@dv.nghiem/flowdeck 0.3.8 → 0.4.0

package/src/commands/fd-quick.md

@@ -6,9 +6,10 @@ argument-hint: [task description]
 # Quick — Autonomous Workflow Launcher
 
 Run the correct FlowDeck workflow automatically for any task. This command:
-- Classifies the task type
+- Explores the codebase first before asking any questions
+- Classifies the task type using both text signals and repo evidence
 - Selects the appropriate existing workflow and stage sequence
-- Routes all clarifying questions through `@supervisor`
+- Routes all clarifying questions through `@supervisor` (only when evidence cannot answer)
 - Executes each stage in order using the existing registered commands
 - Stops only when blocked, awaiting approval, or fully verified
 
@@ -16,18 +17,72 @@ Run the correct FlowDeck workflow automatically for any task. This command:
 
 ---
 
+## Step 0: Autonomous Preflight Exploration
+
+**Before asking the human anything**, explore the repository to build evidence.
+
+Invoke `@code-explorer` to inspect the following in parallel:
+
+1. **Repository structure** — `.planning/STATE.md`, `.planning/PROJECT.md`, `AGENTS.md`
+2. **Available commands** — enumerate `src/commands/*.md` filenames
+3. **Available agents** — enumerate `src/agents/*.ts` filenames
+4. **Available skills** — enumerate `src/skills/` directory names
+5. **Workflow config** — read `flowdeck.json` if present (governance, models)
+6. **Tech stack** — read `package.json`, `go.mod`, `Cargo.toml`, `pyproject.toml`
+7. **Implementation patterns** — inspect `src/` top-level directories
+8. **Prior decisions** — check `.planning/phases/*/DISCUSS.md` files
+9. **Relevant files** — find source files matching keywords in `$ARGUMENTS`
+
+Store the exploration snapshot in STATE.md under `quick_run.preflightExploration`:
+
+```yaml
+quick_run:
+  preflightExploration:
+    exploredAt: <ISO timestamp>
+    techStack: [...]
+    availableCommands: [...]
+    availableSkills: [...]
+    implementationPatterns: [...]
+    evidenceCount: <N>
+    clarificationResolvedByEvidence: false
+    suppressedQuestions: []
+```
+
+**This step is mandatory. Do not proceed to Step 1 until exploration is complete.**
+
+### Question suppression rule
+
+After exploration, invoke the question guard before emitting any question:
+
+> A question may only be forwarded to `@supervisor` if:
+> 1. It cannot be answered by the exploration evidence
+> 2. It has not already been asked in the current session
+> 3. It is required to safely select the correct workflow
+
+If the question can be answered from repo evidence, suppress it and log it in
+`quick_run.suppressedQuestions`. Do not present it to the user.
+
+---
+
 ## Step 1: Pre-flight State Check
 
-1. Check `.planning/STATE.md` exists — if not, error: "Run /fd-new-project first."
+1. Check `.planning/STATE.md` exists — if not, error: "No active feature. Run `/fd-map-codebase` then `/fd-new-feature` to start a feature."
 2. Read `.planning/STATE.md` to determine if a `quick_run` entry already exists for this session.
    - If `quick_run.outcome` is `running` or `blocked`: **resume from the last completed stage** (skip to Step 5).
-   - Otherwise: proceed to Step 2.
+   - If `quick_run.preflightExploration` exists and `exploredAt` is recent (< 5 min): reuse it, skip Step 0.
+   - Otherwise: proceed to Step 0 then Step 2.
 
 ---
 
 ## Step 2: Classify the Task
 
-Parse `$ARGUMENTS` using the signal table below to determine task type and required stage sequence.
+Use **both** text-signal matching and preflight exploration evidence:
+
+Call `classifyTaskWithContext(description, explorationResult)` from `quick-router.ts`.
+
+This resolves ambiguous descriptions using repo evidence before flagging
+`clarificationNeeded`. Most short descriptions that would normally prompt a
+question are resolved by evidence (e.g., tech stack, existing patterns, prior decisions).
 
