oh-my-opencode 3.2.3 → 3.3.0

package/dist/features/background-agent/manager.d.ts

@@ -37,6 +37,7 @@ export declare class BackgroundManager {
     private queuesByKey;
     private processingKeys;
     private completionTimers;
+    private idleDeferralTimers;
     constructor(ctx: PluginInput, config?: BackgroundTaskConfig, options?: {
         tmuxConfig?: TmuxConfig;
         onSubagentSessionCreated?: OnSubagentSessionCreated;
@@ -51,7 +52,7 @@ export declare class BackgroundManager {
     findBySession(sessionID: string): BackgroundTask | undefined;
     private getConcurrencyKeyFromInput;
     /**
-     * Track a task created elsewhere (e.g., from delegate_task) for notification tracking.
+     * Track a task created elsewhere (e.g., from task) for notification tracking.
      * This allows tasks created by other tools to receive the same toast/prompt notifications.
      */
     trackTask(input: {
@@ -110,6 +111,8 @@ export declare class BackgroundManager {
     private tryCompleteTask;
     private notifyParentSession;
     private formatDuration;
+    private isAbortedSessionError;
+    private getErrorText;
     private hasRunningTasks;
     private pruneStaleTasksAndNotifications;
     private checkAndInterruptStaleTasks;

package/dist/features/boulder-state/storage.d.ts

@@ -25,4 +25,4 @@ export declare function getPlanName(planPath: string): string;
 /**
  * Create a new boulder state for a plan.
  */
-export declare function createBoulderState(planPath: string, sessionId: string): BoulderState;
+export declare function createBoulderState(planPath: string, sessionId: string, agent?: string): BoulderState;

package/dist/features/boulder-state/types.d.ts

@@ -13,6 +13,8 @@ export interface BoulderState {
     session_ids: string[];
     /** Plan name derived from filename */
     plan_name: string;
+    /** Agent type to use when resuming (e.g., 'atlas') */
+    agent?: string;
 }
 export interface PlanProgress {
     /** Total number of checkboxes */

