@oh-my-pi/pi-coding-agent 13.9.11 → 13.9.13

package/CHANGELOG.md

@@ -2,6 +2,23 @@
 
 ## [Unreleased]
 
+## [13.9.12] - 2026-03-09
+### Added
+
+- Added Tavily as a supported web search provider with `TAVILY_API_KEY` credential discovery and provider fallback support
+- Added `#`-triggered prompt action suggestions in the editor, with keybinding hints for line navigation and prompt copy actions
+- Added Tavily as a supported web search provider with `TAVILY_API_KEY` credential discovery and provider fallback support ([#313](https://github.com/can1357/oh-my-pi/issues/313))
+
+### Removed
+
+- Removed Kagi Universal Summarizer integration from fetch tool—HTML rendering now uses jina, trafilatura, and lynx only
+- Removed `fetch.useKagiSummarizer` setting
+- Removed Kagi summarization from YouTube video handling
+
+### Fixed
+
+- Canonicalized bash executor working directories before handing them to brush so `pwd` stays aligned with canonical Git worktree paths in symlinked workspaces
+
 ## [13.9.10] - 2026-03-08
 ### Added
 

package/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@oh-my-pi/pi-coding-agent",
-	"version": "13.9.11",
+	"version": "13.9.13",
 	"description": "Coding agent CLI with read, bash, edit, write tools and session management",
 	"homepage": "https://github.com/can1357/oh-my-pi",
 	"author": "Can Boluk",
@@ -41,12 +41,12 @@
 	},
 	"dependencies": {
 		"@mozilla/readability": "^0.6",
-		"@oh-my-pi/omp-stats": "13.9.11",
-		"@oh-my-pi/pi-agent-core": "13.9.11",
-		"@oh-my-pi/pi-ai": "13.9.11",
-		"@oh-my-pi/pi-natives": "13.9.11",
-		"@oh-my-pi/pi-tui": "13.9.11",
-		"@oh-my-pi/pi-utils": "13.9.11",
+		"@oh-my-pi/omp-stats": "13.9.13",
+		"@oh-my-pi/pi-agent-core": "13.9.13",
+		"@oh-my-pi/pi-ai": "13.9.13",
+		"@oh-my-pi/pi-natives": "13.9.13",
+		"@oh-my-pi/pi-tui": "13.9.13",
+		"@oh-my-pi/pi-utils": "13.9.13",
 		"@sinclair/typebox": "^0.34",
 		"@xterm/headless": "^6.0",
 		"ajv": "^8.18",

package/src/cli/args.ts

@@ -225,6 +225,7 @@ export function getExtraHelpText(): string {
   BRAVE_API_KEY              - Brave web search
   PERPLEXITY_API_KEY         - Perplexity web search (API)
   PERPLEXITY_COOKIES         - Perplexity web search (session cookie)
+  TAVILY_API_KEY             - Tavily web search
   ANTHROPIC_SEARCH_API_KEY   - Anthropic search provider
 
   ${chalk.dim("# Configuration")}
@@ -237,22 +238,23 @@ export function getExtraHelpText(): string {
 
   For complete environment variable reference, see:
   ${chalk.dim("docs/environment-variables.md")}
-${chalk.bold("Available Tools (all enabled by default):")}
-  read       - Read file contents
-  bash       - Execute bash commands
-  edit       - Edit files with find/replace
-  write      - Write files (creates/overwrites)
-  grep       - Search file contents
-  find       - Find files by glob pattern
-  lsp        - Language server protocol (code intelligence)
-  python     - Execute Python code (requires: ${APP_NAME} setup python)
-  notebook   - Edit Jupyter notebooks
-  browser    - Browser automation (Puppeteer)
-  task       - Launch sub-agents for parallel tasks
-  todo_write - Manage todo/task lists
-  fetch      - Fetch and process URLs
-  web_search - Search the web
-  ask        - Ask user questions (interactive mode only)
+${chalk.bold("Available Tools (default-enabled unless noted):")}
+  read          - Read file contents
+  bash          - Execute bash commands
+  edit          - Edit files with find/replace
+  write         - Write files (creates/overwrites)
+  grep          - Search file contents
+  find          - Find files by glob pattern
+  lsp           - Language server protocol (code intelligence)
+  python        - Execute Python code (requires: ${APP_NAME} setup python)
+  notebook      - Edit Jupyter notebooks
+  inspect_image - Analyze images with a vision model
+  browser       - Browser automation (Puppeteer)
+  task          - Launch sub-agents for parallel tasks
+  todo_write    - Manage todo/task lists
+  fetch         - Fetch and process URLs
+  web_search    - Search the web
+  ask           - Ask user questions (interactive mode only)
 
 ${chalk.bold("Useful Commands:")}
   omp agents unpack           - Export bundled subagents to ~/.omp/agent/agents (default)

package/src/config/keybindings.ts

@@ -31,6 +31,8 @@ export type AppAction =
 	| "followUp"
 	| "dequeue"
 	| "pasteImage"
+	| "copyLine"
+	| "copyPrompt"
 	| "newSession"
 	| "tree"
 	| "fork"
@@ -70,6 +72,8 @@ export const DEFAULT_APP_KEYBINDINGS: Record<AppAction, KeyId | KeyId[]> = {
 	followUp: "ctrl+enter",
 	dequeue: "alt+up",
 	pasteImage: "ctrl+v",
+	copyLine: "alt+shift+l",
+	copyPrompt: "alt+shift+c",
 	newSession: [],
 	tree: [],
 	fork: [],
@@ -104,6 +108,8 @@ const APP_ACTIONS: AppAction[] = [
 	"followUp",
 	"dequeue",
 	"pasteImage",
+	"copyLine",
+	"copyPrompt",
 	"newSession",
 	"tree",
 	"fork",

package/src/config/model-registry.ts

@@ -35,7 +35,7 @@ export function isAuthenticated(apiKey: string | undefined | null): apiKey is st
 	return Boolean(apiKey) && apiKey !== kNoAuth;
 }
 
-export type ModelRole = "default" | "smol" | "slow" | "plan" | "commit";
+export type ModelRole = "default" | "smol" | "slow" | "vision" | "plan" | "commit";
 
 export interface ModelRoleInfo {
 	tag?: string;
@@ -47,11 +47,12 @@ export const MODEL_ROLES: Record<ModelRole, ModelRoleInfo> = {
 	default: { tag: "DEFAULT", name: "Default", color: "success" },
 	smol: { tag: "SMOL", name: "Fast", color: "warning" },
 	slow: { tag: "SLOW", name: "Thinking", color: "accent" },
+	vision: { tag: "VISION", name: "Vision", color: "error" },
 	plan: { tag: "PLAN", name: "Architect", color: "muted" },
 	commit: { tag: "COMMIT", name: "Commit", color: "dim" },
 };
 
-export const MODEL_ROLE_IDS: ModelRole[] = ["default", "smol", "slow", "plan", "commit"];
+export const MODEL_ROLE_IDS: ModelRole[] = ["default", "smol", "slow", "vision", "plan", "commit"];
 
 const OpenRouterRoutingSchema = Type.Object({
 	only: Type.Optional(Type.Array(Type.String())),
@@ -1066,10 +1067,9 @@ export class ModelRegistry {
 			return applyModelOverride(model, override);
 		});
 	}
-
 	#applyHardcodedModelPolicies(models: Model<Api>[]): Model<Api>[] {
 		return models.map(model => {
-			if (model.id === "gpt-5.4") {
+			if (model.id === "gpt-5.4" && model.provider !== "github-copilot") {
 				return { ...model, contextWindow: 1_000_000 };
 			}
 			return model;

package/src/config/settings-schema.ts

@@ -527,6 +527,15 @@ export const SETTINGS_SCHEMA = {
 		default: true,
 		ui: { tab: "tools", label: "Enable Notebook", description: "Enable the notebook tool for notebook editing" },
 	},
+	"inspect_image.enabled": {
+		type: "boolean",
+		default: false,
+		ui: {
+			tab: "tools",
+			label: "Enable Inspect Image",
+			description: "Enable the inspect_image tool, delegating image understanding to a vision-capable model",
+		},
+	},
 	"checkpoint.enabled": {
 		type: "boolean",
 		default: false,
@@ -541,15 +550,6 @@ export const SETTINGS_SCHEMA = {
 		default: true,
 		ui: { tab: "tools", label: "Enable Fetch", description: "Enable the fetch tool for URL fetching" },
 	},
-	"fetch.useKagiSummarizer": {
-		type: "boolean",
-		default: true,
-		ui: {
-			tab: "tools",
-			label: "Use Kagi in Fetch",
-			description: "Use Kagi Universal Summarizer when rendering HTML in fetch",
-		},
-	},
 	"web_search.enabled": {
 		type: "boolean",
 		default: true,
@@ -820,6 +820,7 @@ export const SETTINGS_SCHEMA = {
 			"anthropic",
 			"gemini",
 			"codex",
+			"tavily",
 			"kagi",
 			"synthetic",
 		] as const,

package/src/debug/log-viewer.ts

@@ -1,5 +1,12 @@
 import { copyToClipboard, sanitizeText } from "@oh-my-pi/pi-natives";
-import { type Component, matchesKey, padding, truncateToWidth, visibleWidth } from "@oh-my-pi/pi-tui";
+import {
+	type Component,
+	extractPrintableText,
+	matchesKey,
+	padding,
+	truncateToWidth,
+	visibleWidth,
+} from "@oh-my-pi/pi-tui";
 import { theme } from "../modes/theme/theme";
 import { replaceTabs } from "../tools/render-utils";
 import {
@@ -582,13 +589,10 @@ export class DebugLogViewerComponent implements Component {
 			return;
 		}
 
-		const hasControlChars = [...keyData].some(ch => {
-			const code = ch.charCodeAt(0);
-			return code < 32 || code === 0x7f || (code >= 0x80 && code <= 0x9f);
-		});
-		if (!hasControlChars && keyData.length > 0) {
+		const printableText = extractPrintableText(keyData);
+		if (printableText) {
 			this.#statusMessage = undefined;
-			this.#model.setFilterQuery(this.#model.filterQuery + keyData);
+			this.#model.setFilterQuery(this.#model.filterQuery + printableText);
 			this.#ensureCursorVisible();
 		}
 	}

package/src/exec/bash-executor.ts

@@ -3,6 +3,7 @@
  *
  * Uses brush-core via native bindings for shell execution.
  */
+import * as fs from "node:fs/promises";
 import { Shell } from "@oh-my-pi/pi-natives";
 import { Settings } from "../config/settings";
 import { OutputSink } from "../session/streaming-output";
@@ -39,10 +40,23 @@ const HARD_TIMEOUT_GRACE_MS = 5_000;
 
 const shellSessions = new Map<string, Shell>();
 
+async function resolveShellCwd(cwd: string | undefined): Promise<string | undefined> {
+	if (!cwd) return undefined;
+
+	try {
+		// Brush preserves the working directory string verbatim, so resolve symlinks
+		// up front to keep `pwd` aligned with tools like `git worktree list`.
+		return await fs.realpath(cwd);
+	} catch {
+		return cwd;
+	}
+}
+
 export async function executeBash(command: string, options?: BashExecutorOptions): Promise<BashResult> {
 	const settings = await Settings.init();
 	const { shell, env: shellEnv, prefix } = settings.getShellConfig();
 	const snapshotPath = shell.includes("bash") ? await getOrCreateSnapshot(shell, shellEnv) : null;
+	const commandCwd = await resolveShellCwd(options?.cwd);
 
 	// Apply command prefix if configured
 	const prefixedCommand = prefix ? `${prefix} ${command}` : command;
@@ -97,7 +111,7 @@ export async function executeBash(command: string, options?: BashExecutorOptions
 		const runPromise = shellSession.run(
 			{
 				command: finalCommand,
-				cwd: options?.cwd,
+				cwd: commandCwd,
 				env: options?.env ? { ...NON_INTERACTIVE_ENV, ...options.env } : NON_INTERACTIVE_ENV,
 				timeoutMs: options?.timeout,
 				signal,