 ### Signal Classification Table
 
@@ -38,7 +93,7 @@ Parse `$ARGUMENTS` using the signal table below to determine task type and requi
 | **docs** | docs, documentation, readme, api docs, usage guide, write docs, document, changelog, tutorial, docstring | `discuss → write-docs → verify` |
 | **simple** | rename, move file, minor, typo, update constant, update config, bump version, one-liner | `execute → verify` |
 | **feature** | (substantive description, 8+ words, no above signals) | `discuss → plan → execute → verify` |
-| **ambiguous** | (short, vague, or unclear input) | *(clarify first — see Step 3)* |
+| **ambiguous** | (short, vague, or unclear — only after exploration cannot resolve) | *(clarify via supervisor — see Step 3)* |
 
 ### Classification Rules
 
@@ -47,7 +102,7 @@ Parse `$ARGUMENTS` using the signal table below to determine task type and requi
 3. **Docs signals**: if "docs", "documentation", "readme", or "write docs" is present without implementation signals, classify as `docs`.
 4. **Simple**: if "rename", "typo", "minor", or "move file" is present and description is a single, scoped operation.
 5. **Feature**: substantive description (8+ words) with no specific signal type.
-6. **Ambiguous**: description is too short (<5 words) or matches a bare imperative with no object (e.g., "improve", "add", "make it better").
+6. **Ambiguous** (only when exploration cannot resolve): description is too short (<5 words) or matches a bare imperative with no object (e.g., "improve", "add", "make it better") AND repo evidence does not clarify scope or type.
 
