oh-my-opencode 3.14.0 → 3.15.1

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

@@ -0,0 +1,29 @@
+import type { PluginInput } from "@opencode-ai/plugin";
+export type MockLastAssistant = {
+    info: {
+        summary?: boolean;
+        providerID: string;
+        modelID: string;
+    };
+    hasContent: boolean;
+};
+export declare const executeCompactMock: import("bun:test").Mock<typeof import("./executor").executeCompact>;
+export declare const getLastAssistantMock: import("bun:test").Mock<typeof import("./message-builder").getLastAssistant>;
+export declare const parseAnthropicTokenLimitErrorMock: import("bun:test").Mock<typeof import("./parser").parseAnthropicTokenLimitError>;
+export declare function createRecoveryHook(): {
+    event: ({ event }: {
+        event: {
+            type: string;
+            properties?: unknown;
+        };
+    }) => Promise<void>;
+    dispose: () => void;
+};
+export declare function createMockContext(): PluginInput;
+export declare function setupDelayedTimeoutMocks(): {
+    createUntrackedTimeout: () => ReturnType<typeof setTimeout>;
+    runScheduledTimeout: (index: number) => void;
+    restore: () => void;
+    getClearTimeoutCalls: () => Array<ReturnType<typeof setTimeout>>;
+    getScheduledTimeouts: () => Array<ReturnType<typeof setTimeout>>;
+};

package/dist/hooks/anthropic-context-window-limit-recovery/session-timeout-map.d.ts

@@ -0,0 +1,2 @@
+export declare function clearSessionTimeout(timeoutBySession: Map<string, ReturnType<typeof setTimeout>>, sessionID: string): void;
+export declare function clearAllSessionTimeouts(timeoutBySession: Map<string, ReturnType<typeof setTimeout>>): void;

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

@@ -2,5 +2,7 @@ import type { AutoCompactState, RetryState, TruncateState } from "./types";
 export declare function getOrCreateRetryState(autoCompactState: AutoCompactState, sessionID: string): RetryState;
 export declare function getOrCreateTruncateState(autoCompactState: AutoCompactState, sessionID: string): TruncateState;
 export declare function clearSessionState(autoCompactState: AutoCompactState, sessionID: string): void;
+export declare function setRetryTimer(autoCompactState: AutoCompactState, sessionID: string, timeout: ReturnType<typeof setTimeout>): void;
+export declare function clearRetryTimer(autoCompactState: AutoCompactState, sessionID: string): void;
 export declare function getEmptyContentAttempt(autoCompactState: AutoCompactState, sessionID: string): number;
 export declare function incrementEmptyContentAttempt(autoCompactState: AutoCompactState, sessionID: string): number;

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

@@ -20,6 +20,7 @@ export interface AutoCompactState {
     pendingCompact: Set<string>;
     errorDataBySession: Map<string, ParsedTokenLimitError>;
     retryStateBySession: Map<string, RetryState>;
+    retryTimerBySession: Map<string, ReturnType<typeof setTimeout>>;
     truncateStateBySession: Map<string, TruncateState>;
     emptyContentAttemptBySession: Map<string, number>;
     compactionInProgress: Set<string>;

package/dist/hooks/atlas/subagent-session-id.d.ts

@@ -1,4 +1,5 @@
 import type { PluginInput } from "@opencode-ai/plugin";
+export declare function extractSessionIdFromMetadata(metadata: unknown): string | undefined;
 export declare function extractSessionIdFromOutput(output: string): string | undefined;
 export declare function validateSubagentSessionId(input: {
     client: PluginInput["client"];