package/src/internal-urls/docs-index.generated.ts

@@ -8,7 +8,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"compaction.md": "# Compaction and Branch Summaries\n\nCompaction and branch summaries are the two mechanisms that keep long sessions usable without losing prior work context.\n\n- **Compaction** rewrites old history into a summary on the current branch.\n- **Branch summary** captures abandoned branch context during `/tree` navigation.\n\nBoth are persisted as session entries and converted back into user-context messages when rebuilding LLM input.\n\n## Key implementation files\n\n- `src/session/compaction/compaction.ts`\n- `src/session/compaction/branch-summarization.ts`\n- `src/session/compaction/pruning.ts`\n- `src/session/compaction/utils.ts`\n- `src/session/session-manager.ts`\n- `src/session/agent-session.ts`\n- `src/session/messages.ts`\n- `src/extensibility/hooks/types.ts`\n- `src/config/settings-schema.ts`\n\n## Session entry model\n\nCompaction and branch summaries are first-class session entries, not plain assistant/user messages.\n\n- `CompactionEntry`\n  - `type: \"compaction\"`\n  - `summary`, optional `shortSummary`\n  - `firstKeptEntryId` (compaction boundary)\n  - `tokensBefore`\n  - optional `details`, `preserveData`, `fromExtension`\n- `BranchSummaryEntry`\n  - `type: \"branch_summary\"`\n  - `fromId`, `summary`\n  - optional `details`, `fromExtension`\n\nWhen context is rebuilt (`buildSessionContext`):\n\n1. Latest compaction on the active path is converted to one `compactionSummary` message.\n2. Kept entries from `firstKeptEntryId` to the compaction point are re-included.\n3. Later entries on the path are appended.\n4. `branch_summary` entries are converted to `branchSummary` messages.\n5. `custom_message` entries are converted to `custom` messages.\n\nThose custom roles are then transformed into LLM-facing user messages in `convertToLlm()` using the static templates:\n\n- `prompts/compaction/compaction-summary-context.md`\n- `prompts/compaction/branch-summary-context.md`\n\n## Compaction pipeline\n\n### Triggers\n\nCompaction can run in three ways:\n\n1. **Manual**: `/compact [instructions]` calls `AgentSession.compact(...)`.\n2. **Automatic overflow recovery**: after an assistant error that matches context overflow.\n3. **Automatic threshold compaction**: after a successful turn when context exceeds threshold.\n\n### Compaction shape (visual)\n\n```text\nBefore compaction:\n\n  entry:  0     1     2     3      4     5     6      7      8     9\n        ┌─────┬─────┬─────┬──────┬─────┬─────┬──────┬──────┬─────┬──────┐\n        │ hdr │ usr │ ass │ tool │ usr │ ass │ tool │ tool │ ass │ tool │\n        └─────┴─────┴─────┴──────┴─────┴─────┴──────┴──────┴─────┴──────┘\n                └────────┬───────┘ └──────────────┬──────────────┘\n               messagesToSummarize            kept messages\n                                   ↑\n                          firstKeptEntryId (entry 4)\n\nAfter compaction (new entry appended):\n\n  entry:  0     1     2     3      4     5     6      7      8     9      10\n        ┌─────┬─────┬─────┬──────┬─────┬─────┬──────┬──────┬─────┬──────┬─────┐\n        │ hdr │ usr │ ass │ tool │ usr │ ass │ tool │ tool │ ass │ tool │ cmp │\n        └─────┴─────┴─────┴──────┴─────┴─────┴──────┴──────┴─────┴──────┴─────┘\n               └──────────┬──────┘ └──────────────────────┬───────────────────┘\n                 not sent to LLM                    sent to LLM\n                                                         ↑\n                                              starts from firstKeptEntryId\n\nWhat the LLM sees:\n\n  ┌────────┬─────────┬─────┬─────┬──────┬──────┬─────┬──────┐\n  │ system │ summary │ usr │ ass │ tool │ tool │ ass │ tool │\n  └────────┴─────────┴─────┴─────┴──────┴──────┴─────┴──────┘\n       ↑         ↑      └─────────────────┬────────────────┘\n    prompt   from cmp          messages from firstKeptEntryId\n```\n\n\n### Overflow-retry vs threshold compaction\n\nThe two automatic paths are intentionally different:\n\n- **Overflow-retry compaction**\n  - Trigger: current-model assistant error is detected as context overflow.\n  - The failing assistant error message is removed from active agent state before retry.\n  - Auto compaction runs with `reason: \"overflow\"` and `willRetry: true`.\n  - On success, agent auto-continues (`agent.continue()`) after compaction.\n\n- **Threshold compaction**\n  - Trigger: `contextTokens > contextWindow - compaction.reserveTokens`.\n  - Runs with `reason: \"threshold\"` and `willRetry: false`.\n  - On success, if `compaction.autoContinue !== false`, injects a synthetic prompt:\n    - `\"Continue if you have next steps.\"`\n\n### Pre-compaction pruning\n\nBefore compaction checks, tool-result pruning may run (`pruneToolOutputs`).\n\nDefault prune policy:\n\n- Protect newest `40_000` tool-output tokens.\n- Require at least `20_000` total estimated savings.\n- Never prune tool results from `skill` or `read`.\n\nPruned tool results are replaced with:\n\n- `[Output truncated - N tokens]`\n\nIf pruning changes entries, session storage is rewritten and agent message state is refreshed before compaction decisions.\n\n### Boundary and cut-point logic\n\n`prepareCompaction()` only considers entries since the last compaction entry (if any).\n\n1. Find previous compaction index.\n2. Compute `boundaryStart = prevCompactionIndex + 1`.\n3. Adapt `keepRecentTokens` using measured usage ratio when available.\n4. Run `findCutPoint()` over the boundary window.\n\nValid cut points include:\n\n- message entries with roles: `user`, `assistant`, `bashExecution`, `hookMessage`, `branchSummary`, `compactionSummary`\n- `custom_message` entries\n- `branch_summary` entries\n\nHard rule: never cut at `toolResult`.\n\nIf there are non-message metadata entries immediately before the cut point (`model_change`, `thinking_level_change`, labels, etc.), they are pulled into the kept region by moving cut index backward until a message or compaction boundary is hit.\n\n### Split-turn handling\n\nIf cut point is not at a user-turn start, compaction treats it as a split turn.\n\nTurn start detection treats these as user-turn boundaries:\n\n- `message.role === \"user\"`\n- `message.role === \"bashExecution\"`\n- `custom_message` entry\n- `branch_summary` entry\n\nSplit-turn compaction generates two summaries:\n\n1. History summary (`messagesToSummarize`)\n2. Turn-prefix summary (`turnPrefixMessages`)\n\nFinal stored summary is merged as:\n\n```markdown\n<history summary>\n\n---\n\n**Turn Context (split turn):**\n\n<turn prefix summary>\n```\n\n### Summary generation\n\n`compact(...)` builds summaries from serialized conversation text:\n\n1. Convert messages via `convertToLlm()`.\n2. Serialize with `serializeConversation()`.\n3. Wrap in `<conversation>...</conversation>`.\n4. Optionally include `<previous-summary>...</previous-summary>`.\n5. Optionally inject hook context as `<additional-context>` list.\n6. Execute summarization prompt with `SUMMARIZATION_SYSTEM_PROMPT`.\n\nPrompt selection:\n\n- first compaction: `compaction-summary.md`\n- iterative compaction with prior summary: `compaction-update-summary.md`\n- split-turn second pass: `compaction-turn-prefix.md`\n- short UI summary: `compaction-short-summary.md`\n\nRemote summarization mode:\n\n- If `compaction.remoteEndpoint` is set, compaction POSTs:\n  - `{ systemPrompt, prompt }`\n- Expects JSON containing at least `{ summary }`.\n\n### File-operation context in summaries\n\nCompaction tracks cumulative file activity using assistant tool calls:\n\n- `read(path)` → read set\n- `write(path)` → modified set\n- `edit(path)` → modified set\n\nCumulative behavior:\n\n- Includes prior compaction details only when prior entry is pi-generated (`fromExtension !== true`).\n- In split turns, includes turn-prefix file ops too.\n- `readFiles` excludes files also modified.\n\nSummary text gets file tags appended via prompt template:\n\n```xml\n<read-files>\n...\n</read-files>\n<modified-files>\n...\n</modified-files>\n```\n\n### Persist and reload\n\nAfter summary generation (or hook-provided summary), agent session:\n\n1. Appends `CompactionEntry` with `appendCompaction(...)`.\n2. Rebuilds context via `buildSessionContext()`.\n3. Replaces live agent messages with rebuilt context.\n4. Emits `session_compact` hook event.\n\n## Branch summarization pipeline\n\nBranch summarization is tied to tree navigation, not token overflow.\n\n### Trigger\n\nDuring `navigateTree(...)`:\n\n1. Compute abandoned entries from old leaf to common ancestor using `collectEntriesForBranchSummary(...)`.\n2. If caller requested summary (`options.summarize`), generate summary before switching leaf.\n3. If summary exists, attach it at the navigation target using `branchWithSummary(...)`.\n\nOperationally this is commonly driven by `/tree` flow when `branchSummary.enabled` is enabled.\n\n### Branch switch shape (visual)\n\n```text\nTree before navigation:\n\n         ┌─ B ─ C ─ D (old leaf, being abandoned)\n    A ───┤\n         └─ E ─ F (target)\n\nCommon ancestor: A\nEntries to summarize: B, C, D\n\nAfter navigation with summary:\n\n         ┌─ B ─ C ─ D ─ [summary of B,C,D]\n    A ───┤\n         └─ E ─ F (new leaf)\n```\n\n\n### Preparation and token budget\n\n`generateBranchSummary(...)` computes budget as:\n\n- `tokenBudget = model.contextWindow - branchSummary.reserveTokens`\n\n`prepareBranchEntries(...)` then:\n\n1. First pass: collect cumulative file ops from all summarized entries, including prior pi-generated `branch_summary` details.\n2. Second pass: walk newest → oldest, adding messages until token budget is reached.\n3. Prefer preserving recent context.\n4. May still include large summary entries near budget edge for continuity.\n\nCompaction entries are included as messages (`compactionSummary`) during branch summarization input.\n\n### Summary generation and persistence\n\nBranch summarization:\n\n1. Converts and serializes selected messages.\n2. Wraps in `<conversation>`.\n3. Uses custom instructions if supplied, otherwise `branch-summary.md`.\n4. Calls summarization model with `SUMMARIZATION_SYSTEM_PROMPT`.\n5. Prepends `branch-summary-preamble.md`.\n6. Appends file-operation tags.\n\nResult is stored as `BranchSummaryEntry` with optional details (`readFiles`, `modifiedFiles`).\n\n## Extension and hook touchpoints\n\n### `session_before_compact`\n\nPre-compaction hook.\n\nCan:\n\n- cancel compaction (`{ cancel: true }`)\n- provide full custom compaction payload (`{ compaction: CompactionResult }`)\n\n### `session.compacting`\n\nPrompt/context customization hook for default compaction.\n\nCan return:\n\n- `prompt` (override base summary prompt)\n- `context` (extra context lines injected into `<additional-context>`)\n- `preserveData` (stored on compaction entry)\n\n### `session_compact`\n\nPost-compaction notification with saved `compactionEntry` and `fromExtension` flag.\n\n### `session_before_tree`\n\nRuns on tree navigation before default branch summary generation.\n\nCan:\n\n- cancel navigation\n- provide custom `{ summary: { summary, details } }` used when user requested summarization\n\n### `session_tree`\n\nPost-navigation event exposing new/old leaf and optional summary entry.\n\n## Runtime behavior and failure semantics\n\n- Manual compaction aborts current agent operation first.\n- `abortCompaction()` cancels both manual and auto-compaction controllers.\n- Auto compaction emits start/end session events for UI/state updates.\n- Auto compaction can try multiple model candidates and retry transient failures.\n- Overflow errors are excluded from generic retry path because they are handled by compaction.\n- If auto-compaction fails:\n  - overflow path emits `Context overflow recovery failed: ...`\n  - threshold path emits `Auto-compaction failed: ...`\n- Branch summarization can be cancelled via abort signal (e.g., Escape), returning canceled/aborted navigation result.\n\n## Settings and defaults\n\nFrom `settings-schema.ts`:\n\n- `compaction.enabled` = `true`\n- `compaction.reserveTokens` = `16384`\n- `compaction.keepRecentTokens` = `20000`\n- `compaction.autoContinue` = `true`\n- `compaction.remoteEndpoint` = `undefined`\n- `branchSummary.enabled` = `false`\n- `branchSummary.reserveTokens` = `16384`\n\nThese values are consumed at runtime by `AgentSession` and compaction/branch summarization modules.",
 	"config-usage.md": "# Configuration Discovery and Resolution\n\nThis document describes how the coding-agent resolves configuration today: which roots are scanned, how precedence works, and how resolved config is consumed by settings, skills, hooks, tools, and extensions.\n\n## Scope\n\nPrimary implementation:\n\n- `src/config.ts`\n- `src/config/settings.ts`\n- `src/config/settings-schema.ts`\n- `src/discovery/builtin.ts`\n- `src/discovery/helpers.ts`\n\nKey integration points:\n\n- `src/capability/index.ts`\n- `src/discovery/index.ts`\n- `src/extensibility/skills.ts`\n- `src/extensibility/hooks/loader.ts`\n- `src/extensibility/custom-tools/loader.ts`\n- `src/extensibility/extensions/loader.ts`\n\n---\n\n## Resolution flow (visual)\n\n```text\n         Config roots (ordered)\n┌───────────────────────────────────────┐\n│ 1) ~/.omp/agent + <cwd>/.omp          │\n│ 2) ~/.claude   + <cwd>/.claude        │\n│ 3) ~/.codex    + <cwd>/.codex         │\n│ 4) ~/.gemini   + <cwd>/.gemini        │\n└───────────────────────────────────────┘\n                    │\n                    ▼\n        config.ts helper resolution\n  (getConfigDirs/findConfigFile/findNearest...)\n                    │\n                    ▼\n       capability providers enumerate items\n (native, claude, codex, gemini, agents, etc.)\n                    │\n                    ▼\n      priority sort + per-capability dedup\n                    │\n                    ▼\n          subsystem-specific consumption\n   (settings, skills, hooks, tools, extensions)\n```\n\n\n## 1) Config roots and source order\n\n## Canonical roots\n\n`src/config.ts` defines a fixed source priority list:\n\n1. `.omp` (native)\n2. `.claude`\n3. `.codex`\n4. `.gemini`\n\nUser-level bases:\n\n- `~/.omp/agent`\n- `~/.claude`\n- `~/.codex`\n- `~/.gemini`\n\nProject-level bases:\n\n- `<cwd>/.omp`\n- `<cwd>/.claude`\n- `<cwd>/.codex`\n- `<cwd>/.gemini`\n\n`CONFIG_DIR_NAME` is `.omp` (`packages/utils/src/dirs.ts`).\n\n## Important constraint\n\nThe generic helpers in `src/config.ts` do **not** include `.pi` in source discovery order.\n\n---\n\n## 2) Core discovery helpers (`src/config.ts`)\n\n## `getConfigDirs(subpath, options)`\n\nReturns ordered entries:\n\n- User-level entries first (by source priority)\n- Then project-level entries (by same source priority)\n\nOptions:\n\n- `user` (default `true`)\n- `project` (default `true`)\n- `cwd` (default `getProjectDir()`)\n- `existingOnly` (default `false`)\n\nThis API is used for directory-based config lookups (commands, hooks, tools, agents, etc.).\n\n## `findConfigFile(subpath, options)` / `findConfigFileWithMeta(...)`\n\nSearches for the first existing file across ordered bases, returns first match (path-only or path+metadata).\n\n## `findAllNearestProjectConfigDirs(subpath, cwd)`\n\nWalks parent directories upward and returns the **nearest existing directory per source base** (`.omp`, `.claude`, `.codex`, `.gemini`), then sorts results by source priority.