@oh-my-pi/pi-coding-agent 15.5.15 → 15.6.0

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

@@ -1,6 +1,6 @@
 // Auto-generated by scripts/generate-docs-index.ts - DO NOT EDIT
 
-export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.md","ai-schema-normalize.md","approval-mode.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","compaction.md","config-usage.md","custom-tools.md","environment-variables.md","extension-loading.md","extensions.md","fs-scan-cache-architecture.md","gemini-manifest-extensions.md","handoff-generation-pipeline.md","hooks.md","install-id.md","keybindings.md","lsp-config.md","marketplace.md","mcp-config.md","mcp-protocol-transports.md","mcp-runtime-lifecycle.md","mcp-server-tool-authoring.md","memory.md","models.md","natives-addon-loader-runtime.md","natives-architecture.md","natives-binding-contract.md","natives-build-release-debugging.md","natives-media-system-utils.md","natives-rust-task-cancellation.md","natives-shell-pty-process.md","natives-text-search-pipeline.md","non-compaction-retry-policy.md","notebook-tool-runtime.md","plugin-manager-installer-plumbing.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","python-repl.md","render-mermaid.md","resolve-tool-runtime.md","rpc.md","rulebook-matching-pipeline.md","sdk.md","secrets.md","session-operations-export-share-fork-resume.md","session-switching-and-recent-listing.md","session-tree-plan.md","session.md","skills.md","skills/authoring-extensions.md","skills/authoring-hooks.md","skills/authoring-marketplaces.md","skills/examples/hello-extension/README.md","skills/examples/mini-marketplace/README.md","skills/examples/safety-hook/README.md","slash-command-internals.md","task-agent-discovery.md","theme.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/checkpoint.md","tools/debug.md","tools/edit.md","tools/eval.md","tools/find.md","tools/github.md","tools/inspect_image.md","tools/irc.md","tools/job.md","tools/lsp.md","tools/read.md","tools/recall.md","tools/recipe.md","tools/reflect.md","tools/render_mermaid.md","tools/resolve.md","tools/retain.md","tools/rewind.md","tools/search.md","tools/search_tool_bm25.md","tools/ssh.md","tools/task.md","tools/todo_write.md","tools/web_search.md","tools/write.md","tree.md","ttsr-injection-lifecycle.md","tui-runtime-internals.md","tui.md"];
+export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.md","ai-schema-normalize.md","approval-mode.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","compaction.md","config-usage.md","custom-tools.md","environment-variables.md","extension-loading.md","extensions.md","fs-scan-cache-architecture.md","gemini-manifest-extensions.md","handoff-generation-pipeline.md","hooks.md","install-id.md","keybindings.md","local-models.md","lsp-config.md","marketplace.md","mcp-config.md","mcp-protocol-transports.md","mcp-runtime-lifecycle.md","mcp-server-tool-authoring.md","memory.md","mnemosyne-memory-backend.md","models.md","natives-addon-loader-runtime.md","natives-architecture.md","natives-binding-contract.md","natives-build-release-debugging.md","natives-media-system-utils.md","natives-rust-task-cancellation.md","natives-shell-pty-process.md","natives-text-search-pipeline.md","non-compaction-retry-policy.md","notebook-tool-runtime.md","plugin-manager-installer-plumbing.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","python-repl.md","render-mermaid.md","resolve-tool-runtime.md","rpc.md","rulebook-matching-pipeline.md","sdk.md","secrets.md","session-operations-export-share-fork-resume.md","session-switching-and-recent-listing.md","session-tree-plan.md","session.md","skills.md","skills/authoring-extensions.md","skills/authoring-hooks.md","skills/authoring-marketplaces.md","skills/examples/hello-extension/README.md","skills/examples/mini-marketplace/README.md","skills/examples/safety-hook/README.md","slash-command-internals.md","task-agent-discovery.md","theme.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/checkpoint.md","tools/debug.md","tools/edit.md","tools/eval.md","tools/find.md","tools/github.md","tools/inspect_image.md","tools/irc.md","tools/job.md","tools/lsp.md","tools/read.md","tools/recall.md","tools/recipe.md","tools/reflect.md","tools/render_mermaid.md","tools/resolve.md","tools/retain.md","tools/rewind.md","tools/search.md","tools/search_tool_bm25.md","tools/ssh.md","tools/task.md","tools/todo_write.md","tools/web_search.md","tools/write.md","tree.md","ttsr-injection-lifecycle.md","tui-runtime-internals.md","tui.md"];
 
 export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"ERRATA-GPT5-HARMONY.md": "# ERRATA — GPT-5 Harmony-Header Leakage\n\n## 1. The problem\n\nOpenAI frames tool calls in the Harmony chat protocol:\n\n```\n<|start|>assistant<|channel|>commentary to=functions.<NAME><|message|>{ARGS}<|call|>\n```\n\n`<|channel|>commentary to=functions.NAME` is the **routing header** —\ncontrol tokens consumed by the runtime to dispatch the call. These\ntokens never appear as content under normal operation; the runtime\nstrips them.\n\nThe defect: gpt-5 models occasionally emit, **as ordinary content\ninside `{ARGS}`**, the **plain-text shadow** of these routing tokens —\nthe same characters without the `<|…|>` brackets — and continue\nproducing more pseudo-routing structure (channel name, body marker,\nmultilingual spam, fake tool-result framing). The contamination lives\ninside the visible tool argument and is dispatched to the tool as if it\nwere intended content.\n\n**Critical detail.