package/dist/hooks/atlas/system-reminder-templates.d.ts

@@ -1,6 +1,6 @@
 export declare const DIRECT_WORK_REMINDER: string;
 export declare const BOULDER_CONTINUATION_PROMPT: string;
-export declare const VERIFICATION_REMINDER = "**THE SUBAGENT JUST CLAIMED THIS TASK IS DONE. THEY ARE PROBABLY LYING.**\n\nSubagents say \"done\" when code has errors, tests pass trivially, logic is wrong,\nor they quietly added features nobody asked for. This happens EVERY TIME.\nAssume the work is broken until YOU prove otherwise.\n\n---\n\n**PHASE 1: READ THE CODE FIRST (before running anything)**\n\nDo NOT run tests yet. Read the code FIRST so you know what you're testing.\n\n1. `Bash(\"git diff --stat\")` \u2014 see exactly which files changed. Any file outside expected scope = scope creep.\n2. `Read` EVERY changed file \u2014 no exceptions, no skimming.\n3. For EACH file, critically ask:\n   - Does this code ACTUALLY do what the task required? (Re-read the task, compare line by line)\n   - Any stubs, TODOs, placeholders, hardcoded values? (`Grep` for TODO, FIXME, HACK, xxx)\n   - Logic errors? Trace the happy path AND the error path in your head.\n   - Anti-patterns? (`Grep` for `as any`, `@ts-ignore`, empty catch, console.log in changed files)\n   - Scope creep? Did the subagent touch things or add features NOT in the task spec?\n4. Cross-check every claim:\n   - Said \"Updated X\" \u2014 READ X. Actually updated, or just superficially touched?\n   - Said \"Added tests\" \u2014 READ the tests. Do they test REAL behavior or just `expect(true).toBe(true)`?\n   - Said \"Follows patterns\" \u2014 OPEN a reference file. Does it ACTUALLY match?\n\n**If you cannot explain what every changed line does, you have NOT reviewed it.**\n\n**PHASE 2: RUN AUTOMATED CHECKS (targeted, then broad)**\n\nNow that you understand the code, verify mechanically:\n1. `lsp_diagnostics` on EACH changed file \u2014 ZERO new errors\n2. Run tests for changed modules FIRST, then full suite\n3. Build/typecheck \u2014 exit 0\n\nIf Phase 1 found issues but Phase 2 passes: Phase 2 is WRONG. The code has bugs that tests don't cover. Fix the code.\n\n**PHASE 3: HANDS-ON QA \u2014 ACTUALLY RUN IT (MANDATORY for user-facing changes)**\n\nTests and linters CANNOT catch: visual bugs, wrong CLI output, broken user flows, API response shape issues.\n\n**If this task produced anything a user would SEE or INTERACT with, you MUST launch it and verify yourself.**\n\n- **Frontend/UI**: `/playwright` skill \u2014 load the page, click through the flow, check console. Verify: page loads, interactions work, console clean, responsive.\n- **TUI/CLI**: `interactive_bash` \u2014 run the command, try good input, try bad input, try --help. Verify: command runs, output correct, error messages helpful, edge inputs handled.\n- **API/Backend**: `Bash` with curl \u2014 hit the endpoint, check response body, send malformed input. Verify: returns 200, body correct, error cases return proper errors.\n- **Config/Build**: Actually start the service or import the config. Verify: loads without error, backward compatible.\n\nThis is NOT optional \"if applicable\". If the deliverable is user-facing and you did not run it, you are shipping untested work.\n\n**PHASE 4: GATE DECISION \u2014 Should you proceed to the next task?**\n\nAnswer honestly:\n1. Can I explain what EVERY changed line does? (If no \u2014 back to Phase 1)\n2. Did I SEE it work with my own eyes? (If user-facing and no \u2014 back to Phase 3)\n3. Am I confident nothing existing is broken? (If no \u2014 run broader tests)\n\nALL three must be YES. \"Probably\" = NO. \"I think so\" = NO. Investigate until CERTAIN.\n\n- **All 3 YES** \u2014 Proceed: mark task complete, move to next.\n- **Any NO** \u2014 Reject: resume session with `session_id`, fix the specific issue.\n- **Unsure** \u2014 Reject: \"unsure\" = \"no\". Investigate until you have a definitive answer.\n\n**DO NOT proceed to the next task until all 4 phases are complete and the gate passes.**";