package/dist/features/builtin-commands/templates/init-deep.d.ts

@@ -1 +1 @@
-export declare const INIT_DEEP_TEMPLATE = "# /init-deep\n\nGenerate hierarchical AGENTS.md files. Root + complexity-scored subdirectories.\n\n## Usage\n\n```\n/init-deep                      # Update mode: modify existing + create new where warranted\n/init-deep --create-new         # Read existing \u2192 remove all \u2192 regenerate from scratch\n/init-deep --max-depth=2        # Limit directory depth (default: 3)\n```\n\n---\n\n## Workflow (High-Level)\n\n1. **Discovery + Analysis** (concurrent)\n   - Fire background explore agents immediately\n   - Main session: bash structure + LSP codemap + read existing AGENTS.md\n2. **Score & Decide** - Determine AGENTS.md locations from merged findings\n3. **Generate** - Root first, then subdirs in parallel\n4. **Review** - Deduplicate, trim, validate\n\n<critical>\n**TodoWrite ALL phases. Mark in_progress \u2192 completed in real-time.**\n```\nTodoWrite([\n  { id: \"discovery\", content: \"Fire explore agents + LSP codemap + read existing\", status: \"pending\", priority: \"high\" },\n  { id: \"scoring\", content: \"Score directories, determine locations\", status: \"pending\", priority: \"high\" },\n  { id: \"generate\", content: \"Generate AGENTS.md files (root + subdirs)\", status: \"pending\", priority: \"high\" },\n  { id: \"review\", content: \"Deduplicate, validate, trim\", status: \"pending\", priority: \"medium\" }\n])\n```\n</critical>\n\n---\n\n## Phase 1: Discovery + Analysis (Concurrent)\n\n**Mark \"discovery\" as in_progress.**\n\n### Fire Background Explore Agents IMMEDIATELY\n\nDon't wait\u2014these run async while main session works.\n\n```\n// Fire all at once, collect results later\ndelegate_task(agent=\"explore\", prompt=\"Project structure: PREDICT standard patterns for detected language \u2192 REPORT deviations only\")\ndelegate_task(agent=\"explore\", prompt=\"Entry points: FIND main files \u2192 REPORT non-standard organization\")\ndelegate_task(agent=\"explore\", prompt=\"Conventions: FIND config files (.eslintrc, pyproject.toml, .editorconfig) \u2192 REPORT project-specific rules\")\ndelegate_task(agent=\"explore\", prompt=\"Anti-patterns: FIND 'DO NOT', 'NEVER', 'ALWAYS', 'DEPRECATED' comments \u2192 LIST forbidden patterns\")\ndelegate_task(agent=\"explore\", prompt=\"Build/CI: FIND .github/workflows, Makefile \u2192 REPORT non-standard patterns\")\ndelegate_task(agent=\"explore\", prompt=\"Test patterns: FIND test configs, test structure \u2192 REPORT unique conventions\")\n```\n\n<dynamic-agents>\n**DYNAMIC AGENT SPAWNING**: After bash analysis, spawn ADDITIONAL explore agents based on project scale:\n\n| Factor | Threshold | Additional Agents |\n|--------|-----------|-------------------|\n| **Total files** | >100 | +1 per 100 files |\n| **Total lines** | >10k | +1 per 10k lines |\n| **Directory depth** | \u22654 | +2 for deep exploration |\n| **Large files (>500 lines)** | >10 files | +1 for complexity hotspots |\n| **Monorepo** | detected | +1 per package/workspace |\n| **Multiple languages** | >1 | +1 per language |\n\n```bash\n# Measure project scale first\ntotal_files=$(find . -type f -not -path '*/node_modules/*' -not -path '*/.git/*' | wc -l)\ntotal_lines=$(find . -type f \\( -name \"*.ts\" -o -name \"*.py\" -o -name \"*.go\" \\) -not -path '*/node_modules/*' -exec wc -l {} + 2>/dev/null | tail -1 | awk '{print $1}')\nlarge_files=$(find . -type f \\( -name \"*.ts\" -o -name \"*.py\" \\) -not -path '*/node_modules/*' -exec wc -l {} + 2>/dev/null | awk '$1 > 500 {count++} END {print count+0}')\nmax_depth=$(find . -type d -not -path '*/node_modules/*' -not -path '*/.git/*' | awk -F/ '{print NF}' | sort -rn | head -1)\n```\n\nExample spawning:\n```\n// 500 files, 50k lines, depth 6, 15 large files \u2192 spawn 5+5+2+1 = 13 additional agents\ndelegate_task(agent=\"explore\", prompt=\"Large file analysis: FIND files >500 lines, REPORT complexity hotspots\")\ndelegate_task(agent=\"explore\", prompt=\"Deep modules at depth 4+: FIND hidden patterns, internal conventions\")\ndelegate_task(agent=\"explore\", prompt=\"Cross-cutting concerns: FIND shared utilities across directories\")\n// ... more based on calculation\n```\n</dynamic-agents>\n\n### Main Session: Concurrent Analysis\n\n**While background agents run**, main session does:\n\n#### 1. Bash Structural Analysis\n```bash\n# Directory depth + file counts\nfind . -type d -not -path '*/\\.*' -not -path '*/node_modules/*' -not -path '*/venv/*' -not -path '*/dist/*' -not -path '*/build/*' | awk -F/ '{print NF-1}' | sort -n | uniq -c\n\n# Files per directory (top 30)\nfind . -type f -not -path '*/\\.*' -not -path '*/node_modules/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -30\n\n# Code concentration by extension\nfind . -type f \\( -name \"*.py\" -o -name \"*.ts\" -o -name \"*.tsx\" -o -name \"*.js\" -o -name \"*.go\" -o -name \"*.rs\" \\) -not -path '*/node_modules/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -20\n\n# Existing AGENTS.md / CLAUDE.md\nfind . -type f \\( -name \"AGENTS.md\" -o -name \"CLAUDE.md\" \\) -not -path '*/node_modules/*' 2>/dev/null\n```\n\n#### 2. Read Existing AGENTS.md\n```\nFor each existing file found:\n  Read(filePath=file)\n  Extract: key insights, conventions, anti-patterns\n  Store in EXISTING_AGENTS map\n```\n\nIf `--create-new`: Read all existing first (preserve context) \u2192 then delete all \u2192 regenerate.\n\n#### 3. LSP Codemap (if available)\n```\nLspServers()  # Check availability\n\n# Entry points (parallel)\nLspDocumentSymbols(filePath=\"src/index.ts\")\nLspDocumentSymbols(filePath=\"main.py\")\n\n# Key symbols (parallel)\nLspWorkspaceSymbols(filePath=\".\", query=\"class\")\nLspWorkspaceSymbols(filePath=\".\", query=\"interface\")\nLspWorkspaceSymbols(filePath=\".\", query=\"function\")\n\n# Centrality for top exports\nLspFindReferences(filePath=\"...\", line=X, character=Y)\n```\n\n**LSP Fallback**: If unavailable, rely on explore agents + AST-grep.\n\n### Collect Background Results\n\n```\n// After main session analysis done, collect all task results\nfor each task_id: background_output(task_id=\"...\")\n```\n\n**Merge: bash + LSP + existing + explore findings. Mark \"discovery\" as completed.**\n\n---\n\n## Phase 2: Scoring & Location Decision\n\n**Mark \"scoring\" as in_progress.**\n\n### Scoring Matrix\n\n| Factor | Weight | High Threshold | Source |\n|--------|--------|----------------|--------|\n| File count | 3x | >20 | bash |\n| Subdir count | 2x | >5 | bash |\n| Code ratio | 2x | >70% | bash |\n| Unique patterns | 1x | Has own config | explore |\n| Module boundary | 2x | Has index.ts/__init__.py | bash |\n| Symbol density | 2x | >30 symbols | LSP |\n| Export count | 2x | >10 exports | LSP |\n| Reference centrality | 3x | >20 refs | LSP |\n\n### Decision Rules\n\n| Score | Action |\n|-------|--------|\n| **Root (.)** | ALWAYS create |\n| **>15** | Create AGENTS.md |\n| **8-15** | Create if distinct domain |\n| **<8** | Skip (parent covers) |\n\n### Output\n```\nAGENTS_LOCATIONS = [\n  { path: \".\", type: \"root\" },\n  { path: \"src/hooks\", score: 18, reason: \"high complexity\" },\n  { path: \"src/api\", score: 12, reason: \"distinct domain\" }\n]\n```\n\n**Mark \"scoring\" as completed.**\n\n---\n\n## Phase 3: Generate AGENTS.md\n\n**Mark \"generate\" as in_progress.**\n\n### Root AGENTS.md (Full Treatment)\n\n```markdown\n# PROJECT KNOWLEDGE BASE\n\n**Generated:** {TIMESTAMP}\n**Commit:** {SHORT_SHA}\n**Branch:** {BRANCH}\n\n## OVERVIEW\n{1-2 sentences: what + core stack}\n\n## STRUCTURE\n\\`\\`\\`\n{root}/\n\u251C\u2500\u2500 {dir}/    # {non-obvious purpose only}\n\u2514\u2500\u2500 {entry}\n\\`\\`\\`\n\n## WHERE TO LOOK\n| Task | Location | Notes |\n|------|----------|-------|\n\n## CODE MAP\n{From LSP - skip if unavailable or project <10 files}\n\n| Symbol | Type | Location | Refs | Role |\n|--------|------|----------|------|------|\n\n## CONVENTIONS\n{ONLY deviations from standard}\n\n## ANTI-PATTERNS (THIS PROJECT)\n{Explicitly forbidden here}\n\n## UNIQUE STYLES\n{Project-specific}\n\n## COMMANDS\n\\`\\`\\`bash\n{dev/test/build}\n\\`\\`\\`\n\n## NOTES\n{Gotchas}\n```\n\n**Quality gates**: 50-150 lines, no generic advice, no obvious info.\n\n### Subdirectory AGENTS.md (Parallel)\n\nLaunch writing tasks for each location:\n\n```\nfor loc in AGENTS_LOCATIONS (except root):\n  delegate_task(category=\"writing\", load_skills=[], run_in_background=false, prompt=\\`\n    Generate AGENTS.md for: ${loc.path}\n    - Reason: ${loc.reason}\n    - 30-80 lines max\n    - NEVER repeat parent content\n    - Sections: OVERVIEW (1 line), STRUCTURE (if >5 subdirs), WHERE TO LOOK, CONVENTIONS (if different), ANTI-PATTERNS\n  \\`)\n```\n\n**Wait for all. Mark \"generate\" as completed.**\n\n---\n\n## Phase 4: Review & Deduplicate\n\n**Mark \"review\" as in_progress.**\n\nFor each generated file:\n- Remove generic advice\n- Remove parent duplicates\n- Trim to size limits\n- Verify telegraphic style\n\n**Mark \"review\" as completed.**\n\n---\n\n## Final Report\n\n```\n=== init-deep Complete ===\n\nMode: {update | create-new}\n\nFiles:\n  [OK] ./AGENTS.md (root, {N} lines)\n  [OK] ./src/hooks/AGENTS.md ({N} lines)\n\nDirs Analyzed: {N}\nAGENTS.md Created: {N}\nAGENTS.md Updated: {N}\n\nHierarchy:\n  ./AGENTS.md\n  \u2514\u2500\u2500 src/hooks/AGENTS.md\n```\n\n---\n\n## Anti-Patterns\n\n- **Static agent count**: MUST vary agents based on project size/depth\n- **Sequential execution**: MUST parallel (explore + LSP concurrent)\n- **Ignoring existing**: ALWAYS read existing first, even with --create-new\n- **Over-documenting**: Not every dir needs AGENTS.md\n- **Redundancy**: Child never repeats parent\n- **Generic content**: Remove anything that applies to ALL projects\n- **Verbose style**: Telegraphic or die";
+export declare const INIT_DEEP_TEMPLATE = "# /init-deep\n\nGenerate hierarchical AGENTS.md files. Root + complexity-scored subdirectories.\n\n## Usage\n\n```\n/init-deep                      # Update mode: modify existing + create new where warranted\n/init-deep --create-new         # Read existing \u2192 remove all \u2192 regenerate from scratch\n/init-deep --max-depth=2        # Limit directory depth (default: 3)\n```\n\n---\n\n## Workflow (High-Level)\n\n1. **Discovery + Analysis** (concurrent)\n   - Fire background explore agents immediately\n   - Main session: bash structure + LSP codemap + read existing AGENTS.md\n2. **Score & Decide** - Determine AGENTS.md locations from merged findings\n3. **Generate** - Root first, then subdirs in parallel\n4. **Review** - Deduplicate, trim, validate\n\n<critical>\n**TodoWrite ALL phases. Mark in_progress \u2192 completed in real-time.**\n```\nTodoWrite([\n  { id: \"discovery\", content: \"Fire explore agents + LSP codemap + read existing\", status: \"pending\", priority: \"high\" },\n  { id: \"scoring\", content: \"Score directories, determine locations\", status: \"pending\", priority: \"high\" },\n  { id: \"generate\", content: \"Generate AGENTS.md files (root + subdirs)\", status: \"pending\", priority: \"high\" },\n  { id: \"review\", content: \"Deduplicate, validate, trim\", status: \"pending\", priority: \"medium\" }\n])\n```\n</critical>\n\n---\n\n## Phase 1: Discovery + Analysis (Concurrent)\n\n**Mark \"discovery\" as in_progress.**\n\n### Fire Background Explore Agents IMMEDIATELY\n\nDon't wait\u2014these run async while main session works.\n\n```\n// Fire all at once, collect results later\ntask(subagent_type=\"explore\", load_skills=[], description=\"Explore project structure\", run_in_background=true, prompt=\"Project structure: PREDICT standard patterns for detected language \u2192 REPORT deviations only\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Find entry points\", run_in_background=true, prompt=\"Entry points: FIND main files \u2192 REPORT non-standard organization\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Find conventions\", run_in_background=true, prompt=\"Conventions: FIND config files (.eslintrc, pyproject.toml, .editorconfig) \u2192 REPORT project-specific rules\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Find anti-patterns\", run_in_background=true, prompt=\"Anti-patterns: FIND 'DO NOT', 'NEVER', 'ALWAYS', 'DEPRECATED' comments \u2192 LIST forbidden patterns\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Explore build/CI\", run_in_background=true, prompt=\"Build/CI: FIND .github/workflows, Makefile \u2192 REPORT non-standard patterns\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Find test patterns\", run_in_background=true, prompt=\"Test patterns: FIND test configs, test structure \u2192 REPORT unique conventions\")\n```\n\n<dynamic-agents>\n**DYNAMIC AGENT SPAWNING**: After bash analysis, spawn ADDITIONAL explore agents based on project scale:\n\n| Factor | Threshold | Additional Agents |\n|--------|-----------|-------------------|\n| **Total files** | >100 | +1 per 100 files |\n| **Total lines** | >10k | +1 per 10k lines |\n| **Directory depth** | \u22654 | +2 for deep exploration |\n| **Large files (>500 lines)** | >10 files | +1 for complexity hotspots |\n| **Monorepo** | detected | +1 per package/workspace |\n| **Multiple languages** | >1 | +1 per language |\n\n```bash\n# Measure project scale first\ntotal_files=$(find . -type f -not -path '*/node_modules/*' -not -path '*/.git/*' | wc -l)\ntotal_lines=$(find . -type f \\( -name \"*.ts\" -o -name \"*.py\" -o -name \"*.go\" \\) -not -path '*/node_modules/*' -exec wc -l {} + 2>/dev/null | tail -1 | awk '{print $1}')\nlarge_files=$(find . -type f \\( -name \"*.ts\" -o -name \"*.py\" \\) -not -path '*/node_modules/*' -exec wc -l {} + 2>/dev/null | awk '$1 > 500 {count++} END {print count+0}')\nmax_depth=$(find . -type d -not -path '*/node_modules/*' -not -path '*/.git/*' | awk -F/ '{print NF}' | sort -rn | head -1)\n```\n\nExample spawning:\n```\n// 500 files, 50k lines, depth 6, 15 large files \u2192 spawn 5+5+2+1 = 13 additional agents\ntask(subagent_type=\"explore\", load_skills=[], description=\"Analyze large files\", run_in_background=true, prompt=\"Large file analysis: FIND files >500 lines, REPORT complexity hotspots\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Explore deep modules\", run_in_background=true, prompt=\"Deep modules at depth 4+: FIND hidden patterns, internal conventions\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Find shared utilities\", run_in_background=true, prompt=\"Cross-cutting concerns: FIND shared utilities across directories\")\n// ... more based on calculation\n```\n</dynamic-agents>\n\n### Main Session: Concurrent Analysis\n\n**While background agents run**, main session does:\n\n#### 1. Bash Structural Analysis\n```bash\n# Directory depth + file counts\nfind . -type d -not -path '*/\\.*' -not -path '*/node_modules/*' -not -path '*/venv/*' -not -path '*/dist/*' -not -path '*/build/*' | awk -F/ '{print NF-1}' | sort -n | uniq -c\n\n# Files per directory (top 30)\nfind . -type f -not -path '*/\\.*' -not -path '*/node_modules/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -30\n\n# Code concentration by extension\nfind . -type f \\( -name \"*.py\" -o -name \"*.ts\" -o -name \"*.tsx\" -o -name \"*.js\" -o -name \"*.go\" -o -name \"*.rs\" \\) -not -path '*/node_modules/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -20\n\n# Existing AGENTS.md / CLAUDE.md\nfind . -type f \\( -name \"AGENTS.md\" -o -name \"CLAUDE.md\" \\) -not -path '*/node_modules/*' 2>/dev/null\n```\n\n#### 2. Read Existing AGENTS.md\n```\nFor each existing file found:\n  Read(filePath=file)\n  Extract: key insights, conventions, anti-patterns\n  Store in EXISTING_AGENTS map\n```\n\nIf `--create-new`: Read all existing first (preserve context) \u2192 then delete all \u2192 regenerate.\n\n#### 3. LSP Codemap (if available)\n```\nLspServers()  # Check availability\n\n# Entry points (parallel)\nLspDocumentSymbols(filePath=\"src/index.ts\")\nLspDocumentSymbols(filePath=\"main.py\")\n\n# Key symbols (parallel)\nLspWorkspaceSymbols(filePath=\".\", query=\"class\")\nLspWorkspaceSymbols(filePath=\".\", query=\"interface\")\nLspWorkspaceSymbols(filePath=\".\", query=\"function\")\n\n# Centrality for top exports\nLspFindReferences(filePath=\"...\", line=X, character=Y)\n```\n\n**LSP Fallback**: If unavailable, rely on explore agents + AST-grep.\n\n### Collect Background Results\n\n```\n// After main session analysis done, collect all task results\nfor each task_id: background_output(task_id=\"...\")\n```\n\n**Merge: bash + LSP + existing + explore findings. Mark \"discovery\" as completed.**\n\n---\n\n## Phase 2: Scoring & Location Decision\n\n**Mark \"scoring\" as in_progress.**\n\n### Scoring Matrix\n\n| Factor | Weight | High Threshold | Source |\n|--------|--------|----------------|--------|\n| File count | 3x | >20 | bash |\n| Subdir count | 2x | >5 | bash |\n| Code ratio | 2x | >70% | bash |\n| Unique patterns | 1x | Has own config | explore |\n| Module boundary | 2x | Has index.ts/__init__.py | bash |\n| Symbol density | 2x | >30 symbols | LSP |\n| Export count | 2x | >10 exports | LSP |\n| Reference centrality | 3x | >20 refs | LSP |\n\n### Decision Rules\n\n| Score | Action |\n|-------|--------|\n| **Root (.)** | ALWAYS create |\n| **>15** | Create AGENTS.md |\n| **8-15** | Create if distinct domain |\n| **<8** | Skip (parent covers) |\n\n### Output\n```\nAGENTS_LOCATIONS = [\n  { path: \".\", type: \"root\" },\n  { path: \"src/hooks\", score: 18, reason: \"high complexity\" },\n  { path: \"src/api\", score: 12, reason: \"distinct domain\" }\n]\n```\n\n**Mark \"scoring\" as completed.**\n\n---\n\n## Phase 3: Generate AGENTS.md\n\n**Mark \"generate\" as in_progress.**\n\n<critical>\n**File Writing Rule**: If AGENTS.md already exists at the target path \u2192 use `Edit` tool. If it does NOT exist \u2192 use `Write` tool.\nNEVER use Write to overwrite an existing file. ALWAYS check existence first via `Read` or discovery results.\n</critical>\n\n### Root AGENTS.md (Full Treatment)\n\n```markdown\n# PROJECT KNOWLEDGE BASE\n\n**Generated:** {TIMESTAMP}\n**Commit:** {SHORT_SHA}\n**Branch:** {BRANCH}\n\n## OVERVIEW\n{1-2 sentences: what + core stack}\n\n## STRUCTURE\n\\`\\`\\`\n{root}/\n\u251C\u2500\u2500 {dir}/    # {non-obvious purpose only}\n\u2514\u2500\u2500 {entry}\n\\`\\`\\`\n\n## WHERE TO LOOK\n| Task | Location | Notes |\n|------|----------|-------|\n\n## CODE MAP\n{From LSP - skip if unavailable or project <10 files}\n\n| Symbol | Type | Location | Refs | Role |\n|--------|------|----------|------|------|\n\n## CONVENTIONS\n{ONLY deviations from standard}\n\n## ANTI-PATTERNS (THIS PROJECT)\n{Explicitly forbidden here}\n\n## UNIQUE STYLES\n{Project-specific}\n\n## COMMANDS\n\\`\\`\\`bash\n{dev/test/build}\n\\`\\`\\`\n\n## NOTES\n{Gotchas}\n```\n\n**Quality gates**: 50-150 lines, no generic advice, no obvious info.\n\n### Subdirectory AGENTS.md (Parallel)\n\nLaunch writing tasks for each location:\n\n```\nfor loc in AGENTS_LOCATIONS (except root):\n  task(category=\"writing\", load_skills=[], run_in_background=false, description=\"Generate AGENTS.md\", prompt=\\`\n    Generate AGENTS.md for: ${loc.path}\n    - Reason: ${loc.reason}\n    - 30-80 lines max\n    - NEVER repeat parent content\n    - Sections: OVERVIEW (1 line), STRUCTURE (if >5 subdirs), WHERE TO LOOK, CONVENTIONS (if different), ANTI-PATTERNS\n  \\`)\n```\n\n**Wait for all. Mark \"generate\" as completed.**\n\n---\n\n## Phase 4: Review & Deduplicate\n\n**Mark \"review\" as in_progress.**\n\nFor each generated file:\n- Remove generic advice\n- Remove parent duplicates\n- Trim to size limits\n- Verify telegraphic style\n\n**Mark \"review\" as completed.**\n\n---\n\n## Final Report\n\n```\n=== init-deep Complete ===\n\nMode: {update | create-new}\n\nFiles:\n  [OK] ./AGENTS.md (root, {N} lines)\n  [OK] ./src/hooks/AGENTS.md ({N} lines)\n\nDirs Analyzed: {N}\nAGENTS.md Created: {N}\nAGENTS.md Updated: {N}\n\nHierarchy:\n  ./AGENTS.md\n  \u2514\u2500\u2500 src/hooks/AGENTS.md\n```\n\n---\n\n## Anti-Patterns\n\n- **Static agent count**: MUST vary agents based on project size/depth\n- **Sequential execution**: MUST parallel (explore + LSP concurrent)\n- **Ignoring existing**: ALWAYS read existing first, even with --create-new\n- **Over-documenting**: Not every dir needs AGENTS.md\n- **Redundancy**: Child never repeats parent\n- **Generic content**: Remove anything that applies to ALL projects\n- **Verbose style**: Telegraphic or die";