** The actual `<|start|>` / `<|channel|>` /\n`<|message|>` / `<|call|>` special tokens almost never appear in tool\nargs. What leaks is the bracket-less spelling — `analysis to=functions.X\ncode …` — because OpenAI applies a logit mask suppressing the\ncontrol-token IDs inside the args region. The mass that would have gone\nto those special tokens redistributes onto the un-bracketed plain-text\nrepresentation the model also learned. This makes the leak structurally\ninvisible to the routing parser and lands it in the tool input verbatim.\n\nManifestation in tool args (real corpus example):\n\n```\n~      add_function(iso, ctx, ns, \"installSystemChangeObserver\",\n        os_install_system_change_observer);】【\"】【analysis to=functions.edit\n        code above เงินไทยฟรีuser to=functions.edit code …\n```\n\nThe leading code is real and intended. Everything after the first\nnon-Latin token through the next clean structural boundary is corruption.\n\n---\n\n## 2. Observed statistics & failure modes\n\nSource: `~/.omp/stats.db` (`ss_tool_calls`, `ss_assistant_msgs`), through\n2026-05-10. 1.05M tool calls scanned.\n\n### 2.1 Rate\n\n| Model            | Leaks in tool args | Calls   | per million |\n|------------------|-------------------:|--------:|------------:|\n| gpt-5.4          | 37                 | 226,957 | 163         |\n| gpt-5.3-codex    | 17                 | 112,243 | 151         |\n| gpt-5.5          | 2                  |  80,750 |  25         |\n| gpt-5.2-codex    | 0                  |    —    |   —         |\n\nPlus 15 hits in assistant visible text / thinking blobs.\n\n### 2.2 Tool distribution\n\n| Tool                | Hits |\n|---------------------|-----:|\n| `edit`              | 38   |\n| `eval`              | 11   |\n| `report_tool_issue` | 3    |\n| `grep`/`read`/`search`/`yield` | 1 each |\n\nConcentrated in tools with free-form (non-JSON-schema) argument formats.\n\n### 2.3 Leak shape (deterministic)\n\n```\nLEAK         ::= JUNK_PREFIX MARKER CHANNEL_BODY (LEAK)?\nMARKER       ::= \"to=functions.\" TOOL_NAME\nCHANNEL_BODY ::= \" code \" (SPAM | reasoning_prose | fake_tool_output)*\nJUNK_PREFIX  ::= (GLITCH_TOKEN | CHANNEL_WORD | NON_LATIN_RUN | \"}\" | \"】【\")+\n```\n\n**Cascading is common.** Of 96 marker occurrences across 71 contaminated\nrecords, 39 contain ≥2 markers and 7 contain ≥3 — the model emits\nmultiple fake `to=functions.X code …` blocks back-to-back, often with\nfake `code_output\\nCell N:\\n…` framing between them. Once the\nplain-text scaffolding is in the residual stream, the prefix now *looks\nlike* a fresh tool envelope start, so the macro prior over continuations\nkeeps voting for more scaffolding. Self-amplifying.\n\n### 2.4 Glitch tokens\n\nSingle-token identifiers in `o200k_base` whose embeddings appear to be\nnear-init from underrepresentation in post-training. ASCII residue\nimmediately before the marker in the natural corpus:\n\n| Surface string    | Single-token | Token ID | Hits in corpus |\n|-------------------|:-:|---------:|---:|\n| `Japgolly`        | ✅ | 199,745 | 1 |\n| `Jsii`            | ✅ | 114,318 | (subtoken of `Jsii_commentary`) |\n| `Jsii_commentary` | — (3 toks) | — | 2 |\n| `changedFiles`    | — (2 toks) | — | 8 |\n| `RTLU`            | — (2 toks) | — | 3 |\n\n`Japgolly` is in the last 0.13% of the vocabulary — the same family of\nGitHub-corpus residue that produced `SolidGoldMagikarp` in the 2023\nGPT-2 vocabulary (Rumbelow & Watkins). `SolidGoldMagikarp` itself\ntokenizes to 5 tokens in `o200k_base` — that specific token was retired,\nbut the class wasn't.\n\nFor the multi-token entries, the corpus-level signature is the surface\nstring; the underlying glitch trigger is a sub-token (e.g. `Jsii` inside\n`Jsii_commentary`). The detector list (`G` signal) keys on the surface\nstrings.\n\nStable across unrelated sessions. Treated as a high-precision detector\nsignal.\n\n### 2.5 Channel-word leakage\n\n`analysis` (5), `assistant` (5), `commentary` (3), `user` (1) appear\ndirectly preceding `to=`. Always bare words; never `<|channel|>analysis`\nor any other bracketed form. Consistent with §1 — the brackets are\nmasked, the words are not.\n\n### 2.6 Non-Latin spam residue\n\n96 marker hits, by script: CJK 40, Cyrillic 12, Telugu/Kannada/Malayalam\n18, Thai 8, Georgian 7, Armenian 7, Arabic 1. Recurring fragments are\nChinese gambling SEO (`大发时时彩`, `天天中彩票`), Georgian/Abkhaz junk,\nand Thai casino spam — well-known low-quality crawl residue.\n\nThis is the same script distribution observed in the controlled\nreproduction (§7.3), independent of the prompt's natural language.\n\n### 2.7 Failure-mode breakdown for the `edit` tool\n\nThe `edit` tool exists in two variants in the corpus:\n\n| Variant                  | Calls | Recovery |\n|--------------------------|------:|----------|\n| Patch-DSL (`§PATH`/anchor/`«»≔` ops) | 27 | **Recoverable** by op-truncation (§3.3) |\n| JSON-schema (`{path,edits:[…]}`)      | 11 | **Not recoverable** — contamination is escaped *inside* JSON strings, parser accepts it cleanly, content would be written verbatim into source files |\n\nFor Patch-DSL leaks specifically:\n\n- 20/27 cases: contamination on the last input line; nothing follows.\n- 7/27 cases: contamination mid-input; what follows is one of: a\n  duplicate replay of an earlier file/anchor, intended content for a\n  *different* tool call (the model started its next call inline), or\n  pure hallucination. Post-contamination content is never trustworthy.