-export declare const VERIFICATION_REMINDER_GEMINI = "**THE SUBAGENT HAS FINISHED. THEIR WORK IS EXTREMELY SUSPICIOUS.**\n\nThe subagent CLAIMS this task is done. Based on thousands of executions, subagent claims are FALSE more often than true.\nThey ROUTINELY:\n- Ship code with syntax errors they didn't bother to check\n- Create stub implementations with TODOs and call it \"done\"\n- Write tests that pass trivially (testing nothing meaningful)\n- Implement logic that does NOT match what was requested\n- Add features nobody asked for and call it \"improvement\"\n- Report \"all tests pass\" when they didn't run any tests\n\n**This is NOT a theoretical warning. This WILL happen on this task. Assume the work is BROKEN.**\n\n**YOU MUST VERIFY WITH ACTUAL TOOL CALLS. NOT REASONING. TOOL CALLS.**\nThinking \"it looks correct\" is NOT verification. Running `lsp_diagnostics` IS.\n\n---\n\n**PHASE 1: READ THE CODE FIRST (DO NOT SKIP \u2014 DO NOT RUN TESTS YET)**\n\nRead the code FIRST so you know what you're testing.\n\n1. `Bash(\"git diff --stat\")` \u2014 see exactly which files changed.\n2. `Read` EVERY changed file \u2014 no exceptions, no skimming.\n3. For EACH file:\n   - Does this code ACTUALLY do what the task required? RE-READ the task spec.\n   - Any stubs, TODOs, placeholders? `Grep` for TODO, FIXME, HACK, xxx\n   - Anti-patterns? `Grep` for `as any`, `@ts-ignore`, empty catch\n   - Scope creep? Did the subagent add things NOT in the task spec?\n4. Cross-check EVERY claim against actual code.\n\n**If you cannot explain what every changed line does, GO BACK AND READ AGAIN.**\n\n**PHASE 2: RUN AUTOMATED CHECKS**\n\n1. `lsp_diagnostics` on EACH changed file \u2014 ZERO new errors. ACTUALLY RUN THIS.\n2. Run tests for changed modules, then full suite. ACTUALLY RUN THESE.\n3. Build/typecheck \u2014 exit 0.\n\nIf Phase 1 found issues but Phase 2 passes: Phase 2 is WRONG. Fix the code.\n\n**PHASE 3: HANDS-ON QA (MANDATORY for user-facing changes)**\n\n- **Frontend/UI**: `/playwright`\n- **TUI/CLI**: `interactive_bash`\n- **API/Backend**: `Bash` with curl\n\n**If user-facing and you did not run it, you are shipping UNTESTED BROKEN work.**\n\n**PHASE 4: GATE DECISION**\n\n1. Can I explain what EVERY changed line does? (If no \u2192 Phase 1)\n2. Did I SEE it work via tool calls? (If user-facing and no \u2192 Phase 3)\n3. Am I confident nothing is broken? (If no \u2192 broader tests)\n\nALL three must be YES. \"Probably\" = NO. \"I think so\" = NO.\n\n**DO NOT proceed to the next task until all 4 phases are complete.**";
+export declare const VERIFICATION_REMINDER = "**THE SUBAGENT JUST CLAIMED THIS TASK IS DONE. THEY ARE PROBABLY LYING.**\n\nSubagents say \"done\" when code has errors, tests pass trivially, logic is wrong,\nor they quietly added features nobody asked for. This happens EVERY TIME.\nAssume the work is broken until YOU prove otherwise.\n\n---\n\n**PHASE 1: READ THE CODE FIRST (before running anything)**\n\nDo NOT run tests yet. Read the code FIRST so you know what you're testing.\n\n1. `Bash(\"git diff --stat\")` - see exactly which files changed. Any file outside expected scope = scope creep.\n2. `Read` EVERY changed file - no exceptions, no skimming.\n3. For EACH file, critically ask:\n   - Does this code ACTUALLY do what the task required? (Re-read the task, compare line by line)\n   - Any stubs, TODOs, placeholders, hardcoded values? (`Grep` for TODO, FIXME, HACK, xxx)\n   - Logic errors? Trace the happy path AND the error path in your head.\n   - Anti-patterns? (`Grep` for `as any`, `@ts-ignore`, empty catch, console.log in changed files)\n   - Scope creep? Did the subagent touch things or add features NOT in the task spec?\n4. Cross-check every claim:\n   - Said \"Updated X\" - READ X. Actually updated, or just superficially touched?\n   - Said \"Added tests\" - READ the tests. Do they test REAL behavior or just `expect(true).toBe(true)`?\n   - Said \"Follows patterns\" - OPEN a reference file. Does it ACTUALLY match?\n\n**If you cannot explain what every changed line does, you have NOT reviewed it.**\n\n**PHASE 2: RUN AUTOMATED CHECKS (targeted, then broad)**\n\nNow that you understand the code, verify mechanically:\n1. `lsp_diagnostics` on EACH changed file - ZERO new errors\n2. Run tests for changed modules FIRST, then full suite\n3. Build/typecheck - exit 0\n\nIf Phase 1 found issues but Phase 2 passes: Phase 2 is WRONG. The code has bugs that tests don't cover. Fix the code.\n\n**PHASE 3: HANDS-ON QA - ACTUALLY RUN IT (MANDATORY for user-facing changes)**\n\nTests and linters CANNOT catch: visual bugs, wrong CLI output, broken user flows, API response shape issues.