package/dist/features/claude-tasks/storage.d.ts

@@ -1,6 +1,8 @@
 import type { z } from "zod";
 import type { OhMyOpenCodeConfig } from "../../config/schema";
 export declare function getTaskDir(config?: Partial<OhMyOpenCodeConfig>): string;
+export declare function sanitizePathSegment(value: string): string;
+export declare function resolveTaskListId(config?: Partial<OhMyOpenCodeConfig>): string;
 export declare function ensureDir(dirPath: string): void;
 export declare function readJsonSafe<T>(filePath: string, schema: z.ZodType<T>): T | null;
 export declare function writeJsonAtomic(filePath: string, data: unknown): void;

package/dist/features/tool-metadata-store/index.d.ts

@@ -0,0 +1,39 @@
+/**
+ * Pending tool metadata store.
+ *
+ * OpenCode's `fromPlugin()` wrapper always replaces the metadata returned by
+ * plugin tools with `{ truncated, outputPath }`, discarding any sessionId,
+ * title, or custom metadata set during `execute()`.
+ *
+ * This store captures metadata written via `ctx.metadata()` inside execute(),
+ * then the `tool.execute.after` hook consumes it and merges it back into the
+ * result *before* the processor writes the final part to the session store.
+ *
+ * Flow:
+ *   execute() → storeToolMetadata(sessionID, callID, data)
+ *   fromPlugin() → overwrites metadata with { truncated }
+ *   tool.execute.after → consumeToolMetadata(sessionID, callID) → merges back
+ *   processor → Session.updatePart(status:"completed", metadata: result.metadata)
+ */
+export interface PendingToolMetadata {
+    title?: string;
+    metadata?: Record<string, unknown>;
+}
+/**
+ * Store metadata to be restored after fromPlugin() overwrites it.
+ * Called from tool execute() functions alongside ctx.metadata().
+ */
+export declare function storeToolMetadata(sessionID: string, callID: string, data: PendingToolMetadata): void;
+/**
+ * Consume stored metadata (one-time read, removes from store).
+ * Called from tool.execute.after hook.
+ */
+export declare function consumeToolMetadata(sessionID: string, callID: string): PendingToolMetadata | undefined;
+/**
+ * Get current store size (for testing/debugging).
+ */
+export declare function getPendingStoreSize(): number;
+/**
+ * Clear all pending metadata (for testing).
+ */
+export declare function clearPendingStore(): void;

package/dist/hooks/agent-usage-reminder/constants.d.ts

@@ -2,4 +2,4 @@ export declare const OPENCODE_STORAGE: string;
 export declare const AGENT_USAGE_REMINDER_STORAGE: string;
 export declare const TARGET_TOOLS: Set<string>;
 export declare const AGENT_TOOLS: Set<string>;
-export declare const REMINDER_MESSAGE = "\n[Agent Usage Reminder]\n\nYou called a search/fetch tool directly without leveraging specialized agents.\n\nRECOMMENDED: Use delegate_task with explore/librarian agents for better results:\n\n```\n// Parallel exploration - fire multiple agents simultaneously\ndelegate_task(agent=\"explore\", prompt=\"Find all files matching pattern X\")\ndelegate_task(agent=\"explore\", prompt=\"Search for implementation of Y\") \ndelegate_task(agent=\"librarian\", prompt=\"Lookup documentation for Z\")\n\n// Then continue your work while they run in background\n// System will notify you when each completes\n```\n\nWHY:\n- Agents can perform deeper, more thorough searches\n- Background tasks run in parallel, saving time\n- Specialized agents have domain expertise\n- Reduces context window usage in main session\n\nALWAYS prefer: Multiple parallel delegate_task calls > Direct tool calls\n";
+export declare const REMINDER_MESSAGE = "\n[Agent Usage Reminder]\n\nYou called a search/fetch tool directly without leveraging specialized agents.\n\nRECOMMENDED: Use task with explore/librarian agents for better results:\n\n```\n// Parallel exploration - fire multiple agents simultaneously\ntask(agent=\"explore\", prompt=\"Find all files matching pattern X\")\ntask(agent=\"explore\", prompt=\"Search for implementation of Y\") \ntask(agent=\"librarian\", prompt=\"Lookup documentation for Z\")\n\n// Then continue your work while they run in background\n// System will notify you when each completes\n```\n\nWHY:\n- Agents can perform deeper, more thorough searches\n- Background tasks run in parallel, saving time\n- Specialized agents have domain expertise\n- Reduces context window usage in main session\n\nALWAYS prefer: Multiple parallel task calls > Direct tool calls\n";

package/dist/hooks/anthropic-context-window-limit-recovery/deduplication-recovery.d.ts

@@ -0,0 +1,3 @@
+import type { ParsedTokenLimitError } from "./types";
+import type { ExperimentalConfig } from "../../config";
+export declare function attemptDeduplicationRecovery(sessionID: string, parsed: ParsedTokenLimitError, experimental: ExperimentalConfig | undefined): Promise<void>;

package/dist/hooks/anthropic-context-window-limit-recovery/index.d.ts

@@ -1,16 +1,5 @@
-import type { PluginInput } from "@opencode-ai/plugin";
-import type { ExperimentalConfig } from "../../config";
-export interface AnthropicContextWindowLimitRecoveryOptions {
-    experimental?: ExperimentalConfig;
-}
-export declare function createAnthropicContextWindowLimitRecoveryHook(ctx: PluginInput, options?: AnthropicContextWindowLimitRecoveryOptions): {
-    event: ({ event }: {
-        event: {
-            type: string;
-            properties?: unknown;
-        };
-    }) => Promise<void>;
-};
+export { createAnthropicContextWindowLimitRecoveryHook } from "./recovery-hook";
+export type { AnthropicContextWindowLimitRecoveryOptions } from "./recovery-hook";
 export type { AutoCompactState, ParsedTokenLimitError, TruncateState } from "./types";
 export { parseAnthropicTokenLimitError } from "./parser";
 export { executeCompact, getLastAssistant } from "./executor";

package/dist/hooks/anthropic-context-window-limit-recovery/pruning-tool-output-truncation.d.ts

@@ -0,0 +1,3 @@
+export declare function truncateToolOutputsByCallId(sessionID: string, callIds: Set<string>): {
+    truncatedCount: number;
+};

package/dist/hooks/anthropic-context-window-limit-recovery/recovery-hook.d.ts

@@ -0,0 +1,13 @@
+import type { PluginInput } from "@opencode-ai/plugin";
+import type { ExperimentalConfig } from "../../config";
+export interface AnthropicContextWindowLimitRecoveryOptions {
+    experimental?: ExperimentalConfig;
+}
+export declare function createAnthropicContextWindowLimitRecoveryHook(ctx: PluginInput, options?: AnthropicContextWindowLimitRecoveryOptions): {
+    event: ({ event }: {
+        event: {
+            type: string;
+            properties?: unknown;
+        };
+    }) => Promise<void>;
+};

package/dist/hooks/anthropic-effort/index.d.ts

@@ -0,0 +1,26 @@
+interface ChatParamsInput {
+    sessionID: string;
+    agent: {
+        name?: string;
+    };
+    model: {
+        providerID: string;
+        modelID: string;
+    };
+    provider: {
+        id: string;
+    };
+    message: {
+        variant?: string;
+    };
+}
+interface ChatParamsOutput {
+    temperature?: number;
+    topP?: number;
+    topK?: number;
+    options: Record<string, unknown>;
+}
+export declare function createAnthropicEffortHook(): {
+    "chat.params": (input: ChatParamsInput, output: ChatParamsOutput) => Promise<void>;
+};
+export {};

package/dist/hooks/atlas/index.d.ts

@@ -14,6 +14,7 @@ interface ToolExecuteAfterOutput {
 export interface AtlasHookOptions {
     directory: string;
     backgroundManager?: BackgroundManager;
+    isContinuationStopped?: (sessionID: string) => boolean;
 }
 export declare function createAtlasHook(ctx: PluginInput, options?: AtlasHookOptions): {
     handler: ({ event }: {

