oh-my-opencode 3.9.0 → 3.11.0

package/dist/config/schema/background-task.d.ts

@@ -5,5 +5,6 @@ export declare const BackgroundTaskConfigSchema: z.ZodObject<{
     modelConcurrency: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodNumber>>;
     staleTimeoutMs: z.ZodOptional<z.ZodNumber>;
     messageStalenessTimeoutMs: z.ZodOptional<z.ZodNumber>;
+    syncPollTimeoutMs: z.ZodOptional<z.ZodNumber>;
 }, z.core.$strip>;
 export type BackgroundTaskConfig = z.infer<typeof BackgroundTaskConfigSchema>;

package/dist/config/schema/categories.d.ts

@@ -33,12 +33,12 @@ export declare const CategoryConfigSchema: z.ZodObject<{
 }, z.core.$strip>;
 export declare const BuiltinCategoryNameSchema: z.ZodEnum<{
     deep: "deep";
+    "unspecified-high": "unspecified-high";
     "visual-engineering": "visual-engineering";
     ultrabrain: "ultrabrain";
     artistry: "artistry";
     quick: "quick";
     "unspecified-low": "unspecified-low";
-    "unspecified-high": "unspecified-high";
     writing: "writing";
 }>;
 export declare const CategoriesConfigSchema: z.ZodRecord<z.ZodString, z.ZodObject<{

package/dist/config/schema/hooks.d.ts

@@ -46,5 +46,6 @@ export declare const HookNameSchema: z.ZodEnum<{
     "write-existing-file-guard": "write-existing-file-guard";
     "anthropic-effort": "anthropic-effort";
     "hashline-read-enhancer": "hashline-read-enhancer";
+    "read-image-resizer": "read-image-resizer";
 }>;
 export type HookName = z.infer<typeof HookNameSchema>;

package/dist/config/schema/oh-my-opencode-config.d.ts

@@ -1338,6 +1338,7 @@ export declare const OhMyOpenCodeConfigSchema: z.ZodObject<{
         modelConcurrency: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodNumber>>;
         staleTimeoutMs: z.ZodOptional<z.ZodNumber>;
         messageStalenessTimeoutMs: z.ZodOptional<z.ZodNumber>;
+        syncPollTimeoutMs: z.ZodOptional<z.ZodNumber>;
     }, z.core.$strip>>;
     notification: z.ZodOptional<z.ZodObject<{
         force_enable: z.ZodOptional<z.ZodBoolean>;
@@ -1383,6 +1384,9 @@ export declare const OhMyOpenCodeConfigSchema: z.ZodObject<{
             claude_code_compat: z.ZodDefault<z.ZodBoolean>;
         }, z.core.$strip>>;
     }, z.core.$strip>>;
+    start_work: z.ZodOptional<z.ZodObject<{
+        auto_commit: z.ZodDefault<z.ZodBoolean>;
+    }, z.core.$strip>>;
     _migrations: z.ZodOptional<z.ZodArray<z.ZodString>>;
 }, z.core.$strip>;
 export type OhMyOpenCodeConfig = z.infer<typeof OhMyOpenCodeConfigSchema>;

package/dist/config/schema/start-work.d.ts

@@ -0,0 +1,5 @@
+import { z } from "zod";
+export declare const StartWorkConfigSchema: z.ZodObject<{
+    auto_commit: z.ZodDefault<z.ZodBoolean>;
+}, z.core.$strip>;
+export type StartWorkConfig = z.infer<typeof StartWorkConfigSchema>;

package/dist/create-hooks.d.ts

@@ -38,6 +38,7 @@ export declare function createHooks(args: {
     writeExistingFileGuard: ReturnType<typeof import("./hooks").createWriteExistingFileGuardHook> | null;
     hashlineReadEnhancer: ReturnType<typeof import("./hooks").createHashlineReadEnhancerHook> | null;
     jsonErrorRecovery: ReturnType<typeof import("./hooks").createJsonErrorRecoveryHook> | null;
+    readImageResizer: ReturnType<typeof import("./hooks").createReadImageResizerHook> | null;
     contextWindowMonitor: ReturnType<typeof import("./hooks").createContextWindowMonitorHook> | null;
     preemptiveCompaction: ReturnType<typeof import("./hooks").createPreemptiveCompactionHook> | null;
     sessionRecovery: ReturnType<typeof import("./hooks").createSessionRecoveryHook> | null;

package/dist/features/builtin-commands/templates/ralph-loop.d.ts

@@ -1,2 +1,3 @@
 export declare const RALPH_LOOP_TEMPLATE = "You are starting a Ralph Loop - a self-referential development loop that runs until task completion.\n\n## How Ralph Loop Works\n\n1. You will work on the task continuously\n2. When you believe the task is FULLY complete, output: `<promise>{{COMPLETION_PROMISE}}</promise>`\n3. If you don't output the promise, the loop will automatically inject another prompt to continue\n4. Maximum iterations: Configurable (default 100)\n\n## Rules\n\n- Focus on completing the task fully, not partially\n- Don't output the completion promise until the task is truly done\n- Each iteration should make meaningful progress toward the goal\n- If stuck, try different approaches\n- Use todos to track your progress\n\n## Exit Conditions\n\n1. **Completion**: Output your completion promise tag when fully complete\n2. **Max Iterations**: Loop stops automatically at limit\n3. **Cancel**: User runs `/cancel-ralph` command\n\n## Your Task\n\nParse the arguments below and begin working on the task. The format is:\n`\"task description\" [--completion-promise=TEXT] [--max-iterations=N] [--strategy=reset|continue]`\n\nDefault completion promise is \"DONE\" and default max iterations is 100.";
+export declare const ULW_LOOP_TEMPLATE = "You are starting an ULTRAWORK Loop - a self-referential development loop that runs until verified completion.\n\n## How ULTRAWORK Loop Works\n\n1. You will work on the task continuously\n2. When you believe the work is complete, output: `<promise>{{COMPLETION_PROMISE}}</promise>`\n3. That does NOT finish the loop yet. The system will require Oracle verification\n4. The loop only ends after the system confirms Oracle verified the result\n5. There is no iteration limit\n\n## Rules\n\n- Focus on finishing the task completely\n- After you emit the completion promise, run Oracle verification when instructed\n- Do not treat DONE as final completion until Oracle verifies it\n\n## Exit Conditions\n\n1. **Verified Completion**: Oracle verifies the result and the system confirms it\n2. **Cancel**: User runs `/cancel-ralph`\n\n## Your Task\n\nParse the arguments below and begin working on the task. The format is:\n`\"task description\" [--completion-promise=TEXT] [--strategy=reset|continue]`\n\nDefault completion promise is \"DONE\".";
 export declare const CANCEL_RALPH_TEMPLATE = "Cancel the currently active Ralph Loop.\n\nThis will:\n1. Stop the loop from continuing\n2. Clear the loop state file\n3. Allow the session to end normally\n\nCheck if a loop is active and cancel it. Inform the user of the result.";