\n\n**If this task produced anything a user would SEE or INTERACT with, you MUST launch it and verify yourself.**\n\n- **Frontend/UI**: `/playwright` skill - load the page, click through the flow, check console. Verify: page loads, interactions work, console clean, responsive.\n- **TUI/CLI**: `interactive_bash` - run the command, try good input, try bad input, try --help. Verify: command runs, output correct, error messages helpful, edge inputs handled.\n- **API/Backend**: `Bash` with curl - hit the endpoint, check response body, send malformed input. Verify: returns 200, body correct, error cases return proper errors.\n- **Config/Build**: Actually start the service or import the config. Verify: loads without error, backward compatible.\n\nThis is NOT optional \"if applicable\". If the deliverable is user-facing and you did not run it, you are shipping untested work.\n\n**PHASE 4: GATE DECISION - Should you proceed to the next task?**\n\nAnswer honestly:\n1. Can I explain what EVERY changed line does? (If no - back to Phase 1)\n2. Did I SEE it work with my own eyes? (If user-facing and no - back to Phase 3)\n3. Am I confident nothing existing is broken? (If no - run broader tests)\n\nALL three must be YES. \"Probably\" = NO. \"I think so\" = NO. Investigate until CERTAIN.\n\n- **All 3 YES** - Proceed: mark task complete, move to next.\n- **Any NO** - Reject: resume session with `session_id`, fix the specific issue.\n- **Unsure** - Reject: \"unsure\" = \"no\". Investigate until you have a definitive answer.\n\n**DO NOT proceed to the next task until all 4 phases are complete and the gate passes.**";
+export declare const VERIFICATION_REMINDER_GEMINI = "**THE SUBAGENT HAS FINISHED. THEIR WORK IS EXTREMELY SUSPICIOUS.**\n\nThe subagent CLAIMS this task is done. Based on thousands of executions, subagent claims are FALSE more often than true.\nThey ROUTINELY:\n- Ship code with syntax errors they didn't bother to check\n- Create stub implementations with TODOs and call it \"done\"\n- Write tests that pass trivially (testing nothing meaningful)\n- Implement logic that does NOT match what was requested\n- Add features nobody asked for and call it \"improvement\"\n- Report \"all tests pass\" when they didn't run any tests\n\n**This is NOT a theoretical warning. This WILL happen on this task. Assume the work is BROKEN.**\n\n**YOU MUST VERIFY WITH ACTUAL TOOL CALLS. NOT REASONING. TOOL CALLS.**\nThinking \"it looks correct\" is NOT verification. Running `lsp_diagnostics` IS.\n\n---\n\n**PHASE 1: READ THE CODE FIRST (DO NOT SKIP - DO NOT RUN TESTS YET)**\n\nRead the code FIRST so you know what you're testing.\n\n1. `Bash(\"git diff --stat\")` - see exactly which files changed.\n2. `Read` EVERY changed file - no exceptions, no skimming.\n3. For EACH file:\n   - Does this code ACTUALLY do what the task required? RE-READ the task spec.\n   - Any stubs, TODOs, placeholders? `Grep` for TODO, FIXME, HACK, xxx\n   - Anti-patterns? `Grep` for `as any`, `@ts-ignore`, empty catch\n   - Scope creep? Did the subagent add things NOT in the task spec?\n4. Cross-check EVERY claim against actual code.\n\n**If you cannot explain what every changed line does, GO BACK AND READ AGAIN.**\n\n**PHASE 2: RUN AUTOMATED CHECKS**\n\n1. `lsp_diagnostics` on EACH changed file - ZERO new errors. ACTUALLY RUN THIS.\n2. Run tests for changed modules, then full suite. ACTUALLY RUN THESE.\n3. Build/typecheck - exit 0.\n\nIf Phase 1 found issues but Phase 2 passes: Phase 2 is WRONG. Fix the code.\n\n**PHASE 3: HANDS-ON QA (MANDATORY for user-facing changes)**\n\n- **Frontend/UI**: `/playwright`\n- **TUI/CLI**: `interactive_bash`\n- **API/Backend**: `Bash` with curl\n\n**If user-facing and you did not run it, you are shipping UNTESTED BROKEN work.**\n\n**PHASE 4: GATE DECISION**\n\n1. Can I explain what EVERY changed line does? (If no \u2192 Phase 1)\n2. Did I SEE it work via tool calls? (If user-facing and no \u2192 Phase 3)\n3. Am I confident nothing is broken? (If no \u2192 broader tests)\n\nALL three must be YES. \"Probably\" = NO. \"I think so\" = NO.\n\n**DO NOT proceed to the next task until all 4 phases are complete.**";
 export declare const ORCHESTRATOR_DELEGATION_REQUIRED: string;
 export declare const SINGLE_TASK_DIRECTIVE: string;