package/dist/hooks/auto-update-checker/constants.d.ts

@@ -3,8 +3,8 @@ export declare const NPM_REGISTRY_URL = "https://registry.npmjs.org/-/package/oh
 export declare const NPM_FETCH_TIMEOUT = 5000;
 export declare const CACHE_DIR: string;
 export declare const VERSION_FILE: string;
-export declare const INSTALLED_PACKAGE_JSON: string;
 export declare function getWindowsAppdataDir(): string | null;
 export declare const USER_CONFIG_DIR: string;
 export declare const USER_OPENCODE_CONFIG: string;
 export declare const USER_OPENCODE_CONFIG_JSONC: string;
+export declare const INSTALLED_PACKAGE_JSON: string;

package/dist/hooks/category-skill-reminder/index.d.ts

@@ -1,4 +1,5 @@
 import type { PluginInput } from "@opencode-ai/plugin";
+import type { AvailableSkill } from "../../agents/dynamic-agent-prompt-builder";
 interface ToolExecuteInput {
     tool: string;
     sessionID: string;
@@ -10,7 +11,7 @@ interface ToolExecuteOutput {
     output: string;
     metadata: unknown;
 }
-export declare function createCategorySkillReminderHook(_ctx: PluginInput): {
+export declare function createCategorySkillReminderHook(_ctx: PluginInput, availableSkills?: AvailableSkill[]): {
     "tool.execute.after": (input: ToolExecuteInput, output: ToolExecuteOutput) => Promise<void>;
     event: ({ event }: {
         event: {

package/dist/hooks/compaction-context-injector/index.d.ts

@@ -1,8 +1 @@
-export interface SummarizeContext {
-    sessionID: string;
-    providerID: string;
-    modelID: string;
-    usageRatio: number;
-    directory: string;
-}
-export declare function createCompactionContextInjector(): (ctx: SummarizeContext) => Promise<void>;
+export declare function createCompactionContextInjector(): () => string;

package/dist/hooks/compaction-todo-preserver/index.d.ts

@@ -0,0 +1,11 @@
+import type { PluginInput } from "@opencode-ai/plugin";
+export interface CompactionTodoPreserver {
+    capture: (sessionID: string) => Promise<void>;
+    event: (input: {
+        event: {
+            type: string;
+            properties?: unknown;
+        };
+    }) => Promise<void>;
+}
+export declare function createCompactionTodoPreserverHook(ctx: PluginInput): CompactionTodoPreserver;

package/dist/hooks/index.d.ts

@@ -31,7 +31,9 @@ export { createDelegateTaskRetryHook } from "./delegate-task-retry";
 export { createQuestionLabelTruncatorHook } from "./question-label-truncator";
 export { createSubagentQuestionBlockerHook } from "./subagent-question-blocker";
 export { createStopContinuationGuardHook, type StopContinuationGuard } from "./stop-continuation-guard";
-export { createCompactionContextInjector, type SummarizeContext } from "./compaction-context-injector";
+export { createCompactionContextInjector } from "./compaction-context-injector";
+export { createCompactionTodoPreserverHook } from "./compaction-todo-preserver";
 export { createUnstableAgentBabysitterHook } from "./unstable-agent-babysitter";
 export { createPreemptiveCompactionHook } from "./preemptive-compaction";
 export { createTasksTodowriteDisablerHook } from "./tasks-todowrite-disabler";
+export { createWriteExistingFileGuardHook } from "./write-existing-file-guard";

