see lib/core/active-plugin-root.cjs) or run from Claude Code.}}/scripts/mva-run.cjs"` via Bash with no arguments. The script reads
+the pending state file, runs the orchestrator, and writes the rendered output
+to stdout.
+
+Relay the stdout to the user VERBATIM. Do NOT:
+
+- Add commentary or interpretation before the rendered output
+- Re-summarize the agent findings ("So basically what this means is...")
+- Skip the 3-option footer
+- Autonomously pick option 1, 2, or 3 for the user
+- Add Larry-voice framing ("Here's what I found for you...") -- the renderer
+  already speaks in Larry's voice; double-voicing breaks the GUIDED tone
+
+The 3-option footer IS the user's decision point. Wait for the user to type
+1, 2, or 3 (or their own free-text), then route per the option behavior:
+
+- 1: stay in JUST_TALK mode; keep brief in scrollback; user can ask follow-ups
+- 2: invoke /mos:new-project (stub for v1.13.0; Phase 119 wires fully)
+- 3: invoke /mos:challenge-assumptions against the brief
+
+## Canon parts implemented
+
+- Part 2 (team around navigator -- 6 agents as a parallel team)
+- Part 8 (boundary -- agents send only generic handles to Brain / Tavily)
+- Part 10 sub-claim 3 (room as receipt -- the brief IS the reward)

package/skills/mva-option/SKILL.md

@@ -0,0 +1,120 @@
+---
+name: mva-option
+description: Route the user's 3-option footer selection after a 30-second MVA brief
+license: BSL-1.1. See LICENSE for complete terms (Business Source License 1.1, Change Date 2030-04-16 to Apache License 2.0).
+help_jtbd: "Compose option packages for your MVA."
+body_shape: E
+hitl_shape: "F.8"
+hitl_why: "Candidate options are surfaced as an independent set to weigh in any order before a pick."
+argument-hint: <1|2|3> [<sha8>]
+serves_jtbd: ["explore"]
+teaching: "When the 3-option footer shows after an MVA brief, /mos:mva-option routes your pick (refine / build a room / iterate) into the right next move. The hand-off after the first reward."
+allowed-tools: Bash, AskUserQuestion
+interactive_first_reward: --none (scripting only)
+# --- Phase 144.1 connector frontmatter ---
+connector:
+  connects_to_spine: true
+  sensor_triggers: []
+  reach_id: context_block
+  sub_mode: mva-option
+  framework: null
+  posture: push_forward
+  hierarchy_rank: 11
+  filing: none
+  plan_gated: false
+  web_scope: null
+---
+
+<!-- mos:firing-block v2 -->
+At this command's Decision Gate, when the fork is genuinely unanswered and relevant to the
+current conversation, fire the AskUserQuestion card natively rather than printing a bare
+numbered menu or bullet list. Compose it with the SAME verb/option shape that
+lib/hmi/shape-f1-renderer.cjs (renderShapeF1) produces and that lib/hmi/selector-dispatcher.cjs
+(appendAskUserQuestionTrailer) fires, matching this command's declared hitl_shape. Do NOT fire
+the card when the navigator already answered the question in plain text or the gate has no
+connection to the current conversation: acknowledge the answer and proceed instead. Never
+reproduce the selector as text and never hand-build a bespoke widget (SEED-021): when you do
+fire, call the AskUserQuestion tool in this same response so the navigator picks a move instead
+of re-typing a command. Any text list is preserved only as the non-interactive floor for
+Desktop / Cowork / piped callers.
+<!-- /mos:firing-block -->
+
+# /mos:mva-option <N> [<sha8>]
+
+Route the user's selection from the 3-option footer that appears after a 30-second MVA brief.
+
+## Why this exists
+
+The 3-option footer renders after every MVA brief (per binding decision B4):
+
+```
+What now?
+  [1] Just tell me what's new         (stay in "tell me" mode)
+  [2] Build a room around this        (invest)
+  [3] Challenge me -- Devil's Advocate (go deeper cognitively)
+```
+
+The user types `1`, `2`, or `3` (or `/mos:mva-option N` directly). This command dispatches the routing.
+
+## Arguments
+
+- `<N>` (required): `1`, `2`, or `3` -- the user's selection
+- `[<sha8>]` (optional): the 8-char prefix identifying the target brief. When OMITTED, the command auto-discovers the most recent brief by calling `resolveCurrentSha8()` which reads `~/.mindrian/mva/state.json` (the manifest atomically written by Plan 118-03's orchestrator after `mva_brief_rendered` fires).