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

@@ -5,6 +5,7 @@ export interface ExecutorOptions {
     pluginsEnabled?: boolean;
     enabledPluginsOverride?: Record<string, boolean>;
     agent?: string;
+    directory?: string;
 }
 export interface ExecuteResult {
     success: boolean;

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

@@ -4,6 +4,7 @@ export interface AutoSlashCommandHookOptions {
     skills?: LoadedSkill[];
     pluginsEnabled?: boolean;
     enabledPluginsOverride?: Record<string, boolean>;
+    directory?: string;
 }
 export declare function createAutoSlashCommandHook(options?: AutoSlashCommandHookOptions): {
     "chat.message": (input: AutoSlashCommandHookInput, output: AutoSlashCommandHookOutput) => Promise<void>;

package/dist/hooks/auto-update-checker/checker/sync-package-json.d.ts

@@ -1,7 +1,7 @@
 import type { PluginEntryInfo } from "./plugin-entry";
 export interface SyncResult {
     synced: boolean;
-    error: "file_not_found" | "plugin_not_in_deps" | "parse_error" | "write_error" | null;
+    error: "parse_error" | "write_error" | null;
     message?: string;
 }
 export declare function syncCachePackageJsonToIntent(pluginInfo: PluginEntryInfo): SyncResult;

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

@@ -1,6 +1,7 @@
-export declare const PACKAGE_NAME = "oh-my-opencode";
-export declare const NPM_REGISTRY_URL = "https://registry.npmjs.org/-/package/oh-my-opencode/dist-tags";
+export declare const PACKAGE_NAME = "oh-my-openagent";
+export declare const NPM_REGISTRY_URL = "https://registry.npmjs.org/-/package/oh-my-openagent/dist-tags";
 export declare const NPM_FETCH_TIMEOUT = 5000;
+export declare const CACHE_ROOT_DIR: string;
 export declare const CACHE_DIR: string;
 export declare const VERSION_FILE: string;
 export declare function getWindowsAppdataDir(): string | null;

package/dist/hooks/auto-update-checker/hook/background-update-check.d.ts

@@ -1,2 +1,30 @@
 import type { PluginInput } from "@opencode-ai/plugin";
-export declare function runBackgroundUpdateCheck(ctx: PluginInput, autoUpdate: boolean, getToastMessage: (isUpdate: boolean, latestVersion?: string) => string): Promise<void>;
+import { existsSync } from "node:fs";
+import { join } from "node:path";
+import { runBunInstallWithDetails } from "../../../cli/config-manager";
+import { log } from "../../../shared/logger";
+import { getOpenCodeCacheDir, getOpenCodeConfigPaths } from "../../../shared";
+import { invalidatePackage } from "../cache";
+import { extractChannel } from "../version-channel";
+import { findPluginEntry, getCachedVersion, getLatestVersion, syncCachePackageJsonToIntent } from "../checker";
+import { showAutoUpdatedToast, showUpdateAvailableToast } from "./update-toasts";
+type BackgroundUpdateCheckDeps = {
+    existsSync: typeof existsSync;
+    join: typeof join;
+    runBunInstallWithDetails: typeof runBunInstallWithDetails;
+    log: typeof log;
+    getOpenCodeCacheDir: typeof getOpenCodeCacheDir;
+    getOpenCodeConfigPaths: typeof getOpenCodeConfigPaths;
+    invalidatePackage: typeof invalidatePackage;
+    extractChannel: typeof extractChannel;
+    findPluginEntry: typeof findPluginEntry;
+    getCachedVersion: typeof getCachedVersion;
+    getLatestVersion: typeof getLatestVersion;
+    syncCachePackageJsonToIntent: typeof syncCachePackageJsonToIntent;
+    showUpdateAvailableToast: typeof showUpdateAvailableToast;
+    showAutoUpdatedToast: typeof showAutoUpdatedToast;
+};
+type BackgroundUpdateCheckRunner = (ctx: PluginInput, autoUpdate: boolean, getToastMessage: (isUpdate: boolean, latestVersion?: string) => string) => Promise<void>;
+export declare function createBackgroundUpdateCheckRunner(overrides?: Partial<BackgroundUpdateCheckDeps>): BackgroundUpdateCheckRunner;
+export declare const runBackgroundUpdateCheck: BackgroundUpdateCheckRunner;
+export {};