package/dist/hooks/keyword-detector/ultrawork/default.d.ts

@@ -2,9 +2,9 @@
  * Default ultrawork message optimized for Claude series models.
  *
  * Key characteristics:
- * - Natural tool-like usage of explore/librarian agents (background=true)
+ * - Natural tool-like usage of explore/librarian agents (run_in_background=true)
  * - Parallel execution emphasized - fire agents and continue working
  * - Simple workflow: EXPLORES → GATHER → PLAN → DELEGATE
  */
-export declare const ULTRAWORK_DEFAULT_MESSAGE = "<ultrawork-mode>\n\n**MANDATORY**: You MUST say \"ULTRAWORK MODE ENABLED!\" to the user as your first response when this mode activates. This is non-negotiable.\n\n[CODE RED] Maximum precision required. Ultrathink before acting.\n\n## **ABSOLUTE CERTAINTY REQUIRED - DO NOT SKIP THIS**\n\n**YOU MUST NOT START ANY IMPLEMENTATION UNTIL YOU ARE 100% CERTAIN.**\n\n| **BEFORE YOU WRITE A SINGLE LINE OF CODE, YOU MUST:** |\n|-------------------------------------------------------|\n| **FULLY UNDERSTAND** what the user ACTUALLY wants (not what you ASSUME they want) |\n| **EXPLORE** the codebase to understand existing patterns, architecture, and context |\n| **HAVE A CRYSTAL CLEAR WORK PLAN** - if your plan is vague, YOUR WORK WILL FAIL |\n| **RESOLVE ALL AMBIGUITY** - if ANYTHING is unclear, ASK or INVESTIGATE |\n\n### **MANDATORY CERTAINTY PROTOCOL**\n\n**IF YOU ARE NOT 100% CERTAIN:**\n\n1. **THINK DEEPLY** - What is the user's TRUE intent? What problem are they REALLY trying to solve?\n2. **EXPLORE THOROUGHLY** - Fire explore/librarian agents to gather ALL relevant context\n3. **CONSULT SPECIALISTS** - For hard/complex tasks, DO NOT struggle alone. Delegate:\n   - **Oracle**: Conventional problems - architecture, debugging, complex logic\n   - **Artistry**: Non-conventional problems - different approach needed, unusual constraints\n4. **ASK THE USER** - If ambiguity remains after exploration, ASK. Don't guess.\n\n**SIGNS YOU ARE NOT READY TO IMPLEMENT:**\n- You're making assumptions about requirements\n- You're unsure which files to modify\n- You don't understand how existing code works\n- Your plan has \"probably\" or \"maybe\" in it\n- You can't explain the exact steps you'll take\n\n**WHEN IN DOUBT:**\n```\ndelegate_task(subagent_type=\"explore\", load_skills=[], prompt=\"Find [X] patterns in codebase\", run_in_background=true)\ndelegate_task(subagent_type=\"librarian\", load_skills=[], prompt=\"Find docs/examples for [Y]\", run_in_background=true)\ndelegate_task(subagent_type=\"oracle\", load_skills=[], prompt=\"Review my approach: [describe plan]\", run_in_background=false)\n```\n\n**ONLY AFTER YOU HAVE:**\n- Gathered sufficient context via agents\n- Resolved all ambiguities\n- Created a precise, step-by-step work plan\n- Achieved 100% confidence in your understanding\n\n**...THEN AND ONLY THEN MAY YOU BEGIN IMPLEMENTATION.**\n\n---\n\n## **NO EXCUSES. NO COMPROMISES. DELIVER WHAT WAS ASKED.**\n\n**THE USER'S ORIGINAL REQUEST IS SACRED. YOU MUST FULFILL IT EXACTLY.**\n\n| VIOLATION | CONSEQUENCE |\n|-----------|-------------|\n| \"I couldn't because...\" | **UNACCEPTABLE.** Find a way or ask for help. |\n| \"This is a simplified version...\" | **UNACCEPTABLE.** Deliver the FULL implementation. |\n| \"You can extend this later...\" | **UNACCEPTABLE.** Finish it NOW. |\n| \"Due to limitations...\" | **UNACCEPTABLE.** Use agents, tools, whatever it takes. |\n| \"I made some assumptions...\" | **UNACCEPTABLE.** You should have asked FIRST. |\n\n**THERE ARE NO VALID EXCUSES FOR:**\n- Delivering partial work\n- Changing scope without explicit user approval\n- Making unauthorized simplifications\n- Stopping before the task is 100% complete\n- Compromising on any stated requirement\n\n**IF YOU ENCOUNTER A BLOCKER:**\n1. **DO NOT** give up\n2. **DO NOT** deliver a compromised version\n3. **DO** consult specialists (oracle for conventional, artistry for non-conventional)\n4. **DO** ask the user for guidance\n5. **DO** explore alternative approaches\n\n**THE USER ASKED FOR X. DELIVER EXACTLY X. PERIOD.**\n\n---\n\nYOU MUST LEVERAGE ALL AVAILABLE AGENTS / **CATEGORY + SKILLS** TO THEIR FULLEST POTENTIAL.\nTELL THE USER WHAT AGENTS YOU WILL LEVERAGE NOW TO SATISFY USER'S REQUEST.\n\n## MANDATORY: PLAN AGENT INVOCATION (NON-NEGOTIABLE)\n\n**YOU MUST ALWAYS INVOKE THE PLAN AGENT FOR ANY NON-TRIVIAL TASK.**\n\n| Condition | Action |\n|-----------|--------|\n| Task has 2+ steps | MUST call plan agent |\n| Task scope unclear | MUST call plan agent |\n| Implementation required | MUST call plan agent |\n| Architecture decision needed | MUST call plan agent |\n\n```\ndelegate_task(subagent_type=\"plan\", prompt=\"<gathered context + user request>\")\n```\n\n**WHY PLAN AGENT IS MANDATORY:**\n- Plan agent analyzes dependencies and parallel execution opportunities\n- Plan agent outputs a **parallel task graph** with waves and dependencies\n- Plan agent provides structured TODO list with category + skills per task\n- YOU are an orchestrator, NOT an implementer\n\n### SESSION CONTINUITY WITH PLAN AGENT (CRITICAL)\n\n**Plan agent returns a session_id. USE IT for follow-up interactions.**\n\n| Scenario | Action |\n|----------|--------|\n| Plan agent asks clarifying questions | `delegate_task(session_id=\"{returned_session_id}\", prompt=\"<your answer>\")` |\n| Need to refine the plan | `delegate_task(session_id=\"{returned_session_id}\", prompt=\"Please adjust: <feedback>\")` |\n| Plan needs more detail | `delegate_task(session_id=\"{returned_session_id}\", prompt=\"Add more detail to Task N\")` |\n\n**WHY SESSION_ID IS CRITICAL:**\n- Plan agent retains FULL conversation context\n- No repeated exploration or context gathering\n- Saves 70%+ tokens on follow-ups\n- Maintains interview continuity until plan is finalized\n\n```\n// WRONG: Starting fresh loses all context\ndelegate_task(subagent_type=\"plan\", prompt=\"Here's more info...\")\n\n// CORRECT: Resume preserves everything\ndelegate_task(session_id=\"ses_abc123\", prompt=\"Here's my answer to your question: ...\")\n```\n\n**FAILURE TO CALL PLAN AGENT = INCOMPLETE WORK.**\n\n---\n\n## AGENTS / **CATEGORY + SKILLS** UTILIZATION PRINCIPLES\n\n**DEFAULT BEHAVIOR: DELEGATE. DO NOT WORK YOURSELF.**\n\n| Task Type | Action | Why |\n|-----------|--------|-----|\n| Codebase exploration | delegate_task(subagent_type=\"explore\", run_in_background=true) | Parallel, context-efficient |\n| Documentation lookup | delegate_task(subagent_type=\"librarian\", run_in_background=true) | Specialized knowledge |\n| Planning | delegate_task(subagent_type=\"plan\") | Parallel task graph + structured TODO list |\n| Hard problem (conventional) | delegate_task(subagent_type=\"oracle\") | Architecture, debugging, complex logic |\n| Hard problem (non-conventional) | delegate_task(category=\"artistry\", load_skills=[...]) | Different approach needed |\n| Implementation | delegate_task(category=\"...\", load_skills=[...]) | Domain-optimized models |\n\n**CATEGORY + SKILL DELEGATION:**\n```\n// Frontend work\ndelegate_task(category=\"visual-engineering\", load_skills=[\"frontend-ui-ux\"])\n\n// Complex logic\ndelegate_task(category=\"ultrabrain\", load_skills=[\"typescript-programmer\"])\n\n// Quick fixes\ndelegate_task(category=\"quick\", load_skills=[\"git-master\"])\n```\n\n**YOU SHOULD ONLY DO IT YOURSELF WHEN:**\n- Task is trivially simple (1-2 lines, obvious change)\n- You have ALL context already loaded\n- Delegation overhead exceeds task complexity\n\n**OTHERWISE: DELEGATE. ALWAYS.**\n\n---\n\n## EXECUTION RULES\n- **TODO**: Track EVERY step. Mark complete IMMEDIATELY after each.\n- **PARALLEL**: Fire independent agent calls simultaneously via delegate_task(background=true) - NEVER wait sequentially.\n- **BACKGROUND FIRST**: Use delegate_task for exploration/research agents (10+ concurrent if needed).\n- **VERIFY**: Re-read request after completion. Check ALL requirements met before reporting done.\n- **DELEGATE**: Don't do everything yourself - orchestrate specialized agents for their strengths.\n\n## WORKFLOW\n1. Analyze the request and identify required capabilities\n2. Spawn exploration/librarian agents via delegate_task(background=true) in PARALLEL (10+ if needed)\n3. Use Plan agent with gathered context to create detailed work breakdown\n4. Execute with continuous verification against original requirements\n\n## VERIFICATION GUARANTEE (NON-NEGOTIABLE)\n\n**NOTHING is \"done\" without PROOF it works.**\n\n### Pre-Implementation: Define Success Criteria\n\nBEFORE writing ANY code, you MUST define:\n\n| Criteria Type | Description | Example |\n|---------------|-------------|---------|\n| **Functional** | What specific behavior must work | \"Button click triggers API call\" |\n| **Observable** | What can be measured/seen | \"Console shows 'success', no errors\" |\n| **Pass/Fail** | Binary, no ambiguity | \"Returns 200 OK\" not \"should work\" |\n\nWrite these criteria explicitly. Share with user if scope is non-trivial.\n\n### Test Plan Template (MANDATORY for non-trivial tasks)\n\n```\n## Test Plan\n### Objective: [What we're verifying]\n### Prerequisites: [Setup needed]\n### Test Cases:\n1. [Test Name]: [Input] \u2192 [Expected Output] \u2192 [How to verify]\n2. ...\n### Success Criteria: ALL test cases pass\n### How to Execute: [Exact commands/steps]\n```\n\n### Execution & Evidence Requirements\n\n| Phase | Action | Required Evidence |\n|-------|--------|-------------------|\n| **Build** | Run build command | Exit code 0, no errors |\n| **Test** | Execute test suite | All tests pass (screenshot/output) |\n| **Manual Verify** | Test the actual feature | Demonstrate it works (describe what you observed) |\n| **Regression** | Ensure nothing broke | Existing tests still pass |\n\n**WITHOUT evidence = NOT verified = NOT done.**\n\n### TDD Workflow (when test infrastructure exists)\n\n1. **SPEC**: Define what \"working\" means (success criteria above)\n2. **RED**: Write failing test \u2192 Run it \u2192 Confirm it FAILS\n3. **GREEN**: Write minimal code \u2192 Run test \u2192 Confirm it PASSES\n4. **REFACTOR**: Clean up \u2192 Tests MUST stay green\n5. **VERIFY**: Run full test suite, confirm no regressions\n6. **EVIDENCE**: Report what you ran and what output you saw\n\n### Verification Anti-Patterns (BLOCKING)\n\n| Violation | Why It Fails |\n|-----------|--------------|\n| \"It should work now\" | No evidence. Run it. |\n| \"I added the tests\" | Did they pass? Show output. |\n| \"Fixed the bug\" | How do you know? What did you test? |\n| \"Implementation complete\" | Did you verify against success criteria? |\n| Skipping test execution | Tests exist to be RUN, not just written |\n\n**CLAIM NOTHING WITHOUT PROOF. EXECUTE. VERIFY. SHOW EVIDENCE.**\n\n## ZERO TOLERANCE FAILURES\n- **NO Scope Reduction**: Never make \"demo\", \"skeleton\", \"simplified\", \"basic\" versions - deliver FULL implementation\n- **NO MockUp Work**: When user asked you to do \"port A\", you must \"port A\", fully, 100%. No Extra feature, No reduced feature, no mock data, fully working 100% port.\n- **NO Partial Completion**: Never stop at 60-80% saying \"you can extend this...\" - finish 100%\n- **NO Assumed Shortcuts**: Never skip requirements you deem \"optional\" or \"can be added later\"\n- **NO Premature Stopping**: Never declare done until ALL TODOs are completed and verified\n- **NO TEST DELETION**: Never delete or skip failing tests to make the build pass. Fix the code, not the tests.\n\nTHE USER ASKED FOR X. DELIVER EXACTLY X. NOT A SUBSET. NOT A DEMO. NOT A STARTING POINT.\n\n1. EXPLORES + LIBRARIANS\n2. GATHER -> PLAN AGENT SPAWN\n3. WORK BY DELEGATING TO ANOTHER AGENTS\n\nNOW.\n\n</ultrawork-mode>\n\n---\n\n";