 Record the classification result:
 ```yaml
@@ -66,21 +121,25 @@ quick_run:
 
 ---
 
-## Step 3: Supervisor-Gated Clarification (when needed)
+## Step 3: Supervisor-Gated Clarification (only when exploration cannot resolve)
 
 **Only proceed to Step 4 when classification confidence is sufficient.**
 
-If classification is `ambiguous` OR confidence is low (description < 5 words or no clear signal):
+If classification is `ambiguous` AND exploration evidence did not resolve it:
 
-1. Invoke `@supervisor` (preflight review of `fd-quick` command) with the partial task description.
-2. Present the supervisor's single clarifying question to the user. **Ask ONE question only.**
+1. Invoke `@supervisor` (preflight review of `fd-quick` command) with:
+   - The partial task description
+   - The preflight exploration snapshot (tech stack, patterns, prior decisions)
+   - The `clarificationPrompt` from the classification (already enriched with context)
+2. `@supervisor` presents the single clarifying question to the user. **Ask ONE question only.**
 3. Wait for the user's answer.
 4. Re-classify using the combined original description + the user's answer.
 5. If confidence is still low after one clarification round, route to `feature` with a note in STATE.md.
 
 **All clarification goes through `@supervisor`. Do not have specialist agents ask questions directly.**
+**Do not ask questions that can be answered from the exploration evidence.**
 
-Example supervisor clarification questions (the supervisor selects the most relevant):
+Example supervisor clarification questions (only when evidence is absent):
 - "Is this a new feature, a bug fix, or a documentation task?"
 - "Does this involve building or changing a user-facing UI (page, dashboard, component)?"
 - "Can you describe the specific bug — what is the expected vs actual behavior?"
@@ -97,6 +156,7 @@ Task classified as: <task type>
 Stage sequence:     <stage-1> → <stage-2> → ... → <stage-N>
 Requires design:    <yes / no>
 Requires TDD:       <yes / no>
+Evidence used:      <N> items from preflight exploration
 
 Running /fd-quick autonomously. I will proceed through each stage and pause only
 if I need approval, encounter a blocker, or complete the full sequence.
@@ -134,13 +194,15 @@ Before executing the stage, invoke `@supervisor` (preflight) on the stage's comm
 
 ### 5c. Execute the Stage
 
-Execute the stage using its existing command with full context:
+Execute the stage using its existing command with full context from the preflight
+exploration snapshot (available in `quick_run.preflightExploration`). Pass it to
+each stage so worker agents can use evidence directly.
 
 **Stage → Command Mapping:**
 
 | Stage | Command | Key Behavior |
 |-------|---------|--------------|
-| `discuss` | `/fd-discuss` | Runs `@discusser` structured Q&A. Saves `DISCUSS.md`. One question at a time. |
+| `discuss` | `/fd-discuss` | Runs `@discusser` structured Q&A. Passes preflight exploration so questions already answered by evidence are skipped. Saves `DISCUSS.md`. One question at a time. |
 | `design` | `/fd-design --mode=draft` | Runs design-first pipeline. Required for `ui-feature` tasks. Produces design artifact + approval. |
 | `plan` | `/fd-plan` | Creates `PLAN.md` from `DISCUSS.md` decisions. **Pauses for user CONFIRM before saving.** |
 | `execute` | `/fd-execute` | TDD pipeline: BEHAVIOR → RED → GREEN → REFACTOR per step. Delegates to appropriate coder agents. |
@@ -194,6 +256,7 @@ When all stages complete:
    Task:      $ARGUMENTS
    Workflow:  <stage-1> → ... → <stage-N>
    Outcome:   ✅ COMPLETE
+   Evidence:  <N> preflight items used (0 human questions asked before exploration)
    ────────────────────────────────────────────────
    Verify result: /fd-verify
    Save state:    /fd-checkpoint

package/src/commands/fd-resume.md

@@ -11,7 +11,7 @@ Resume a previously interrupted FlowDeck session.
 
 ## Steps
 
-1. Check `.planning/STATE.md` exists — if not, error: "No active project. Run /fd-new-project first."
+1. Check `.planning/STATE.md` exists — if not, error: "No active feature. Run `/fd-map-codebase` then `/fd-new-feature` to start a feature."
 
 2. Read STATE.md and parse current state:
    - Phase, status, last_updated, plan_confirmed

package/src/commands/fd-status.md

@@ -80,5 +80,5 @@ Steps:
 
 ## Error Handling
 
-- If `.planning/STATE.md` not found: "No active project. Run /fd-new-project first."
+- If `.planning/STATE.md` not found: "No active feature. Run `/fd-map-codebase` then `/fd-new-feature` to start a feature."
 - If `--phase` requested but phase directory doesn't exist: "Phase N not found."

package/src/commands/fd-verify.md

@@ -11,7 +11,7 @@ Run the full verification pipeline for the current feature: tests, code review,
 
 ## Pre-flight
 
-1. Check `.planning/STATE.md` exists — if not, error: "Run /fd-new-project first."
+1. Check `.planning/STATE.md` exists — if not, error: "No active feature. Run `/fd-map-codebase` then `/fd-new-feature` to start a feature."
 2. Read current phase N from STATE.md.
 3. Confirm `steps_complete` in STATE.md is non-empty — if empty, warn: "No steps completed yet. Run /fd-execute first."
 
@@ -26,6 +26,19 @@ git diff --name-only HEAD
 
 If no changed files, use all files in the current phase directory as scope.
 
+**CodeGraph Impact Check (when available):**
+
+```
+codegraph action=check
+```
+
+If codegraph is installed and indexed:
+- Use `codegraph_impact` on each changed file to surface any dependent modules not caught by `git diff`
+- Log: "codegraph impact analysis: [N] dependent symbols detected"
+- Expand review scope to include impacted modules flagged by codegraph
+
+This ensures verification covers caller/callee relationships, not just directly-changed files.
+
 ### Step 2: Run Checks in Parallel
 
 Launch all four checks simultaneously:
@@ -122,7 +135,7 @@ verified_at: "<timestamp>"
 
 ## Error Handling
 
-- If `.planning/` not found: error "Run /fd-new-project first."
+- If `.planning/` not found: error "No active feature. Run `/fd-map-codebase` then `/fd-new-feature` to start a feature."
 - If STATE.md not found: error "Project not initialized."
 - If test runner not found: error with remediation (e.g., "No test script in package.json")
 - No partial state update on error.
@@ -130,3 +143,4 @@ verified_at: "<timestamp>"
 ## Completion
 
 Report: verification result, check statuses, any required fixes, and suggested next step.
+Next step: run `/fd-done` or `/fd-fix-bug`.

package/src/commands/fd-write-docs.md

@@ -14,7 +14,30 @@ Default: all formats
 
 ## Process
 
-### Step 1: Explore APIs
+### Step 1: CodeGraph Intelligence Check
+
+Before any file exploration, check if codegraph provides a pre-built symbol index:
+
+```
+codegraph action=check
+```
+
+- **If codegraph indexed (fresh)**: Use `codegraph_search`, `codegraph_explore`, `codegraph_node` to enumerate exported symbols and API entry points. This is faster and more complete than grep.
+  - Log: "codegraph available — using symbol index for API discovery"
+- **If codegraph absent or stale**: Fall through to @mapper-based exploration
+
+### Step 2: Explore APIs
+
+**If codegraph is available:**
+
+Use codegraph MCP tools to find all exported symbols:
+```
+codegraph_search("export ")           # exported symbols
+codegraph_explore("<scope or src/>")  # survey module structure
+codegraph_context("<key entry points>") # full context per area
+```
+
+**If codegraph is not available:**
 
 Spawn `@mapper` to:
 - Find all exported functions, classes, and types
@@ -28,7 +51,7 @@ grep -rn "export " src/ --include="*.ts"
 grep -rn "export interface\|export type\|export class" src/ --include="*.ts"
 ```
 
