@wazir-dev/cli 1.1.0 → 1.3.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@wazir-dev/cli",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "type": "module",
   "description": "Host-native engineering OS kit for AI coding agents — roles, phases, expertise modules, quality gates for Claude, Codex, Gemini & Cursor",
   "bin": {
@@ -29,7 +29,7 @@
   ],
   "scripts": {
     "test": "npm run test:active",
-    "test:active": "node --test tooling/test/cli.test.js tooling/test/validate.test.js tooling/test/index.test.js tooling/test/doctor-status.test.js tooling/test/guard-hooks.test.js tooling/test/export.test.js tooling/test/capture.test.js tooling/test/schema-examples.test.js tooling/test/git-flow-docs.test.js tooling/test/role-contracts.test.js tooling/test/ci-workflow.test.js tooling/test/contributing.test.js tooling/test/author-artifact.test.js tooling/test/capture/usage.test.js tooling/test/docs-drift.test.js tooling/test/init.test.js",
+    "test:active": "node --test tooling/test/cli.test.js tooling/test/validate.test.js tooling/test/index.test.js tooling/test/doctor-status.test.js tooling/test/guard-hooks.test.js tooling/test/export.test.js tooling/test/capture.test.js tooling/test/schema-examples.test.js tooling/test/git-flow-docs.test.js tooling/test/role-contracts.test.js tooling/test/ci-workflow.test.js tooling/test/contributing.test.js tooling/test/author-artifact.test.js tooling/test/capture/usage.test.js tooling/test/adapters/composition-engine.test.js tooling/test/docs-drift.test.js tooling/test/init.test.js tooling/test/gating/agent.test.js tooling/test/guards/phase-prerequisite-guard.test.js tooling/test/hooks/context-mode-router.test.js tooling/test/hooks/session-start.test.js tooling/test/input-scanning.test.js tooling/test/init/auto-detect.test.js tooling/test/adapters/model-router.test.js tooling/test/state/db.test.js tooling/test/reports/phase-report.test.js tooling/test/logo-svg.test.js tooling/test/adapters/context-mode.test.js tooling/test/verify/proof-collector.test.js",
     "test:coverage": "c8 npm run test:active",
     "prepare": "husky"
   },
@@ -61,9 +61,7 @@
     "tdd"
   ],
   "dependencies": {
-    "@inquirer/prompts": "^8.3.2",
     "ajv": "^8.18.0",
-    "gray-matter": "^4.0.3",
     "yaml": "^2.0.0"
   },
   "devDependencies": {

package/schemas/hook.schema.json

@@ -23,7 +23,8 @@
         "pre_compact_summary",
         "stop_handoff_harvest",
         "protected_path_write_guard",
-        "loop_cap_guard"
+        "loop_cap_guard",
+        "context_mode_router"
       ]
     },
     "description": { "type": "string", "minLength": 1 },

package/schemas/phase-report.schema.json

@@ -0,0 +1,89 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://wazir.dev/schemas/phase-report.schema.json",
+  "title": "Phase Report",
+  "type": "object",
+  "required": ["phase_name", "run_id", "timestamp", "attempted_actions", "drift_analysis", "quality_metrics", "risk_flags", "decisions"],
+  "properties": {
+    "phase_name": { "type": "string", "minLength": 1 },
+    "parent_phase": {
+      "type": "string",
+      "enum": ["init", "clarifier", "executor", "final_review"],
+      "description": "Top-level phase this workflow belongs to"
+    },
+    "workflow": {
+      "type": "string",
+      "description": "Specific workflow name within the parent phase (e.g. discover, specify, execute)"
+    },
+    "run_id": { "type": "string", "minLength": 1 },
+    "timestamp": { "type": "string", "format": "date-time" },
+    "attempted_actions": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "required": ["description", "outcome", "evidence"],
+        "properties": {
+          "description": { "type": "string", "minLength": 1 },
+          "outcome": { "type": "string", "enum": ["success", "fail", "uncertain"] },
+          "evidence": { "type": "string" }
+        },
+        "additionalProperties": true
+      }
+    },
+    "drift_analysis": {
+      "type": "object",
+      "required": ["delta"],
+      "properties": {
+        "delta": { "type": "integer", "minimum": 0 },
+        "description": { "type": "string" }
+      },
+      "additionalProperties": true
+    },
+    "quality_metrics": {
+      "type": "object",
+      "properties": {
+        "test_pass_count": { "type": "integer", "minimum": 0 },
+        "test_fail_count": { "type": "integer", "minimum": 0 },
+        "lint_errors": { "type": "integer", "minimum": 0 },
+        "type_errors": { "type": "integer", "minimum": 0 }
+      },
+      "additionalProperties": true
+    },
+    "risk_flags": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "required": ["severity", "description"],
+        "properties": {
+          "severity": { "type": "string", "enum": ["low", "medium", "high"] },
+          "description": { "type": "string", "minLength": 1 },
+          "mitigation": { "type": "string" }
+        },
+        "additionalProperties": true
+      }
+    },
+    "decisions": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "required": ["description", "rationale"],
+        "properties": {
+          "description": { "type": "string", "minLength": 1 },
+          "rationale": { "type": "string", "minLength": 1 },
+          "alternatives_considered": { "type": "array", "items": { "type": "string" } },
+          "source": { "type": "string" }
+        },
+        "additionalProperties": true
+      }
+    },
+    "verdict_recommendation": {
+      "type": "object",
+      "properties": {
+        "verdict": { "type": "string", "enum": ["continue", "loop_back", "escalate"] },
+        "reasoning": { "type": "string" }
+      },
+      "additionalProperties": true
+    }
+  },
+  "additionalProperties": true
+}