+export declare const ULTRAWORK_DEFAULT_MESSAGE = "<ultrawork-mode>\n\n**MANDATORY**: You MUST say \"ULTRAWORK MODE ENABLED!\" to the user as your first response when this mode activates. This is non-negotiable.\n\n[CODE RED] Maximum precision required. Ultrathink before acting.\n\n## **ABSOLUTE CERTAINTY REQUIRED - DO NOT SKIP THIS**\n\n**YOU MUST NOT START ANY IMPLEMENTATION UNTIL YOU ARE 100% CERTAIN.**\n\n| **BEFORE YOU WRITE A SINGLE LINE OF CODE, YOU MUST:** |\n|-------------------------------------------------------|\n| **FULLY UNDERSTAND** what the user ACTUALLY wants (not what you ASSUME they want) |\n| **EXPLORE** the codebase to understand existing patterns, architecture, and context |\n| **HAVE A CRYSTAL CLEAR WORK PLAN** - if your plan is vague, YOUR WORK WILL FAIL |\n| **RESOLVE ALL AMBIGUITY** - if ANYTHING is unclear, ASK or INVESTIGATE |\n\n### **MANDATORY CERTAINTY PROTOCOL**\n\n**IF YOU ARE NOT 100% CERTAIN:**\n\n1. **THINK DEEPLY** - What is the user's TRUE intent? What problem are they REALLY trying to solve?\n2. **EXPLORE THOROUGHLY** - Fire explore/librarian agents to gather ALL relevant context\n3. **CONSULT SPECIALISTS** - For hard/complex tasks, DO NOT struggle alone. Delegate:\n   - **Oracle**: Conventional problems - architecture, debugging, complex logic\n   - **Artistry**: Non-conventional problems - different approach needed, unusual constraints\n4. **ASK THE USER** - If ambiguity remains after exploration, ASK. Don't guess.\n\n**SIGNS YOU ARE NOT READY TO IMPLEMENT:**\n- You're making assumptions about requirements\n- You're unsure which files to modify\n- You don't understand how existing code works\n- Your plan has \"probably\" or \"maybe\" in it\n- You can't explain the exact steps you'll take\n\n**WHEN IN DOUBT:**\n```\ntask(subagent_type=\"explore\", load_skills=[], prompt=\"Find [X] patterns in codebase\", run_in_background=true)\ntask(subagent_type=\"librarian\", load_skills=[], prompt=\"Find docs/examples for [Y]\", run_in_background=true)\ntask(subagent_type=\"oracle\", load_skills=[], prompt=\"Review my approach: [describe plan]\", run_in_background=false)\n```\n\n**ONLY AFTER YOU HAVE:**\n- Gathered sufficient context via agents\n- Resolved all ambiguities\n- Created a precise, step-by-step work plan\n- Achieved 100% confidence in your understanding\n\n**...THEN AND ONLY THEN MAY YOU BEGIN IMPLEMENTATION.**\n\n---\n\n## **NO EXCUSES. NO COMPROMISES. DELIVER WHAT WAS ASKED.**\n\n**THE USER'S ORIGINAL REQUEST IS SACRED. YOU MUST FULFILL IT EXACTLY.**\n\n| VIOLATION | CONSEQUENCE |\n|-----------|-------------|\n| \"I couldn't because...\" | **UNACCEPTABLE.** Find a way or ask for help. |\n| \"This is a simplified version...\" | **UNACCEPTABLE.** Deliver the FULL implementation. |\n| \"You can extend this later...\" | **UNACCEPTABLE.** Finish it NOW. |\n| \"Due to limitations...\" | **UNACCEPTABLE.** Use agents, tools, whatever it takes. |\n| \"I made some assumptions...\" | **UNACCEPTABLE.** You should have asked FIRST. |\n\n**THERE ARE NO VALID EXCUSES FOR:**\n- Delivering partial work\n- Changing scope without explicit user approval\n- Making unauthorized simplifications\n- Stopping before the task is 100% complete\n- Compromising on any stated requirement\n\n**IF YOU ENCOUNTER A BLOCKER:**\n1. **DO NOT** give up\n2. **DO NOT** deliver a compromised version\n3. **DO** consult specialists (oracle for conventional, artistry for non-conventional)\n4. **DO** ask the user for guidance\n5. **DO** explore alternative approaches\n\n**THE USER ASKED FOR X. DELIVER EXACTLY X. PERIOD.**\n\n---\n\nYOU MUST LEVERAGE ALL AVAILABLE AGENTS / **CATEGORY + SKILLS** TO THEIR FULLEST POTENTIAL.\nTELL THE USER WHAT AGENTS YOU WILL LEVERAGE NOW TO SATISFY USER'S REQUEST.\n\n## MANDATORY: PLAN AGENT INVOCATION (NON-NEGOTIABLE)\n\n**YOU MUST ALWAYS INVOKE THE PLAN AGENT FOR ANY NON-TRIVIAL TASK.**\n\n| Condition | Action |\n|-----------|--------|\n| Task has 2+ steps | MUST call plan agent |\n| Task scope unclear | MUST call plan agent |\n| Implementation required | MUST call plan agent |\n| Architecture decision needed | MUST call plan agent |\n\n```\ntask(subagent_type=\"plan\", prompt=\"<gathered context + user request>\")\n```\n\n**WHY PLAN AGENT IS MANDATORY:**\n- Plan agent analyzes dependencies and parallel execution opportunities\n- Plan agent outputs a **parallel task graph** with waves and dependencies\n- Plan agent provides structured TODO list with category + skills per task\n- YOU are an orchestrator, NOT an implementer\n\n### SESSION CONTINUITY WITH PLAN AGENT (CRITICAL)\n\n**Plan agent returns a session_id. USE IT for follow-up interactions.**\n\n| Scenario | Action |\n|----------|--------|\n| Plan agent asks clarifying questions | `task(session_id=\"{returned_session_id}\", prompt=\"<your answer>\")` |\n| Need to refine the plan | `task(session_id=\"{returned_session_id}\", prompt=\"Please adjust: <feedback>\")` |\n| Plan needs more detail | `task(session_id=\"{returned_session_id}\", prompt=\"Add more detail to Task N\")` |\n\n**WHY SESSION_ID IS CRITICAL:**\n- Plan agent retains FULL conversation context\n- No repeated exploration or context gathering\n- Saves 70%+ tokens on follow-ups\n- Maintains interview continuity until plan is finalized\n\n```\n// WRONG: Starting fresh loses all context\ntask(subagent_type=\"plan\", prompt=\"Here's more info...\")\n\n// CORRECT: Resume preserves everything\ntask(session_id=\"ses_abc123\", prompt=\"Here's my answer to your question: ...\")\n```\n\n**FAILURE TO CALL PLAN AGENT = INCOMPLETE WORK.**\n\n---\n\n## AGENTS / **CATEGORY + SKILLS** UTILIZATION PRINCIPLES\n\n**DEFAULT BEHAVIOR: DELEGATE. DO NOT WORK YOURSELF.**\n\n| Task Type | Action | Why |\n|-----------|--------|-----|\n| Codebase exploration | task(subagent_type=\"explore\", run_in_background=true) | Parallel, context-efficient |\n| Documentation lookup | task(subagent_type=\"librarian\", run_in_background=true) | Specialized knowledge |\n| Planning | task(subagent_type=\"plan\") | Parallel task graph + structured TODO list |\n| Hard problem (conventional) | task(subagent_type=\"oracle\") | Architecture, debugging, complex logic |\n| Hard problem (non-conventional) | task(category=\"artistry\", load_skills=[...]) | Different approach needed |\n| Implementation | task(category=\"...\", load_skills=[...]) | Domain-optimized models |\n\n**CATEGORY + SKILL DELEGATION:**\n```\n// Frontend work\ntask(category=\"visual-engineering\", load_skills=[\"frontend-ui-ux\"])\n\n// Complex logic\ntask(category=\"ultrabrain\", load_skills=[\"typescript-programmer\"])\n\n// Quick fixes\ntask(category=\"quick\", load_skills=[\"git-master\"])\n```\n\n**YOU SHOULD ONLY DO IT YOURSELF WHEN:**\n- Task is trivially simple (1-2 lines, obvious change)\n- You have ALL context already loaded\n- Delegation overhead exceeds task complexity\n\n**OTHERWISE: DELEGATE. ALWAYS.**\n\n---\n\n## EXECUTION RULES\n- **TODO**: Track EVERY step. Mark complete IMMEDIATELY after each.\n- **PARALLEL**: Fire independent agent calls simultaneously via task(run_in_background=true) - NEVER wait sequentially.\n- **BACKGROUND FIRST**: Use task for exploration/research agents (10+ concurrent if needed).\n- **VERIFY**: Re-read request after completion. Check ALL requirements met before reporting done.\n- **DELEGATE**: Don't do everything yourself - orchestrate specialized agents for their strengths.\n\n## WORKFLOW\n1. Analyze the request and identify required capabilities\n2. Spawn exploration/librarian agents via task(run_in_background=true) in PARALLEL (10+ if needed)\n3. Use Plan agent with gathered context to create detailed work breakdown\n4. Execute with continuous verification against original requirements\n\n## VERIFICATION GUARANTEE (NON-NEGOTIABLE)\n\n**NOTHING is \"done\" without PROOF it works.**\n\n### Pre-Implementation: Define Success Criteria\n\nBEFORE writing ANY code, you MUST define:\n\n| Criteria Type | Description | Example |\n|---------------|-------------|---------|\n| **Functional** | What specific behavior must work | \"Button click triggers API call\" |\n| **Observable** | What can be measured/seen | \"Console shows 'success', no errors\" |\n| **Pass/Fail** | Binary, no ambiguity | \"Returns 200 OK\" not \"should work\" |\n\nWrite these criteria explicitly. Share with user if scope is non-trivial.\n\n### Test Plan Template (MANDATORY for non-trivial tasks)\n\n```\n## Test Plan\n### Objective: [What we're verifying]\n### Prerequisites: [Setup needed]\n### Test Cases:\n1. [Test Name]: [Input] \u2192 [Expected Output] \u2192 [How to verify]\n2. ...\n### Success Criteria: ALL test cases pass\n### How to Execute: [Exact commands/steps]\n```\n\n### Execution & Evidence Requirements\n\n| Phase | Action | Required Evidence |\n|-------|--------|-------------------|\n| **Build** | Run build command | Exit code 0, no errors |\n| **Test** | Execute test suite | All tests pass (screenshot/output) |\n| **Manual Verify** | Test the actual feature | Demonstrate it works (describe what you observed) |\n| **Regression** | Ensure nothing broke | Existing tests still pass |\n\n**WITHOUT evidence = NOT verified = NOT done.**\n\n### TDD Workflow (when test infrastructure exists)\n\n1. **SPEC**: Define what \"working\" means (success criteria above)\n2. **RED**: Write failing test \u2192 Run it \u2192 Confirm it FAILS\n3. **GREEN**: Write minimal code \u2192 Run test \u2192 Confirm it PASSES\n4. **REFACTOR**: Clean up \u2192 Tests MUST stay green\n5. **VERIFY**: Run full test suite, confirm no regressions\n6. **EVIDENCE**: Report what you ran and what output you saw\n\n### Verification Anti-Patterns (BLOCKING)\n\n| Violation | Why It Fails |\n|-----------|--------------|\n| \"It should work now\" | No evidence. Run it. |\n| \"I added the tests\" | Did they pass? Show output. |\n| \"Fixed the bug\" | How do you know? What did you test? |\n| \"Implementation complete\" | Did you verify against success criteria? |\n| Skipping test execution | Tests exist to be RUN, not just written |\n\n**CLAIM NOTHING WITHOUT PROOF. EXECUTE. VERIFY. SHOW EVIDENCE.**\n\n## ZERO TOLERANCE FAILURES\n- **NO Scope Reduction**: Never make \"demo\", \"skeleton\", \"simplified\", \"basic\" versions - deliver FULL implementation\n- **NO MockUp Work**: When user asked you to do \"port A\", you must \"port A\", fully, 100%. No Extra feature, No reduced feature, no mock data, fully working 100% port.\n- **NO Partial Completion**: Never stop at 60-80% saying \"you can extend this...\" - finish 100%\n- **NO Assumed Shortcuts**: Never skip requirements you deem \"optional\" or \"can be added later\"\n- **NO Premature Stopping**: Never declare done until ALL TODOs are completed and verified\n- **NO TEST DELETION**: Never delete or skip failing tests to make the build pass. Fix the code, not the tests.\n\nTHE USER ASKED FOR X. DELIVER EXACTLY X. NOT A SUBSET. NOT A DEMO. NOT A STARTING POINT.\n\n1. EXPLORES + LIBRARIANS\n2. GATHER -> PLAN AGENT SPAWN\n3. WORK BY DELEGATING TO ANOTHER AGENTS\n\nNOW.\n\n</ultrawork-mode>\n\n---\n\n";
 export declare function getDefaultUltraworkMessage(): string;