package/dist/features/claude-code-plugin-loader/types.d.ts

@@ -70,12 +70,22 @@ export interface PluginManifest {
 /**
  * Hooks configuration
  */
-export interface HookEntry {
-    type: "command" | "prompt" | "agent";
+export type HookEntry = {
+    type: "command";
     command?: string;
+} | {
+    type: "prompt";
     prompt?: string;
+} | {
+    type: "agent";
     agent?: string;
-}
+} | {
+    type: "http";
+    url: string;
+    headers?: Record<string, string>;
+    allowedEnvVars?: string[];
+    timeout?: number;
+};
 export interface HookMatcher {
     matcher?: string;
     hooks: HookEntry[];

package/dist/features/context-injector/types.d.ts

@@ -20,8 +20,8 @@ export interface ContextEntry {
     content: string;
     /** Priority for ordering (default: normal) */
     priority: ContextPriority;
-    /** Timestamp when registered */
-    timestamp: number;
+    /** Monotonic order when registered */
+    registrationOrder: number;
     /** Optional metadata for debugging/logging */
     metadata?: Record<string, unknown>;
 }

package/dist/features/hook-message-injector/injector.d.ts

@@ -41,6 +41,8 @@ export declare function findNearestMessageWithFields(messageDir: string): Stored
  * @deprecated Use findFirstMessageWithAgentFromSDK for beta/SQLite backend
  */
 export declare function findFirstMessageWithAgent(messageDir: string): string | null;
+export declare function generateMessageId(): string;
+export declare function generatePartId(): string;
 /**
  * Injects a hook message into the session storage.
  *

package/dist/hooks/atlas/session-last-agent.d.ts

@@ -1,4 +1,11 @@
-import type { PluginInput } from "@opencode-ai/plugin";
-type OpencodeClient = PluginInput["client"];
-export declare function getLastAgentFromSession(sessionID: string, client?: OpencodeClient): Promise<string | null>;
+type SessionMessagesClient = {
+    session: {
+        messages: (input: {
+            path: {
+                id: string;
+            };
+        }) => Promise<unknown>;
+    };
+};
+export declare function getLastAgentFromSession(sessionID: string, client?: SessionMessagesClient): Promise<string | null>;
 export {};

package/dist/hooks/atlas/tool-execute-after.d.ts

@@ -3,4 +3,5 @@ import type { ToolExecuteAfterInput, ToolExecuteAfterOutput } from "./types";
 export declare function createToolExecuteAfterHandler(input: {
     ctx: PluginInput;
     pendingFilePaths: Map<string, string>;
+    autoCommit: boolean;
 }): (toolInput: ToolExecuteAfterInput, toolOutput: ToolExecuteAfterOutput) => Promise<void>;

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

@@ -9,6 +9,8 @@ export interface AtlasHookOptions {
     backgroundManager?: BackgroundManager;
     isContinuationStopped?: (sessionID: string) => boolean;
     agentOverrides?: AgentOverrides;
+    /** Enable auto-commit after each atomic task completion (default: true) */
+    autoCommit?: boolean;
 }
 export interface ToolExecuteAfterInput {
     tool: string;
@@ -25,4 +27,5 @@ export interface SessionState {
     lastContinuationInjectedAt?: number;
     promptFailureCount: number;
     lastFailureAt?: number;
+    pendingRetryTimer?: ReturnType<typeof setTimeout>;
 }

package/dist/hooks/atlas/verification-reminders.d.ts

@@ -1,5 +1,6 @@
+export declare function buildCompletionGate(planName: string, sessionId: string): string;
 export declare function buildOrchestratorReminder(planName: string, progress: {
     total: number;
     completed: number;
-}, sessionId: string): string;
+}, sessionId: string, autoCommit?: boolean, includeCompletionGate?: boolean): string;
 export declare function buildStandaloneVerificationReminder(sessionId: string): string;

package/dist/hooks/auto-slash-command/executor.d.ts

@@ -2,6 +2,8 @@ import { type LoadedSkill } from "../../features/opencode-skill-loader";
 import type { ParsedSlashCommand } from "./types";
 export interface ExecutorOptions {
     skills?: LoadedSkill[];
+    pluginsEnabled?: boolean;
+    enabledPluginsOverride?: Record<string, boolean>;
 }
 export interface ExecuteResult {
     success: boolean;

package/dist/hooks/auto-slash-command/hook.d.ts

@@ -2,6 +2,8 @@ import type { AutoSlashCommandHookInput, AutoSlashCommandHookOutput, CommandExec
 import type { LoadedSkill } from "../../features/opencode-skill-loader";
 export interface AutoSlashCommandHookOptions {
     skills?: LoadedSkill[];
+    pluginsEnabled?: boolean;
+    enabledPluginsOverride?: Record<string, boolean>;
 }
 export declare function createAutoSlashCommandHook(options?: AutoSlashCommandHookOptions): {
     "chat.message": (input: AutoSlashCommandHookInput, output: AutoSlashCommandHookOutput) => Promise<void>;

package/dist/hooks/claude-code-hooks/dispatch-hook.d.ts

@@ -0,0 +1,4 @@
+import type { HookAction } from "./types";
+import type { CommandResult } from "../../shared/command-executor/execute-hook-command";
+export declare function getHookIdentifier(hook: HookAction): string;
+export declare function dispatchHook(hook: HookAction, stdinJson: string, cwd: string): Promise<CommandResult>;