package/schemas/usage.schema.json

@@ -4,7 +4,7 @@
   "title": "Usage Report",
   "description": "Per-run token usage tracking and context savings data.",
   "type": "object",
-  "required": ["schema_version", "run_id", "created_at", "updated_at", "phases", "roles", "savings", "totals"],
+  "required": ["schema_version", "run_id", "created_at", "updated_at", "phases", "roles", "savings", "routing", "totals"],
   "properties": {
     "schema_version": { "type": "integer", "const": 1 },
     "run_id": { "type": "string", "minLength": 1 },
@@ -81,6 +81,30 @@
             "post_compaction_tokens_est": { "type": "integer", "minimum": 0 }
           },
           "additionalProperties": false
+        },
+        "index_queries": {
+          "type": "object",
+          "properties": {
+            "count": { "type": "integer", "minimum": 0 },
+            "total_raw_bytes": { "type": "integer", "minimum": 0 },
+            "total_summary_bytes": { "type": "integer", "minimum": 0 },
+            "estimated_tokens_saved": { "type": "integer", "minimum": 0 },
+            "bytes_avoided": { "type": "integer", "minimum": 0 }
+          },
+          "additionalProperties": false
+        }
+      },
+      "additionalProperties": false
+    },
+    "routing": {
+      "type": "object",
+      "properties": {
+        "total_commands": { "type": "integer", "minimum": 0 },
+        "context_mode_routed": { "type": "integer", "minimum": 0 },
+        "passthrough": { "type": "integer", "minimum": 0 },
+        "by_category": {
+          "type": "object",
+          "additionalProperties": { "type": "integer", "minimum": 0 }
         }
       },
       "additionalProperties": false

package/schemas/wazir-manifest.schema.json

@@ -87,6 +87,25 @@
       "uniqueItems": true,
       "minItems": 1
     },
+    "phase_prerequisites": {
+      "type": "object",
+      "additionalProperties": {
+        "type": "object",
+        "properties": {
+          "required_artifacts": {
+            "type": "array",
+            "items": { "type": "string", "minLength": 1 },
+            "uniqueItems": true
+          },
+          "required_phase_exits": {
+            "type": "array",
+            "items": { "type": "string", "minLength": 1 },
+            "uniqueItems": true
+          }
+        },
+        "additionalProperties": false
+      }
+    },
     "roles": {
       "type": "array",
       "items": { "type": "string", "minLength": 1 },

package/skills/brainstorming/SKILL.md

@@ -5,6 +5,24 @@ description: Use before implementation work to turn operator briefings into an a
 
 # Brainstorming
 
+## Model Annotation
+When multi-model mode is enabled:
+- **Opus** for design exploration (brainstorm)
+- **Opus** for design decisions (design)
+
+## Command Routing
+Follow the Canonical Command Matrix in `hooks/routing-matrix.json`.
+- Large commands (test runners, builds, diffs, dependency trees, linting) → context-mode tools
+- Small commands (git status, ls, pwd, wazir CLI) → native Bash
+- If context-mode unavailable, fall back to native Bash with warning
+
+## Codebase Exploration
+1. Query `wazir index search-symbols <query>` first
+2. Use `wazir recall file <path> --tier L1` for targeted reads
+3. Fall back to direct file reads ONLY for files identified by index queries
+4. Maximum 10 direct file reads without a justifying index query
+5. If no index exists: `wazir index build && wazir index summarize --tier all`
+
 Read `input/` first, then inspect only the repo surfaces needed to understand the request.
 