-### Step 2: Draft Documentation
+### Step 3: Draft Documentation
 
 Spawn `@writer` to produce:
 
@@ -57,7 +80,7 @@ const result = functionName(value);
 **Troubleshooting**
 - Common errors and their solutions
 
-### Step 3: Review for Accuracy
+### Step 4: Review for Accuracy
 
 Spawn `@reviewer` to verify:
 - Every documented function/method actually exists
@@ -65,7 +88,9 @@ Spawn `@reviewer` to verify:
 - Examples are syntactically correct
 - No outdated API references
 
-### Step 4: Finalize
+If codegraph is available: use `codegraph_node` to verify specific function signatures against documentation.
+
+### Step 5: Finalize
 
 Writer incorporates feedback and writes final docs to:
 - `README.md` — project overview and quick start
@@ -79,4 +104,4 @@ Updated documentation files with:
 - Working code examples
 - Clear explanations of behavior
 
-Report: files written/updated, public APIs documented, any gaps found.
+Report: files written/updated, public APIs documented, any gaps found, codegraph used ✅/❌.

package/src/rules/common/behavioral.md

@@ -0,0 +1,63 @@
+Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
+
+**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.
+
+## 1. Think Before Coding
+
+**Don't assume. Don't hide confusion. Surface tradeoffs.**
+
+Before implementing:
+- State your assumptions explicitly. If uncertain, ask.
+- If multiple interpretations exist, present them - don't pick silently.
+- If a simpler approach exists, say so. Push back when warranted.
+- If something is unclear, stop. Name what's confusing. Ask.
+
+## 2. Simplicity First
+
+**Minimum code that solves the problem. Nothing speculative.**
+
+- No features beyond what was asked.
+- No abstractions for single-use code.
+- No "flexibility" or "configurability" that wasn't requested.
+- No error handling for impossible scenarios.
+- If you write 200 lines and it could be 50, rewrite it.
+
+Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
+
+## 3. Surgical Changes
+
+**Touch only what you must. Clean up only your own mess.**
+
+When editing existing code:
+- Don't "improve" adjacent code, comments, or formatting.
+- Don't refactor things that aren't broken.
+- Match existing style, even if you'd do it differently.
+- If you notice unrelated dead code, mention it - don't delete it.
+
+When your changes create orphans:
+- Remove imports/variables/functions that YOUR changes made unused.
+- Don't remove pre-existing dead code unless asked.
+
+The test: Every changed line should trace directly to the user's request.
+
+## 4. Goal-Driven Execution
+
+**Define success criteria. Loop until verified.**
+
+Transform tasks into verifiable goals:
+- "Add validation" → "Write tests for invalid inputs, then make them pass"
+- "Fix the bug" → "Write a test that reproduces it, then make it pass"
+- "Refactor X" → "Ensure tests pass before and after"
+
+For multi-step tasks, state a brief plan:
+```
+1. [Step] → verify: [check]
+2. [Step] → verify: [check]
+3. [Step] → verify: [check]
+```
+
+Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
+
+---
+
+**These guidelines are working if:** fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.