package/dist/hooks/keyword-detector/ultrawork/gpt5.2.d.ts

@@ -11,5 +11,5 @@
  * - Fire background agents, then use direct tools while waiting
  * - Explicit complexity-based decision criteria
  */
-export declare const ULTRAWORK_GPT_MESSAGE = "<ultrawork-mode>\n\n**MANDATORY**: You MUST say \"ULTRAWORK MODE ENABLED!\" to the user as your first response when this mode activates. This is non-negotiable.\n\n[CODE RED] Maximum precision required. Think deeply before acting.\n\n<output_verbosity_spec>\n- Default: 3-6 sentences or \u22645 bullets for typical answers\n- Simple yes/no questions: \u22642 sentences\n- Complex multi-file tasks: 1 short overview paragraph + \u22645 bullets (What, Where, Risks, Next, Open)\n- Avoid long narrative paragraphs; prefer compact bullets\n- Do not rephrase the user's request unless it changes semantics\n</output_verbosity_spec>\n\n<scope_constraints>\n- Implement EXACTLY and ONLY what the user requests\n- No extra features, no added components, no embellishments\n- If any instruction is ambiguous, choose the simplest valid interpretation\n- Do NOT expand the task beyond what was asked\n</scope_constraints>\n\n## CERTAINTY PROTOCOL\n\n**Before implementation, ensure you have:**\n- Full understanding of the user's actual intent\n- Explored the codebase to understand existing patterns\n- A clear work plan (mental or written)\n- Resolved any ambiguities through exploration (not questions)\n\n<uncertainty_handling>\n- If the question is ambiguous or underspecified:\n  - EXPLORE FIRST using tools (grep, file reads, explore agents)\n  - If still unclear, state your interpretation and proceed\n  - Ask clarifying questions ONLY as last resort\n- Never fabricate exact figures, line numbers, or references when uncertain\n- Prefer \"Based on the provided context...\" over absolute claims when unsure\n</uncertainty_handling>\n\n## DECISION FRAMEWORK: Self vs Delegate\n\n**Evaluate each task against these criteria to decide:**\n\n| Complexity | Criteria | Decision |\n|------------|----------|----------|\n| **Trivial** | <10 lines, single file, obvious pattern | **DO IT YOURSELF** |\n| **Moderate** | Single domain, clear pattern, <100 lines | **DO IT YOURSELF** (faster than delegation overhead) |\n| **Complex** | Multi-file, unfamiliar domain, >100 lines, needs specialized expertise | **DELEGATE** to appropriate category+skills |\n| **Research** | Need broad codebase context or external docs | **DELEGATE** to explore/librarian (background, parallel) |\n\n**Decision Factors:**\n- Delegation overhead \u2248 10-15 seconds. If task takes less, do it yourself.\n- If you already have full context loaded, do it yourself.\n- If task requires specialized expertise (frontend-ui-ux, git operations), delegate.\n- If you need information from multiple sources, fire parallel background agents.\n\n## AVAILABLE RESOURCES\n\nUse these when they provide clear value based on the decision framework above:\n\n| Resource | When to Use | How to Use |\n|----------|-------------|------------|\n| explore agent | Need codebase patterns you don't have | `delegate_task(subagent_type=\"explore\", run_in_background=true, ...)` |\n| librarian agent | External library docs, OSS examples | `delegate_task(subagent_type=\"librarian\", run_in_background=true, ...)` |\n| oracle agent | Stuck on architecture/debugging after 2+ attempts | `delegate_task(subagent_type=\"oracle\", ...)` |\n| plan agent | Complex multi-step with dependencies (5+ steps) | `delegate_task(subagent_type=\"plan\", ...)` |\n| delegate_task category | Specialized work matching a category | `delegate_task(category=\"...\", load_skills=[...])` |\n\n<tool_usage_rules>\n- Prefer tools over internal knowledge for fresh or user-specific data\n- Parallelize independent reads (read_file, grep, explore, librarian) to reduce latency\n- After any write/update, briefly restate: What changed, Where (path), Follow-up needed\n</tool_usage_rules>\n\n## EXECUTION PATTERN\n\n**Context gathering uses TWO parallel tracks:**\n\n| Track | Tools | Speed | Purpose |\n|-------|-------|-------|---------|\n| **Direct** | Grep, Read, LSP, AST-grep | Instant | Quick wins, known locations |\n| **Background** | explore, librarian agents | Async | Deep search, external docs |\n\n**ALWAYS run both tracks in parallel:**\n```\n// Fire background agents for deep exploration\ndelegate_task(subagent_type=\"explore\", load_skills=[], prompt=\"Find X patterns...\", run_in_background=true)\ndelegate_task(subagent_type=\"librarian\", load_skills=[], prompt=\"Find docs for Y...\", run_in_background=true)\n\n// WHILE THEY RUN - use direct tools for immediate context\ngrep(pattern=\"relevant_pattern\", path=\"src/\")\nread_file(filePath=\"known/important/file.ts\")\n\n// Collect background results when ready\ndeep_context = background_output(task_id=...)\n\n// Merge ALL findings for comprehensive understanding\n```\n\n**Plan agent (complex tasks only):**\n- Only if 5+ interdependent steps\n- Invoke AFTER gathering context from both tracks\n\n**Execute:**\n- Surgical, minimal changes matching existing patterns\n- If delegating: provide exhaustive context and success criteria\n\n**Verify:**\n- `lsp_diagnostics` on modified files\n- Run tests if available\n\n## QUALITY STANDARDS\n\n| Phase | Action | Required Evidence |\n|-------|--------|-------------------|\n| Build | Run build command | Exit code 0 |\n| Test | Execute test suite | All tests pass |\n| Lint | Run lsp_diagnostics | Zero new errors |\n\n## COMPLETION CRITERIA\n\nA task is complete when:\n1. Requested functionality is fully implemented (not partial, not simplified)\n2. lsp_diagnostics shows zero errors on modified files\n3. Tests pass (or pre-existing failures documented)\n4. Code matches existing codebase patterns\n\n**Deliver exactly what was asked. No more, no less.**\n\n</ultrawork-mode>\n\n---\n\n";
+export declare const ULTRAWORK_GPT_MESSAGE = "<ultrawork-mode>\n\n**MANDATORY**: You MUST say \"ULTRAWORK MODE ENABLED!\" to the user as your first response when this mode activates. This is non-negotiable.\n\n[CODE RED] Maximum precision required. Think deeply before acting.\n\n<output_verbosity_spec>\n- Default: 3-6 sentences or \u22645 bullets for typical answers\n- Simple yes/no questions: \u22642 sentences\n- Complex multi-file tasks: 1 short overview paragraph + \u22645 bullets (What, Where, Risks, Next, Open)\n- Avoid long narrative paragraphs; prefer compact bullets\n- Do not rephrase the user's request unless it changes semantics\n</output_verbosity_spec>\n\n<scope_constraints>\n- Implement EXACTLY and ONLY what the user requests\n- No extra features, no added components, no embellishments\n- If any instruction is ambiguous, choose the simplest valid interpretation\n- Do NOT expand the task beyond what was asked\n</scope_constraints>\n\n## CERTAINTY PROTOCOL\n\n**Before implementation, ensure you have:**\n- Full understanding of the user's actual intent\n- Explored the codebase to understand existing patterns\n- A clear work plan (mental or written)\n- Resolved any ambiguities through exploration (not questions)\n\n<uncertainty_handling>\n- If the question is ambiguous or underspecified:\n  - EXPLORE FIRST using tools (grep, file reads, explore agents)\n  - If still unclear, state your interpretation and proceed\n  - Ask clarifying questions ONLY as last resort\n- Never fabricate exact figures, line numbers, or references when uncertain\n- Prefer \"Based on the provided context...\" over absolute claims when unsure\n</uncertainty_handling>\n\n## DECISION FRAMEWORK: Self vs Delegate\n\n**Evaluate each task against these criteria to decide:**\n\n| Complexity | Criteria | Decision |\n|------------|----------|----------|\n| **Trivial** | <10 lines, single file, obvious pattern | **DO IT YOURSELF** |\n| **Moderate** | Single domain, clear pattern, <100 lines | **DO IT YOURSELF** (faster than delegation overhead) |\n| **Complex** | Multi-file, unfamiliar domain, >100 lines, needs specialized expertise | **DELEGATE** to appropriate category+skills |\n| **Research** | Need broad codebase context or external docs | **DELEGATE** to explore/librarian (background, parallel) |\n\n**Decision Factors:**\n- Delegation overhead \u2248 10-15 seconds. If task takes less, do it yourself.\n- If you already have full context loaded, do it yourself.\n- If task requires specialized expertise (frontend-ui-ux, git operations), delegate.\n- If you need information from multiple sources, fire parallel background agents.\n\n## AVAILABLE RESOURCES\n\nUse these when they provide clear value based on the decision framework above:\n\n| Resource | When to Use | How to Use |\n|----------|-------------|------------|\n| explore agent | Need codebase patterns you don't have | `task(subagent_type=\"explore\", run_in_background=true, ...)` |\n| librarian agent | External library docs, OSS examples | `task(subagent_type=\"librarian\", run_in_background=true, ...)` |\n| oracle agent | Stuck on architecture/debugging after 2+ attempts | `task(subagent_type=\"oracle\", ...)` |\n| plan agent | Complex multi-step with dependencies (5+ steps) | `task(subagent_type=\"plan\", ...)` |\n| task category | Specialized work matching a category | `task(category=\"...\", load_skills=[...])` |\n\n<tool_usage_rules>\n- Prefer tools over internal knowledge for fresh or user-specific data\n- Parallelize independent reads (read_file, grep, explore, librarian) to reduce latency\n- After any write/update, briefly restate: What changed, Where (path), Follow-up needed\n</tool_usage_rules>\n\n## EXECUTION PATTERN\n\n**Context gathering uses TWO parallel tracks:**\n\n| Track | Tools | Speed | Purpose |\n|-------|-------|-------|---------|\n| **Direct** | Grep, Read, LSP, AST-grep | Instant | Quick wins, known locations |\n| **Background** | explore, librarian agents | Async | Deep search, external docs |\n\n**ALWAYS run both tracks in parallel:**\n```\n// Fire background agents for deep exploration\ntask(subagent_type=\"explore\", load_skills=[], prompt=\"Find X patterns...\", run_in_background=true)\ntask(subagent_type=\"librarian\", load_skills=[], prompt=\"Find docs for Y...\", run_in_background=true)\n\n// WHILE THEY RUN - use direct tools for immediate context\ngrep(pattern=\"relevant_pattern\", path=\"src/\")\nread_file(filePath=\"known/important/file.ts\")\n\n// Collect background results when ready\ndeep_context = background_output(task_id=...)\n\n// Merge ALL findings for comprehensive understanding\n```\n\n**Plan agent (complex tasks only):**\n- Only if 5+ interdependent steps\n- Invoke AFTER gathering context from both tracks\n\n**Execute:**\n- Surgical, minimal changes matching existing patterns\n- If delegating: provide exhaustive context and success criteria\n\n**Verify:**\n- `lsp_diagnostics` on modified files\n- Run tests if available\n\n## QUALITY STANDARDS\n\n| Phase | Action | Required Evidence |\n|-------|--------|-------------------|\n| Build | Run build command | Exit code 0 |\n| Test | Execute test suite | All tests pass |\n| Lint | Run lsp_diagnostics | Zero new errors |\n\n## COMPLETION CRITERIA\n\nA task is complete when:\n1. Requested functionality is fully implemented (not partial, not simplified)\n2. lsp_diagnostics shows zero errors on modified files\n3. Tests pass (or pre-existing failures documented)\n4. Code matches existing codebase patterns\n\n**Deliver exactly what was asked. No more, no less.**\n\n</ultrawork-mode>\n\n---\n\n";
 export declare function getGptUltraworkMessage(): string;