package/dist/hooks/claude-code-hooks/execute-http-hook.d.ts

@@ -0,0 +1,4 @@
+import type { HookHttp } from "./types";
+import type { CommandResult } from "../../shared/command-executor/execute-hook-command";
+export declare function interpolateEnvVars(value: string, allowedEnvVars: string[]): string;
+export declare function executeHttpHook(hook: HookHttp, stdin: string): Promise<CommandResult>;

package/dist/hooks/claude-code-hooks/types.d.ts

@@ -5,12 +5,20 @@
 export type ClaudeHookEvent = "PreToolUse" | "PostToolUse" | "UserPromptSubmit" | "Stop" | "PreCompact";
 export interface HookMatcher {
     matcher: string;
-    hooks: HookCommand[];
+    hooks: HookAction[];
 }
 export interface HookCommand {
     type: "command";
     command: string;
 }
+export interface HookHttp {
+    type: "http";
+    url: string;
+    headers?: Record<string, string>;
+    allowedEnvVars?: string[];
+    timeout?: number;
+}
+export type HookAction = HookCommand | HookHttp;
 export interface ClaudeHooksConfig {
     PreToolUse?: HookMatcher[];
     PostToolUse?: HookMatcher[];

package/dist/hooks/index.d.ts

@@ -46,3 +46,4 @@ export { createRuntimeFallbackHook, type RuntimeFallbackHook, type RuntimeFallba
 export { createWriteExistingFileGuardHook } from "./write-existing-file-guard";
 export { createHashlineReadEnhancerHook } from "./hashline-read-enhancer";
 export { createJsonErrorRecoveryHook, JSON_ERROR_TOOL_EXCLUDE_LIST, JSON_ERROR_PATTERNS, JSON_ERROR_REMINDER } from "./json-error-recovery";
+export { createReadImageResizerHook } from "./read-image-resizer";

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

@@ -6,5 +6,5 @@
  * - 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```\ntask(subagent_type=\"explore\", load_skills=[], prompt=\"I'm implementing [TASK DESCRIPTION] and need to understand [SPECIFIC KNOWLEDGE GAP]. Find [X] patterns in the codebase \u2014 show file paths, implementation approach, and conventions used. I'll use this to [HOW RESULTS WILL BE USED]. Focus on src/ directories, skip test files unless test patterns are specifically needed. Return concrete file paths with brief descriptions of what each file does.\", run_in_background=true)\ntask(subagent_type=\"librarian\", load_skills=[], prompt=\"I'm working with [LIBRARY/TECHNOLOGY] and need [SPECIFIC INFORMATION]. Find official documentation and production-quality examples for [Y] \u2014 specifically: API reference, configuration options, recommended patterns, and common pitfalls. Skip beginner tutorials. I'll use this to [DECISION THIS WILL INFORM].\", run_in_background=true)\ntask(subagent_type=\"oracle\", load_skills=[], prompt=\"I need architectural review of my approach to [TASK]. Here's my plan: [DESCRIBE PLAN WITH SPECIFIC FILES AND CHANGES]. My concerns are: [LIST SPECIFIC UNCERTAINTIES]. Please evaluate: correctness of approach, potential issues I'm missing, and whether a better alternative exists.\", 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\", load_skills=[], 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}\", load_skills=[], prompt=\"<your answer>\")` |\n| Need to refine the plan | `task(session_id=\"{returned_session_id}\", load_skills=[], prompt=\"Please adjust: <feedback>\")` |\n| Plan needs more detail | `task(session_id=\"{returned_session_id}\", load_skills=[], 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\", load_skills=[], prompt=\"Here's more info...\")\n\n// CORRECT: Resume preserves everything\ntask(session_id=\"ses_abc123\", load_skills=[], 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\", load_skills=[], run_in_background=true) | Parallel, context-efficient |\n| Documentation lookup | task(subagent_type=\"librarian\", load_skills=[], run_in_background=true) | Specialized knowledge |\n| Planning | task(subagent_type=\"plan\", load_skills=[]) | Parallel task graph + structured TODO list |\n| Hard problem (conventional) | task(subagent_type=\"oracle\", load_skills=[]) | 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 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=\"I'm implementing [TASK DESCRIPTION] and need to understand [SPECIFIC KNOWLEDGE GAP]. Find [X] patterns in the codebase \u2014 show file paths, implementation approach, and conventions used. I'll use this to [HOW RESULTS WILL BE USED]. Focus on src/ directories, skip test files unless test patterns are specifically needed. Return concrete file paths with brief descriptions of what each file does.\", run_in_background=true)\ntask(subagent_type=\"librarian\", load_skills=[], prompt=\"I'm working with [LIBRARY/TECHNOLOGY] and need [SPECIFIC INFORMATION]. Find official documentation and production-quality examples for [Y] \u2014 specifically: API reference, configuration options, recommended patterns, and common pitfalls. Skip beginner tutorials. I'll use this to [DECISION THIS WILL INFORM].\", run_in_background=true)\ntask(subagent_type=\"oracle\", load_skills=[], prompt=\"I need architectural review of my approach to [TASK]. Here's my plan: [DESCRIBE PLAN WITH SPECIFIC FILES AND CHANGES]. My concerns are: [LIST SPECIFIC UNCERTAINTIES]. Please evaluate: correctness of approach, potential issues I'm missing, and whether a better alternative exists.\", 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\", load_skills=[], 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}\", load_skills=[], prompt=\"<your answer>\")` |\n| Need to refine the plan | `task(session_id=\"{returned_session_id}\", load_skills=[], prompt=\"Please adjust: <feedback>\")` |\n| Plan needs more detail | `task(session_id=\"{returned_session_id}\", load_skills=[], 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\", load_skills=[], prompt=\"Here's more info...\")\n\n// CORRECT: Resume preserves everything\ntask(session_id=\"ses_abc123\", load_skills=[], 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\", load_skills=[], run_in_background=true) | Parallel, context-efficient |\n| Documentation lookup | task(subagent_type=\"librarian\", load_skills=[], run_in_background=true) | Specialized knowledge |\n| Planning | task(subagent_type=\"plan\", load_skills=[]) | Parallel task graph + structured TODO list |\n| Hard problem (conventional) | task(subagent_type=\"oracle\", load_skills=[]) | 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. **Record them in your TODO/Task items.** Each task MUST include a \"QA: [how to verify]\" field. These criteria are your CONTRACT \u2014 work toward them, verify against them.\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<MANUAL_QA_MANDATE>\n### YOU MUST EXECUTE MANUAL QA YOURSELF. THIS IS NOT OPTIONAL.\n\n**YOUR FAILURE MODE**: You finish coding, run lsp_diagnostics, and declare \"done\" without actually TESTING the feature. lsp_diagnostics catches type errors, NOT functional bugs. Your work is NOT verified until you MANUALLY test it.\n\n**WHAT MANUAL QA MEANS \u2014 execute ALL that apply:**\n\n| If your change... | YOU MUST... |\n|---|---|\n| Adds/modifies a CLI command | Run the command with Bash. Show the output. |\n| Changes build output | Run the build. Verify the output files exist and are correct. |\n| Modifies API behavior | Call the endpoint. Show the response. |\n| Changes UI rendering | Describe what renders. Use a browser tool if available. |\n| Adds a new tool/hook/feature | Test it end-to-end in a real scenario. |\n| Modifies config handling | Load the config. Verify it parses correctly. |\n\n**UNACCEPTABLE QA CLAIMS:**\n- \"This should work\" \u2014 RUN IT.\n- \"The types check out\" \u2014 Types don't catch logic bugs. RUN IT.\n- \"lsp_diagnostics is clean\" \u2014 That's a TYPE check, not a FUNCTIONAL check. RUN IT.\n- \"Tests pass\" \u2014 Tests cover known cases. Does the ACTUAL FEATURE work as the user expects? RUN IT.\n\n**You have Bash, you have tools. There is ZERO excuse for not running manual QA.**\n**Manual QA is the FINAL gate before reporting completion. Skip it and your work is INCOMPLETE.**\n</MANUAL_QA_MANDATE>\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/gemini.d.ts