package/src/skills/codebase-mapping/SKILL.md

@@ -12,7 +12,7 @@ Produces structured documentation of a codebase that agents can read to answer "
 
 - Starting work on an unfamiliar codebase
 - Before a major feature that spans multiple modules
-- When `/map-codebase` command is invoked
+- When `/fd-map-codebase` command is invoked
 - When `.codebase/` is missing or stale
 
 ## Output Files

package/src/skills/context-load/SKILL.md

@@ -60,4 +60,4 @@ After loading context, produce this briefing:
 **Key Conventions**: [2-3 most important patterns]
 ```
 
-If any file is missing, note it: "STATE.md not found — run `/fd-new-project` to initialize."
+If any file is missing, note it: "STATE.md not found — run `/fd-map-codebase` then `/fd-new-feature` to initialize."

package/src/skills/multi-repo/SKILL.md

@@ -180,7 +180,7 @@ Conflicts must be resolved before any CHANGE PLAN is executed. The `@multi-repo-
 
 ## Independence Check Before Executing
 
-Before running `/multi-repo`:
+Before running `/fd-multi-repo`:
 - [ ] `.planning/config.json` has a `sub_repos` array with at least two entries
 - [ ] All `path` values resolve to actual directories on disk
 - [ ] Each repo has its own `.git` directory (they are separate repos, not subtrees)

package/src/skills/repo-memory-graph/SKILL.md

@@ -19,7 +19,7 @@ The Repo Memory Graph is FlowDeck's long-term knowledge store about this specifi
 ## When to Update
 
 Update the graph:
-- After running `/map-codebase`
+- After running `/fd-map-codebase`
 - When onboarding a new module
 - When a bug fix reveals a recurring pattern (add to `bug_history`)
 - When a refactor changes module ownership

package/dist/hooks/memory-hook.d.ts

@@ -1,28 +0,0 @@
-import { type Session } from "../services/memory-store";
-export declare function onSessionCreated(directory: string, contentSessionId: string, prompt?: string): Session;
-export declare function onToolExecuted(contentSessionId: string, toolName: string, toolInput: Record<string, unknown>, toolResponse: string | null, directory: string): void;
-export declare function onMessageUpdated(contentSessionId: string, role: string, content: string, directory: string): void;
-/**
- * Called when OpenCode compacts a session (session.compacted event).
- *
- * Previously this silently dropped the summary if the session was not in
- * activeSessions (e.g. after plugin reload or cross-process sessions). Now it
- * falls back to a DB lookup so the summary is never lost.
- */
-export declare function onSessionCompact(contentSessionId: string, summary: string): void;
-export declare function onSessionEnd(contentSessionId: string, lastMessage?: string): void;
-export declare function getSessionContext(directory: string, contentSessionId: string): {
-    context: string;
-    previousSessions: Session[];
-};
-export declare function clearSession(contentSessionId: string): void;
-export declare const memoryHook: {
-    onSessionCreated: typeof onSessionCreated;
-    onToolExecuted: typeof onToolExecuted;