\n\n### 2.8 Mechanism (confirmed)\n\n**Prior collapse from null-embedding glitch tokens, into a\ncontrol-token-masked basin whose mass redistributes onto the\nplain-text shadow of the Harmony protocol.**\n\nStep by step:\n\n1. The model is mid-`{ARGS}` of a Harmony tool call. The runtime applies\n   a logit mask suppressing structural control tokens (`<|channel|>`,\n   `<|message|>`, `<|call|>`, `<|start|>`, `<|end|>`) inside the args\n   region. Without this mask, normal generation would constantly\n   hallucinate envelope-closes; with it, those token IDs have logit\n   `-∞` in args.\n2. A glitch token `g` is sampled. By construction `g` was in the BPE\n   merge corpus but barely in LM/RL training, so its **input embedding\n   `e_g` ≈ near-init noise of small norm**.\n3. At position t+1, the residual update `h_{t+1} ≈ LN(h_t + e_g + Attn +\n   MLP)` is dominated by the prefix-derived terms; the just-emitted-token\n   signal is effectively absent. Generation diversity normally comes\n   from `e_x` steering the residual into different sub-regions —\n   stripped here.\n4. The next-token distribution therefore collapses onto the **conditional\n   prior over continuations of the prefix, with local conditioning\n   removed**. In a tool-calling rollout context, that prior is sharply\n   peaked on Harmony scaffolding (control tokens + routing tokens) —\n   that's what RL trained.\n5. The mask zeros the control-token IDs. Mass redistributes onto the\n   **next-best continuation**: the un-bracketed surface-form spelling of\n   the same protocol (`analysis`, `commentary`, ` to=functions.X`,\n   ` code `). This spelling is unmasked because those characters are\n   ordinary tokens.\n6. Once a few tokens of plain-text scaffolding land in the residual\n   stream, the prefix now resembles a fresh envelope start. The macro\n   prior keeps voting for more scaffolding. Cascading (§2.3) follows.\n7. Multilingual spam after the marker is the same prior-collapse\n   continuation, drawn from the training neighborhood of the glitch\n   token (often ESL/auto-generated multilingual web junk — exactly the\n   crawl residue in §2.6).\n\n**Two corollaries the corpus data demanded but only the experiment\nexplained:**\n\n- **The brackets never appear** (§1, §2.5). The mask is what makes the\n  leak land in plain text instead of as a real envelope-close.\n- **Counterintuitive grammar dependency** (§7.4). The leak is *worse* in\n  formats closest to OpenAI's training distribution. Off-distribution\n  custom grammars dampen the macro-prior basin; the official\n  `*** Begin Patch` format is the strongest collapse target.\n\nThe 2023 SolidGoldMagikarp paper documented mechanism (1)+(2)+(4). The\nnew piece is (5): when constrained decoding masks the natural collapse\ntarget, the mass laundered through the un-masked plain-text shadow\nbecomes a structurally-invisible exfiltration channel.",
@@ -21,6 +21,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"hooks.md": "# Hooks\n\nThis document describes the **current hook subsystem code** in `src/extensibility/hooks/*`.\n\n## Current status in runtime\n\nThe hook package (`src/extensibility/hooks/`) is still exported and usable as an API surface, but the default CLI runtime now initializes the **extension runner** path. In current startup flow:\n\n- `--hook` is treated as an alias for `--extension` (CLI paths are merged into `additionalExtensionPaths`)\n- tools are wrapped by `ExtensionToolWrapper`, not `HookToolWrapper`\n- context transforms and lifecycle emissions go through `ExtensionRunner`\n\nSo this file documents the hook subsystem implementation itself (types/loader/runner/wrapper), including legacy behavior and constraints.\n\n## Key files\n\n- `src/extensibility/hooks/types.ts` — hook context, event types, and result contracts\n- `src/extensibility/hooks/loader.ts` — module loading and hook discovery bridge\n- `src/extensibility/hooks/runner.ts` — event dispatch, command lookup, error signaling\n- `src/extensibility/hooks/tool-wrapper.ts` — pre/post tool interception wrapper\n- `src/extensibility/hooks/index.ts` — exports/re-exports\n\n## What a hook module is\n\nA hook module must default-export a factory:\n\n```ts\nimport type { HookAPI } from \"@oh-my-pi/pi-coding-agent/extensibility/hooks\";\n\nexport default function hook(pi: HookAPI): void {\n  pi.on(\"tool_call\", async (event, ctx) => {\n    if (\n      event.toolName === \"bash\" &&\n      String(event.input.command ?? \"\").includes(\"rm -rf\")\n    ) {\n      return { block: true, reason: \"blocked by policy\" };\n    }\n  });\n}\n```\n\nThe factory can:\n\n- register event handlers with `pi.on(...)`\n- send persistent custom messages with `pi.sendMessage(...)`\n- persist non-LLM state with `pi.appendEntry(...)`\n- register slash commands via `pi.registerCommand(...)`\n- register custom message renderers via `pi.registerMessageRenderer(...)`\n- run shell commands via `pi.exec(...)`\n\n## Discovery and loading\n\n`discoverAndLoadHooks(configuredPaths, cwd)` does:\n\n1. Load discovered hooks from capability registry (`loadCapability(\"hooks\")`)\n2. Append explicitly configured paths (deduped by absolute path)\n3. Call `loadHooks(allPaths, cwd)`\n\n`loadHooks` then imports each path and expects a `default` function.\n\n### Path resolution\n\n`loader.ts` resolves hook paths as:\n\n- absolute path: used as-is\n- `~` path: expanded\n- relative path: resolved against `cwd`\n\n### Important legacy mismatch\n\nDiscovery providers for `hookCapability` still model pre/post shell-style hook files (for example `.claude/hooks/pre/*`, `.omp/.../hooks/pre/*`).