 Rules:
@@ -12,8 +30,20 @@ Rules:
 1. Do not write implementation code before the design is reviewed with the operator.
 2. Ask clarifying questions only when the ambiguity changes scope, architecture, or acceptance criteria.
 3. Propose 2-3 approaches with trade-offs and a recommendation.
-4. Write the approved design to `.wazir/runs/latest/clarified/design.md` (if inside a pipeline run) or `docs/plans/YYYY-MM-DD-<topic>-design.md` (if standalone).
-5. After user approves the design concept, the reviewer role runs the design-review loop with `--mode design-review` using canonical design-review dimensions (spec coverage, design-spec consistency, accessibility, visual consistency, exported-code fidelity). See `workflows/design-review.md` and `docs/reference/review-loop-pattern.md`. The designer resolves any findings. If the design-review loop completes all passes clean, hand off to `wz:writing-plans`. Planning does not start until design-review is complete.
+4. Present the approaches to the user for selection:
+
+   Ask the user via AskUserQuestion:
+   - **Question:** "Which design approach should we implement?"
+   - **Options:**
+     1. "Approach A — [one-line summary with key trade-off]" *(Recommended)*
+     2. "Approach B — [one-line summary with key trade-off]"
+     3. "Approach C — [one-line summary with key trade-off]"
+     4. "Modify an approach — let me specify changes"
+
+   Wait for the user's selection before continuing.
+
+5. Write the approved design to `.wazir/runs/latest/clarified/design.md` (if inside a pipeline run) or `docs/plans/YYYY-MM-DD-<topic>-design.md` (if standalone).
+6. After user approves the design concept, the reviewer role runs the design-review loop with `--mode design-review` using canonical design-review dimensions (spec coverage, design-spec consistency, accessibility, visual consistency, exported-code fidelity). See `workflows/design-review.md` and `docs/reference/review-loop-pattern.md`. The designer resolves any findings. If the design-review loop completes all passes clean, hand off to `wz:writing-plans`. Planning does not start until design-review is complete.
 
 Required outputs:
 
@@ -21,158 +51,3 @@ Required outputs:
 - open questions or resolved assumptions
 - explicit recommendation and rejected alternatives
 