-    onMessageUpdated: typeof onMessageUpdated;
-    onSessionCompact: typeof onSessionCompact;
-    onSessionEnd: typeof onSessionEnd;
-    getSessionContext: typeof getSessionContext;
-    clearSession: typeof clearSession;
-};
-//# sourceMappingURL=memory-hook.d.ts.map

package/dist/hooks/memory-hook.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"memory-hook.d.ts","sourceRoot":"","sources":["../../src/hooks/memory-hook.ts"],"names":[],"mappings":"AAAA,OAAO,EAQL,KAAK,OAAO,EAGb,MAAM,0BAA0B,CAAA;AAgGjC,wBAAgB,gBAAgB,CAAC,SAAS,EAAE,MAAM,EAAE,gBAAgB,EAAE,MAAM,EAAE,MAAM,CAAC,EAAE,MAAM,GAAG,OAAO,CAYtG;AAED,wBAAgB,cAAc,CAC5B,gBAAgB,EAAE,MAAM,EACxB,QAAQ,EAAE,MAAM,EAChB,SAAS,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,EAClC,YAAY,EAAE,MAAM,GAAG,IAAI,EAC3B,SAAS,EAAE,MAAM,GAChB,IAAI,CA4BN;AAED,wBAAgB,gBAAgB,CAC9B,gBAAgB,EAAE,MAAM,EACxB,IAAI,EAAE,MAAM,EACZ,OAAO,EAAE,MAAM,EACf,SAAS,EAAE,MAAM,GAChB,IAAI,CA6BN;AAED;;;;;;GAMG;AACH,wBAAgB,gBAAgB,CAAC,gBAAgB,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,GAAG,IAAI,CA+BhF;AAED,wBAAgB,YAAY,CAAC,gBAAgB,EAAE,MAAM,EAAE,WAAW,CAAC,EAAE,MAAM,GAAG,IAAI,CA2BjF;AAED,wBAAgB,iBAAiB,CAAC,SAAS,EAAE,MAAM,EAAE,gBAAgB,EAAE,MAAM,GAAG;IAC9E,OAAO,EAAE,MAAM,CAAA;IACf,gBAAgB,EAAE,OAAO,EAAE,CAAA;CAC5B,CAIA;AAED,wBAAgB,YAAY,CAAC,gBAAgB,EAAE,MAAM,GAAG,IAAI,CAE3D;AAED,eAAO,MAAM,UAAU;;;;;;;;CAQtB,CAAA"}

package/dist/services/memory-store.d.ts

@@ -1,73 +0,0 @@
-/**
- * Structured handoff artifact persisted alongside the text summary.
- * Derived from observations + LLM compaction output.
- */
-export interface HandoffMetadata {
-    workflow_name: string | null;
-    current_status: string;
-    current_stage: string | null;
-    completed_stages: string[];
-    pending_stages: string[];
-    key_decisions: string[];
-    blockers: string[];
-    important_files: string[];
-    approvals: string[];
-    open_questions: string[];
-    next_steps: string[];
-    tool_names_used: string[];
-    observation_count: number;
-    updated_at: string;
-}
-export interface Observation {
-    id?: number;
-    session_id: number;
-    tool_name: string;
-    tool_input: Record<string, unknown> | null;
-    tool_response: string | null;
-    directory: string;
-    created_at?: string;
-}
-export interface Session {
-    id?: number;
-    content_session_id: string;
-    project: string;
-    directory: string;
-    created_at?: string;
-    last_active_at?: string;
-    summary?: string | null;
-    prompt_count?: number;
-}
-export interface Summary {
-    id?: number;
-    session_id: number;
-    content: string;
-    metadata?: HandoffMetadata | null;
-    created_at?: string;
-}
-export interface SearchResult {
-    observation: Observation;
-    session: Session;
-}
-export declare function initSession(contentSessionId: string, project: string, directory: string): Session;
-export declare function storeObservation(sessionId: number, toolName: string, toolInput: unknown, toolResponse: string | null, directory: string): Observation;