\n\nThe hook loader here uses dynamic module import and requires a default JS/TS hook factory. If a discovered hook path is not importable as a module, load fails and is reported in `LoadHooksResult.errors`.\n\n## Event surfaces\n\nHook events are strongly typed in `types.ts`.\n\n### Session events\n\n- `session_start`\n- `session_before_switch` → can return `{ cancel?: boolean }`\n- `session_switch`\n- `session_before_branch` → can return `{ cancel?: boolean; skipConversationRestore?: boolean }`\n- `session_branch`\n- `session_before_compact` → can return `{ cancel?: boolean; compaction?: CompactionResult }`\n- `session.compacting` → can return `{ context?: string[]; prompt?: string; preserveData?: Record<string, unknown> }`\n- `session_compact`\n- `session_before_tree` → can return `{ cancel?: boolean; summary?: { summary: string; details?: unknown } }`\n- `session_tree`\n- `session_shutdown`\n\n### Agent/context events\n\n- `context` → can return `{ messages?: Message[] }`\n- `before_agent_start` → can return `{ message?: { customType; content; display; details } }`\n- `agent_start`\n- `agent_end`\n- `turn_start`\n- `turn_end`\n- `auto_compaction_start`\n- `auto_compaction_end`\n- `auto_retry_start`\n- `auto_retry_end`\n- `ttsr_triggered`\n- `todo_reminder`\n\n### Tool events (pre/post model)\n\n- `tool_call` (pre-execution) → can return `{ block?: boolean; reason?: string }`\n- `tool_result` (post-execution) → can return `{ content?; details?; isError? }`\n\nThis is the hook subsystem’s core pre/post interception model.\n\n```text\nHook tool interception flow\n\ntool_call handlers\n   │\n   ├─ any { block: true }? ── yes ──> throw (tool blocked)\n   │\n   └─ no\n      │\n      ▼\n   execute underlying tool\n      │\n      ├─ success ──> tool_result handlers can override { content, details }\n      │\n      └─ error   ──> emit tool_result(isError=true) then rethrow original error\n```\n\n## Execution model and mutation semantics\n\n### 1) Pre-execution: `tool_call`\n\n`HookToolWrapper.execute()` emits `tool_call` before tool execution.\n\n- if any handler returns `{ block: true }`, execution stops\n- if handler throws, wrapper fails closed and blocks execution\n- returned `reason` becomes the thrown error text\n\n### 2) Tool execution\n\nUnderlying tool executes normally if not blocked.\n\n### 3) Post-execution: `tool_result`\n\nAfter success, wrapper emits `tool_result` with:\n\n- `toolName`, `toolCallId`, `input`\n- `content`\n- `details`\n- `isError: false`\n\nIf handler returns overrides:\n\n- `content` can replace result content\n- `details` can replace result details\n\nOn tool failure, wrapper emits `tool_result` with `isError: true` and error text content, then rethrows original error.\n\n### What hooks can mutate\n\n- LLM context for a single call via `context` (`messages` replacement chain)\n- tool output content/details on successful tool calls (`tool_result` path)\n- pre-agent injected message via `before_agent_start`\n- cancellation/custom compaction/tree behavior via `session_before_*` and `session.compacting`\n\n### What hooks cannot mutate in this implementation\n\n- raw tool input parameters in-place (only block/allow on `tool_call`)\n- execution continuation after thrown tool errors (error path rethrows)\n- final success/error status in wrapper behavior (returned `isError` is typed but not applied by `HookToolWrapper`)\n\n## Ordering and conflict behavior\n\n### Discovery-level ordering\n\nCapability providers are priority-sorted (higher first). Dedupe is by capability key, first wins.\n\nFor `hooks`, capability key is `${type}:${tool}:${name}`. Shadowed duplicates from lower-priority providers are marked and excluded from effective discovered list.\n\n### Load order\n\n`discoverAndLoadHooks` builds a flat `allPaths` list, deduped by resolved absolute path, then `loadHooks` iterates in that order.\nFile order within each discovered directory depends on `readdir` output; the hook loader does not perform an additional sort.\n\n### Runtime handler order\n\nInside `HookRunner`, order is deterministic by registration sequence:\n\n1. hooks array order\n2. handler registration order per hook/event\n\nConflict behavior by event type:\n\n- `tool_call`: last returned result wins unless a handler blocks; first block short-circuits\n- `tool_result`: last returned override wins (no short-circuit)\n- `context`: chained; each handler receives prior handler’s message output\n- `before_agent_start`: first returned message is kept; later messages ignored\n- `session_before_*`: latest returned result is tracked; `cancel: true` short-circuits immediately\n- `session.compacting`: latest returned result wins\n\nCommand/renderer conflicts:\n\n- `getCommand(name)` returns first match across hooks (first loaded wins)\n- `getMessageRenderer(customType)` returns first match\n- `getRegisteredCommands()` returns all commands (no dedupe)\n\n## UI interactions (`HookContext.ui`)\n\n`HookUIContext` includes:\n\n- `select`, `confirm`, `input`, `editor`\n- `notify`\n- `setStatus`\n- `custom`\n- `setEditorText`, `getEditorText`\n- `theme` getter\n\n`ctx.hasUI` indicates whether interactive UI is available.