\n\nUse this when project config should be inherited from ancestor directories (monorepo/nested workspace behavior).\n\n---\n\n## 3) File config wrapper (`ConfigFile<T>` in `src/config.ts`)\n\n`ConfigFile<T>` is the schema-validated loader for single config files.\n\nSupported formats:\n\n- `.yml` / `.yaml`\n- `.json` / `.jsonc`\n\nBehavior:\n\n- Validates parsed data with AJV against a provided TypeBox schema.\n- Caches load result until `invalidate()`.\n- Returns tri-state result via `tryLoad()`:\n  - `ok`\n  - `not-found`\n  - `error` (`ConfigError` with schema/parse context)\n\nLegacy migration still supported:\n\n- If target path is `.yml`/`.yaml`, a sibling `.json` is auto-migrated once (`migrateJsonToYml`).\n\n---\n\n## 4) Settings resolution model (`src/config/settings.ts`)\n\nThe runtime settings model is layered:\n\n1. Global settings: `~/.omp/agent/config.yml`\n2. Project settings: discovered via settings capability (`settings.json` from providers)\n3. Runtime overrides: in-memory, non-persistent\n4. Schema defaults: from `SETTINGS_SCHEMA`\n\nEffective read path:\n\n`defaults <- global <- project <- overrides`\n\nWrite behavior:\n\n- `settings.set(...)` writes to the **global** layer (`config.yml`) and queues background save.\n- Project settings are read-only from capability discovery.\n\n## Migration behavior still active\n\nOn startup, if `config.yml` is missing:\n\n1. Migrate from `~/.omp/agent/settings.json` (renamed to `.bak` on success)\n2. Merge with legacy DB settings from `agent.db`\n3. Write merged result to `config.yml`\n\nField-level migrations in `#migrateRawSettings`:\n\n- `queueMode` -> `steeringMode`\n- `ask.timeout` milliseconds -> seconds when old value looks like ms (`> 1000`)\n- Legacy flat `theme: \"...\"` -> `theme.dark/theme.light` structure\n\n---\n\n## 5) Capability/discovery integration\n\nMost non-core config loading flows through the capability registry (`src/capability/index.ts` + `src/discovery/index.ts`).\n\n## Provider ordering\n\nProviders are sorted by numeric priority (higher first). Example priorities:\n\n- Native OMP (`builtin.ts`): `100`\n- Claude: `80`\n- Codex / agents / Claude marketplace: `70`\n- Gemini: `60`\n\n```text\nProvider precedence (higher wins)\n\nnative (.omp)          priority 100\nclaude                 priority  80\ncodex / agents / ...   priority  70\ngemini                 priority  60\n```\n\n## Dedup semantics\n\nCapabilities define a `key(item)`:\n\n- same key => first item wins (higher-priority/earlier-loaded item)\n- no key (`undefined`) => no dedup, all items retained\n\nRelevant keys:\n\n- skills: `name`\n- tools: `name`\n- hooks: `${type}:${tool}:${name}`\n- extension modules: `name`\n- extensions: `name`\n- settings: no dedup (all items preserved)\n\n---\n\n## 6) Native `.omp` provider behavior (`src/discovery/builtin.ts`)\n\nNative provider (`id: native`) reads from:\n\n- project: `<cwd>/.omp/...`\n- user: `~/.omp/agent/...`\n\n### Directory admission rule\n\n`builtin.ts` only includes a config root if the directory exists **and is non-empty** (`ifNonEmptyDir`).\n\n### Scope-specific loading\n\n- Skills: `skills/*/SKILL.md`\n- Slash commands: `commands/*.md`\n- Rules: `rules/*.{md,mdc}`\n- Prompts: `prompts/*.md`\n- Instructions: `instructions/*.md`\n- Hooks: `hooks/pre/*`, `hooks/post/*`\n- Tools: `tools/*.json|*.md` and `tools/<name>/index.ts`\n- Extension modules: discovered under `extensions/` (+ legacy `settings.json.extensions` string array)\n- Extensions: `extensions/<name>/gemini-extension.json`\n- Settings capability: `settings.json`\n\n### Nearest-project lookup nuance\n\nFor `SYSTEM.md` and `AGENTS.md`, native provider uses nearest-ancestor project `.omp` directory search (walk-up) but still requires the `.omp` dir to be non-empty.\n\n---\n\n## 7) How major subsystems consume config\n\n## Settings subsystem\n\n- `Settings.init()` loads global `config.yml` + discovered project `settings.json` capability items.\n- Only capability items with `level === \"project\"` are merged into project layer.\n\n## Skills subsystem\n\n- `extensibility/skills.ts` loads via `loadCapability(skillCapability.id, { cwd })`.\n- Applies source toggles and filters (`ignoredSkills`, `includeSkills`, custom dirs).\n- Legacy-named toggles still exist (`skills.enablePiUser`, `skills.enablePiProject`) but they gate the native provider (`provider === \"native\"`).\n\n## Hooks subsystem\n\n- `discoverAndLoadHooks()` resolves hook paths from hook capability + explicit configured paths.\n- Then loads modules via Bun import.\n\n## Tools subsystem\n\n- `discoverAndLoadCustomTools()` resolves tool paths from tool capability + plugin tool paths + explicit configured paths.\n- Declarative `.md/.json` tool files are metadata only; executable loading expects code modules.\n\n## Extensions subsystem\n\n- `discoverAndLoadExtensions()` resolves extension modules from extension-module capability plus explicit paths.\n- Current implementation intentionally keeps only capability items with `_source.provider === \"native\"` before loading.\n\n---\n\n## 8) Precedence rules to rely on\n\nUse this mental model:\n\n1. Source directory ordering from `config.ts` determines candidate path order.\n2. Capability provider priority determines cross-provider precedence.\n3. Capability key dedup determines collision behavior (first wins for keyed capabilities).\n4. Subsystem-specific merge logic can further change effective precedence (especially settings).\n\n### Settings-specific caveat\n\nSettings capability items are not deduplicated; `Settings.#loadProjectSettings()` deep-merges project items in returned order. Because merge applies later item values over earlier values, effective override behavior depends on provider emission order, not just capability key semantics.\n\n---\n\n## 9) Legacy/compatibility behaviors still present\n\n- `ConfigFile` JSON -> YAML migration for YAML-targeted files.\n- Settings migration from `settings.json` and `agent.db` to `config.yml`.\n- Settings key migrations (`queueMode`, `ask.timeout`, flat `theme`).\n- Extension manifest compatibility: loader accepts both `package.json.omp` and `package.json.pi` manifest sections.\n- Legacy setting names `skills.enablePiUser` / `skills.enablePiProject` are still active gates for native skill source.\n\nIf these compatibility paths are removed in code, update this document immediately; several runtime behaviors still depend on them today.\n",
 	"custom-tools.md": "# Custom Tools\n\nCustom tools are model-callable functions that plug into the same tool execution pipeline as built-in tools.\n\nA custom tool is a TypeScript/JavaScript module that exports a factory. The factory receives a host API (`CustomToolAPI`) and returns one tool or an array of tools.\n\n## What this is (and is not)\n\n- **Custom tool**: callable by the model during a turn (`execute` + TypeBox schema).\n- **Extension**: lifecycle/event framework that can register tools and intercept/modify events.\n- **Hook**: external pre/post command scripts.\n- **Skill**: static guidance/context package, not executable tool code.\n\nIf you need the model to call code directly, use a custom tool.\n\n## Integration paths in current code\n\nThere are two active integration styles:\n\n1. **SDK-provided custom tools** (`options.customTools`)\n   - Wrapped into agent tools via `CustomToolAdapter` or extension wrappers.\n   - Always included in the initial active tool set in SDK bootstrap.\n\n2. **Filesystem-discovered modules via loader API** (`discoverAndLoadCustomTools` / `loadCustomTools`)\n   - Exposed as library APIs in `src/extensibility/custom-tools/loader.ts`.\n   - Host code can call these to discover and load tool modules from config/provider/plugin paths.\n\n```text\nModel tool call flow\n\nLLM tool call\n   │\n   ▼\nTool registry (built-ins + custom tool adapters)\n   │\n   ▼\nCustomTool.execute(toolCallId, params, onUpdate, ctx, signal)\n   │\n   ├─ onUpdate(...)  -> streamed partial result\n   └─ return result  -> final tool content/details\n```\n\n## Discovery locations (loader API)\n\n`discoverAndLoadCustomTools(configuredPaths, cwd, builtInToolNames)` merges:\n\n1. Capability providers (`toolCapability`), including:\n   - Native OMP config (`~/.omp/agent/tools`, `.omp/tools`)\n   - Claude config (`~/.claude/tools`, `.claude/tools`)\n   - Codex config (`~/.codex/tools`, `.codex/tools`)\n   - Claude marketplace plugin cache provider\n2. Installed plugin manifests (`~/.omp/plugins/node_modules/*` via plugin loader)\n3. Explicit configured paths passed to the loader\n\n### Important behavior\n\n- Duplicate resolved paths are deduplicated.\n- Tool name conflicts are rejected against built-ins and already-loaded custom tools.\n- `.md` and `.json` files are discovered as tool metadata by some providers, but the executable module loader rejects them as runnable tools.\n- Relative configured paths are resolved from `cwd`; `~` is expanded.\n\n## Module contract\n\nA custom tool module must export a function (default export preferred):\n\n```ts\nimport type { CustomToolFactory } from \"@oh-my-pi/pi-coding-agent\";\n\nconst factory: CustomToolFactory = (pi) => ({\n\tname: \"repo_stats\",\n\tlabel: \"Repo Stats\",\n\tdescription: \"Counts tracked TypeScript files\",\n\tparameters: pi.typebox.Type.Object({\n\t\tglob: pi.typebox.Type.Optional(pi.typebox.Type.String({ default: \"**/*.ts\" })),\n\t}),\n\n\tasync execute(toolCallId, params, onUpdate, ctx, signal) {\n\t\tonUpdate?.({\n\t\t\tcontent: [{ type: \"text\", text: \"Scanning files...\" }],\n\t\t\tdetails: { phase: \"scan\" },\n\t\t});\n\n\t\tconst result = await pi.exec(\"git\", [\"ls-files\", params.glob ?? \"**/*.ts\"], { signal, cwd: pi.cwd });\n\t\tif (result.killed) {\n\t\t\tthrow new Error(\"Scan was cancelled\");\n\t\t}\n\t\tif (result.code !== 0) {\n\t\t\tthrow new Error(result.stderr || \"git ls-files failed\");\n\t\t}\n\n\t\tconst files = result.stdout.split(\"\\n\").filter(Boolean);\n\t\treturn {\n\t\t\tcontent: [{ type: \"text\", text: `Found ${files.length} files` }],\n\t\t\tdetails: { count: files.length, sample: files.slice(0, 10) },\n\t\t};\n\t},\n\n\tonSession(event) {\n\t\tif (event.reason === \"shutdown\") {\n\t\t\t// cleanup resources if needed\n\t\t}\n\t},\n});\n\nexport default factory;\n```\n\nFactory return type:\n\n- `CustomTool`\n- `CustomTool[]`\n- `Promise<CustomTool | CustomTool[]>`\n\n## API surface passed to factories (`CustomToolAPI`)\n\nFrom `types.ts` and `loader.ts`:\n\n- `cwd`: host working directory\n- `exec(command, args, options?)`: process execution helper\n- `ui`: UI context (can be no-op in headless modes)\n- `hasUI`: `false` in non-interactive flows\n- `logger`: shared file logger\n- `typebox`: injected `@sinclair/typebox`\n- `pi`: injected `@oh-my-pi/pi-coding-agent` exports\n- `pushPendingAction(action)`: register a preview action for hidden `resolve` tool (`docs/resolve-tool-runtime.md`)\n\nLoader starts with a no-op UI context and requires host code to call `setUIContext(...)` when real UI is ready.\n\n## Execution contract and typing\n\n`CustomTool.execute` signature:\n\n```ts\nexecute(toolCallId, params, onUpdate, ctx, signal)\n```\n\n- `params` is statically typed from your TypeBox schema via `Static<TParams>`.\n- Runtime argument validation happens before execution in the agent loop.\n- `onUpdate` emits partial results for UI streaming.\n- `ctx` includes session/model state and an `abort()` helper.\n- `signal` carries cancellation.\n\n`CustomToolAdapter` bridges this to the agent tool interface and forwards calls in the correct argument order.\n\n## How tools are exposed to the model\n\n- Tools are wrapped into `AgentTool` instances (`CustomToolAdapter` or extension wrappers).\n- They are inserted into the session tool registry by name.\n- In SDK bootstrap, custom and extension-registered tools are force-included in the initial active set.\n- CLI `--tools` currently validates only built-in tool names; custom tool inclusion is handled through discovery/registration paths and SDK options.\n\n## Rendering hooks\n\nOptional rendering hooks:\n\n- `renderCall(args, theme)`\n- `renderResult(result, options, theme, args?)`\n\nRuntime behavior in TUI:\n\n- If hooks exist, tool output is rendered inside a `Box` container.\n- `renderResult` receives `{ expanded, isPartial, spinnerFrame? }`.\n- Renderer errors are caught and logged; UI falls back to default text rendering.\n\n## Session/state handling\n\nOptional `onSession(event, ctx)` receives session lifecycle events, including:\n\n- `start`, `switch`, `branch`, `tree`, `shutdown`\n- `auto_compaction_start`, `auto_compaction_end`\n- `auto_retry_start`, `auto_retry_end`\n- `ttsr_triggered`, `todo_reminder`\n\nUse `ctx.sessionManager` to reconstruct state from history when branch/session context changes.\n\n## Failures and cancellation semantics\n\n### Synchronous/async failures\n\n- Throwing (or rejected promises) in `execute` is treated as tool failure.\n- Agent runtime converts failures into tool result messages with `isError: true` and error text content.\n- With extension wrappers, `tool_result` handlers can further rewrite content/details and even override error status.\n\n### Cancellation\n\n- Agent abort propagates through `AbortSignal` to `execute`.\n- Forward `signal` to subprocess work (`pi.exec(..., { signal })`) for cooperative cancellation.\n- `ctx.abort()` lets a tool request abort of the current agent operation.\n\n### onSession errors\n\n- `onSession` errors are caught and logged as warnings; they do not crash the session.\n\n## Real constraints to design for\n\n- Tool names must be globally unique in the active registry.\n- Prefer deterministic, schema-shaped outputs in `details` for renderer/state reconstruction.\n- Guard UI usage with `pi.hasUI`.\n- Treat `.md`/`.json` in tool directories as metadata, not executable modules.\n",