+
+## How to invoke
+
+The model invokes this command via Bash + Node. Two patterns:
+
+**With explicit sha8:**
+
+```bash
+node -e "const r=require('./lib/core/mva-option-router.cjs'); r.routeOption(N, '<sha8>').then(out => console.log(JSON.stringify(out, null, 2)))"
+```
+
+**Without sha8 (auto-resolve via state.json):**
+
+```bash
+node -e "const r=require('./lib/core/mva-option-router.cjs'); const sha=r.resolveCurrentSha8(); if(!sha){console.log(JSON.stringify({ok:false,error:'no_current_brief',message:'No recent brief found. Type your venture sentence to fire the pipeline.'}));process.exit(0);} r.routeOption(N, sha).then(out => console.log(JSON.stringify(out, null, 2)))"
+```
+
+The auto-resolve form is what the `mva-pipeline` skill instructs the model to run when the user types `1`, `2`, or `3` as a plain message immediately after a brief renders. See the "## Routing the 3-option footer" section in `skills/mva-pipeline/SKILL.md` for the full recognition rule.
+
+## What happens per option
+
+- **Option 1** -- operator transitions to `JUST_TALK`; the brief stays in scrollback; the user can ask any follow-up about the 6 cells. The router returns `{ action: 'stay_in_just_talk', next_state: 'JUST_TALK', message: ... }`.
+
+- **Option 2** -- operator unchanged; the router returns `{ action: 'phase_119_stub', next_state: null, message: STUB_MESSAGE_119 }`. The stub message reads:
+
+  > Building a room around this is the next layer; shipping in beta.18 (Phase 119). For now, press option 1 to keep this brief visible, or option 3 to go deeper.
+
+  Per binding decision B6 OPTION A, option 2 is deferred to Phase 119 / v1.13.0-beta.18. The router does NOT invoke `/mos:new-project` in v1.13.0.
+
+- **Option 3** -- operator transitions to `METHODOLOGY`; the router returns `{ action: 'invoke_challenge_assumptions', next_state: 'METHODOLOGY', invoke_command: '/mos:challenge-assumptions --from-brief <sha8>' }`. The model then runs the named slash command against the brief.
+
+## Edge cases
+
+| Situation | Router return | Model surfaces |
+| --------- | ------------- | -------------- |
+| No `state.json` (fresh install / Hebrew refusal) | wrapper short-circuits | "No recent brief found. Type your venture sentence to fire the pipeline." |
+| Side-file `<sha8>.json` missing (brief expired) | `{ ok:false, error:'brief_not_found' }` | "The brief data has expired or was not deployed. Type your sentence again to re-fire the pipeline." |
+| `mva_brief_rendered` event not yet logged (pipeline still streaming) | `{ ok:false, error:'brief_still_rendering' }` | "Brief is still rendering -- options will activate when it completes." |
+| Invalid `N` (0, 4, 99, "1", null) | `{ ok:false, error:'invalid_option' }` | Treat as free-text; route through normal Larry conversation. |
+
+## Telemetry
+
+Each successful invocation emits `mva_option_selected` to `~/.mindrian/telemetry/v1.13/mva.jsonl` with the frozen `ALLOWED_FIELDS` schema:
+
+```
+{ sentence_sha256, option_id, time_to_click_ms }
+```
+
+`time_to_click_ms` is computed from the most recent `mva_brief_rendered` event timestamp for the brief's `sentence_sha256`. Plan 118-06's Dror 2.0 harness reads these events to validate "subject types one sentence and clicks an option within 60 seconds of brief rendering."
+
+Per Canon Part 8: the telemetry payload carries ONLY the sha256 hash + option_id + time delta. Zero user content. Zero URLs.
+
+## Canon parts implemented
+
+- Part 3 (Tri-Context Decision Gate) -- the 3-option footer IS a Decision Gate offering a closed-vocabulary choice (verbs 7 Synthesize / 8 Bank Opportunity / 5 Devil's Advocate)
+- Part 4 (Every Choice Is Graph Data) -- `mva_option_selected` telemetry captures every click; operator transitions write `OPERATOR_TRANSITION` edges to the local room graph (Phase 99 substrate)
+- Part 8 (Graph Boundary) -- zero user content in telemetry; zero raw_sentence reads from the side-file; the router source passes the forbidden-token sweep
+- Part 10 sub-claim 3 (room as receipt) -- the 3-option footer is the user's self-selected commitment level immediately after the reward (the brief itself)