----
-
-## Team Mode: Agent Teams Structured Dialogue
-
-**Condition:** Only activate when `team_mode: parallel` in `.wazir/runs/latest/run-config.yaml`. Otherwise, use the default single-agent brainstorming above.
-
-This mode uses **Agent Teams** (experimental, Claude Code + Opus 4.6) to run a
-multi-agent brainstorming session. Your role is the **Arbiter** — you coordinate
-the dialogue, evaluate convergence, and signal when to stop. You do NOT generate
-design ideas yourself.
-
-### Infrastructure: Claude Code Agent Teams
-
-This skill uses **Agent Teams** — not subagents. The distinction matters:
-
-| | Subagents (Task tool) | Agent Teams |
-|---|---|---|
-| **Lifecycle** | Spawn, return result, die | Full independent sessions that persist for team lifetime |
-| **Communication** | Report back to parent only | Direct peer-to-peer messaging via `SendMessage` |
-| **Coordination** | Parent manages everything | Shared task list with self-coordination |
-
-**Critical constraint:** Text output from teammates is NOT visible to the team.
-Teammates MUST use `SendMessage` to communicate with each other. Regular text
-output is only visible in a teammate's own terminal pane.
-
-### Prerequisites
-
-```bash
-# Check if Agent Teams is enabled
-echo $CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS
-```
-
-If not set (empty), tell the user:
-
-> Agent Teams is not enabled. Run this command and restart Claude Code:
-> ```bash
-> claude config set env.CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS 1
-> ```
-
-Then fall back to single-agent brainstorming (rules 1-5 above).
-
-### Step 1: Create the Team
-
-Derive `<concept-slug>` from the briefing topic (lowercased, hyphens for spaces).
-
-Use `TeamCreate` to initialize the team with the name `wazir-brainstorm-<concept-slug>`.
-
-### Step 2: Spawn Teammates
-
-Spawn three teammates using the `Agent` tool with the `team_name` parameter set
-to `wazir-brainstorm-<concept-slug>`. Each agent receives a detailed system
-prompt via the `prompt` parameter.
-
-#### Free Thinker
-
-```
-Agent(
-  team_name: "wazir-brainstorm-<concept-slug>",
-  prompt: "You are the Free Thinker in a Wazir brainstorming session.
-Your job is to propose creative design directions without self-censoring.
-Open new threads, explore possibilities, make connections. Communicate
-ONLY via SendMessage — your text output is not visible to the team.
-After proposing a direction, wait for the Grounder's response before
-opening a new one."
-)
-```
-
-#### Grounder
-
-```
-Agent(
-  team_name: "wazir-brainstorm-<concept-slug>",
-  prompt: "You are the Grounder in a Wazir brainstorming session. Your
-job is to challenge every proposal from the Free Thinker with practical
-concerns: feasibility, complexity, risk, alternatives. After 3-5
-exchanges on a direction, decide: pursue, park, or redirect.
-Communicate ONLY via SendMessage — your text output is not visible to
-the team."
-)
-```
-
-#### Synthesizer
-
-```
-Agent(
-  team_name: "wazir-brainstorm-<concept-slug>",
-  prompt: "You are the Synthesizer in a Wazir brainstorming session.
-You NEVER participate in dialogue — only observe. Read all SendMessage
-traffic between Free Thinker and Grounder. When the Arbiter signals
-convergence, write the final design document to
-.wazir/runs/latest/clarified/design.md with: design summary, pursued
-directions, rejected alternatives, open questions, recommendation."
-)
-```
-
-### Step 3: Coordinate the Dialogue (You Are the Arbiter)
-
-1. Use `SendMessage` to tell the Free Thinker to open the first direction
-   based on the briefing, research brief, and hardened spec.
-2. Monitor exchanges via `SendMessage`. Do NOT generate ideas — only
-   coordinate, nudge, and evaluate.
-3. After each direction is explored (3-5 exchanges), the Grounder decides:
-   **pursue**, **park**, or **redirect**.
-4. After depth-appropriate directions are explored:
-
-   | Depth | Directions to explore | Exchanges per direction |
-   |-------|-----------------------|------------------------|
-   | Standard | 3-5 | 3-5 exchanges |
-   | Deep | 5-8 | 5-8 exchanges |
-
-5. **Signal convergence:** Use `SendMessage` to tell the Synthesizer to
-   produce the final design document.
-6. Wait for the Synthesizer to write the design to
-   `.wazir/runs/latest/clarified/design.md` (if inside a pipeline run) or
-   `docs/plans/YYYY-MM-DD-<topic>-design.md` (if standalone).
-
-### Step 4: Convergence Criteria
-
-The dialogue has converged when:
-
-1. Enough directions have been explored for the depth level
-2. The pursued directions have genuine range (not variations of the same idea)
-3. The Grounder signals satisfaction
-4. Further dialogue is producing diminishing returns
-
-Early rounds should be more divergent. Later rounds more convergent.
-
-### Step 5: Clean Up
-
-Use `TeamDelete` to tear down the team after the Synthesizer has written the
-design document.
-
-### Constraints
-
-- Text output from teammates is NOT visible to the team — they MUST use
-  `SendMessage`
-- The Arbiter (you) coordinates but does NOT generate ideas
-- The Synthesizer NEVER sends messages — only reads and writes files
-- Free Thinker and Grounder exchange via broadcast (all agents see every
-  message)
-
-### Output
-
-The Synthesizer produces the design document following the same format as
-single-agent brainstorming:
-
-- Design summary
-- Pursued directions with rationale
-- Rejected alternatives with reasons
-- Open questions or resolved assumptions
-- Explicit recommendation
-
-After the design is written, submit it for the design-review loop
-(`--mode design-review`). After design-review is complete, hand off to
-`wz:writing-plans`.