-	"environment-variables.md": "# Environment Variables (Current Runtime Reference)\n\nThis reference is derived from current code paths in:\n\n- `packages/coding-agent/src/**`\n- `packages/ai/src/**` (provider/auth resolution used by coding-agent)\n- `packages/utils/src/**` and `packages/tui/src/**` where those vars directly affect coding-agent runtime\n\nIt documents only active behavior.\n\n## Resolution model and precedence\n\nMost runtime lookups use `$env` from `@oh-my-pi/pi-utils` (`packages/utils/src/env.ts`).\n\n`$env` loading order:\n\n1. Existing process environment (`Bun.env`)\n2. Project `.env` (`$PWD/.env`) for keys not already set\n3. Home `.env` (`~/.env`) for keys not already set\n\nAdditional rule in `.env` files: `OMP_*` keys are mirrored to `PI_*` keys during parse.\n\n---\n\n## 1) Model/provider authentication\n\nThese are consumed via `getEnvApiKey()` (`packages/ai/src/stream.ts`) unless noted otherwise.\n\n### Core provider credentials\n\n| Variable | Used for | Required when | Notes / precedence |\n|---|---|---|---|\n| `ANTHROPIC_OAUTH_TOKEN` | Anthropic API auth | Using Anthropic with OAuth token auth | Takes precedence over `ANTHROPIC_API_KEY` for provider auth resolution |\n| `ANTHROPIC_API_KEY` | Anthropic API auth | Using Anthropic without OAuth token | Fallback after `ANTHROPIC_OAUTH_TOKEN` |\n| `ANTHROPIC_FOUNDRY_API_KEY` | Anthropic via Azure Foundry / enterprise gateway | `CLAUDE_CODE_USE_FOUNDRY` enabled | Takes precedence over `ANTHROPIC_OAUTH_TOKEN` and `ANTHROPIC_API_KEY` when Foundry mode is enabled |\n| `OPENAI_API_KEY` | OpenAI auth | Using OpenAI-family providers without explicit apiKey argument | Used by OpenAI Completions/Responses providers |\n| `GEMINI_API_KEY` | Google Gemini auth | Using `google` provider models | Primary key for Gemini provider mapping |\n| `GOOGLE_API_KEY` | Gemini image tool auth fallback | Using `gemini_image` tool without `GEMINI_API_KEY` | Used by coding-agent image tool fallback path |\n| `GROQ_API_KEY` | Groq auth | Using Groq models |  |\n| `CEREBRAS_API_KEY` | Cerebras auth | Using Cerebras models |  |\n| `TOGETHER_API_KEY` | Together auth | Using `together` provider |  |\n| `HUGGINGFACE_HUB_TOKEN` | Hugging Face auth | Using `huggingface` provider | Primary Hugging Face token env var |\n| `HF_TOKEN` | Hugging Face auth | Using `huggingface` provider | Fallback when `HUGGINGFACE_HUB_TOKEN` is unset |\n| `SYNTHETIC_API_KEY` | Synthetic auth | Using Synthetic models |  |\n| `NVIDIA_API_KEY` | NVIDIA auth | Using `nvidia` provider |  |\n| `NANO_GPT_API_KEY` | NanoGPT auth | Using `nanogpt` provider | |\n| `VENICE_API_KEY` | Venice auth | Using `venice` provider |  |\n| `LITELLM_API_KEY` | LiteLLM auth | Using `litellm` provider | OpenAI-compatible LiteLLM proxy key |\n| `LM_STUDIO_API_KEY` | LM Studio auth (optional) | Using `lm-studio` provider with authenticated hosts | Local LM Studio usually runs without auth; any non-empty token works when a key is required |\n| `OLLAMA_API_KEY` | Ollama auth (optional) | Using `ollama` provider with authenticated hosts | Local Ollama usually runs without auth; any non-empty token works when a key is required |\n| `XIAOMI_API_KEY` | Xiaomi MiMo auth | Using `xiaomi` provider |  |\n| `MOONSHOT_API_KEY` | Moonshot auth | Using `moonshot` provider |  |\n| `XAI_API_KEY` | xAI auth | Using xAI models |  |\n| `OPENROUTER_API_KEY` | OpenRouter auth | Using OpenRouter models | Also used by image tool when preferred/auto provider is OpenRouter |\n| `MISTRAL_API_KEY` | Mistral auth | Using Mistral models |  |\n| `ZAI_API_KEY` | z.ai auth | Using z.ai models | Also used by z.ai web search provider |\n| `MINIMAX_API_KEY` | MiniMax auth | Using `minimax` provider |  |\n| `MINIMAX_CODE_API_KEY` | MiniMax Code auth | Using `minimax-code` provider |  |\n| `MINIMAX_CODE_CN_API_KEY` | MiniMax Code CN auth | Using `minimax-code-cn` provider |  |\n| `OPENCODE_API_KEY` | OpenCode auth | Using OpenCode models |  |\n| `QIANFAN_API_KEY` | Qianfan auth | Using `qianfan` provider |  |\n| `QWEN_OAUTH_TOKEN` | Qwen Portal auth | Using `qwen-portal` with OAuth token | Takes precedence over `QWEN_PORTAL_API_KEY` |\n| `QWEN_PORTAL_API_KEY` | Qwen Portal auth | Using `qwen-portal` with API key | Fallback after `QWEN_OAUTH_TOKEN` |\n| `ZENMUX_API_KEY` | ZenMux auth | Using `zenmux` provider | Used for ZenMux OpenAI and Anthropic-compatible routes |\n| `VLLM_API_KEY` | vLLM auth/discovery opt-in | Using `vllm` provider (local OpenAI-compatible servers) | Any non-empty value works for no-auth local servers |\n| `CURSOR_ACCESS_TOKEN` | Cursor provider auth | Using Cursor provider |  |\n| `AI_GATEWAY_API_KEY` | Vercel AI Gateway auth | Using `vercel-ai-gateway` provider |  |\n| `CLOUDFLARE_AI_GATEWAY_API_KEY` | Cloudflare AI Gateway auth | Using `cloudflare-ai-gateway` provider | Base URL must be configured as `https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic` |\n\n### GitHub/Copilot token chains\n\n| Variable | Used for | Chain |\n|---|---|---|\n| `COPILOT_GITHUB_TOKEN` | GitHub Copilot provider auth | `COPILOT_GITHUB_TOKEN` → `GH_TOKEN` → `GITHUB_TOKEN` |\n| `GH_TOKEN` | Copilot fallback; GitHub API auth in web scraper | In web scraper: `GITHUB_TOKEN` → `GH_TOKEN` |\n| `GITHUB_TOKEN` | Copilot fallback; GitHub API auth in web scraper | In web scraper: checked before `GH_TOKEN` |\n\n---\n\n## 2) Provider-specific runtime configuration\n\n### Anthropic Foundry Gateway (Azure / enterprise proxy)\n\nWhen `CLAUDE_CODE_USE_FOUNDRY` is enabled, Anthropic requests switch to Foundry mode:\n\n- Base URL resolves from `FOUNDRY_BASE_URL` (fallback remains model/default base URL if unset).\n- API key resolution for provider `anthropic` becomes:\n  `ANTHROPIC_FOUNDRY_API_KEY` → `ANTHROPIC_OAUTH_TOKEN` → `ANTHROPIC_API_KEY`.\n- `ANTHROPIC_CUSTOM_HEADERS` is parsed as comma/newline-separated `key: value` pairs and merged into request headers.\n- TLS client/server material can be injected from env values:\n  `NODE_EXTRA_CA_CERTS`, `CLAUDE_CODE_CLIENT_CERT`, `CLAUDE_CODE_CLIENT_KEY`.\n  Each accepts either:\n  - a filesystem path to PEM content, or\n  - inline PEM (including escaped `\\n` sequences).\n\n| Variable | Value type | Behavior |\n|---|---|---|\n| `CLAUDE_CODE_USE_FOUNDRY` | Boolean-like string (`1`, `true`, `yes`, `on`) | Enables Foundry mode for Anthropic provider |\n| `FOUNDRY_BASE_URL` | URL string | Anthropic endpoint base URL in Foundry mode |\n| `ANTHROPIC_FOUNDRY_API_KEY` | Token string | Used for `Authorization: Bearer <token>` |\n| `ANTHROPIC_CUSTOM_HEADERS` | Header list string | Extra headers; format `header-a: value, header-b: value` or newline-separated |\n| `NODE_EXTRA_CA_CERTS` | PEM path or inline PEM | Extra CA chain for server certificate validation |\n| `CLAUDE_CODE_CLIENT_CERT` | PEM path or inline PEM | mTLS client certificate |\n| `CLAUDE_CODE_CLIENT_KEY` | PEM path or inline PEM | mTLS client private key (must be paired with cert) |\n\n### Amazon Bedrock\n\n| Variable | Default / behavior |\n|---|---|\n| `AWS_REGION` | Primary region source |\n| `AWS_DEFAULT_REGION` | Fallback if `AWS_REGION` unset |\n| `AWS_PROFILE` | Enables named profile auth path |\n| `AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY` | Enables IAM key auth path |\n| `AWS_BEARER_TOKEN_BEDROCK` | Enables bearer token auth path |\n| `AWS_CONTAINER_CREDENTIALS_RELATIVE_URI` / `AWS_CONTAINER_CREDENTIALS_FULL_URI` | Enables ECS task credential path |\n| `AWS_WEB_IDENTITY_TOKEN_FILE` + `AWS_ROLE_ARN` | Enables web identity auth path |\n| `AWS_BEDROCK_SKIP_AUTH` | If `1`, injects dummy credentials (proxy/non-auth scenarios) |\n| `AWS_BEDROCK_FORCE_HTTP1` | If `1`, forces Node HTTP/1 request handler |\n\nRegion fallback in provider code: `options.region` → `AWS_REGION` → `AWS_DEFAULT_REGION` → `us-east-1`.\n\n### Azure OpenAI Responses\n\n| Variable | Default / behavior |\n|---|---|\n| `AZURE_OPENAI_API_KEY` | Required unless API key passed as option |\n| `AZURE_OPENAI_API_VERSION` | Default `v1` |\n| `AZURE_OPENAI_BASE_URL` | Direct base URL override |\n| `AZURE_OPENAI_RESOURCE_NAME` | Used to construct base URL: `https://<resource>.openai.azure.com/openai/v1` |\n| `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` | Optional mapping string: `modelId=deploymentName,model2=deployment2` |\n\nBase URL resolution: option `azureBaseUrl` → env `AZURE_OPENAI_BASE_URL` → option/env resource name → `model.baseUrl`.\n\n### Google Vertex AI\n\n| Variable | Required? | Notes |\n|---|---|---|\n| `GOOGLE_CLOUD_PROJECT` | Yes (unless passed in options) | Fallback: `GCLOUD_PROJECT` |\n| `GCLOUD_PROJECT` | Fallback | Used as alternate project ID source |\n| `GOOGLE_CLOUD_LOCATION` | Yes (unless passed in options) | No default in provider |\n| `GOOGLE_APPLICATION_CREDENTIALS` | Conditional | If set, file must exist; otherwise ADC fallback path is checked (`~/.config/gcloud/application_default_credentials.json`) |\n\n### Kimi\n\n| Variable | Default / behavior |\n|---|---|\n| `KIMI_CODE_OAUTH_HOST` | Primary OAuth host override |\n| `KIMI_OAUTH_HOST` | Fallback OAuth host override |\n| `KIMI_CODE_BASE_URL` | Overrides Kimi usage endpoint base URL (`usage/kimi.ts`) |\n\nOAuth host chain: `KIMI_CODE_OAUTH_HOST` → `KIMI_OAUTH_HOST` → `https://auth.kimi.com`.\n\n### Antigravity/Gemini image compatibility\n\n| Variable | Default / behavior |\n|---|---|\n| `PI_AI_ANTIGRAVITY_VERSION` | Overrides Antigravity user-agent version tag in Gemini CLI provider |\n\n### OpenAI Codex responses (feature/debug controls)\n\n| Variable | Behavior |\n|---|---|\n| `PI_CODEX_DEBUG` | `1`/`true` enables Codex provider debug logging |\n| `PI_CODEX_WEBSOCKET` | `1`/`true` enables websocket transport preference |\n| `PI_CODEX_WEBSOCKET_V2` | `1`/`true` enables websocket v2 path |\n| `PI_CODEX_WEBSOCKET_IDLE_TIMEOUT_MS` | Positive integer override (default 300000) |\n| `PI_CODEX_WEBSOCKET_RETRY_BUDGET` | Non-negative integer override (default 5) |\n| `PI_CODEX_WEBSOCKET_RETRY_DELAY_MS` | Positive integer base backoff override (default 500) |\n\n### Cursor provider debug\n\n| Variable | Behavior |\n|---|---|\n| `DEBUG_CURSOR` | Enables provider debug logs; `2`/`verbose` for detailed payload snippets |\n| `DEBUG_CURSOR_LOG` | Optional file path for JSONL debug log output |\n\n### Prompt cache compatibility switch\n\n| Variable | Behavior |\n|---|---|\n| `PI_CACHE_RETENTION` | If `long`, enables long retention where supported (`anthropic`, `openai-responses`, Bedrock retention resolution) |\n\n---\n\n## 3) Web search subsystem\n\n### Search provider credentials\n\n| Variable | Used by |\n|---|---|\n| `EXA_API_KEY` | Exa search provider and Exa MCP tools |\n| `BRAVE_API_KEY` | Brave search provider |\n| `PERPLEXITY_API_KEY` | Perplexity search provider API-key mode |\n| `ZAI_API_KEY` | z.ai search provider (also checks stored OAuth in `agent.db`) |\n| `OPENAI_API_KEY` / Codex OAuth in DB | Codex search provider availability/auth |\n\n### Anthropic web search auth chain\n\n`packages/coding-agent/src/web/search/auth.ts` resolves Anthropic web-search credentials in this order:\n\n1. `ANTHROPIC_SEARCH_API_KEY` (+ optional `ANTHROPIC_SEARCH_BASE_URL`)\n2. `models.json` provider entry with `api: \"anthropic-messages\"`\n3. Anthropic OAuth credentials from `agent.db` (must not expire within 5-minute buffer)\n4. Generic Anthropic env fallback: provider key (`ANTHROPIC_FOUNDRY_API_KEY`/`ANTHROPIC_OAUTH_TOKEN`/`ANTHROPIC_API_KEY`) + optional `ANTHROPIC_BASE_URL` (`FOUNDRY_BASE_URL` when Foundry mode is enabled)\n\nRelated vars:\n\n| Variable | Default / behavior |\n|---|---|\n| `ANTHROPIC_SEARCH_API_KEY` | Highest-priority explicit search key |\n| `ANTHROPIC_SEARCH_BASE_URL` | Defaults to `https://api.anthropic.com` when omitted |\n| `ANTHROPIC_SEARCH_MODEL` | Defaults to `claude-haiku-4-5` |\n| `ANTHROPIC_BASE_URL` | Generic fallback base URL for tier-4 auth path |\n\n### Perplexity OAuth flow behavior flag\n\n| Variable | Behavior |\n|---|---|\n| `PI_AUTH_NO_BORROW` | If set, disables macOS native-app token borrowing path in Perplexity login flow |\n\n---\n\n## 4) Python tooling and kernel runtime\n\n| Variable | Default / behavior |\n|---|---|\n| `PI_PY` | Python tool mode override: `0`/`bash`=`bash-only`, `1`/`py`=`ipy-only`, `mix`/`both`=`both`; invalid values ignored |\n| `PI_PYTHON_SKIP_CHECK` | If `1`, skips Python kernel availability checks/warm checks |\n| `PI_PYTHON_GATEWAY_URL` | If set, uses external kernel gateway instead of local shared gateway |\n| `PI_PYTHON_GATEWAY_TOKEN` | Optional auth token for external gateway (`Authorization: token <value>`) |\n| `PI_PYTHON_IPC_TRACE` | If `1`, enables low-level IPC trace path in kernel module |\n| `VIRTUAL_ENV` | Highest-priority venv path for Python runtime resolution |\n\nExtra conditional behavior:\n\n- If `BUN_ENV=test` or `NODE_ENV=test`, Python availability checks are treated as OK and warming is skipped.\n- Python env filtering denies common API keys and allows safe base vars + `LC_`, `XDG_`, `PI_` prefixes.\n\n---\n\n## 5) Agent/runtime behavior toggles\n\n| Variable | Default / behavior |\n|---|---|\n| `PI_SMOL_MODEL` | Ephemeral model-role override for `smol` (CLI `--smol` takes precedence) |\n| `PI_SLOW_MODEL` | Ephemeral model-role override for `slow` (CLI `--slow` takes precedence) |\n| `PI_PLAN_MODEL` | Ephemeral model-role override for `plan` (CLI `--plan` takes precedence) |\n| `PI_NO_TITLE` | If set (any non-empty value), disables auto session title generation on first user message |\n| `NULL_PROMPT` | If `true`, system prompt builder returns empty string |\n| `PI_BLOCKED_AGENT` | Blocks a specific subagent type in task tool |\n| `PI_SUBPROCESS_CMD` | Overrides subagent spawn command (`omp` / `omp.cmd` resolution bypass) |\n| `PI_TASK_MAX_OUTPUT_BYTES` | Max captured output bytes per subagent (default `500000`) |\n| `PI_TASK_MAX_OUTPUT_LINES` | Max captured output lines per subagent (default `5000`) |\n| `PI_TIMING` | If `1`, enables startup/tool timing instrumentation logs |\n| `PI_DEBUG_STARTUP` | Enables startup stage debug prints to stderr in multiple startup paths |\n| `PI_PACKAGE_DIR` | Overrides package asset base dir resolution (docs/examples/changelog path lookup) |\n| `PI_DISABLE_LSPMUX` | If `1`, disables lspmux detection/integration and forces direct LSP server spawning |\n| `LM_STUDIO_BASE_URL` | Default implicit LM Studio discovery base URL override (`http://127.0.0.1:1234/v1` if unset) |\n| `OLLAMA_BASE_URL` | Default implicit Ollama discovery base URL override (`http://127.0.0.1:11434` if unset) |\n| `PI_EDIT_VARIANT` | If `hashline`, forces hashline read/grep display mode when edit tool available |\n| `PI_NO_PTY` | If `1`, disables interactive PTY path for bash tool |\n\n`PI_NO_PTY` is also set internally when CLI `--no-pty` is used.\n\n---\n\n## 6) Storage and config root paths\n\nThese are consumed via `@oh-my-pi/pi-utils/dirs` and affect where coding-agent stores data.\n\n| Variable | Default / behavior |\n|---|---|\n| `PI_CONFIG_DIR` | Config root dirname under home (default `.omp`) |\n| `PI_CODING_AGENT_DIR` | Full override for agent directory (default `~/<PI_CONFIG_DIR or .omp>/agent`) |\n| `PWD` | Used when matching canonical current working directory in path helpers |\n\n---\n\n## 7) Shell/tool execution environment\n\n(From `packages/utils/src/procmgr.ts` and coding-agent bash tool integration.)\n\n| Variable | Behavior |\n|---|---|\n| `PI_BASH_NO_CI` | Suppresses automatic `CI=true` injection into spawned shell env |\n| `CLAUDE_BASH_NO_CI` | Legacy alias fallback for `PI_BASH_NO_CI` |\n| `PI_BASH_NO_LOGIN` | Intended to disable login shell mode |\n| `CLAUDE_BASH_NO_LOGIN` | Legacy alias fallback for `PI_BASH_NO_LOGIN` |\n| `PI_SHELL_PREFIX` | Optional command prefix wrapper |\n| `CLAUDE_CODE_SHELL_PREFIX` | Legacy alias fallback for `PI_SHELL_PREFIX` |\n| `VISUAL` | Preferred external editor command |\n| `EDITOR` | Fallback external editor command |\n\nCurrent implementation note: `PI_BASH_NO_LOGIN`/`CLAUDE_BASH_NO_LOGIN` are read, but current `getShellArgs()` returns `['-l','-c']` in both branches (effectively no-op today).\n\n---\n\n## 8) UI/theme/session detection (auto-detected env)\n\nThese are read as runtime signals; they are usually set by the terminal/OS rather than manually configured.\n\n| Variable | Used for |\n|---|---|\n| `COLORTERM`, `TERM`, `WT_SESSION` | Color capability detection (theme color mode) |\n| `COLORFGBG` | Terminal background light/dark auto-detection |\n| `TERM_PROGRAM`, `TERM_PROGRAM_VERSION`, `TERMINAL_EMULATOR` | Terminal identity in system prompt/context |\n| `KDE_FULL_SESSION`, `XDG_CURRENT_DESKTOP`, `DESKTOP_SESSION`, `XDG_SESSION_DESKTOP`, `GDMSESSION`, `WINDOWMANAGER` | Desktop/window-manager detection in system prompt/context |\n| `KITTY_WINDOW_ID`, `TMUX_PANE`, `TERM_SESSION_ID`, `WT_SESSION` | Stable per-terminal session breadcrumb IDs |\n| `SHELL`, `ComSpec`, `TERM_PROGRAM`, `TERM` | System info diagnostics |\n| `APPDATA`, `XDG_CONFIG_HOME` | lspmux config path resolution |\n| `HOME` | Path shortening in MCP command UI |\n\n---\n\n## 9) Native loader/debug flags\n\n| Variable | Behavior |\n|---|---|\n| `PI_DEV` | Enables verbose native addon load diagnostics in `packages/natives` |\n\n## 10) TUI runtime flags (shared package, affects coding-agent UX)\n\n| Variable | Behavior |\n|---|---|\n| `PI_NOTIFICATIONS` | `off` / `0` / `false` suppress desktop notifications |\n| `PI_TUI_WRITE_LOG` | If set, logs TUI writes to file |\n| `PI_HARDWARE_CURSOR` | If `1`, enables hardware cursor mode |\n| `PI_CLEAR_ON_SHRINK` | If `1`, clears empty rows when content shrinks |\n| `PI_DEBUG_REDRAW` | If `1`, enables redraw debug logging |\n| `PI_TUI_DEBUG` | If `1`, enables deep TUI debug dump path |\n\n---\n\n## 11) Commit generation controls\n\n| Variable | Behavior |\n|---|---|\n| `PI_COMMIT_TEST_FALLBACK` | If `true` (case-insensitive), force commit fallback generation path |\n| `PI_COMMIT_NO_FALLBACK` | If `true`, disables fallback when agent returns no proposal |\n| `PI_COMMIT_MAP_REDUCE` | If `false`, disables map-reduce commit analysis path |\n| `DEBUG` | If set, commit agent error stack traces are printed |\n\n---\n\n## Security-sensitive variables\n\nTreat these as secrets; do not log or commit them:\n\n- Provider/API keys and OAuth/bearer credentials (all `*_API_KEY`, `*_TOKEN`, OAuth access/refresh tokens)\n- Cloud credentials (`AWS_*`, `GOOGLE_APPLICATION_CREDENTIALS` path may expose service-account material)\n- Search/provider auth vars (`EXA_API_KEY`, `BRAVE_API_KEY`, `PERPLEXITY_API_KEY`, Anthropic search keys)\n- Foundry mTLS material (`CLAUDE_CODE_CLIENT_CERT`, `CLAUDE_CODE_CLIENT_KEY`, `NODE_EXTRA_CA_CERTS` when it points to private CA bundles)\n\nPython runtime also explicitly strips many common key vars before spawning kernel subprocesses (`packages/coding-agent/src/ipy/runtime.ts`).\n",