\n\nWhen running with no UI, the default no-op context behavior is:\n\n- `select/input/editor` return `undefined`\n- `confirm` returns `false`\n- `notify`, `setStatus`, `setEditorText` are no-ops\n- `getEditorText` returns `\"\"`\n\n### Status line behavior\n\nHook status text set via `ctx.ui.setStatus(key, text)` is:\n\n- stored per key\n- sorted by key name\n- sanitized (`\\r`, `\\n`, `\\t` → spaces; repeated spaces collapsed)\n- joined and width-truncated for display\n\n## Error propagation and fallback\n\n### Load-time\n\n- invalid module or missing default export → captured in `LoadHooksResult.errors`\n- loading continues for other hooks\n\n### Event-time\n\n`HookRunner.emit(...)` catches handler errors for most events and emits `HookError` to listeners (`hookPath`, `event`, `error`), then continues.\n\n`emitToolCall(...)` is stricter: handler errors are not swallowed there; they propagate to caller. In `HookToolWrapper`, this blocks the tool call (fail-safe).\n\n## Realistic API examples\n\n### Block unsafe bash commands\n\n```ts\nimport type { HookAPI } from \"@oh-my-pi/pi-coding-agent/extensibility/hooks\";\n\nexport default function (pi: HookAPI): void {\n  pi.on(\"tool_call\", async (event, ctx) => {\n    if (event.toolName !== \"bash\") return;\n    const cmd = String(event.input.command ?? \"\");\n    if (!cmd.includes(\"rm -rf\")) return;\n\n    if (!ctx.hasUI) return { block: true, reason: \"rm -rf blocked (no UI)\" };\n    const ok = await ctx.ui.confirm(\"Dangerous command\", `Allow: ${cmd}`);\n    if (!ok) return { block: true, reason: \"user denied command\" };\n  });\n}\n```\n\n### Redact tool output on post-execution\n\n```ts\nimport type { HookAPI } from \"@oh-my-pi/pi-coding-agent/extensibility/hooks\";\n\nexport default function (pi: HookAPI): void {\n  pi.on(\"tool_result\", async (event) => {\n    if (event.toolName !== \"read\" || event.isError) return;\n\n    const redacted = event.content.map((chunk) => {\n      if (chunk.type !== \"text\") return chunk;\n      return {\n        ...chunk,\n        text: chunk.text.replaceAll(/API_KEY=\\S+/g, \"API_KEY=[REDACTED]\"),\n      };\n    });\n\n    return { content: redacted };\n  });\n}\n```\n\n### Modify model context per LLM call\n\n```ts\nimport type { HookAPI } from \"@oh-my-pi/pi-coding-agent/extensibility/hooks\";\n\nexport default function (pi: HookAPI): void {\n  pi.on(\"context\", async (event) => {\n    const filtered = event.messages.filter(\n      (msg) => !(msg.role === \"custom\" && msg.customType === \"debug-only\"),\n    );\n    return { messages: filtered };\n  });\n}\n```\n\n### Register slash command with command-safe context methods\n\n```ts\nimport type { HookAPI } from \"@oh-my-pi/pi-coding-agent/extensibility/hooks\";\n\nexport default function (pi: HookAPI): void {\n  pi.registerCommand(\"handoff\", {\n    description: \"Create a new session with setup message\",\n    handler: async (_args, ctx) => {\n      await ctx.waitForIdle();\n      await ctx.newSession({\n        parentSession: ctx.sessionManager.getSessionFile(),\n        setup: async (sm) => {\n          sm.appendMessage({\n            role: \"user\",\n            content: [\n              { type: \"text\", text: \"Continue from prior session summary.\" },\n            ],\n            timestamp: Date.now(),\n          });\n        },\n      });\n    },\n  });\n}\n```\n\n## Export surface\n\n`src/extensibility/hooks/index.ts` and the package subpath `@oh-my-pi/pi-coding-agent/extensibility/hooks` export:\n\n- loading APIs (`discoverAndLoadHooks`, `loadHooks`)\n- runner and wrapper (`HookRunner`, `HookToolWrapper`)\n- all hook types\n- `execCommand` re-export\n\nThe package root (`@oh-my-pi/pi-coding-agent`) does not re-export `HookAPI`; import legacy hook types from the hooks subpath.\n",
 	"install-id.md": "# Install ID\n\nA persistent per-install UUID that identifies a single oh-my-pi installation across sessions. Used as a stable correlation key for server-side dedup of telemetry-style pushes (currently the auto-QA grievance flush from `report_tool_issue`).\n\n## API\n\nExported from `@oh-my-pi/pi-utils` (`packages/utils/src/dirs.ts`):\n\n| Symbol | Purpose |\n| --- | --- |\n| `getInstallId(): string` | Returns the install ID, generating and persisting one on first call. Result is cached in-process for the lifetime of the runtime. |\n| `__resetInstallIdCacheForTests(): void` | Clears the in-process cache. Test-only — MUST NOT be called from production code. |\n\nThe returned value is a canonical lowercase RFC 4122 UUID matching `^[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}$`.\n\n## Storage\n\n- Path: `<config-root>/install-id` — i.e. `~/.omp/install-id` by default, respecting `PI_CONFIG_DIR` via `getConfigRootDir()`.\n- Format: a single UUID line (trailing `\\n`).\n- Permissions: file is created with mode `0o600`.\n- Lifecycle: independent of `~/.omp/agent/`. Wiping agent state (sessions, settings, DB) does NOT regenerate the install ID; only deleting the `install-id` file itself does.\n\n## Generation and lifecycle\n\n1. First call to `getInstallId()` reads the file. If contents parse as a valid UUID, that value is cached and returned.\n2. Otherwise the helper calls `crypto.randomUUID()` (Node's CSPRNG-backed UUID v4) to mint a new ID.\n3. The new value is written via `open(O_WRONLY | O_CREAT | O_EXCL, 0o600)`. The exclusive-create guard means two processes hitting first-call simultaneously cannot both succeed — the loser sees `EEXIST`, re-reads the winner's file, and adopts that ID.\n4. If the existing file contained non-empty garbage (failed UUID regex), it is `unlink`ed before the exclusive create so `O_EXCL` does not trip on stale data.