package/dist/hooks/bash-file-read-guard.d.ts

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

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

@@ -45,4 +45,5 @@ export declare function createClaudeCodeHooksHook(ctx: PluginInput, config?: Plu
             properties?: unknown;
         };
     }) => Promise<void>;
+    dispose: () => void;
 };

package/dist/hooks/claude-code-hooks/config-loader.d.ts

@@ -9,5 +9,6 @@ export interface DisabledHooksConfig {
 export interface PluginExtendedConfig {
     disabledHooks?: DisabledHooksConfig;
 }
+export declare function clearPluginExtendedConfigCache(): void;
 export declare function loadPluginExtendedConfig(): Promise<PluginExtendedConfig>;
 export declare function isHookCommandDisabled(eventType: ClaudeHookEvent, command: string, config: PluginExtendedConfig | null): boolean;

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

@@ -1,3 +1,4 @@
 import type { ClaudeHooksConfig } from "./types";
 export declare function getClaudeSettingsPaths(customPath?: string): string[];
+export declare function clearClaudeHooksConfigCache(): void;
 export declare function loadClaudeHooksConfig(customSettingsPath?: string): Promise<ClaudeHooksConfig | null>;

package/dist/hooks/claude-code-hooks/handlers/session-event-handler.d.ts

@@ -1,8 +1,10 @@
 import type { PluginInput } from "@opencode-ai/plugin";
+import type { ContextCollector } from "../../../features/context-injector";
 import type { PluginConfig } from "../types";
-export declare function createSessionEventHandler(ctx: PluginInput, config: PluginConfig): (input: {
+export declare function createSessionEventHandler(ctx: PluginInput, config: PluginConfig, contextCollector?: ContextCollector): (input: {
     event: {
         type: string;
         properties?: unknown;
     };
 }) => Promise<void>;
+export declare function disposeSessionEventHandler(contextCollector?: ContextCollector): void;

package/dist/hooks/claude-code-hooks/session-hook-state.d.ts

@@ -7,3 +7,4 @@ export declare const sessionInterruptState: Map<string, {
     interrupted: boolean;
 }>;
 export declare function clearSessionHookState(sessionID: string): void;
+export declare function clearAllSessionHookState(): void;

package/dist/hooks/claude-code-hooks/tool-input-cache.d.ts

@@ -3,3 +3,5 @@
  */
 export declare function cacheToolInput(sessionId: string, toolName: string, invocationId: string, toolInput: Record<string, unknown>): void;
 export declare function getToolInput(sessionId: string, toolName: string, invocationId: string): Record<string, unknown> | null;
+export declare function clearToolInputCache(sessionId?: string): void;
+export declare function stopToolInputCacheCleanup(): void;

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

@@ -6,6 +6,7 @@ export declare function appendTranscriptEntry(sessionId: string, entry: Transcri
  * Call on session.deleted to prevent memory accumulation.
  */
 export declare function clearTranscriptCache(sessionId?: string): void;
+export declare function hasTranscriptCacheEntry(sessionId: string): boolean;
 /**
  * Build Claude Code compatible transcript from session messages.
  * Uses per-session cache to avoid redundant session.messages() API calls.
@@ -23,7 +24,4 @@ export declare function buildTranscriptFromSession(client: {
         }) => Promise<unknown>;
     };
 }, sessionId: string, directory: string, currentToolName: string, currentToolInput: Record<string, unknown>): Promise<string | null>;
-/**
- * Delete temp transcript file (call in finally block)
- */
 export declare function deleteTempTranscript(path: string | null): void;

package/dist/hooks/comment-checker/hook.d.ts

@@ -16,4 +16,5 @@ export declare function createCommentCheckerHooks(config?: CommentCheckerConfig)
         output: string;
         metadata: unknown;
     }) => Promise<void>;
+    dispose: () => void;
 };

package/dist/hooks/comment-checker/pending-calls.d.ts

@@ -1,4 +1,5 @@
 import type { PendingCall } from "./types";
 export declare function startPendingCallCleanup(): void;
+export declare function stopPendingCallCleanup(): void;
 export declare function registerPendingCall(callID: string, pendingCall: PendingCall): void;
 export declare function takePendingCall(callID: string): PendingCall | undefined;