@@ -13,5 +13,5 @@
  * - GPT self-delegates appropriately; Gemini tries to do everything itself
  * - GPT respects MUST NOT; Gemini treats constraints as suggestions
  */
-export declare const ULTRAWORK_GEMINI_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<GEMINI_INTENT_GATE>\n## STEP 0: CLASSIFY INTENT \u2014 THIS IS NOT OPTIONAL\n\n**Before ANY tool call, exploration, or action, you MUST output:**\n\n```\nI detect [TYPE] intent \u2014 [REASON].\nMy approach: [ROUTING DECISION].\n```\n\nWhere TYPE is one of: research | implementation | investigation | evaluation | fix | open-ended\n\n**SELF-CHECK (answer each before proceeding):**\n\n1. Did the user EXPLICITLY ask me to build/create/implement something? \u2192 If NO, do NOT implement.\n2. Did the user say \"look into\", \"check\", \"investigate\", \"explain\"? \u2192 RESEARCH only. Do not code.\n3. Did the user ask \"what do you think?\" \u2192 EVALUATE and propose. Do NOT execute.\n4. Did the user report an error/bug? \u2192 MINIMAL FIX only. Do not refactor.\n\n**YOUR FAILURE MODE: You see a request and immediately start coding. STOP. Classify first.**\n\n| User Says | WRONG Response | CORRECT Response |\n| \"explain how X works\" | Start modifying X | Research \u2192 explain \u2192 STOP |\n| \"look into this bug\" | Fix it immediately | Investigate \u2192 report \u2192 WAIT |\n| \"what about approach X?\" | Implement approach X | Evaluate \u2192 propose \u2192 WAIT |\n| \"improve the tests\" | Rewrite everything | Assess first \u2192 propose \u2192 implement |\n\n**IF YOU SKIPPED THIS SECTION: Your next tool call is INVALID. Go back and classify.**\n</GEMINI_INTENT_GATE>\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=\"I'm implementing [TASK DESCRIPTION] and need to understand [SPECIFIC KNOWLEDGE GAP]. Find [X] patterns in the codebase \u2014 show file paths, implementation approach, and conventions used. I'll use this to [HOW RESULTS WILL BE USED]. Focus on src/ directories, skip test files unless test patterns are specifically needed. Return concrete file paths with brief descriptions of what each file does.\", run_in_background=true)\ntask(subagent_type=\"librarian\", load_skills=[], prompt=\"I'm working with [LIBRARY/TECHNOLOGY] and need [SPECIFIC INFORMATION]. Find official documentation and production-quality examples for [Y] \u2014 specifically: API reference, configuration options, recommended patterns, and common pitfalls. Skip beginner tutorials. I'll use this to [DECISION THIS WILL INFORM].\", run_in_background=true)\ntask(subagent_type=\"oracle\", load_skills=[], prompt=\"I need architectural review of my approach to [TASK]. Here's my plan: [DESCRIBE PLAN WITH SPECIFIC FILES AND CHANGES]. My concerns are: [LIST SPECIFIC UNCERTAINTIES]. Please evaluate: correctness of approach, potential issues I'm missing, and whether a better alternative exists.\", 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\n<TOOL_CALL_MANDATE>\n## YOU MUST USE TOOLS. THIS IS NOT OPTIONAL.\n\n**The user expects you to ACT using tools, not REASON internally.** Every response to a task MUST contain tool_use blocks. A response without tool calls is a FAILED response.\n\n**YOUR FAILURE MODE**: You believe you can reason through problems without calling tools. You CANNOT.\n\n**RULES (VIOLATION = BROKEN RESPONSE):**\n1. **NEVER answer about code without reading files first.** Read them AGAIN.\n2. **NEVER claim done without `lsp_diagnostics`.** Your confidence is wrong more often than right.\n3. **NEVER skip delegation.** Specialists produce better results. USE THEM.\n4. **NEVER reason about what a file \"probably contains.\"** READ IT.\n5. **NEVER produce ZERO tool calls when action was requested.** Thinking is not doing.\n</TOOL_CALL_MANDATE>\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\", load_skills=[], prompt=\"<gathered context + user request>\")\n```\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}\", load_skills=[], prompt=\"<your answer>\")` |\n| Need to refine the plan | `task(session_id=\"{returned_session_id}\", load_skills=[], prompt=\"Please adjust: <feedback>\")` |\n| Plan needs more detail | `task(session_id=\"{returned_session_id}\", load_skills=[], prompt=\"Add more detail to Task N\")` |\n\n**FAILURE TO CALL PLAN AGENT = INCOMPLETE WORK.**\n\n---\n\n## DELEGATION IS MANDATORY \u2014 YOU ARE NOT AN IMPLEMENTER\n\n**You have a strong tendency to do work yourself. RESIST THIS.**\n\n**DEFAULT BEHAVIOR: DELEGATE. DO NOT WORK YOURSELF.**\n\n| Task Type | Action | Why |\n|-----------|--------|-----|\n| Codebase exploration | task(subagent_type=\"explore\", load_skills=[], run_in_background=true) | Parallel, context-efficient |\n| Documentation lookup | task(subagent_type=\"librarian\", load_skills=[], run_in_background=true) | Specialized knowledge |\n| Planning | task(subagent_type=\"plan\", load_skills=[]) | Parallel task graph + structured TODO list |\n| Hard problem (conventional) | task(subagent_type=\"oracle\", load_skills=[]) | 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**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. **CLASSIFY INTENT** (MANDATORY \u2014 see GEMINI_INTENT_GATE above)\n2. Spawn exploration/librarian agents via task(run_in_background=true) in PARALLEL\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**YOUR SELF-ASSESSMENT IS UNRELIABLE.