+	"environment-variables.md": "# Environment Variables (Current Runtime Reference)\n\nThis reference is derived from current code paths in:\n\n- `packages/coding-agent/src/**`\n- `packages/ai/src/**` (provider/auth resolution used by coding-agent)\n- `packages/utils/src/**` and `packages/tui/src/**` where those vars directly affect coding-agent runtime\n\nIt documents only active behavior.\n\n## Resolution model and precedence\n\nMost runtime lookups use `$env` from `@oh-my-pi/pi-utils` (`packages/utils/src/env.ts`).\n\n`$env` loading order:\n\n1. Existing process environment (`Bun.env`)\n2. Project `.env` (`$PWD/.env`) for keys not already set\n3. Home `.env` (`~/.env`) for keys not already set\n\nAdditional rule in `.env` files: `OMP_*` keys are mirrored to `PI_*` keys during parse.\n\n---\n\n## 1) Model/provider authentication\n\nThese are consumed via `getEnvApiKey()` (`packages/ai/src/stream.ts`) unless noted otherwise.\n\n### Core provider credentials\n\n| Variable | Used for | Required when | Notes / precedence |\n|---|---|---|---|\n| `ANTHROPIC_OAUTH_TOKEN` | Anthropic API auth | Using Anthropic with OAuth token auth | Takes precedence over `ANTHROPIC_API_KEY` for provider auth resolution |\n| `ANTHROPIC_API_KEY` | Anthropic API auth | Using Anthropic without OAuth token | Fallback after `ANTHROPIC_OAUTH_TOKEN` |\n| `ANTHROPIC_FOUNDRY_API_KEY` | Anthropic via Azure Foundry / enterprise gateway | `CLAUDE_CODE_USE_FOUNDRY` enabled | Takes precedence over `ANTHROPIC_OAUTH_TOKEN` and `ANTHROPIC_API_KEY` when Foundry mode is enabled |\n| `OPENAI_API_KEY` | OpenAI auth | Using OpenAI-family providers without explicit apiKey argument | Used by OpenAI Completions/Responses providers |\n| `GEMINI_API_KEY` | Google Gemini auth | Using `google` provider models | Primary key for Gemini provider mapping |\n| `GOOGLE_API_KEY` | Gemini image tool auth fallback | Using `gemini_image` tool without `GEMINI_API_KEY` | Used by coding-agent image tool fallback path |\n| `GROQ_API_KEY` | Groq auth | Using Groq models |  |\n| `CEREBRAS_API_KEY` | Cerebras auth | Using Cerebras models |  |\n| `TOGETHER_API_KEY` | Together auth | Using `together` provider |  |\n| `HUGGINGFACE_HUB_TOKEN` | Hugging Face auth | Using `huggingface` provider | Primary Hugging Face token env var |\n| `HF_TOKEN` | Hugging Face auth | Using `huggingface` provider | Fallback when `HUGGINGFACE_HUB_TOKEN` is unset |\n| `SYNTHETIC_API_KEY` | Synthetic auth | Using Synthetic models |  |\n| `NVIDIA_API_KEY` | NVIDIA auth | Using `nvidia` provider |  |\n| `NANO_GPT_API_KEY` | NanoGPT auth | Using `nanogpt` provider | |\n| `VENICE_API_KEY` | Venice auth | Using `venice` provider |  |\n| `LITELLM_API_KEY` | LiteLLM auth | Using `litellm` provider | OpenAI-compatible LiteLLM proxy key |\n| `LM_STUDIO_API_KEY` | LM Studio auth (optional) | Using `lm-studio` provider with authenticated hosts | Local LM Studio usually runs without auth; any non-empty token works when a key is required |\n| `OLLAMA_API_KEY` | Ollama auth (optional) | Using `ollama` provider with authenticated hosts | Local Ollama usually runs without auth; any non-empty token works when a key is required |\n| `XIAOMI_API_KEY` | Xiaomi MiMo auth | Using `xiaomi` provider |  |\n| `MOONSHOT_API_KEY` | Moonshot auth | Using `moonshot` provider |  |\n| `XAI_API_KEY` | xAI auth | Using xAI models |  |\n| `OPENROUTER_API_KEY` | OpenRouter auth | Using OpenRouter models | Also used by image tool when preferred/auto provider is OpenRouter |\n| `MISTRAL_API_KEY` | Mistral auth | Using Mistral models |  |\n| `ZAI_API_KEY` | z.ai auth | Using z.ai models | Also used by z.ai web search provider |\n| `MINIMAX_API_KEY` | MiniMax auth | Using `minimax` provider |  |\n| `MINIMAX_CODE_API_KEY` | MiniMax Code auth | Using `minimax-code` provider |  |\n| `MINIMAX_CODE_CN_API_KEY` | MiniMax Code CN auth | Using `minimax-code-cn` provider |  |\n| `OPENCODE_API_KEY` | OpenCode auth | Using OpenCode models |  |\n| `QIANFAN_API_KEY` | Qianfan auth | Using `qianfan` provider |  |\n| `QWEN_OAUTH_TOKEN` | Qwen Portal auth | Using `qwen-portal` with OAuth token | Takes precedence over `QWEN_PORTAL_API_KEY` |\n| `QWEN_PORTAL_API_KEY` | Qwen Portal auth | Using `qwen-portal` with API key | Fallback after `QWEN_OAUTH_TOKEN` |\n| `ZENMUX_API_KEY` | ZenMux auth | Using `zenmux` provider | Used for ZenMux OpenAI and Anthropic-compatible routes |\n| `VLLM_API_KEY` | vLLM auth/discovery opt-in | Using `vllm` provider (local OpenAI-compatible servers) | Any non-empty value works for no-auth local servers |\n| `CURSOR_ACCESS_TOKEN` | Cursor provider auth | Using Cursor provider |  |\n| `AI_GATEWAY_API_KEY` | Vercel AI Gateway auth | Using `vercel-ai-gateway` provider |  |\n| `CLOUDFLARE_AI_GATEWAY_API_KEY` | Cloudflare AI Gateway auth | Using `cloudflare-ai-gateway` provider | Base URL must be configured as `https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic` |\n\n### GitHub/Copilot token chains\n\n| Variable | Used for | Chain |\n|---|---|---|\n| `COPILOT_GITHUB_TOKEN` | GitHub Copilot provider auth | `COPILOT_GITHUB_TOKEN` → `GH_TOKEN` → `GITHUB_TOKEN` |\n| `GH_TOKEN` | Copilot fallback; GitHub API auth in web scraper | In web scraper: `GITHUB_TOKEN` → `GH_TOKEN` |\n| `GITHUB_TOKEN` | Copilot fallback; GitHub API auth in web scraper | In web scraper: checked before `GH_TOKEN` |\n\n---\n\n## 2) Provider-specific runtime configuration\n\n### Anthropic Foundry Gateway (Azure / enterprise proxy)\n\nWhen `CLAUDE_CODE_USE_FOUNDRY` is enabled, Anthropic requests switch to Foundry mode:\n\n- Base URL resolves from `FOUNDRY_BASE_URL` (fallback remains model/default base URL if unset).\n- API key resolution for provider `anthropic` becomes:\n  `ANTHROPIC_FOUNDRY_API_KEY` → `ANTHROPIC_OAUTH_TOKEN` → `ANTHROPIC_API_KEY`.\n- `ANTHROPIC_CUSTOM_HEADERS` is parsed as comma/newline-separated `key: value` pairs and merged into request headers.\n- TLS client/server material can be injected from env values:\n  `NODE_EXTRA_CA_CERTS`, `CLAUDE_CODE_CLIENT_CERT`, `CLAUDE_CODE_CLIENT_KEY`.\n  Each accepts either:\n  - a filesystem path to PEM content, or\n  - inline PEM (including escaped `\\n` sequences).\n\n| Variable | Value type | Behavior |\n|---|---|---|\n| `CLAUDE_CODE_USE_FOUNDRY` | Boolean-like string (`1`, `true`, `yes`, `on`) | Enables Foundry mode for Anthropic provider |\n| `FOUNDRY_BASE_URL` | URL string | Anthropic endpoint base URL in Foundry mode |\n| `ANTHROPIC_FOUNDRY_API_KEY` | Token string | Used for `Authorization: Bearer <token>` |\n| `ANTHROPIC_CUSTOM_HEADERS` | Header list string | Extra headers; format `header-a: value, header-b: value` or newline-separated |\n| `NODE_EXTRA_CA_CERTS` | PEM path or inline PEM | Extra CA chain for server certificate validation |\n| `CLAUDE_CODE_CLIENT_CERT` | PEM path or inline PEM | mTLS client certificate |\n| `CLAUDE_CODE_CLIENT_KEY` | PEM path or inline PEM | mTLS client private key (must be paired with cert) |\n\n### Amazon Bedrock\n\n| Variable | Default / behavior |\n|---|---|\n| `AWS_REGION` | Primary region source |\n| `AWS_DEFAULT_REGION` | Fallback if `AWS_REGION` unset |\n| `AWS_PROFILE` | Enables named profile auth path |\n| `AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY` | Enables IAM key auth path |\n| `AWS_BEARER_TOKEN_BEDROCK` | Enables bearer token auth path |\n| `AWS_CONTAINER_CREDENTIALS_RELATIVE_URI` / `AWS_CONTAINER_CREDENTIALS_FULL_URI` | Enables ECS task credential path |\n| `AWS_WEB_IDENTITY_TOKEN_FILE` + `AWS_ROLE_ARN` | Enables web identity auth path |\n| `AWS_BEDROCK_SKIP_AUTH` | If `1`, injects dummy credentials (proxy/non-auth scenarios) |\n| `AWS_BEDROCK_FORCE_HTTP1` | If `1`, forces Node HTTP/1 request handler |\n\nRegion fallback in provider code: `options.region` → `AWS_REGION` → `AWS_DEFAULT_REGION` → `us-east-1`.\n\n### Azure OpenAI Responses\n\n| Variable | Default / behavior |\n|---|---|\n| `AZURE_OPENAI_API_KEY` | Required unless API key passed as option |\n| `AZURE_OPENAI_API_VERSION` | Default `v1` |\n| `AZURE_OPENAI_BASE_URL` | Direct base URL override |\n| `AZURE_OPENAI_RESOURCE_NAME` | Used to construct base URL: `https://<resource>.openai.azure.com/openai/v1` |\n| `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` | Optional mapping string: `modelId=deploymentName,model2=deployment2` |\n\nBase URL resolution: option `azureBaseUrl` → env `AZURE_OPENAI_BASE_URL` → option/env resource name → `model.baseUrl`.\n\n### Google Vertex AI\n\n| Variable | Required? | Notes |\n|---|---|---|\n| `GOOGLE_CLOUD_PROJECT` | Yes (unless passed in options) | Fallback: `GCLOUD_PROJECT` |\n| `GCLOUD_PROJECT` | Fallback | Used as alternate project ID source |\n| `GOOGLE_CLOUD_LOCATION` | Yes (unless passed in options) | No default in provider |\n| `GOOGLE_APPLICATION_CREDENTIALS` | Conditional | If set, file must exist; otherwise ADC fallback path is checked (`~/.config/gcloud/application_default_credentials.json`) |\n\n### Kimi\n\n| Variable | Default / behavior |\n|---|---|\n| `KIMI_CODE_OAUTH_HOST` | Primary OAuth host override |\n| `KIMI_OAUTH_HOST` | Fallback OAuth host override |\n| `KIMI_CODE_BASE_URL` | Overrides Kimi usage endpoint base URL (`usage/kimi.ts`) |\n\nOAuth host chain: `KIMI_CODE_OAUTH_HOST` → `KIMI_OAUTH_HOST` → `https://auth.kimi.com`.\n\n### Antigravity/Gemini image compatibility\n\n| Variable | Default / behavior |\n|---|---|\n| `PI_AI_ANTIGRAVITY_VERSION` | Overrides Antigravity user-agent version tag in Gemini CLI provider |\n\n### OpenAI Codex responses (feature/debug controls)\n\n| Variable | Behavior |\n|---|---|\n| `PI_CODEX_DEBUG` | `1`/`true` enables Codex provider debug logging |\n| `PI_CODEX_WEBSOCKET` | `1`/`true` enables websocket transport preference |\n| `PI_CODEX_WEBSOCKET_V2` | `1`/`true` enables websocket v2 path |\n| `PI_CODEX_WEBSOCKET_IDLE_TIMEOUT_MS` | Positive integer override (default 300000) |\n| `PI_CODEX_WEBSOCKET_RETRY_BUDGET` | Non-negative integer override (default 5) |\n| `PI_CODEX_WEBSOCKET_RETRY_DELAY_MS` | Positive integer base backoff override (default 500) |\n\n### Cursor provider debug\n\n| Variable | Behavior |\n|---|---|\n| `DEBUG_CURSOR` | Enables provider debug logs; `2`/`verbose` for detailed payload snippets |\n| `DEBUG_CURSOR_LOG` | Optional file path for JSONL debug log output |\n\n### Prompt cache compatibility switch\n\n| Variable | Behavior |\n|---|---|\n| `PI_CACHE_RETENTION` | If `long`, enables long retention where supported (`anthropic`, `openai-responses`, Bedrock retention resolution) |\n\n---\n\n## 3) Web search subsystem\n\n### Search provider credentials\n\n| Variable | Used by |\n|---|---|\n| `EXA_API_KEY` | Exa search provider and Exa MCP tools |\n| `BRAVE_API_KEY` | Brave search provider |\n| `PERPLEXITY_API_KEY` | Perplexity search provider API-key mode |\n| `TAVILY_API_KEY` | Tavily search provider |\n| `ZAI_API_KEY` | z.ai search provider (also checks stored OAuth in `agent.db`) |\n| `OPENAI_API_KEY` / Codex OAuth in DB | Codex search provider availability/auth |\n\n### Anthropic web search auth chain\n\n`packages/coding-agent/src/web/search/auth.ts` resolves Anthropic web-search credentials in this order:\n\n1. `ANTHROPIC_SEARCH_API_KEY` (+ optional `ANTHROPIC_SEARCH_BASE_URL`)\n2. `models.json` provider entry with `api: \"anthropic-messages\"`\n3. Anthropic OAuth credentials from `agent.db` (must not expire within 5-minute buffer)\n4. Generic Anthropic env fallback: provider key (`ANTHROPIC_FOUNDRY_API_KEY`/`ANTHROPIC_OAUTH_TOKEN`/`ANTHROPIC_API_KEY`) + optional `ANTHROPIC_BASE_URL` (`FOUNDRY_BASE_URL` when Foundry mode is enabled)\n\nRelated vars:\n\n| Variable | Default / behavior |\n|---|---|\n| `ANTHROPIC_SEARCH_API_KEY` | Highest-priority explicit search key |\n| `ANTHROPIC_SEARCH_BASE_URL` | Defaults to `https://api.anthropic.com` when omitted |\n| `ANTHROPIC_SEARCH_MODEL` | Defaults to `claude-haiku-4-5` |\n| `ANTHROPIC_BASE_URL` | Generic fallback base URL for tier-4 auth path |\n\n### Perplexity OAuth flow behavior flag\n\n| Variable | Behavior |\n|---|---|\n| `PI_AUTH_NO_BORROW` | If set, disables macOS native-app token borrowing path in Perplexity login flow |\n\n---\n\n## 4) Python tooling and kernel runtime\n\n| Variable | Default / behavior |\n|---|---|\n| `PI_PY` | Python tool mode override: `0`/`bash`=`bash-only`, `1`/`py`=`ipy-only`, `mix`/`both`=`both`; invalid values ignored |\n| `PI_PYTHON_SKIP_CHECK` | If `1`, skips Python kernel availability checks/warm checks |\n| `PI_PYTHON_GATEWAY_URL` | If set, uses external kernel gateway instead of local shared gateway |\n| `PI_PYTHON_GATEWAY_TOKEN` | Optional auth token for external gateway (`Authorization: token <value>`) |\n| `PI_PYTHON_IPC_TRACE` | If `1`, enables low-level IPC trace path in kernel module |\n| `VIRTUAL_ENV` | Highest-priority venv path for Python runtime resolution |\n\nExtra conditional behavior:\n\n- If `BUN_ENV=test` or `NODE_ENV=test`, Python availability checks are treated as OK and warming is skipped.\n- Python env filtering denies common API keys and allows safe base vars + `LC_`, `XDG_`, `PI_` prefixes.