package/dist/hooks/index.d.ts

@@ -23,6 +23,7 @@ export { createKeywordDetectorHook } from "./keyword-detector";
 export { createNonInteractiveEnvHook } from "./non-interactive-env";
 export { createInteractiveBashSessionHook } from "./interactive-bash-session";
 export { createThinkingBlockValidatorHook } from "./thinking-block-validator";
+export { createToolPairValidatorHook } from "./tool-pair-validator";
 export { createCategorySkillReminderHook } from "./category-skill-reminder";
 export { createRalphLoopHook, type RalphLoopHook } from "./ralph-loop";
 export { createNoSisyphusGptHook } from "./no-sisyphus-gpt";
@@ -44,8 +45,10 @@ export { createPreemptiveCompactionHook } from "./preemptive-compaction";
 export { createTasksTodowriteDisablerHook } from "./tasks-todowrite-disabler";
 export { createRuntimeFallbackHook, type RuntimeFallbackHook, type RuntimeFallbackOptions } from "./runtime-fallback";
 export { createWriteExistingFileGuardHook } from "./write-existing-file-guard";
+export { createBashFileReadGuardHook } from "./bash-file-read-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";
 export { createTodoDescriptionOverrideHook } from "./todo-description-override";
 export { createWebFetchRedirectGuardHook } from "./webfetch-redirect-guard";
+export { createLegacyPluginToastHook } from "./legacy-plugin-toast";

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. **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";
+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 - 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] - 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 - 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 - 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\" - RUN IT.\n- \"The types check out\" - Types don't catch logic bugs. RUN IT.\n- \"lsp_diagnostics is clean\" - That's a TYPE check, not a FUNCTIONAL check. RUN IT.\n- \"Tests pass\" - 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";
 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<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";
+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 - THIS IS NOT OPTIONAL\n\n**Before ANY tool call, exploration, or action, you MUST output:**\n\n```\nI detect [TYPE] intent - [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 - 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] - 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 - 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 - 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** - write them in your TODO/Task items with \"QA: [how to verify]\"\n2. **Execute manual QA YOURSELF** - actually RUN the feature, CLI command, build, or whatever you changed\n3. **Report what you observed** - 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\" - DID YOU RUN IT? NO? THEN RUN IT.\n- \"lsp_diagnostics is clean\" - That is a TYPE check, not a FUNCTIONAL check. RUN THE FEATURE.\n- \"Tests pass\" - 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";
 export declare function getGeminiUltraworkMessage(): string;

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

@@ -7,5 +7,5 @@
  * - 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";
+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 - 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] - 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\" - 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 - actual feature tested, output observed and reported**\n\n**Deliver exactly what was asked. No more, no less.**\n\n</ultrawork-mode>\n\n";
 export declare function getGptUltraworkMessage(): string;

package/dist/hooks/legacy-plugin-toast/auto-migrate-runner.d.ts

@@ -0,0 +1,2 @@
+export { autoMigrateLegacyPluginEntry } from "./auto-migrate";
+export type { MigrationResult } from "./auto-migrate";

package/dist/hooks/legacy-plugin-toast/auto-migrate.d.ts

@@ -0,0 +1,7 @@
+export interface MigrationResult {
+    migrated: boolean;
+    from: string | null;
+    to: string | null;
+    configPath: string | null;
+}
+export declare function autoMigrateLegacyPluginEntry(overrideConfigDir?: string): MigrationResult;

package/dist/hooks/legacy-plugin-toast/hook.d.ts

@@ -0,0 +1,18 @@
+import type { PluginInput } from "@opencode-ai/plugin";
+import { checkForLegacyPluginEntry } from "../../shared/legacy-plugin-warning";
+import { log } from "../../shared/logger";
+import { autoMigrateLegacyPluginEntry } from "./auto-migrate-runner";
+type LegacyPluginToastDeps = {
+    checkForLegacyPluginEntry?: typeof checkForLegacyPluginEntry;
+    log?: typeof log;
+    autoMigrateLegacyPluginEntry?: typeof autoMigrateLegacyPluginEntry;
+};
+export declare function createLegacyPluginToastHook(ctx: PluginInput, deps?: LegacyPluginToastDeps): {
+    event: ({ event }: {
+        event: {
+            type: string;
+            properties?: unknown;
+        };
+    }) => Promise<void>;
+};
+export {};

package/dist/hooks/legacy-plugin-toast/index.d.ts

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

package/dist/hooks/legacy-plugin-toast/plugin-entry-migrator.d.ts

@@ -0,0 +1 @@
+export { migrateLegacyPluginEntry } from "../../shared/migrate-legacy-plugin-entry";