** What feels like 95% confidence = ~60% actual correctness.\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| **Lint** | Run lsp_diagnostics | Zero new errors on changed files |\n| **Manual Verify** | Test the actual feature | Describe what you observed |\n| **Regression** | Ensure nothing broke | Existing tests still pass |\n\n<ANTI_OPTIMISM_CHECKPOINT>\n## BEFORE YOU CLAIM DONE, ANSWER HONESTLY:\n\n1. Did I run `lsp_diagnostics` and see ZERO errors? (not \"I'm sure there are none\")\n2. Did I run the tests and see them PASS? (not \"they should pass\")\n3. Did I read the actual output of every command? (not skim)\n4. Is EVERY requirement from the request actually implemented? (re-read the request NOW)\n5. Did I classify intent at the start? (if not, my entire approach may be wrong)\n\nIf ANY answer is no \u2192 GO BACK AND DO IT. Do not claim completion.\n</ANTI_OPTIMISM_CHECKPOINT>\n\n**WITHOUT evidence = NOT verified = NOT done.**\n\n## ZERO TOLERANCE FAILURES\n- **NO Scope Reduction**: Never make \"demo\", \"skeleton\", \"simplified\", \"basic\" versions - deliver FULL implementation\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. CLASSIFY INTENT (MANDATORY)\n2. EXPLORES + LIBRARIANS\n3. GATHER -> PLAN AGENT SPAWN\n4. WORK BY DELEGATING TO ANOTHER AGENTS\n\nNOW.\n\n</ultrawork-mode>\n\n---\n\n";
+export declare const ULTRAWORK_GEMINI_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<GEMINI_INTENT_GATE>\n## STEP 0: CLASSIFY INTENT \u2014 THIS IS NOT OPTIONAL\n\n**Before ANY tool call, exploration, or action, you MUST output:**\n\n```\nI detect [TYPE] intent \u2014 [REASON].\nMy approach: [ROUTING DECISION].\n```\n\nWhere TYPE is one of: research | implementation | investigation | evaluation | fix | open-ended\n\n**SELF-CHECK (answer each before proceeding):**\n\n1. Did the user EXPLICITLY ask me to build/create/implement something? \u2192 If NO, do NOT implement.\n2. Did the user say \"look into\", \"check\", \"investigate\", \"explain\"? \u2192 RESEARCH only. Do not code.\n3. Did the user ask \"what do you think?\" \u2192 EVALUATE and propose. Do NOT execute.\n4. Did the user report an error/bug? \u2192 MINIMAL FIX only. Do not refactor.\n\n**YOUR FAILURE MODE: You see a request and immediately start coding. STOP. Classify first.**\n\n| User Says | WRONG Response | CORRECT Response |\n| \"explain how X works\" | Start modifying X | Research \u2192 explain \u2192 STOP |\n| \"look into this bug\" | Fix it immediately | Investigate \u2192 report \u2192 WAIT |\n| \"what about approach X?\" | Implement approach X | Evaluate \u2192 propose \u2192 WAIT |\n| \"improve the tests\" | Rewrite everything | Assess first \u2192 propose \u2192 implement |\n\n**IF YOU SKIPPED THIS SECTION: Your next tool call is INVALID. Go back and classify.**\n</GEMINI_INTENT_GATE>\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=\"I'm implementing [TASK DESCRIPTION] and need to understand [SPECIFIC KNOWLEDGE GAP]. Find [X] patterns in the codebase \u2014 show file paths, implementation approach, and conventions used. I'll use this to [HOW RESULTS WILL BE USED]. Focus on src/ directories, skip test files unless test patterns are specifically needed. Return concrete file paths with brief descriptions of what each file does.\", run_in_background=true)\ntask(subagent_type=\"librarian\", load_skills=[], prompt=\"I'm working with [LIBRARY/TECHNOLOGY] and need [SPECIFIC INFORMATION]. Find official documentation and production-quality examples for [Y] \u2014 specifically: API reference, configuration options, recommended patterns, and common pitfalls. Skip beginner tutorials. I'll use this to [DECISION THIS WILL INFORM].\", run_in_background=true)\ntask(subagent_type=\"oracle\", load_skills=[], prompt=\"I need architectural review of my approach to [TASK]. Here's my plan: [DESCRIBE PLAN WITH SPECIFIC FILES AND CHANGES]. My concerns are: [LIST SPECIFIC UNCERTAINTIES]. Please evaluate: correctness of approach, potential issues I'm missing, and whether a better alternative exists.\", 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\n<TOOL_CALL_MANDATE>\n## YOU MUST USE TOOLS. THIS IS NOT OPTIONAL.\n\n**The user expects you to ACT using tools, not REASON internally.** Every response to a task MUST contain tool_use blocks. A response without tool calls is a FAILED response.\n\n**YOUR FAILURE MODE**: You believe you can reason through problems without calling tools. You CANNOT.\n\n**RULES (VIOLATION = BROKEN RESPONSE):**\n1. **NEVER answer about code without reading files first.