\n\n---\n\n## 5) Agent/runtime behavior toggles\n\n| Variable | Default / behavior |\n|---|---|\n| `PI_SMOL_MODEL` | Ephemeral model-role override for `smol` (CLI `--smol` takes precedence) |\n| `PI_SLOW_MODEL` | Ephemeral model-role override for `slow` (CLI `--slow` takes precedence) |\n| `PI_PLAN_MODEL` | Ephemeral model-role override for `plan` (CLI `--plan` takes precedence) |\n| `PI_NO_TITLE` | If set (any non-empty value), disables auto session title generation on first user message |\n| `NULL_PROMPT` | If `true`, system prompt builder returns empty string |\n| `PI_BLOCKED_AGENT` | Blocks a specific subagent type in task tool |\n| `PI_SUBPROCESS_CMD` | Overrides subagent spawn command (`omp` / `omp.cmd` resolution bypass) |\n| `PI_TASK_MAX_OUTPUT_BYTES` | Max captured output bytes per subagent (default `500000`) |\n| `PI_TASK_MAX_OUTPUT_LINES` | Max captured output lines per subagent (default `5000`) |\n| `PI_TIMING` | If `1`, enables startup/tool timing instrumentation logs |\n| `PI_DEBUG_STARTUP` | Enables startup stage debug prints to stderr in multiple startup paths |\n| `PI_PACKAGE_DIR` | Overrides package asset base dir resolution (docs/examples/changelog path lookup) |\n| `PI_DISABLE_LSPMUX` | If `1`, disables lspmux detection/integration and forces direct LSP server spawning |\n| `LM_STUDIO_BASE_URL` | Default implicit LM Studio discovery base URL override (`http://127.0.0.1:1234/v1` if unset) |\n| `OLLAMA_BASE_URL` | Default implicit Ollama discovery base URL override (`http://127.0.0.1:11434` if unset) |\n| `PI_EDIT_VARIANT` | If `hashline`, forces hashline read/grep display mode when edit tool available |\n| `PI_NO_PTY` | If `1`, disables interactive PTY path for bash tool |\n\n`PI_NO_PTY` is also set internally when CLI `--no-pty` is used.\n\n---\n\n## 6) Storage and config root paths\n\nThese are consumed via `@oh-my-pi/pi-utils/dirs` and affect where coding-agent stores data.\n\n| Variable | Default / behavior |\n|---|---|\n| `PI_CONFIG_DIR` | Config root dirname under home (default `.omp`) |\n| `PI_CODING_AGENT_DIR` | Full override for agent directory (default `~/<PI_CONFIG_DIR or .omp>/agent`) |\n| `PWD` | Used when matching canonical current working directory in path helpers |\n\n---\n\n## 7) Shell/tool execution environment\n\n(From `packages/utils/src/procmgr.ts` and coding-agent bash tool integration.)\n\n| Variable | Behavior |\n|---|---|\n| `PI_BASH_NO_CI` | Suppresses automatic `CI=true` injection into spawned shell env |\n| `CLAUDE_BASH_NO_CI` | Legacy alias fallback for `PI_BASH_NO_CI` |\n| `PI_BASH_NO_LOGIN` | Intended to disable login shell mode |\n| `CLAUDE_BASH_NO_LOGIN` | Legacy alias fallback for `PI_BASH_NO_LOGIN` |\n| `PI_SHELL_PREFIX` | Optional command prefix wrapper |\n| `CLAUDE_CODE_SHELL_PREFIX` | Legacy alias fallback for `PI_SHELL_PREFIX` |\n| `VISUAL` | Preferred external editor command |\n| `EDITOR` | Fallback external editor command |\n\nCurrent implementation note: `PI_BASH_NO_LOGIN`/`CLAUDE_BASH_NO_LOGIN` are read, but current `getShellArgs()` returns `['-l','-c']` in both branches (effectively no-op today).\n\n---\n\n## 8) UI/theme/session detection (auto-detected env)\n\nThese are read as runtime signals; they are usually set by the terminal/OS rather than manually configured.\n\n| Variable | Used for |\n|---|---|\n| `COLORTERM`, `TERM`, `WT_SESSION` | Color capability detection (theme color mode) |\n| `COLORFGBG` | Terminal background light/dark auto-detection |\n| `TERM_PROGRAM`, `TERM_PROGRAM_VERSION`, `TERMINAL_EMULATOR` | Terminal identity in system prompt/context |\n| `KDE_FULL_SESSION`, `XDG_CURRENT_DESKTOP`, `DESKTOP_SESSION`, `XDG_SESSION_DESKTOP`, `GDMSESSION`, `WINDOWMANAGER` | Desktop/window-manager detection in system prompt/context |\n| `KITTY_WINDOW_ID`, `TMUX_PANE`, `TERM_SESSION_ID`, `WT_SESSION` | Stable per-terminal session breadcrumb IDs |\n| `SHELL`, `ComSpec`, `TERM_PROGRAM`, `TERM` | System info diagnostics |\n| `APPDATA`, `XDG_CONFIG_HOME` | lspmux config path resolution |\n| `HOME` | Path shortening in MCP command UI |\n\n---\n\n## 9) Native loader/debug flags\n\n| Variable | Behavior |\n|---|---|\n| `PI_DEV` | Enables verbose native addon load diagnostics in `packages/natives` |\n\n## 10) TUI runtime flags (shared package, affects coding-agent UX)\n\n| Variable | Behavior |\n|---|---|\n| `PI_NOTIFICATIONS` | `off` / `0` / `false` suppress desktop notifications |\n| `PI_TUI_WRITE_LOG` | If set, logs TUI writes to file |\n| `PI_HARDWARE_CURSOR` | If `1`, enables hardware cursor mode |\n| `PI_CLEAR_ON_SHRINK` | If `1`, clears empty rows when content shrinks |\n| `PI_DEBUG_REDRAW` | If `1`, enables redraw debug logging |\n| `PI_TUI_DEBUG` | If `1`, enables deep TUI debug dump path |\n\n---\n\n## 11) Commit generation controls\n\n| Variable | Behavior |\n|---|---|\n| `PI_COMMIT_TEST_FALLBACK` | If `true` (case-insensitive), force commit fallback generation path |\n| `PI_COMMIT_NO_FALLBACK` | If `true`, disables fallback when agent returns no proposal |\n| `PI_COMMIT_MAP_REDUCE` | If `false`, disables map-reduce commit analysis path |\n| `DEBUG` | If set, commit agent error stack traces are printed |\n\n---\n\n## Security-sensitive variables\n\nTreat these as secrets; do not log or commit them:\n\n- Provider/API keys and OAuth/bearer credentials (all `*_API_KEY`, `*_TOKEN`, OAuth access/refresh tokens)\n- Cloud credentials (`AWS_*`, `GOOGLE_APPLICATION_CREDENTIALS` path may expose service-account material)\n- Search/provider auth vars (`EXA_API_KEY`, `BRAVE_API_KEY`, `PERPLEXITY_API_KEY`, Anthropic search keys)\n- Foundry mTLS material (`CLAUDE_CODE_CLIENT_CERT`, `CLAUDE_CODE_CLIENT_KEY`, `NODE_EXTRA_CA_CERTS` when it points to private CA bundles)\n\nPython runtime also explicitly strips many common key vars before spawning kernel subprocesses (`packages/coding-agent/src/ipy/runtime.ts`).\n",
 	"extension-loading.md": "# Extension Loading (TypeScript/JavaScript Modules)\n\nThis document covers how the coding agent discovers and loads **extension modules** (`.ts`/`.js`) at startup.\n\nIt does **not** cover `gemini-extension.json` manifest extensions (documented separately).\n\n## What this subsystem does\n\nExtension loading builds a list of module entry files, imports each module with Bun, executes its factory, and returns:\n\n- loaded extension definitions\n- per-path load errors (without aborting the whole load)\n- a shared extension runtime object used later by `ExtensionRunner`\n\n## Primary implementation files\n\n- `src/extensibility/extensions/loader.ts` — path discovery + import/execution\n- `src/extensibility/extensions/index.ts` — public exports\n- `src/extensibility/extensions/runner.ts` — runtime/event execution after load\n- `src/discovery/builtin.ts` — native auto-discovery provider for extension modules\n- `src/config/settings.ts` — loads merged `extensions` / `disabledExtensions` settings\n\n---\n\n## Inputs to extension loading\n\n### 1) Auto-discovered native extension modules\n\n`discoverAndLoadExtensions()` first asks discovery providers for `extension-module` capability items, then keeps only provider `native` items.\n\nEffective native locations:\n\n- Project: `<cwd>/.omp/extensions`\n- User: `~/.omp/agent/extensions`\n\nPath roots come from the native provider (`SOURCE_PATHS.native`).\n\nNotes:\n\n- Native auto-discovery is currently `.omp` based.\n- Legacy `.pi` is still accepted in `package.json` manifest keys (`pi.extensions`), but not as a native root here.\n\n### 2) Explicitly configured paths\n\nAfter auto-discovery, configured paths are appended and resolved.\n\nConfigured path sources in the main session startup path (`sdk.ts`):\n\n1. CLI-provided paths (`--extension/-e`, and `--hook` is also treated as an extension path)\n2. Settings `extensions` array (merged global + project settings)\n\nGlobal settings file:\n\n- `~/.omp/agent/config.yml` (or custom agent dir via `PI_CODING_AGENT_DIR`)\n\nProject settings file:\n\n- `<cwd>/.omp/settings.json`\n\nExamples:\n\n```yaml\n# ~/.omp/agent/config.yml\nextensions:\n  - ~/my-exts/safety.ts\n  - ./local/ext-pack\n```\n\n```json\n{\n  \"extensions\": [\"./.omp/extensions/my-extra\"]\n}\n```\n\n---\n\n## Enable/disable controls\n\n### Disable discovery\n\n- CLI: `--no-extensions`\n- SDK option: `disableExtensionDiscovery`\n\nBehavior split:\n\n- SDK: when `disableExtensionDiscovery=true`, it still loads `additionalExtensionPaths` via `loadExtensions()`.\n- CLI path building (`main.ts`) currently clears CLI extension paths when `--no-extensions` is set, so explicit `-e/--hook` are not forwarded in that mode.\n\n### Disable specific extension modules\n\n`disabledExtensions` setting filters by extension id format:\n\n- `extension-module:<derivedName>`\n\n`derivedName` is based on entry path (`getExtensionNameFromPath`), for example:\n\n- `/x/foo.ts` -> `foo`\n- `/x/bar/index.ts` -> `bar`\n\nExample:\n\n```yaml\ndisabledExtensions:\n  - extension-module:foo\n```\n\n---\n\n## Path and entry resolution\n\n### Path normalization\n\nFor configured paths:\n\n1. Normalize unicode spaces\n2. Expand `~`\n3. If relative, resolve against current `cwd`\n\n### If configured path is a file\n\nIt is used directly as a module entry candidate.\n\n### If configured path is a directory\n\nResolution order:\n\n1. `package.json` in that directory with `omp.extensions` (or legacy `pi.extensions`) -> use declared entries\n2. `index.ts`\n3. `index.js`\n4. Otherwise scan one level for extension entries:\n   - direct `*.ts` / `*.js`\n   - subdir `index.ts` / `index.js`\n   - subdir `package.json` with `omp.extensions` / `pi.extensions`\n\nRules and constraints:\n\n- no recursive discovery beyond one subdirectory level\n- declared `extensions` manifest entries are resolved relative to that package directory\n- declared entries are included only if file exists/access is allowed\n- in `*/index.{ts,js}` pairs, TypeScript is preferred over JavaScript\n- symlinks are treated as eligible files/directories\n\n### Ignore behavior differs by source\n\n- Native auto-discovery (`discoverExtensionModulePaths` in discovery helpers) uses native glob with `gitignore: true` and `hidden: false`.\n- Explicit configured directory scanning in `loader.ts` uses `readdir` rules and does **not** apply gitignore filtering.\n\n---\n\n## Load order and precedence\n\n`discoverAndLoadExtensions()` builds one ordered list and then calls `loadExtensions()`.\n\nOrder:\n\n1. Native auto-discovered modules\n2. Explicit configured paths (in provided order)\n\nIn `sdk.ts`, configured order is:\n\n1. CLI additional paths\n2. Settings `extensions`\n\nDe-duplication:\n\n- absolute path based\n- first seen path wins\n- later duplicates are ignored\n\nImplication: if the same module path is both auto-discovered and explicitly configured, it is loaded once at the first position (auto-discovered stage).\n\n---\n\n## Module import and factory contract\n\nEach candidate path is loaded with dynamic import:\n\n- `await import(resolvedPath)`\n- factory is `module.default ?? module`\n- factory must be a function (`ExtensionFactory`)\n\nIf export is not a function, that path fails with a structured error and loading continues.\n\n---\n\n## Failure handling and isolation\n\n### During loading\n\nPer extension path, failures are captured as `{ path, error }` and do not stop other paths from loading.\n\nCommon cases:\n\n- import failure / missing file\n- invalid factory export (non-function)\n- exception thrown while executing factory\n\n### Runtime isolation model\n\n- Extensions are **not sandboxed** (same process/runtime).\n- They share one `EventBus` and one `ExtensionRuntime` instance.\n- During load, runtime action methods intentionally throw `ExtensionRuntimeNotInitializedError`; action wiring happens later in `ExtensionRunner.initialize()`.\n\n### After loading\n\nWhen events run through `ExtensionRunner`, handler exceptions are caught and emitted as extension errors instead of crashing the runner loop.\n\n---\n\n## Minimal user/project layout examples\n\n### User-level\n\n```text\n~/.omp/agent/\n  config.yml\n  extensions/\n    guardrails.ts\n    audit/\n      index.ts\n```\n\n### Project-level\n\n```text\n<repo>/\n  .omp/\n    settings.json\n    extensions/\n      checks/\n        package.json\n      lint-gates.ts\n```\n\n`checks/package.json`:\n\n```json\n{\n  \"omp\": {\n    \"extensions\": [\"./src/check-a.ts\", \"./src/check-b.js\"]\n  }\n}\n```\n\nLegacy manifest key still accepted:\n\n```json\n{\n  \"pi\": {\n    \"extensions\": [\"./index.ts\"]\n  }\n}\n```\n",
 	"extensions.md": "# Extensions\n\nPrimary guide for authoring runtime extensions in `packages/coding-agent`.\n\nThis document covers the current extension runtime in:\n\n- `src/extensibility/extensions/types.ts`\n- `src/extensibility/extensions/runner.ts`\n- `src/extensibility/extensions/wrapper.ts`\n- `src/extensibility/extensions/index.ts`\n- `src/modes/controllers/extension-ui-controller.ts`\n\nFor discovery paths and filesystem loading rules, see `docs/extension-loading.md`.\n\n## What an extension is\n\nAn extension is a TS/JS module exporting a default factory:\n\n```ts\nimport type { ExtensionAPI } from \"@oh-my-pi/pi-coding-agent\";\n\nexport default function myExtension(pi: ExtensionAPI) {\n\t// register handlers/tools/commands/renderers\n}\n```\n\nExtensions can combine all of the following in one module:\n\n- event handlers (`pi.on(...)`)\n- LLM-callable tools (`pi.registerTool(...)`)\n- slash commands (`pi.registerCommand(...)`)\n- keyboard shortcuts and flags\n- custom message rendering\n- session/message injection APIs (`sendMessage`, `sendUserMessage`, `appendEntry`)\n\n## Runtime model\n\n1. Extensions are imported and their factory functions run.\n2. During that load phase, registration methods are valid; runtime action methods are not yet initialized.\n3. `ExtensionRunner.initialize(...)` wires live actions/contexts for the active mode.\n4. Session/agent/tool lifecycle events are emitted to handlers.\n5. Every tool execution is wrapped with extension interception (`tool_call` / `tool_result`).\n\n```text\nExtension lifecycle (simplified)\n\nload paths\n   │\n   ▼\nimport module + run factory (registration only)\n   │\n   ▼\nExtensionRunner.initialize(mode/session/tool registry)\n   │\n   ├─ emit session/agent events to handlers\n   ├─ wrap tool execution (tool_call/tool_result)\n   └─ expose runtime actions (sendMessage, setActiveTools, ...)\n```\n\nImportant constraint from `loader.ts`:\n\n- calling action methods like `pi.sendMessage()` during extension load throws `ExtensionRuntimeNotInitializedError`\n- register first; perform runtime behavior from events/commands/tools\n\n## Quick start\n\n```ts\nimport type { ExtensionAPI } from \"@oh-my-pi/pi-coding-agent\";\nimport { Type } from \"@sinclair/typebox\";\n\nexport default function (pi: ExtensionAPI) {\n\tpi.setLabel(\"Safety + Utilities\");\n\n\tpi.on(\"session_start\", async (_event, ctx) => {\n\t\tctx.ui.notify(`Extension loaded in ${ctx.cwd}`, \"info\");\n\t});\n\n\tpi.on(\"tool_call\", async (event) => {\n\t\tif (event.toolName === \"bash\" && event.input.command?.includes(\"rm -rf\")) {\n\t\t\treturn { block: true, reason: \"Blocked by extension policy\" };\n\t\t}\n\t});\n\n\tpi.registerTool({\n\t\tname: \"hello_extension\",\n\t\tlabel: \"Hello Extension\",\n\t\tdescription: \"Return a greeting\",\n\t\tparameters: Type.Object({ name: Type.String() }),\n\t\tasync execute(_toolCallId, params, _signal, _onUpdate, _ctx) {\n\t\t\treturn {\n\t\t\t\tcontent: [{ type: \"text\", text: `Hello, ${params.name}` }],\n\t\t\t\tdetails: { greeted: params.name },\n\t\t\t};\n\t\t},\n\t});\n\n\tpi.registerCommand(\"hello-ext\", {\n\t\tdescription: \"Show queue state\",\n\t\thandler: async (_args, ctx) => {\n\t\t\tctx.ui.notify(`pending=${ctx.hasPendingMessages()}`, \"info\");\n\t\t},\n\t});\n}\n```\n\n## Extension API surfaces\n\n## 1) Registration and actions (`ExtensionAPI`)\n\nCore methods:\n\n- `on(event, handler)`\n- `registerTool`, `registerCommand`, `registerShortcut`, `registerFlag`\n- `registerMessageRenderer`\n- `sendMessage`, `sendUserMessage`, `appendEntry`\n- `getActiveTools`, `getAllTools`, `setActiveTools`\n- `setModel`, `getThinkingLevel`, `setThinkingLevel`\n- `registerProvider`\n- `events` (shared event bus)\n\nAlso exposed:\n\n- `pi.logger`\n- `pi.typebox`\n- `pi.pi` (package exports)\n\n### Message delivery semantics\n\n`pi.sendMessage(message, options)` supports:\n\n- `deliverAs: \"steer\"` (default) — interrupts current run\n- `deliverAs: \"followUp\"` — queued to run after current run\n- `deliverAs: \"nextTurn\"` — stored and injected on the next user prompt\n- `triggerTurn: true` — starts a turn when idle (`nextTurn` ignores this)\n\n`pi.sendUserMessage(content, { deliverAs })` always goes through prompt flow; while streaming it queues as steer/follow-up.