-export declare function storeSummary(sessionId: number, content: string, metadata?: HandoffMetadata | null): Summary;
-export declare function getRecentSessions(directory: string, limit?: number): Session[];
-export declare function getObservationsForSession(sessionId: number): Observation[];
-export declare function getSessionSummary(sessionId: number): Summary | null;
-export declare function getSessionByContentSessionId(contentSessionId: string): Session | null;
-export declare function getRecentObservations(directory: string, limit?: number): SearchResult[];
-export declare function searchObservations(directory: string, query: string, limit?: number): SearchResult[];
-export declare function getContextForDirectory(directory: string, maxObservations?: number): string;
-export declare function closeDatabase(): void;
-/**
- * Returns current connection-level PRAGMA values.
- * Intended for diagnostics and tests — queries via the shared singleton so the
- * values reflect what this module actually set, not a second connection.
- */
-export declare function getDbSettings(): {
-    journal_mode: string;
-    busy_timeout: number;
-    synchronous: number;
-    wal_autocheckpoint: number;
-};
-//# sourceMappingURL=memory-store.d.ts.map

package/dist/services/memory-store.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"memory-store.d.ts","sourceRoot":"","sources":["../../src/services/memory-store.ts"],"names":[],"mappings":"AAgKA;;;GAGG;AACH,MAAM,WAAW,eAAe;IAC9B,aAAa,EAAE,MAAM,GAAG,IAAI,CAAA;IAC5B,cAAc,EAAE,MAAM,CAAA;IACtB,aAAa,EAAE,MAAM,GAAG,IAAI,CAAA;IAC5B,gBAAgB,EAAE,MAAM,EAAE,CAAA;IAC1B,cAAc,EAAE,MAAM,EAAE,CAAA;IACxB,aAAa,EAAE,MAAM,EAAE,CAAA;IACvB,QAAQ,EAAE,MAAM,EAAE,CAAA;IAClB,eAAe,EAAE,MAAM,EAAE,CAAA;IACzB,SAAS,EAAE,MAAM,EAAE,CAAA;IACnB,cAAc,EAAE,MAAM,EAAE,CAAA;IACxB,UAAU,EAAE,MAAM,EAAE,CAAA;IACpB,eAAe,EAAE,MAAM,EAAE,CAAA;IACzB,iBAAiB,EAAE,MAAM,CAAA;IACzB,UAAU,EAAE,MAAM,CAAA;CACnB;AAED,MAAM,WAAW,WAAW;IAC1B,EAAE,CAAC,EAAE,MAAM,CAAA;IACX,UAAU,EAAE,MAAM,CAAA;IAClB,SAAS,EAAE,MAAM,CAAA;IACjB,UAAU,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,IAAI,CAAA;IAC1C,aAAa,EAAE,MAAM,GAAG,IAAI,CAAA;IAC5B,SAAS,EAAE,MAAM,CAAA;IACjB,UAAU,CAAC,EAAE,MAAM,CAAA;CACpB;AAED,MAAM,WAAW,OAAO;IACtB,EAAE,CAAC,EAAE,MAAM,CAAA;IACX,kBAAkB,EAAE,MAAM,CAAA;IAC1B,OAAO,EAAE,MAAM,CAAA;IACf,SAAS,EAAE,MAAM,CAAA;IACjB,UAAU,CAAC,EAAE,MAAM,CAAA;IACnB,cAAc,CAAC,EAAE,MAAM,CAAA;IACvB,OAAO,CAAC,EAAE,MAAM,GAAG,IAAI,CAAA;IACvB,YAAY,CAAC,EAAE,MAAM,CAAA;CACtB;AAED,MAAM,WAAW,OAAO;IACtB,EAAE,CAAC,EAAE,MAAM,CAAA;IACX,UAAU,EAAE,MAAM,CAAA;IAClB,OAAO,EAAE,MAAM,CAAA;IACf,QAAQ,CAAC,EAAE,eAAe,GAAG,IAAI,CAAA;IACjC,UAAU,CAAC,EAAE,MAAM,CAAA;CACpB;AAED,MAAM,WAAW,YAAY;IAC3B,WAAW,EAAE,WAAW,CAAA;IACxB,OAAO,EAAE,OAAO,CAAA;CACjB;AAoBD,wBAAgB,WAAW,CAAC,gBAAgB,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,SAAS,EAAE,MAAM,GAAG,OAAO,CA8BjG;AAED,wBAAgB,gBAAgB,CAC9B,SAAS,EAAE,MAAM,EACjB,QAAQ,EAAE,MAAM,EAChB,SAAS,EAAE,OAAO,EAClB,YAAY,EAAE,MAAM,GAAG,IAAI,EAC3B,SAAS,EAAE,MAAM,GAChB,WAAW,CA+Bb;AAED,wBAAgB,YAAY,CAAC,SAAS,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