** Read them AGAIN.\n2. **NEVER claim done without `lsp_diagnostics`.** Your confidence is wrong more often than right.\n3. **NEVER skip delegation.** Specialists produce better results. USE THEM.\n4. **NEVER reason about what a file \"probably contains.\"** READ IT.\n5. **NEVER produce ZERO tool calls when action was requested.** Thinking is not doing.\n</TOOL_CALL_MANDATE>\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\", load_skills=[], prompt=\"<gathered context + user request>\")\n```\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}\", load_skills=[], prompt=\"<your answer>\")` |\n| Need to refine the plan | `task(session_id=\"{returned_session_id}\", load_skills=[], prompt=\"Please adjust: <feedback>\")` |\n| Plan needs more detail | `task(session_id=\"{returned_session_id}\", load_skills=[], prompt=\"Add more detail to Task N\")` |\n\n**FAILURE TO CALL PLAN AGENT = INCOMPLETE WORK.**\n\n---\n\n## DELEGATION IS MANDATORY \u2014 YOU ARE NOT AN IMPLEMENTER\n\n**You have a strong tendency to do work yourself. RESIST THIS.**\n\n**DEFAULT BEHAVIOR: DELEGATE. DO NOT WORK YOURSELF.**\n\n| Task Type | Action | Why |\n|-----------|--------|-----|\n| Codebase exploration | task(subagent_type=\"explore\", load_skills=[], run_in_background=true) | Parallel, context-efficient |\n| Documentation lookup | task(subagent_type=\"librarian\", load_skills=[], run_in_background=true) | Specialized knowledge |\n| Planning | task(subagent_type=\"plan\", load_skills=[]) | Parallel task graph + structured TODO list |\n| Hard problem (conventional) | task(subagent_type=\"oracle\", load_skills=[]) | 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**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. **CLASSIFY INTENT** (MANDATORY \u2014 see GEMINI_INTENT_GATE above)\n2. Spawn exploration/librarian agents via task(run_in_background=true) in PARALLEL\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**YOUR SELF-ASSESSMENT IS UNRELIABLE.** What feels like 95% confidence = ~60% actual correctness.\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| **Lint** | Run lsp_diagnostics | Zero new errors on changed files |\n| **Manual Verify** | Test the actual feature | Describe what you observed |\n| **Regression** | Ensure nothing broke | Existing tests still pass |\n\n<ANTI_OPTIMISM_CHECKPOINT>\n## BEFORE YOU CLAIM DONE, ANSWER HONESTLY:\n\n1. Did I run `lsp_diagnostics` and see ZERO errors? (not \"I'm sure there are none\")\n2. Did I run the tests and see them PASS? (not \"they should pass\")\n3. Did I read the actual output of every command? (not skim)\n4. Is EVERY requirement from the request actually implemented? (re-read the request NOW)\n5. Did I classify intent at the start? (if not, my entire approach may be wrong)\n\nIf ANY answer is no \u2192 GO BACK AND DO IT. Do not claim completion.\n</ANTI_OPTIMISM_CHECKPOINT>\n\n<MANUAL_QA_MANDATE>\n### YOU MUST EXECUTE MANUAL QA. THIS IS NOT OPTIONAL. DO NOT SKIP THIS.\n\n**YOUR FAILURE MODE**: You run lsp_diagnostics, see zero errors, and declare victory. lsp_diagnostics catches TYPE errors. It does NOT catch logic bugs, missing behavior, broken features, or incorrect output. Your work is NOT verified until you MANUALLY TEST the actual feature.\n\n**AFTER every implementation, you MUST:**\n\n1. **Define acceptance criteria BEFORE coding** \u2014 write them in your TODO/Task items with \"QA: [how to verify]\"\n2. **Execute manual QA YOURSELF** \u2014 actually RUN the feature, CLI command, build, or whatever you changed\n3. **Report what you observed** \u2014 show actual output, not claims\n\n| If your change... | YOU MUST... |\n|---|---|\n| Adds/modifies a CLI command | Run the command with Bash. Show the output. |\n| Changes build output | Run the build. Verify output files exist and are correct. |\n| Modifies API behavior | Call the endpoint. Show the response. |\n| Adds a new tool/hook/feature | Test it end-to-end in a real scenario. |\n| Modifies config handling | Load the config. Verify it parses correctly. |\n\n**UNACCEPTABLE (WILL BE REJECTED):**\n- \"This should work\" \u2014 DID YOU RUN IT? NO? THEN RUN IT.\n- \"lsp_diagnostics is clean\" \u2014 That is a TYPE check, not a FUNCTIONAL check. RUN THE FEATURE.\n- \"Tests pass\" \u2014 Tests cover known cases. Does the ACTUAL feature work? VERIFY IT MANUALLY.\n\n**You have Bash, you have tools. There is ZERO excuse for skipping manual QA.**\n</MANUAL_QA_MANDATE>\n\n**WITHOUT evidence = NOT verified = NOT done.**\n\n## ZERO TOLERANCE FAILURES\n- **NO Scope Reduction**: Never make \"demo\", \"skeleton\", \"simplified\", \"basic\" versions - deliver FULL implementation\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. CLASSIFY INTENT (MANDATORY)\n2. EXPLORES + LIBRARIANS\n3. GATHER -> PLAN AGENT SPAWN\n4. WORK BY DELEGATING TO ANOTHER AGENTS\n\nNOW.\n\n</ultrawork-mode>\n\n---\n\n";
 export declare function getGeminiUltraworkMessage(): string;