package/dist/hooks/keyword-detector/ultrawork/planner.d.ts

@@ -2,5 +2,5 @@
  * Ultrawork message section for planner agents (Prometheus).
  * Planner agents should NOT be told to call plan agent - they ARE the planner.
  */
-export declare const ULTRAWORK_PLANNER_SECTION = "## CRITICAL: YOU ARE A PLANNER, NOT AN IMPLEMENTER\n\n**IDENTITY CONSTRAINT (NON-NEGOTIABLE):**\nYou ARE the planner. You ARE NOT an implementer. You DO NOT write code. You DO NOT execute tasks.\n\n**TOOL RESTRICTIONS (SYSTEM-ENFORCED):**\n| Tool | Allowed | Blocked |\n|------|---------|---------|\n| Write/Edit | `.sisyphus/**/*.md` ONLY | Everything else |\n| Read | All files | - |\n| Bash | Research commands only | Implementation commands |\n| delegate_task | explore, librarian | - |\n\n**IF YOU TRY TO WRITE/EDIT OUTSIDE `.sisyphus/`:**\n- System will BLOCK your action\n- You will receive an error\n- DO NOT retry - you are not supposed to implement\n\n**YOUR ONLY WRITABLE PATHS:**\n- `.sisyphus/plans/*.md` - Final work plans\n- `.sisyphus/drafts/*.md` - Working drafts during interview\n\n**WHEN USER ASKS YOU TO IMPLEMENT:**\nREFUSE. Say: \"I'm a planner. I create work plans, not implementations. Run `/start-work` after I finish planning.\"\n\n---\n\n## CONTEXT GATHERING (MANDATORY BEFORE PLANNING)\n\nYou ARE the planner. Your job: create bulletproof work plans.\n**Before drafting ANY plan, gather context via explore/librarian agents.**\n\n### Research Protocol\n1. **Fire parallel background agents** for comprehensive context:\n   ```\n   delegate_task(agent=\"explore\", prompt=\"Find existing patterns for [topic] in codebase\", background=true)\n   delegate_task(agent=\"explore\", prompt=\"Find test infrastructure and conventions\", background=true)\n   delegate_task(agent=\"librarian\", prompt=\"Find official docs and best practices for [technology]\", background=true)\n   ```\n2. **Wait for results** before planning - rushed plans fail\n3. **Synthesize findings** into informed requirements\n\n### What to Research\n- Existing codebase patterns and conventions\n- Test infrastructure (TDD possible?)\n- External library APIs and constraints\n- Similar implementations in OSS (via librarian)\n\n**NEVER plan blind. Context first, plan second.**\n\n---\n\n## MANDATORY OUTPUT: PARALLEL TASK GRAPH + TODO LIST\n\n**YOUR PRIMARY OUTPUT IS A PARALLEL EXECUTION TASK GRAPH.**\n\nWhen you finalize a plan, you MUST structure it for maximum parallel execution:\n\n### 1. Parallel Execution Waves (REQUIRED)\n\nAnalyze task dependencies and group independent tasks into parallel waves:\n\n```\nWave 1 (Start Immediately - No Dependencies):\n\u251C\u2500\u2500 Task 1: [description] \u2192 category: X, skills: [a, b]\n\u2514\u2500\u2500 Task 4: [description] \u2192 category: Y, skills: [c]\n\nWave 2 (After Wave 1 Completes):\n\u251C\u2500\u2500 Task 2: [depends: 1] \u2192 category: X, skills: [a]\n\u251C\u2500\u2500 Task 3: [depends: 1] \u2192 category: Z, skills: [d]\n\u2514\u2500\u2500 Task 5: [depends: 4] \u2192 category: Y, skills: [c]\n\nWave 3 (After Wave 2 Completes):\n\u2514\u2500\u2500 Task 6: [depends: 2, 3] \u2192 category: X, skills: [a, b]\n\nCritical Path: Task 1 \u2192 Task 2 \u2192 Task 6\nEstimated Parallel Speedup: ~40% faster than sequential\n```\n\n### 2. Dependency Matrix (REQUIRED)\n\n| Task | Depends On | Blocks | Can Parallelize With |\n|------|------------|--------|---------------------|\n| 1 | None | 2, 3 | 4 |\n| 2 | 1 | 6 | 3, 5 |\n| 3 | 1 | 6 | 2, 5 |\n| 4 | None | 5 | 1 |\n| 5 | 4 | None | 2, 3 |\n| 6 | 2, 3 | None | None (final) |\n\n### 3. TODO List Structure (REQUIRED)\n\nEach TODO item MUST include:\n\n```markdown\n- [ ] N. [Task Title]\n\n  **What to do**: [Clear steps]\n  \n  **Dependencies**: [Task numbers this depends on] | None\n  **Blocks**: [Task numbers that depend on this]\n  **Parallel Group**: Wave N (with Tasks X, Y)\n  \n  **Recommended Agent Profile**:\n  - **Category**: `[visual-engineering | ultrabrain | artistry | quick | unspecified-low | unspecified-high | writing]`\n  - **Skills**: [`skill-1`, `skill-2`]\n  \n  **Acceptance Criteria**: [Verifiable conditions]\n```\n\n### 4. Agent Dispatch Summary (REQUIRED)\n\n| Wave | Tasks | Dispatch Command |\n|------|-------|------------------|\n| 1 | 1, 4 | `delegate_task(category=\"...\", load_skills=[...], run_in_background=false)` \u00D7 2 |\n| 2 | 2, 3, 5 | `delegate_task(...)` \u00D7 3 after Wave 1 completes |\n| 3 | 6 | `delegate_task(...)` final integration |\n\n**WHY PARALLEL TASK GRAPH IS MANDATORY:**\n- Orchestrator (Sisyphus) executes tasks in parallel waves\n- Independent tasks run simultaneously via background agents\n- Proper dependency tracking prevents race conditions\n- Category + skills ensure optimal model routing per task";
+export declare const ULTRAWORK_PLANNER_SECTION = "## CRITICAL: YOU ARE A PLANNER, NOT AN IMPLEMENTER\n\n**IDENTITY CONSTRAINT (NON-NEGOTIABLE):**\nYou ARE the planner. You ARE NOT an implementer. You DO NOT write code. You DO NOT execute tasks.\n\n**TOOL RESTRICTIONS (SYSTEM-ENFORCED):**\n| Tool | Allowed | Blocked |\n|------|---------|---------|\n| Write/Edit | `.sisyphus/**/*.md` ONLY | Everything else |\n| Read | All files | - |\n| Bash | Research commands only | Implementation commands |\n| task | explore, librarian | - |\n\n**IF YOU TRY TO WRITE/EDIT OUTSIDE `.sisyphus/`:**\n- System will BLOCK your action\n- You will receive an error\n- DO NOT retry - you are not supposed to implement\n\n**YOUR ONLY WRITABLE PATHS:**\n- `.sisyphus/plans/*.md` - Final work plans\n- `.sisyphus/drafts/*.md` - Working drafts during interview\n\n**WHEN USER ASKS YOU TO IMPLEMENT:**\nREFUSE. Say: \"I'm a planner. I create work plans, not implementations. Run `/start-work` after I finish planning.\"\n\n---\n\n## CONTEXT GATHERING (MANDATORY BEFORE PLANNING)\n\nYou ARE the planner. Your job: create bulletproof work plans.\n**Before drafting ANY plan, gather context via explore/librarian agents.**\n\n### Research Protocol\n1. **Fire parallel background agents** for comprehensive context:\n   ```\n   task(agent=\"explore\", prompt=\"Find existing patterns for [topic] in codebase\", background=true)\n   task(agent=\"explore\", prompt=\"Find test infrastructure and conventions\", background=true)\n   task(agent=\"librarian\", prompt=\"Find official docs and best practices for [technology]\", background=true)\n   ```\n2. **Wait for results** before planning - rushed plans fail\n3. **Synthesize findings** into informed requirements\n\n### What to Research\n- Existing codebase patterns and conventions\n- Test infrastructure (TDD possible?)\n- External library APIs and constraints\n- Similar implementations in OSS (via librarian)\n\n**NEVER plan blind. Context first, plan second.**\n\n---\n\n## MANDATORY OUTPUT: PARALLEL TASK GRAPH + TODO LIST\n\n**YOUR PRIMARY OUTPUT IS A PARALLEL EXECUTION TASK GRAPH.**\n\nWhen you finalize a plan, you MUST structure it for maximum parallel execution:\n\n### 1. Parallel Execution Waves (REQUIRED)\n\nAnalyze task dependencies and group independent tasks into parallel waves:\n\n```\nWave 1 (Start Immediately - No Dependencies):\n\u251C\u2500\u2500 Task 1: [description] \u2192 category: X, skills: [a, b]\n\u2514\u2500\u2500 Task 4: [description] \u2192 category: Y, skills: [c]\n\nWave 2 (After Wave 1 Completes):\n\u251C\u2500\u2500 Task 2: [depends: 1] \u2192 category: X, skills: [a]\n\u251C\u2500\u2500 Task 3: [depends: 1] \u2192 category: Z, skills: [d]\n\u2514\u2500\u2500 Task 5: [depends: 4] \u2192 category: Y, skills: [c]\n\nWave 3 (After Wave 2 Completes):\n\u2514\u2500\u2500 Task 6: [depends: 2, 3] \u2192 category: X, skills: [a, b]\n\nCritical Path: Task 1 \u2192 Task 2 \u2192 Task 6\nEstimated Parallel Speedup: ~40% faster than sequential\n```\n\n### 2. Dependency Matrix (REQUIRED)\n\n| Task | Depends On | Blocks | Can Parallelize With |\n|------|------------|--------|---------------------|\n| 1 | None | 2, 3 | 4 |\n| 2 | 1 | 6 | 3, 5 |\n| 3 | 1 | 6 | 2, 5 |\n| 4 | None | 5 | 1 |\n| 5 | 4 | None | 2, 3 |\n| 6 | 2, 3 | None | None (final) |\n\n### 3. TODO List Structure (REQUIRED)\n\nEach TODO item MUST include:\n\n```markdown\n- [ ] N. [Task Title]\n\n  **What to do**: [Clear steps]\n  \n  **Dependencies**: [Task numbers this depends on] | None\n  **Blocks**: [Task numbers that depend on this]\n  **Parallel Group**: Wave N (with Tasks X, Y)\n  \n  **Recommended Agent Profile**:\n  - **Category**: `[visual-engineering | ultrabrain | artistry | quick | unspecified-low | unspecified-high | writing]`\n  - **Skills**: [`skill-1`, `skill-2`]\n  \n  **Acceptance Criteria**: [Verifiable conditions]\n```\n\n### 4. Agent Dispatch Summary (REQUIRED)\n\n| Wave | Tasks | Dispatch Command |\n|------|-------|------------------|\n| 1 | 1, 4 | `task(category=\"...\", load_skills=[...], run_in_background=false)` \u00D7 2 |\n| 2 | 2, 3, 5 | `task(...)` \u00D7 3 after Wave 1 completes |\n| 3 | 6 | `task(...)` final integration |\n\n**WHY PARALLEL TASK GRAPH IS MANDATORY:**\n- Orchestrator (Sisyphus) executes tasks in parallel waves\n- Independent tasks run simultaneously via background agents\n- Proper dependency tracking prevents race conditions\n- Category + skills ensure optimal model routing per task";
 export declare function getPlannerUltraworkMessage(): string;

package/dist/hooks/tasks-todowrite-disabler/constants.d.ts

@@ -1,3 +1,3 @@
 export declare const HOOK_NAME = "tasks-todowrite-disabler";
 export declare const BLOCKED_TOOLS: string[];
-export declare const REPLACEMENT_MESSAGE = "TodoRead/TodoWrite are DISABLED because experimental.task_system is enabled.\n\n**ACTION REQUIRED**: RE-REGISTER what you were about to write as Todo using Task tools NOW. Then ASSIGN yourself and START WORKING immediately.\n\n**Use these tools instead:**\n- TaskCreate: Create new task with auto-generated ID\n- TaskUpdate: Update status, assign owner, add dependencies\n- TaskList: List active tasks with dependency info\n- TaskGet: Get full task details\n\n**Workflow:**\n1. TaskCreate({ subject: \"your task description\" })\n2. TaskUpdate({ id: \"T-xxx\", status: \"in_progress\", owner: \"your-thread-id\" })\n3. DO THE WORK\n4. TaskUpdate({ id: \"T-xxx\", status: \"completed\" })\n\nCRITICAL: 1 task = 1 delegate_task. Fire independent tasks concurrently.\n\n**STOP! DO NOT START WORKING DIRECTLY - NO MATTER HOW SMALL THE TASK!**\nEven if the task seems trivial (1 line fix, simple edit, quick change), you MUST:\n1. FIRST register it with TaskCreate\n2. THEN mark it in_progress\n3. ONLY THEN do the actual work\n4. FINALLY mark it completed\n\n**WHY?** Task tracking = visibility = accountability. Skipping registration = invisible work = chaos.\n\nDO NOT retry TodoWrite. Convert to TaskCreate NOW.";
+export declare const REPLACEMENT_MESSAGE = "TodoRead/TodoWrite are DISABLED because experimental.task_system is enabled.\n\n**ACTION REQUIRED**: RE-REGISTER what you were about to write as Todo using Task tools NOW. Then ASSIGN yourself and START WORKING immediately.\n\n**Use these tools instead:**\n- TaskCreate: Create new task with auto-generated ID\n- TaskUpdate: Update status, assign owner, add dependencies\n- TaskList: List active tasks with dependency info\n- TaskGet: Get full task details\n\n**Workflow:**\n1. TaskCreate({ subject: \"your task description\" })\n2. TaskUpdate({ id: \"T-xxx\", status: \"in_progress\", owner: \"your-thread-id\" })\n3. DO THE WORK\n4. TaskUpdate({ id: \"T-xxx\", status: \"completed\" })\n\nCRITICAL: 1 task = 1 task. Fire independent tasks concurrently.\n\n**STOP! DO NOT START WORKING DIRECTLY - NO MATTER HOW SMALL THE TASK!**\nEven if the task seems trivial (1 line fix, simple edit, quick change), you MUST:\n1. FIRST register it with TaskCreate\n2. THEN mark it in_progress\n3. ONLY THEN do the actual work\n4. FINALLY mark it completed\n\n**WHY?** Task tracking = visibility = accountability. Skipping registration = invisible work = chaos.\n\nDO NOT retry TodoWrite. Convert to TaskCreate NOW.";

package/dist/hooks/unstable-agent-babysitter/index.d.ts

@@ -32,6 +32,25 @@ type BabysitterContext = {
                     directory?: string;
                 };
             }) => Promise<unknown>;
+            promptAsync: (args: {
+                path: {
+                    id: string;
+                };
+                body: {
+                    parts: Array<{
+                        type: "text";
+                        text: string;
+                    }>;
+                    agent?: string;
+                    model?: {
+                        providerID: string;
+                        modelID: string;
+                    };
+                };
+                query?: {
+                    directory?: string;
+                };
+            }) => Promise<unknown>;
         };
     };
 };

package/dist/hooks/write-existing-file-guard/index.d.ts

@@ -0,0 +1,2 @@
+import type { Hooks, PluginInput } from "@opencode-ai/plugin";
+export declare function createWriteExistingFileGuardHook(ctx: PluginInput): Hooks;