\n5. Any other write failure (read-only FS, permission error) is swallowed: the freshly generated UUID is still cached in-memory so the rest of the process sees a stable value, and subsequent process launches will retry persistence.\n6. Subsequent in-process calls return the cached value without touching disk. Mutating the file on disk after the first call has no effect until the process restarts (or tests call `__resetInstallIdCacheForTests`).\n\n## Consumers\n\n- `packages/coding-agent/src/tools/report-tool-issue.ts` — included as `installId` in the auto-QA grievance push body so the backend can deduplicate repeated reports from the same install. See `dev.autoqaPush.*` settings and `PI_AUTO_QA_PUSH_*` env vars.\n\nNew consumers MUST treat the value as opaque and MUST NOT derive PII from it; the helper does not mix in hostname, username, or any other host-identifying entropy.\n\n## See also\n\n- [environment-variables.md](environment-variables.md) — `PI_CONFIG_DIR` controls where `install-id` lives.\n- [config-usage.md](config-usage.md) — broader config-root layout.\n",
 	"keybindings.md": "# Keybindings\n\nRun `/hotkeys` inside an `omp` session to see the active chords for your current build. The list reflects any remaps loaded from disk and any bindings added by extensions.\n\n## Customize keybindings\n\nUser remaps live in `~/.omp/agent/keybindings.json`. The file is a JSON object whose keys are keybinding action IDs and whose values are either one chord string or an array of chord strings. It is not read from `~/.omp/agent/config.yml`, and there is no nested `keybindings` object.\n\n```json\n{\n  \"app.model.cycleForward\": \"Ctrl+P\",\n  \"app.model.selectTemporary\": \"Alt+P\",\n  \"app.plan.toggle\": \"Alt+Shift+P\"\n}\n```\n\nChord names are case-insensitive and use the same notation shown in the UI, such as `Ctrl+P`, `Alt+Shift+P`, `Shift+Enter`, and `Ctrl+Backspace`.\n\nSet an action to an empty array to disable it:\n\n```json\n{\n  \"app.stt.toggle\": []\n}\n```\n\n## Common action IDs\n\n| Action ID | Default | Meaning |\n| --- | --- | --- |\n| `app.model.cycleForward` | `Ctrl+P` | Cycle role models forward |\n| `app.model.cycleBackward` | `Shift+Ctrl+P` | Cycle role models backward |\n| `app.model.selectTemporary` | `Alt+P` | Pick a model temporarily for this session |\n| `app.model.select` | `Ctrl+L` | Open the model selector and set roles |\n| `app.plan.toggle` | `Alt+Shift+P` | Toggle plan mode |\n| `app.history.search` | `Ctrl+R` | Search prompt history |\n| `app.tools.expand` | `Ctrl+O` | Toggle tool-output expansion |\n| `app.thinking.toggle` | `Ctrl+T` | Toggle thinking-block visibility |\n| `app.thinking.cycle` | `Shift+Tab` | Cycle thinking level |\n| `app.editor.external` | `Ctrl+G` | Edit the draft in `$VISUAL` / `$EDITOR` |\n| `app.message.followUp` | `Ctrl+Enter` | Queue a follow-up message |\n| `app.message.dequeue` | `Alt+Up` | Dequeue a queued message back into the editor |\n| `app.clipboard.copyLine` | `Alt+Shift+L` | Copy the current line |\n| `app.clipboard.copyPrompt` | `Alt+Shift+C` | Copy the whole prompt |\n| `app.stt.toggle` | `Alt+H` | Toggle speech-to-text recording |\n\nOlder unqualified action names are migrated when `keybindings.json` is loaded, but new docs and new configs should use the namespaced action IDs above.\n",
+	"local-models.md": "# Embedded Local Tiny-Model Experiments\n\nThis document summarizes the experiments behind the optional **local** tiny-model paths for two\ncoding-agent tasks: session-title generation (`providers.tinyModel`) and Mnemosyne memory\nextraction/consolidation (`providers.memoryModel`). It is a factual engineering record for\nmaintainers: what we measured, which recipes won, and which models we shipped. Both settings\ndefault to `online`, so existing users incur no downloads or CPU cost unless they opt in.\n\n## Runtime / environment findings\n\n- **Stack**: `@huggingface/transformers` (transformers.js) v4 running under Bun. In Bun the library\n  loads the **native `onnxruntime-node` backend** (not the WASM build). Available device options are\n  `cpu` / `coreml` / `webgpu` — there is **no `wasm` device** in the node build.\n- **Device verdict: use `device:\"cpu\"`.** CPU is the only reliable path.\n  - `coreml` EP is **broken for decoder LLMs**: it rejects the dynamic KV-cache `past_key_values`\n    zero-element first-token shape.\n  - `webgpu` runs but is **slower and numerically divergent** (worse output quality).\n- **Quantization: q4 is the sweet spot** — smaller on disk, faster to load, and fast at inference.\n  q8/int8 loads slower *and* infers slower on CPU.\n- **Load-time correction (important).** An earlier belief that \"q4 >=1B models take minutes to load\"\n  was a **measurement artifact** caused by running ~5 multi-GB HuggingFace downloads in parallel\n  (I/O saturation). Clean, isolated **warm** loads are all sub-3s:\n  - TinyLlama-1.1B q4: ~0.5s\n  - Llama-3.2-1B q4: ~2.8s (`graphOpt=all`) / ~0.5s (`disabled`)\n  - LFM2-1.2B q4: ~0.36s\n  - Qwen2.5-1.5B q4: ~1.5s\n  - Qwen3-1.7B q4: ~1.6s\n  - gemma-3-1b q4: ~1.1s\n  - Conclusion: **1B–1.7B models are viable on CPU.**\n- **`session_options.graphOptimizationLevel`** trades load vs inference speed: `disabled` = fastest\n  load, slightly slower inference; `all` = default.\n- **First run** downloads weights from the HF Hub to a cache dir (q4 weights ~200MB–1.1GB depending\n  on model); subsequent **warm** loads are sub-second to ~3s. Inference is async and\n  background-friendly for memory tasks; titles are semi-interactive.