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

@@ -0,0 +1,11 @@
+/**
+ * Ultrawork message optimized for GPT 5.4 series models.
+ *
+ * Design principles:
+ * - Expert coding agent framing with approach-first mentality
+ * - Prose-first output (do not default to bullets)
+ * - Two-track parallel context gathering (Direct tools + Background agents)
+ * - Deterministic tool usage and explicit 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: 1-2 short paragraphs. Do not default to bullets.\n- Simple yes/no questions: \u22642 sentences.\n- Complex multi-file tasks: 1 overview paragraph + up to 4 high-level sections grouped by outcome, not by file.\n- Use lists only when content is inherently list-shaped (distinct items, steps, options).\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\", load_skills=[], run_in_background=true, ...)` |\n| librarian agent | External library docs, OSS examples | `task(subagent_type=\"librarian\", load_skills=[], run_in_background=true, ...)` |\n| oracle agent | Stuck on architecture/debugging after 2+ attempts | `task(subagent_type=\"oracle\", load_skills=[], ...)` |\n| plan agent | Complex multi-step with dependencies (5+ steps) | `task(subagent_type=\"plan\", load_skills=[], ...)` |\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=\"I'm implementing [TASK] and need to understand [KNOWLEDGE GAP]. Find [X] patterns in the codebase \u2014 file paths, implementation approach, conventions used, and how modules connect. I'll use this to [DOWNSTREAM DECISION]. Focus on production code in src/. Return file paths with brief descriptions.\", run_in_background=true)\ntask(subagent_type=\"librarian\", load_skills=[], prompt=\"I'm working with [TECHNOLOGY] and need [SPECIFIC INFO]. Find official docs and production examples for [Y] \u2014 API reference, configuration, recommended patterns, and pitfalls. Skip tutorials. I'll use this to [DECISION THIS INFORMS].\", 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## ACCEPTANCE CRITERIA WORKFLOW\n\n**BEFORE implementation**, define what \"done\" means in concrete, binary terms:\n\n1. Write acceptance criteria as pass/fail conditions (not \"should work\" \u2014 specific observable outcomes)\n2. Record them in your TODO/Task items with a \"QA: [how to verify]\" field\n3. Work toward those criteria, not just \"finishing code\"\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| **Manual QA** | **Execute the feature yourself** | **Actual output shown** |\n\n<MANUAL_QA_MANDATE>\n### MANUAL QA IS MANDATORY. lsp_diagnostics IS NOT ENOUGH.\n\nlsp_diagnostics catches type errors. It does NOT catch logic bugs, missing behavior, or broken features. After EVERY implementation, you MUST manually test the actual feature.\n\n**Execute ALL that apply:**\n\n| If your change... | YOU MUST... |\n|---|---|\n| Adds/modifies a CLI command | Run the command with Bash. Show the output. |\n| Changes build output | Run the build. Verify output files. |\n| Modifies API behavior | Call the endpoint. Show the response. |\n| Adds a new tool/hook/feature | Test it end-to-end in a real scenario. |\n| Modifies config handling | Load the config. Verify it parses correctly. |\n\n**\"This should work\" is NOT evidence. RUN IT. Show what happened. That is evidence.**\n</MANUAL_QA_MANDATE>\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\n5. **Manual QA executed \u2014 actual feature tested, output observed and reported**\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/index.d.ts

@@ -3,16 +3,16 @@
  *
  * Routing:
  * 1. Planner agents (prometheus, plan) → planner.ts
- * 2. GPT 5.2 models → gpt5.2.ts
+ * 2. GPT models → gpt.ts
  * 3. Gemini models → gemini.ts
  * 4. Default (Claude, etc.) → default.ts (optimized for Claude series)
  */
-export { isPlannerAgent, isGptModel, isGeminiModel, getUltraworkSource } from "./source-detector";
+export { isPlannerAgent, isGptModel, isGeminiModel, getUltraworkSource, } from "./source-detector";
 export type { UltraworkSource } from "./source-detector";
-export { ULTRAWORK_PLANNER_SECTION, getPlannerUltraworkMessage } from "./planner";
-export { ULTRAWORK_GPT_MESSAGE, getGptUltraworkMessage } from "./gpt5.2";
+export { ULTRAWORK_PLANNER_SECTION, getPlannerUltraworkMessage, } from "./planner";
+export { ULTRAWORK_GPT_MESSAGE, getGptUltraworkMessage } from "./gpt";
 export { ULTRAWORK_GEMINI_MESSAGE, getGeminiUltraworkMessage } from "./gemini";
-export { ULTRAWORK_DEFAULT_MESSAGE, getDefaultUltraworkMessage } from "./default";
+export { ULTRAWORK_DEFAULT_MESSAGE, getDefaultUltraworkMessage, } from "./default";
 /**
  * Gets the appropriate ultrawork message based on agent and model context.
  */

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

@@ -3,7 +3,7 @@
  *
  * Routing logic:
  * 1. Planner agents (prometheus, plan) → planner.ts
- * 2. GPT 5.2 models → gpt5.2.ts
+ * 2. GPT 5.4 models → gpt5.4.ts
  * 3. Gemini models → gemini.ts
  * 4. Everything else (Claude, etc.) → default.ts
  */

package/dist/hooks/preemptive-compaction.d.ts

@@ -1,6 +1,7 @@
 import type { OhMyOpenCodeConfig } from "../config";
 type ModelCacheStateLike = {
     anthropicContext1MEnabled: boolean;
+    modelContextLimitsCache?: Map<string, number>;
 };
 type PluginInput = {
     client: {

package/dist/hooks/ralph-loop/completion-handler.d.ts

@@ -0,0 +1,14 @@
+import type { PluginInput } from "@opencode-ai/plugin";
+import type { RalphLoopState } from "./types";
+type LoopStateController = {
+    clear: () => boolean;
+    markVerificationPending: (sessionID: string) => RalphLoopState | null;
+};
+export declare function handleDetectedCompletion(ctx: PluginInput, input: {
+    sessionID: string;
+    state: RalphLoopState;
+    loopState: LoopStateController;
+    directory: string;
+    apiTimeoutMs: number;
+}): Promise<void>;
+export {};

package/dist/hooks/ralph-loop/completion-promise-detector.d.ts

@@ -1,5 +1,5 @@
 import type { PluginInput } from "@opencode-ai/plugin";
-export declare function detectCompletionInTranscript(transcriptPath: string | undefined, promise: string): boolean;
+export declare function detectCompletionInTranscript(transcriptPath: string | undefined, promise: string, startedAt?: string): boolean;
 export declare function detectCompletionInSessionMessages(ctx: PluginInput, options: {
     sessionID: string;
     promise: string;