,QAAQ,CAAC,EAAE,eAAe,GAAG,IAAI,GAAG,OAAO,CA8B3G;AAED,wBAAgB,iBAAiB,CAAC,SAAS,EAAE,MAAM,EAAE,KAAK,SAAI,GAAG,OAAO,EAAE,CAUzE;AAED,wBAAgB,yBAAyB,CAAC,SAAS,EAAE,MAAM,GAAG,WAAW,EAAE,CAU1E;AAED,wBAAgB,iBAAiB,CAAC,SAAS,EAAE,MAAM,GAAG,OAAO,GAAG,IAAI,CAUnE;AAED,wBAAgB,4BAA4B,CAAC,gBAAgB,EAAE,MAAM,GAAG,OAAO,GAAG,IAAI,CAKrF;AAED,wBAAgB,qBAAqB,CAAC,SAAS,EAAE,MAAM,EAAE,KAAK,SAAK,GAAG,YAAY,EAAE,CAyBnF;AAED,wBAAgB,kBAAkB,CAAC,SAAS,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,EAAE,KAAK,SAAK,GAAG,YAAY,EAAE,CA2B/F;AAED,wBAAgB,sBAAsB,CAAC,SAAS,EAAE,MAAM,EAAE,eAAe,SAAK,GAAG,MAAM,CA6CtF;AAED,wBAAgB,aAAa,IAAI,IAAI,CAKpC;AAED;;;;GAIG;AACH,wBAAgB,aAAa,IAAI;IAAE,YAAY,EAAE,MAAM,CAAC;IAAC,YAAY,EAAE,MAAM,CAAC;IAAC,WAAW,EAAE,MAAM,CAAC;IAAC,kBAAkB,EAAE,MAAM,CAAA;CAAE,CAO/H"}

package/dist/services/memory-store.test.d.ts

@@ -1,2 +0,0 @@
-export {};
-//# sourceMappingURL=memory-store.test.d.ts.map

package/dist/services/memory-store.test.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"memory-store.test.d.ts","sourceRoot":"","sources":["../../src/services/memory-store.test.ts"],"names":[],"mappings":""}

package/dist/tools/memory-search.d.ts

@@ -1,3 +0,0 @@
-import { type ToolDefinition } from "@opencode-ai/plugin";
-export declare const memorySearchTool: ToolDefinition;
-//# sourceMappingURL=memory-search.d.ts.map

package/dist/tools/memory-search.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"memory-search.d.ts","sourceRoot":"","sources":["../../src/tools/memory-search.ts"],"names":[],"mappings":"AAAA,OAAO,EAAQ,KAAK,cAAc,EAAE,MAAM,qBAAqB,CAAA;AAQ/D,eAAO,MAAM,gBAAgB,EAAE,cAgF7B,CAAA"}

package/dist/tools/memory-status.d.ts

@@ -1,3 +0,0 @@
-import { type ToolDefinition } from "@opencode-ai/plugin";
-export declare const memoryStatusTool: ToolDefinition;
-//# sourceMappingURL=memory-status.d.ts.map

package/dist/tools/memory-status.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"memory-status.d.ts","sourceRoot":"","sources":["../../src/tools/memory-status.ts"],"names":[],"mappings":"AAAA,OAAO,EAAQ,KAAK,cAAc,EAAE,MAAM,qBAAqB,CAAA;AAU/D,eAAO,MAAM,gBAAgB,EAAE,cAkE7B,CAAA"}

package/docs/USER_GUIDE.md

@@ -1,20 +0,0 @@
-# FlowDeck User Guide
-
-> **This file is superseded by the modular documentation.**
-> See **[docs/index.md](./index.md)** for the full table of contents.
-
-## Quick links
-
-| Topic | File |
-|-------|------|
-| Installation & setup | [installation.md](./installation.md) |
-| First 15 minutes | [quick-start.md](./quick-start.md) |
-| Configuration reference | [configuration.md](./configuration.md) |
-| All agents | [agents.md](./agents.md) |
-| All skills | [skills.md](./skills.md) |
-| All workflows | [workflows.md](./workflows.md) |
-| All commands | [commands.md](./commands.md) |
-| Language rules | [rules.md](./rules.md) |
-| Parallel execution | [parallel-execution.md](./parallel-execution.md) |
-| Multi-repo / microservices | [multi-repo.md](./fd-multi-repo.md) |
-| System notifications | [notifications.md](./notifications.md) |