\n\n## Task 1: Session title generation (`providers.tinyModel`)\n\n**Task**: turn the first user message into a 3–6 word title. Tiny models (sub-1B) suffice.\n\n**Winning recipe**:\n\n- Plain system prompt (no few-shot).\n- **Prefill** the assistant turn with `<title>` and **stop at `</title>`**, then take the first line.\n- Greedy decoding (`do_sample:false`), `enable_thinking:false` in the chat template.\n\n**What we learned**:\n\n- **Few-shot examples HURT sub-0.6B models** for titles; the tag-prefill rescues even 270M models.\n- **Token biasing (`bad_words_ids`) is a confirmed no-op** here — the prefill already controls the\n  opener.\n\n**Leaderboard** (tag trick, CPU, warm):\n\n| Model | Verdict |\n| --- | --- |\n| LFM2-350M | Best speed/quality balance (~212MB) |\n| Qwen3-0.6B | Most robust |\n| gemma-3-270m | Smallest viable |\n| Qwen2.5-0.5B | Acceptable |\n| SmolLM2-135M | Too small |\n| flan-t5-small | Rejected — just echoes the input |\n\n**Shipped local options**: `lfm2-350m`, `qwen3-0.6b`, `gemma-270m`, `qwen2.5-0.5b`, `lfm2-700m`.\n**Default**: `online` (pi/smol).\n\n## Task 2: Mnemosyne memory (`providers.memoryModel`)\n\nMnemosyne runs two small-LLM tasks:\n\n1. **Extraction** — pull durable, structured items from a single message.\n2. **Consolidation** — summarize a list of memories into 1–3 faithful sentences.\n\nThese need **bigger models than titles: 1B–1.7B**. We tested LFM2-1.2B, Qwen2.5-1.5B, Qwen3-1.7B,\nand gemma-3-1b (q4, CPU) via four parallel agents each running 27–31 experiments.\n\n### Extraction findings\n\nThe stock 5-category JSON prompt fails on small models in two ways:\n\n1. The all-empty example `{\"facts\":[],...}` gets **copied verbatim** → 0 facts extracted.\n2. Capable models emit **JSON objects inside arrays**, which Mnemosyne's `String(item)` coerces into\n   the literal string `[object Object]`.\n\nThe robust fix is a **one-item-per-line output format** (consumed by Mnemosyne's parser line-fallback)\nor a **flat JSON array of strings**. Every model also over-extracts pure small talk; an explicit\nchit-chat → NONE example is the best mitigation.\n\n### Technique polarity flips vs titles\n\n- At 1B+, **few-shot is the dominant quality lever**: e.g. Qwen2.5-1.5B extraction F1 0.52 → 0.83\n  going 1 → 3 shots; gemma recall 0.65 → 0.92 with 2 shots.\n- **Prefill HURTS extraction** — it forces output on small talk, producing false positives.\n- **System-split** (instructions in the system role) helps models that have a system role.\n- **Greedy >= temperature** for both tasks.\n- **Token biasing** is again a no-op.\n\n### Per-model verdicts (head-to-head, 16-fixture set)\n\n- **Qwen3-1.7B** — most disciplined extraction: returns empty on small talk, no buried-fact leak,\n  preserves language, clean flat JSON. Weaknesses: coarse granularity, missed a multi-turn value\n  update.\n- **Qwen2.5-1.5B** — best extraction granularity (atomic facts), caught the value update, zero\n  small-talk leakage. Weaknesses: weakest consolidation (run-on, no dedup) and one degenerate\n  buried-fact output.\n- **gemma-3-1b** — best consolidation (dedup works, faithful, clean single-memory). Weaknesses: leaks\n  small talk and translated German.\n- **LFM2-1.2B** — solid and fastest to load. Weaknesses: `Label: value` noise, small-talk + buried\n  leaks, a fluffy single-memory summary.\n\n### Recommendation\n\nExtraction favors **precision** (do not pollute long-term memory) → **Qwen3-1.7B is the best single\npick** (its consolidation is good enough). If running a second model for consolidation, **gemma-3-1b**\nwins that task.\n\n**Shipped local options**: `qwen3-1.7b` (recommended), `gemma-3-1b`, `qwen2.5-1.5b`, `lfm2-1.2b`.\n**Default**: `online` (the configured smol model).\n\n### Known Mnemosyne parser bugs (surfaced by these experiments)\n\n- `String(item)` produces `[object Object]` on object array items.\n- The line-fallback drops items `<=10` chars, so a correct short fact like `Name: Can` is discarded.\n\n## Integration notes\n\n- Both settings default to `online`, so existing users get **no downloads or CPU cost** unless they\n  opt in.\n- Local inference runs **in a worker** (off the main thread); models are cached on disk and\n  downloaded on first use.\n- The memory local path applies the refined recipes (line-format + small-talk-guarded extraction\n  prompt, hardened consolidation prompt) via Mnemosyne prompt overrides; the **online path is\n  unchanged**.\n",
 	"lsp-config.md": "# LSP configuration in OMP\n\nThis guide explains how to configure language servers for the OMP coding agent.\n\nSource of truth in code:\n\n- Server config type: `packages/coding-agent/src/lsp/types.ts` (`ServerConfig`)\n- Config loader: `packages/coding-agent/src/lsp/config.ts`\n- Built-in server definitions: `packages/coding-agent/src/lsp/defaults.json`\n\n## Auto-detection\n\nWhen no LSP config file is present, OMP auto-detects servers by intersecting two conditions:\n\n1. The project directory contains at least one of the server's `rootMarkers`.\n2. The server binary is available — checked in project-local bin directories first (e.g., `node_modules/.bin/`, `.venv/bin/`), then `$PATH`.\n\nNo configuration is required for common setups. The built-in server list covers most popular languages; see [`defaults.json`](../packages/coding-agent/src/lsp/defaults.json) for the full set.