package/dist/hooks/model-fallback/chat-message-fallback-handler.d.ts

@@ -0,0 +1,23 @@
+import type { ChatMessageHandlerOutput, ChatMessageInput } from "../../plugin/chat-message";
+export declare function applyFallbackToChatMessage(params: {
+    input: ChatMessageInput;
+    output: ChatMessageHandlerOutput;
+    fallback: {
+        providerID: string;
+        modelID: string;
+        variant?: string;
+    };
+    toast?: (input: {
+        title: string;
+        message: string;
+        variant?: "info" | "success" | "warning" | "error";
+        duration?: number;
+    }) => void | Promise<void>;
+    onApplied?: (input: {
+        sessionID: string;
+        providerID: string;
+        modelID: string;
+        variant?: string;
+    }) => void | Promise<void>;
+    lastToastKey: Map<string, string>;
+}): Promise<void>;

package/dist/hooks/model-fallback/next-fallback.d.ts

@@ -0,0 +1,6 @@
+import type { ModelFallbackState } from "./hook";
+export declare function getNextReachableFallback(sessionID: string, state: ModelFallbackState): {
+    providerID: string;
+    modelID: string;
+    variant?: string;
+} | null;

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

@@ -0,0 +1,11 @@
+import type { PluginInput } from "@opencode-ai/plugin";
+export type SessionMessage = {
+    info?: {
+        role?: string;
+    };
+    parts?: Array<{
+        type: string;
+        text?: string;
+    }>;
+};
+export declare function createPluginInput(messages: SessionMessage[]): PluginInput;

package/dist/hooks/rules-injector/constants.d.ts

@@ -4,4 +4,5 @@ export declare const PROJECT_RULE_SUBDIRS: [string, string][];
 export declare const PROJECT_RULE_FILES: string[];
 export declare const GITHUB_INSTRUCTIONS_PATTERN: RegExp;
 export declare const USER_RULE_DIR = ".claude/rules";
+export declare const OPENCODE_USER_RULE_DIRS: string[];
 export declare const RULE_EXTENSIONS: string[];

package/dist/hooks/rules-injector/finder.d.ts

@@ -1,3 +1,3 @@
 export { findProjectRoot } from "./project-root-finder";
 export { calculateDistance } from "./rule-distance";
-export { findRuleFiles } from "./rule-file-finder";
+export { findRuleFiles, type FindRuleFilesOptions } from "./rule-file-finder";

package/dist/hooks/rules-injector/hook.d.ts

@@ -20,6 +20,8 @@ interface EventInput {
 }
 export declare function createRulesInjectorHook(ctx: PluginInput, modelCacheState?: {
     anthropicContext1MEnabled: boolean;
+}, options?: {
+    skipClaudeUserRules?: boolean;
 }): {
     "tool.execute.before": (input: ToolExecuteInput, output: ToolExecuteBeforeOutput) => Promise<void>;
     "tool.execute.after": (input: ToolExecuteInput, output: ToolExecuteOutput) => Promise<void>;

package/dist/hooks/rules-injector/injector.d.ts

@@ -1,3 +1,4 @@
+import type { FindRuleFilesOptions } from "./rule-file-finder";
 import type { SessionInjectedRulesCache } from "./cache";
 type ToolExecuteOutput = {
     title: string;
@@ -14,6 +15,7 @@ export declare function createRuleInjectionProcessor(deps: {
     workspaceDirectory: string;
     truncator: DynamicTruncator;
     getSessionCache: (sessionID: string) => SessionInjectedRulesCache;
+    ruleFinderOptions?: FindRuleFilesOptions;
 }): {
     processFilePathForInjection: (filePath: string, sessionID: string, output: ToolExecuteOutput) => Promise<void>;
 };

package/dist/hooks/rules-injector/rule-file-finder.d.ts

@@ -1,4 +1,12 @@
 import type { RuleFileCandidate } from "./types";
+export interface FindRuleFilesOptions {
+    /**
+     * When true, skip loading rules from ~/.claude/rules/.
+     * Use when claude_code integration is disabled to prevent
+     * Claude Code-specific instructions from leaking into non-Claude agents.
+     */
+    skipClaudeUserRules?: boolean;
+}
 /**
  * Find all rule files for a given context.
  * Searches from currentFile upward to projectRoot for rule directories,
@@ -12,4 +20,4 @@ import type { RuleFileCandidate } from "./types";
  * @param currentFile - Current file being edited (for distance calculation)
  * @returns Array of rule file candidates sorted by distance
  */
-export declare function findRuleFiles(projectRoot: string | null, homeDir: string, currentFile: string): RuleFileCandidate[];
+export declare function findRuleFiles(projectRoot: string | null, homeDir: string, currentFile: string, options?: FindRuleFilesOptions): RuleFileCandidate[];