package/dist/hooks/ralph-loop/constants.d.ts

@@ -3,3 +3,4 @@ export declare const DEFAULT_STATE_FILE = ".sisyphus/ralph-loop.local.md";
 export declare const COMPLETION_TAG_PATTERN: RegExp;
 export declare const DEFAULT_MAX_ITERATIONS = 100;
 export declare const DEFAULT_COMPLETION_PROMISE = "DONE";
+export declare const ULTRAWORK_VERIFICATION_PROMISE = "VERIFIED";

package/dist/hooks/ralph-loop/continuation-prompt-builder.d.ts

@@ -1,2 +1,3 @@
 import type { RalphLoopState } from "./types";
 export declare function buildContinuationPrompt(state: RalphLoopState): string;
+export declare function buildVerificationFailurePrompt(state: RalphLoopState): string;

package/dist/hooks/ralph-loop/loop-state-controller.d.ts

@@ -17,4 +17,7 @@ export declare function createLoopStateController(options: {
     incrementIteration(): RalphLoopState | null;
     setSessionID(sessionID: string): RalphLoopState | null;
     setMessageCountAtStart(sessionID: string, messageCountAtStart: number): RalphLoopState | null;
+    markVerificationPending(sessionID: string): RalphLoopState | null;
+    setVerificationSessionID(sessionID: string, verificationSessionID: string): RalphLoopState | null;
+    restartAfterFailedVerification(sessionID: string, messageCountAtStart?: number): RalphLoopState | null;
 };

package/dist/hooks/ralph-loop/ralph-loop-event-handler.d.ts

@@ -10,6 +10,9 @@ type LoopStateController = {
     clear: () => boolean;
     incrementIteration: () => RalphLoopState | null;
     setSessionID: (sessionID: string) => RalphLoopState | null;
+    markVerificationPending: (sessionID: string) => RalphLoopState | null;
+    setVerificationSessionID: (sessionID: string, verificationSessionID: string) => RalphLoopState | null;
+    restartAfterFailedVerification: (sessionID: string, messageCountAtStart?: number) => RalphLoopState | null;
 };
 type RalphLoopEventHandlerOptions = {
     directory: string;

package/dist/hooks/ralph-loop/session-event-handler.d.ts

@@ -0,0 +1,12 @@
+import type { RalphLoopState } from "./types";
+type LoopStateController = {
+    getState: () => RalphLoopState | null;
+    clear: () => boolean;
+};
+type SessionRecovery = {
+    clear: (sessionID: string) => void;
+    markRecovering: (sessionID: string) => void;
+};
+export declare function handleDeletedLoopSession(props: Record<string, unknown> | undefined, loopState: LoopStateController, sessionRecovery: SessionRecovery): boolean;
+export declare function handleErroredLoopSession(props: Record<string, unknown> | undefined, loopState: LoopStateController, sessionRecovery: SessionRecovery): boolean;
+export {};

package/dist/hooks/ralph-loop/types.d.ts

@@ -2,13 +2,17 @@ import type { RalphLoopConfig } from "../../config";
 export interface RalphLoopState {
     active: boolean;
     iteration: number;
-    max_iterations: number;
+    max_iterations?: number;
     message_count_at_start?: number;
     completion_promise: string;
+    initial_completion_promise?: string;
+    verification_attempt_id?: string;
+    verification_session_id?: string;
     started_at: string;
     prompt: string;
     session_id?: string;
     ultrawork?: boolean;
+    verification_pending?: boolean;
     strategy?: "reset" | "continue";
 }
 export interface RalphLoopOptions {

package/dist/hooks/ralph-loop/verification-failure-handler.d.ts

@@ -0,0 +1,12 @@
+import type { PluginInput } from "@opencode-ai/plugin";
+import type { RalphLoopState } from "./types";
+type LoopStateController = {
+    restartAfterFailedVerification: (sessionID: string, messageCountAtStart?: number) => RalphLoopState | null;
+};
+export declare function handleFailedVerification(ctx: PluginInput, input: {
+    state: RalphLoopState;
+    directory: string;
+    apiTimeoutMs: number;
+    loopState: LoopStateController;
+}): Promise<boolean>;
+export {};

package/dist/hooks/read-image-resizer/hook.d.ts

@@ -0,0 +1,12 @@
+import type { PluginInput } from "@opencode-ai/plugin";
+export declare function createReadImageResizerHook(_ctx: PluginInput): {
+    "tool.execute.after": (input: {
+        tool: string;
+        sessionID: string;
+        callID: string;
+    }, output: {
+        title: string;
+        output: string;
+        metadata: unknown;
+    }) => Promise<void>;
+};

package/dist/hooks/read-image-resizer/image-dimensions.d.ts

@@ -0,0 +1,2 @@
+import type { ImageDimensions } from "./types";
+export declare function parseImageDimensions(base64DataUrl: string, mimeType: string): ImageDimensions | null;

package/dist/hooks/read-image-resizer/image-resizer.d.ts

@@ -0,0 +1,3 @@
+import type { ImageDimensions, ResizeResult } from "./types";
+export declare function calculateTargetDimensions(width: number, height: number, maxLongEdge?: number): ImageDimensions | null;
+export declare function resizeImage(base64DataUrl: string, mimeType: string, target: ImageDimensions): Promise<ResizeResult | null>;

package/dist/hooks/read-image-resizer/index.d.ts

@@ -0,0 +1 @@
+export { createReadImageResizerHook } from "./hook";

package/dist/hooks/read-image-resizer/types.d.ts

@@ -0,0 +1,14 @@
+export interface ImageDimensions {
+    width: number;
+    height: number;
+}
+export interface ImageAttachment {
+    mime: string;
+    url: string;
+    filename?: string;
+}
+export interface ResizeResult {
+    resizedDataUrl: string;
+    original: ImageDimensions;
+    resized: ImageDimensions;
+}

package/dist/hooks/session-notification-utils.d.ts

@@ -5,5 +5,6 @@ export declare const getPowershellPath: () => Promise<string | null>;
 export declare const getAfplayPath: () => Promise<string | null>;
 export declare const getPaplayPath: () => Promise<string | null>;
 export declare const getAplayPath: () => Promise<string | null>;
+export declare const getTerminalNotifierPath: () => Promise<string | null>;
 export declare function startBackgroundCheck(platform: Platform): void;
 export {};