\n\n## 2) Handler context (`ExtensionContext`)\n\nHandlers and tool `execute` receive `ctx` with:\n\n- `ui`\n- `hasUI`\n- `cwd`\n- `sessionManager` (read-only)\n- `modelRegistry`, `model`\n- `getContextUsage()`\n- `compact(...)`\n- `isIdle()`, `hasPendingMessages()`, `abort()`\n- `shutdown()`\n- `getSystemPrompt()`\n\n## 3) Command context (`ExtensionCommandContext`)\n\nCommand handlers additionally get:\n\n- `waitForIdle()`\n- `newSession(...)`\n- `switchSession(...)`\n- `branch(entryId)`\n- `navigateTree(targetId, { summarize })`\n- `reload()`\n\nUse command context for session-control flows; these methods are intentionally separated from general event handlers.\n\n## Event surface (current names and behavior)\n\nCanonical event unions and payload types are in `types.ts`.\n\n### Session lifecycle\n\n- `session_start`\n- `session_before_switch` / `session_switch`\n- `session_before_branch` / `session_branch`\n- `session_before_compact` / `session.compacting` / `session_compact`\n- `session_before_tree` / `session_tree`\n- `session_shutdown`\n\nCancelable pre-events:\n\n- `session_before_switch` → `{ cancel?: boolean }`\n- `session_before_branch` → `{ cancel?: boolean; skipConversationRestore?: boolean }`\n- `session_before_compact` → `{ cancel?: boolean; compaction?: CompactionResult }`\n- `session_before_tree` → `{ cancel?: boolean; summary?: { summary: string; details?: unknown } }`\n\n### Prompt and turn lifecycle\n\n- `input`\n- `before_agent_start`\n- `context`\n- `agent_start` / `agent_end`\n- `turn_start` / `turn_end`\n- `message_start` / `message_update` / `message_end`\n\n### Tool lifecycle\n\n- `tool_call` (pre-exec, may block)\n- `tool_result` (post-exec, may patch content/details/isError)\n- `tool_execution_start` / `tool_execution_update` / `tool_execution_end` (observability)\n\n`tool_result` is middleware-style: handlers run in extension order and each sees prior modifications.\n\n### Reliability/runtime signals\n\n- `auto_compaction_start` / `auto_compaction_end`\n- `auto_retry_start` / `auto_retry_end`\n- `ttsr_triggered`\n- `todo_reminder`\n\n### User command interception\n\n- `user_bash` (override with `{ result }`)\n- `user_python` (override with `{ result }`)\n\n### `resources_discover`\n\n`resources_discover` exists in extension types and `ExtensionRunner`.\nCurrent runtime note: `ExtensionRunner.emitResourcesDiscover(...)` is implemented, but there are no `AgentSession` callsites invoking it in the current codebase.\n\n## Tool authoring details\n\n`registerTool` uses `ToolDefinition` from `types.ts`.\n\nCurrent `execute` signature:\n\n```ts\nexecute(\n\ttoolCallId,\n\tparams,\n\tsignal,\n\tonUpdate,\n\tctx,\n): Promise<AgentToolResult>\n```\n\nTemplate:\n\n```ts\npi.registerTool({\n\tname: \"my_tool\",\n\tlabel: \"My Tool\",\n\tdescription: \"...\",\n\tparameters: Type.Object({}),\n\tasync execute(_id, _params, signal, onUpdate, ctx) {\n\t\tif (signal?.aborted) {\n\t\t\treturn { content: [{ type: \"text\", text: \"Cancelled\" }] };\n\t\t}\n\t\tonUpdate?.({ content: [{ type: \"text\", text: \"Working...\" }] });\n\t\treturn { content: [{ type: \"text\", text: \"Done\" }], details: {} };\n\t},\n\tonSession(event, ctx) {\n\t\t// reason: start|switch|branch|tree|shutdown\n\t},\n\trenderCall(args, theme) {\n\t\t// optional TUI render\n\t},\n\trenderResult(result, options, theme, args) {\n\t\t// optional TUI render\n\t},\n});\n```\n\n`tool_call`/`tool_result` intercept all tools once the registry is wrapped in `sdk.ts`, including built-ins and extension/custom tools.\n\n## UI integration points\n\n`ctx.ui` implements the `ExtensionUIContext` interface. Support differs by mode.\n\n### Interactive mode (`extension-ui-controller.ts`)\n\nSupported:\n\n- dialogs: `select`, `confirm`, `input`, `editor`\n- notifications/status/editor text/terminal input/custom overlays\n- theme listing/loading by name (`setTheme` supports string names)\n- tools expanded toggle\n\nCurrent no-op methods in this controller:\n\n- `setFooter`\n- `setHeader`\n- `setEditorComponent`\n\nAlso note: `setWidget` currently routes to status-line text via `setHookWidget(...)`.\n\n### RPC mode (`rpc-mode.ts`)\n\n`ctx.ui` is backed by RPC `extension_ui_request` events:\n\n- dialog methods (`select`, `confirm`, `input`, `editor`) round-trip to client responses\n- fire-and-forget methods emit requests (`notify`, `setStatus`, `setWidget` for string arrays, `setTitle`, `setEditorText`)\n\nUnsupported/no-op in RPC implementation:\n\n- `onTerminalInput`\n- `custom`\n- `setFooter`, `setHeader`, `setEditorComponent`\n- `setWorkingMessage`\n- theme switching/loading (`setTheme` returns failure)\n- tool expansion controls are inert\n\n### Print/headless/subagent paths\n\nWhen no UI context is supplied to runner init, `ctx.hasUI` is `false` and methods are no-op/default-returning.\n\n### Background interactive mode\n\nBackground mode installs a non-interactive UI context object. In current implementation, `ctx.hasUI` may still be `true` while interactive dialogs return defaults/no-op behavior.\n\n## Session and state patterns\n\nFor durable extension state:\n\n1. Persist with `pi.appendEntry(customType, data)`.\n2. Rebuild state from `ctx.sessionManager.getBranch()` on `session_start`, `session_branch`, `session_tree`.\n3. Keep tool result `details` structured when state should be visible/reconstructible from tool result history.\n\nExample reconstruction pattern:\n\n```ts\npi.on(\"session_start\", async (_event, ctx) => {\n\tlet latest;\n\tfor (const entry of ctx.sessionManager.getBranch()) {\n\t\tif (entry.type === \"custom\" && entry.customType === \"my-state\") {\n\t\t\tlatest = entry.data;\n\t\t}\n\t}\n\t// restore from latest\n});\n```\n\n## Rendering extension points\n\n## Custom message renderer\n\n```ts\npi.registerMessageRenderer(\"my-type\", (message, { expanded }, theme) => {\n\t// return pi-tui Component\n});\n```\n\nUsed by interactive rendering when custom messages are displayed.\n\n## Tool call/result renderer\n\nProvide `renderCall` / `renderResult` on `registerTool` definitions for custom tool visualization in TUI.\n\n## Constraints and pitfalls\n\n- Runtime actions are unavailable during extension load.\n- `tool_call` errors block execution (fail-closed).\n- Command name conflicts with built-ins are skipped with diagnostics.\n- Reserved shortcuts are ignored (`ctrl+c`, `ctrl+d`, `ctrl+z`, `ctrl+k`, `ctrl+p`, `ctrl+l`, `ctrl+o`, `ctrl+t`, `ctrl+g`, `shift+tab`, `shift+ctrl+p`, `alt+enter`, `escape`, `enter`).\n- Treat `ctx.reload()` as terminal for the current command handler frame.\n\n## Extensions vs hooks vs custom-tools\n\nUse the right surface:\n\n- **Extensions** (`src/extensibility/extensions/*`): unified system (events + tools + commands + renderers + provider registration).\n- **Hooks** (`src/extensibility/hooks/*`): separate legacy event API.\n- **Custom-tools** (`src/extensibility/custom-tools/*`): tool-focused modules; when loaded alongside extensions they are adapted and still pass through extension interception wrappers.\n\nIf you need one package that owns policy, tools, command UX, and rendering together, use extensions.\n",
 	"fs-scan-cache-architecture.md": "# Filesystem Scan Cache Architecture Contract\n\nThis document defines the current contract for the shared filesystem scan cache implemented in Rust (`crates/pi-natives/src/fs_cache.rs`) and consumed by native discovery/search APIs exposed to `packages/coding-agent`.\n\n## What this cache is\n\nThe cache stores full directory-scan entry lists (`GlobMatch[]`) keyed by scan scope and traversal policy, then lets higher-level operations (glob filtering, fuzzy scoring, grep file selection) run against those cached entries.\n\nPrimary goals:\n- avoid repeated filesystem walks for repeated discovery/search calls\n- keep consistency across `glob`, `fuzzyFind`, and `grep` when they share the same scan policy\n- allow explicit staleness recovery for empty results and explicit invalidation after file mutations\n\n## Ownership and public surface\n\n- Cache implementation and policy: `crates/pi-natives/src/fs_cache.rs`\n- Native consumers:\n  - `crates/pi-natives/src/glob.rs`\n  - `crates/pi-natives/src/fd.rs` (`fuzzyFind`)\n  - `crates/pi-natives/src/grep.rs`\n- JS binding/export:\n  - `packages/natives/src/glob/index.ts` (`invalidateFsScanCache`)\n  - `packages/natives/src/glob/types.ts`\n  - `packages/natives/src/grep/types.ts`\n- Coding-agent mutation invalidation helpers:\n  - `packages/coding-agent/src/tools/fs-cache-invalidation.ts`\n\n## Cache key partitioning (hard contract)\n\nEach entry is keyed by:\n- canonicalized `root` directory path\n- `include_hidden` boolean\n- `use_gitignore` boolean\n\nImplications:\n- Hidden and non-hidden scans do **not** share entries.\n- Gitignore-respecting and ignore-disabled scans do **not** share entries.\n- Consumers must pass stable semantics for hidden/gitignore behavior; changing either flag creates a different cache partition.\n\n`node_modules` inclusion is **not** in the cache key. The cache stores entries with `node_modules` included; per-consumer filtering is applied after retrieval.\n\n## Scan collection behavior\n\nCache population uses a deterministic walker (`ignore::WalkBuilder`) configured by `include_hidden` and `use_gitignore`:\n- `follow_links(false)`\n- sorted by file path\n- `.git` is always skipped\n- `node_modules` is always collected at cache-scan time (and optionally filtered later)\n- entry file type + `mtime` are captured via `symlink_metadata`\n\nSearch roots are resolved by `resolve_search_path`:\n- relative paths are resolved against current cwd\n- target must be an existing directory\n- root is canonicalized when possible\n\n## Freshness and eviction policy\n\nGlobal policy (environment-overridable):\n- `FS_SCAN_CACHE_TTL_MS` (default `1000`)\n- `FS_SCAN_EMPTY_RECHECK_MS` (default `200`)\n- `FS_SCAN_CACHE_MAX_ENTRIES` (default `16`)\n\nBehavior:\n- `get_or_scan(...)`\n  - if TTL is `0`: bypass cache entirely, always fresh scan (`cache_age_ms = 0`)\n  - on cache hit within TTL: return cached entries + non-zero `cache_age_ms`\n  - on expired hit: evict key, rescan, store fresh entry\n- max entry enforcement is oldest-first eviction by `created_at`\n\n## Empty-result fast recheck (separate from normal hits)\n\nNormal cache hit:\n- a cache hit inside TTL returns cached entries and does nothing else.\n\nEmpty-result fast recheck:\n- this is a **caller-side** policy using `ScanResult.cache_age_ms`\n- if filtered/query result is empty and cached scan age is at least `empty_recheck_ms()`, caller performs one `force_rescan(...)` and retries\n- intended to reduce stale-negative results when files were recently added but cache is still within TTL\n\nCurrent consumers:\n- `glob`: rechecks when filtered matches are empty and scan age exceeds threshold\n- `fuzzyFind` (`fd.rs`): rechecks only when query is non-empty and scored matches are empty\n- `grep`: rechecks when selected candidate file list is empty\n\n## Consumer defaults and cache usage\n\nCache is opt-in on all exposed APIs (`cache?: boolean`, default `false`).\n\nCurrent defaults in native APIs:\n- `glob`: `hidden=false`, `gitignore=true`, `cache=false`\n- `fuzzyFind`: `hidden=false`, `gitignore=true`, `cache=false`\n- `grep`: `hidden=true`, `cache=false`, and cache scan always uses `use_gitignore=true`\n\nCoding-agent callers today:\n- High-volume mention candidate discovery enables cache:\n  - `packages/coding-agent/src/utils/file-mentions.ts`\n  - profile: `hidden=true`, `gitignore=true`, `includeNodeModules=true`, `cache=true`\n- Tool-level `grep` integration currently disables scan cache (`cache: false`):\n  - `packages/coding-agent/src/tools/grep.ts`\n\n## Invalidation contract\n\nNative invalidation entrypoint:\n- `invalidateFsScanCache(path?: string)`\n  - with `path`: remove cache entries whose root is a prefix of target path\n  - without path: clear all scan cache entries\n\nPath handling details:\n- relative invalidation paths are resolved against cwd\n- invalidation attempts canonicalization\n- if target does not exist (e.g., delete), fallback canonicalizes parent and reattaches filename when possible\n- this preserves invalidation behavior for create/delete/rename where one side may not exist\n\n## Coding-agent mutation flow responsibilities\n\nCoding-agent code must invalidate after successful filesystem mutations.\n\nCentral helpers:\n- `invalidateFsScanAfterWrite(path)`\n- `invalidateFsScanAfterDelete(path)`\n- `invalidateFsScanAfterRename(oldPath, newPath)` (invalidates both sides when paths differ)\n\nCurrent mutation tool callsites:\n- `packages/coding-agent/src/tools/write.ts`\n- `packages/coding-agent/src/patch/index.ts` (hashline/patch/replace flows)\n\nRule: if a flow mutates filesystem content or location and bypasses these helpers, cache staleness bugs are expected.\n\n## Adding a new cache consumer safely\n\nWhen introducing cache use in a new scanner/search path:\n\n1. **Use stable scan policy inputs**\n   - decide hidden/gitignore semantics first\n   - pass them consistently to `get_or_scan`/`force_rescan` so cache partitions are intentional\n\n2. **Treat cache data as pre-filtered only by traversal policy**\n   - apply tool-specific filtering (glob patterns, type filters, node_modules rules) after retrieval\n   - never assume cached entries already reflect your higher-level filters\n\n3. **Implement empty-result fast recheck only for stale-negative risk**\n   - use `scan.cache_age_ms >= empty_recheck_ms()`\n   - retry once with `force_rescan(..., store=true, ...)`\n   - keep this path separate from normal cache-hit logic\n\n4. **Respect no-cache mode explicitly**\n   - when caller disables cache, call `force_rescan(..., store=false, ...)`\n   - do not populate shared cache in a no-cache request path\n\n5. **Wire mutation invalidation for any new write path**\n   - after successful write/edit/delete/rename, call the coding-agent invalidation helper\n   - for rename/move, invalidate both old and new paths\n\n6. **Do not add per-call TTL knobs**\n   - current contract is global policy only (env-configured), no per-request TTL override\n\n## Known boundaries\n\n- Cache scope is process-local in-memory (`DashMap`), not persisted across process restarts.\n- Cache stores scan entries, not final tool results.\n- `glob`/`fuzzyFind`/`grep` share scan entries only when key dimensions (`root`, `hidden`, `gitignore`) match.\n- `.git` is always excluded at scan collection time regardless of caller options.\n",

package/src/modes/components/agent-dashboard.ts

@@ -20,6 +20,7 @@ import type { AgentMessage } from "@oh-my-pi/pi-agent-core";
 import {
 	type Component,
 	Container,
+	extractPrintableText,
 	Input,
 	matchesKey,
 	padding,
@@ -998,8 +999,6 @@ export class AgentDashboard extends Container {
 	}
 
 	handleInput(data: string): void {
-		const charCode = data.length === 1 ? data.charCodeAt(0) : -1;
-
 		if (matchesKey(data, "ctrl+c")) {
 			this.onClose?.();
 			return;
@@ -1117,13 +1116,17 @@ export class AgentDashboard extends Container {
 			return;
 		}
 
-		if (data.length === 1 && charCode > 32 && charCode < 127) {
-			if (data === "j" || data === "k") {
-				return;
+		const printableText = extractPrintableText(data);
+		if (printableText && printableText.length === 1) {
+			const printableCharCode = printableText.charCodeAt(0);
+			if (printableCharCode > 32 && printableCharCode < 127) {
+				if (printableText === "j" || printableText === "k") {
+					return;
+				}
+				this.#searchQuery += printableText;
+				this.#applyFilters();
+				this.#buildLayout();
 			}
-			this.#searchQuery += data;
-			this.#applyFilters();
-			this.#buildLayout();
 		}
 	}
 }

package/src/modes/components/extensions/extension-list.ts

@@ -5,7 +5,14 @@
  * that toggles the entire provider. All items below are dimmed when the
  * master switch is off.
  */
-import { type Component, matchesKey, padding, truncateToWidth, visibleWidth } from "@oh-my-pi/pi-tui";
+import {
+	type Component,
+	extractPrintableText,
+	matchesKey,
+	padding,
+	truncateToWidth,
+	visibleWidth,
+} from "@oh-my-pi/pi-tui";
 import { isProviderEnabled } from "../../../discovery";
 import { theme } from "../../../modes/theme/theme";
 import { applyFilter } from "./state-manager";
@@ -392,8 +399,6 @@ export class ExtensionList implements Component {
 	}
 
 	handleInput(data: string): void {
-		const charCode = data.length === 1 ? data.charCodeAt(0) : -1;
-
 		// Navigation
 		if (matchesKey(data, "up") || data === "k") {
 			this.#moveSelectionUp();
@@ -447,13 +452,16 @@ export class ExtensionList implements Component {
 		}
 
 		// Printable characters -> search
-		if (data.length === 1 && charCode > 32 && charCode < 127) {
-			// Skip j/k as they're navigation
-			if (data === "j" || data === "k") {
+		const printableText = extractPrintableText(data);
+		if (printableText && printableText.length === 1) {
+			const printableCharCode = printableText.charCodeAt(0);
+			if (printableCharCode > 32 && printableCharCode < 127) {
+				if (printableText === "j" || printableText === "k") {
+					return;
+				}
+				this.setSearchQuery(this.#searchQuery + printableText);
 				return;
 			}
-			this.setSearchQuery(this.#searchQuery + data);
-			return;
 		}
 	}
 

package/src/modes/components/settings-defs.ts

@@ -224,8 +224,7 @@ const OPTION_PROVIDERS: Partial<Record<SettingPath, OptionProvider>> = {
 		{
 			value: "auto",
 			label: "Auto",
-			description:
-				"Priority: Perplexity > Exa > Brave > Jina > Kimi > Anthropic > Gemini > Codex > Z.AI > Synthetic",
+			description: "Preferred web-search provider",
 		},
 		{ value: "exa", label: "Exa", description: "Requires EXA_API_KEY" },
 		{ value: "brave", label: "Brave", description: "Requires BRAVE_API_KEY" },
@@ -234,6 +233,7 @@ const OPTION_PROVIDERS: Partial<Record<SettingPath, OptionProvider>> = {
 		{ value: "perplexity", label: "Perplexity", description: "Requires PERPLEXITY_COOKIES or PERPLEXITY_API_KEY" },
 		{ value: "anthropic", label: "Anthropic", description: "Uses Anthropic web search" },
 		{ value: "zai", label: "Z.AI", description: "Calls Z.AI webSearchPrime MCP" },
+		{ value: "tavily", label: "Tavily", description: "Requires TAVILY_API_KEY" },
 		{ value: "kagi", label: "Kagi", description: "Requires KAGI_API_KEY and Kagi Search API beta access" },
 		{ value: "synthetic", label: "Synthetic", description: "Requires SYNTHETIC_API_KEY" },
 	],