\n\n## Config file locations\n\nOMP merges LSP config from multiple files, lowest to highest priority:\n\n| Priority | Location |\n|----------|----------|\n| 5 (lowest) | `~/lsp.json`, `~/.lsp.json`, `~/lsp.yaml`, `~/.lsp.yaml` |\n| 4 | Plugin LSP configs (marketplace / `--plugin-dir` roots) |\n| 3 | `~/.omp/agent/lsp.json`, `~/.omp/agent/lsp.yaml`, `~/.claude/lsp.*` |\n| 2 | `<project>/.omp/lsp.json`, `<project>/.omp/lsp.yaml`, `<project>/.claude/lsp.*` |\n| 1 (highest) | `<project>/lsp.json`, `<project>/.lsp.json`, `<project>/lsp.yaml` |\n\nEach location accepts both `.json` and `.yaml` / `.yml` variants, as well as hidden-file versions (`.lsp.json`, `.lsp.yaml`). Files are merged in order: higher-priority files override lower-priority fields for the same server. Servers not mentioned in any override file remain at their built-in defaults.\n\n**Recommended locations:**\n\n- User-wide preferences → `~/.omp/agent/lsp.json`\n- Project-specific overrides → `<project>/.omp/lsp.json`\n\n> **Note:** The presence of any LSP config file disables auto-detection. When at least one file is found, OMP skips the binary-scan phase and loads all servers that have matching `rootMarkers`, an available binary, and are not explicitly `disabled`.\n\n## File shape\n\nBoth JSON and YAML are accepted. The top-level object can use either a `servers` wrapper key or a flat map directly:\n\n```json\n{\n  \"servers\": {\n    \"server-name\": { ... }\n  },\n  \"idleTimeoutMs\": 300000\n}\n```\n\nor (flat, without the `servers` wrapper):\n\n```json\n{\n  \"server-name\": { ... },\n  \"idleTimeoutMs\": 300000\n}\n```\n\nTop-level keys:\n\n- `servers` — map of server name to `ServerConfig` (optional wrapper; flat form is equivalent)\n- `idleTimeoutMs` — shut down idle language servers after this many milliseconds; disabled by default\n\n## ServerConfig fields\n\n| Field | Type | Required | Description |\n|-------|------|----------|-------------|\n| `command` | `string` | yes | Binary name (resolved via PATH/local bins) or absolute path |\n| `args` | `string[]` | no | Arguments passed to the binary |\n| `fileTypes` | `string[]` | yes | File extensions this server handles, e.g. `[\".ts\", \".tsx\"]` |\n| `rootMarkers` | `string[]` | yes | Files/dirs that indicate a project root; glob patterns (e.g. `*.cabal`) are supported |\n| `initOptions` | `object` | no | Sent as `initializationOptions` during LSP handshake |\n| `settings` | `object` | no | Workspace settings pushed via `workspace/didChangeConfiguration` |\n| `disabled` | `boolean` | no | Set to `true` to disable this server entirely |\n| `warmupTimeoutMs` | `number` | no | Startup timeout in ms for this server (overrides the global default) |\n| `isLinter` | `boolean` | no | Mark server as linter/formatter only; excluded from type-intelligence operations (hover, go-to-definition, etc.) |\n| `capabilities` | `object` | no | Opt-in server-specific features; see [Capabilities](#capabilities) |\n\n`resolvedCommand` is populated automatically at runtime — do not set it manually.\n\n### Capabilities\n\nThe `capabilities` object enables optional server-specific features that OMP supports on a per-server basis:\n\n```json\n{\n  \"capabilities\": {\n    \"flycheck\": true,\n    \"ssr\": true,\n    \"expandMacro\": true,\n    \"runnables\": true,\n    \"relatedTests\": true\n  }\n}\n```\n\nAll fields are boolean and optional. They are currently used by `rust-analyzer`.\n\n## Common recipes\n\n### Override a built-in server's settings\n\nPartial overrides are merged onto the built-in defaults. You only need to specify the fields you want to change.\n\n```json\n{\n  \"servers\": {\n    \"typescript-language-server\": {\n      \"args\": [\"--stdio\", \"--log-level\", \"4\"]\n    }\n  }\n}\n```\n\n```yaml\nservers:\n  gopls:\n    settings:\n      gopls:\n        gofumpt: false\n        staticcheck: false\n```\n\n### Disable a built-in server\n\n```json\n{\n  \"servers\": {\n    \"eslint\": {\n      \"disabled\": true\n    }\n  }\n}\n```\n\n### Register a custom server\n\nNew servers require `command`, `fileTypes`, and `rootMarkers`. All other fields are optional.\n\n```json\n{\n  \"servers\": {\n    \"my-lsp\": {\n      \"command\": \"my-lsp-server\",\n      \"args\": [\"--stdio\"],\n      \"fileTypes\": [\".xyz\"],\n      \"rootMarkers\": [\".xyz-project\", \".git\"]\n    }\n  }\n}\n```\n\n### Set a global idle timeout\n\nShut down language servers that have been inactive for more than five minutes:\n\n```json\n{\n  \"idleTimeoutMs\": 300000\n}\n```\n\n### Disable a server for one project, keep it globally\n\nPlace the override in `<project>/.omp/lsp.json`:\n\n```json\n{\n  \"servers\": {\n    \"pylsp\": {\n      \"disabled\": true\n    }\n  }\n}\n```\n\nThe user-level config in `~/.omp/agent/lsp.json` is unaffected; pylsp is only suppressed in this project.\n\n## Built-in server list\n\nThe following servers ship in `defaults.json` and are eligible for auto-detection:\n\n| Server key | Language(s) | Binary |\n|---|---|---|\n| `rust-analyzer` | Rust | `rust-analyzer` |\n| `clangd` | C, C++, ObjC | `clangd` |\n| `zls` | Zig | `zls` |\n| `gopls` | Go | `gopls` |\n| `typescript-language-server` | TypeScript, JavaScript | `typescript-language-server` |\n| `denols` | TypeScript, JavaScript (Deno) | `deno` |\n| `biome` | TS/JS/JSON (linter) | `biome` |\n| `eslint` | TS/JS/Vue/Svelte (linter) | `vscode-eslint-language-server` |\n| `vscode-html-language-server` | HTML | `vscode-html-language-server` |\n| `vscode-css-language-server` | CSS, SCSS, Less | `vscode-css-language-server` |\n| `vscode-json-language-server` | JSON | `vscode-json-language-server` |\n| `tailwindcss` | HTML, CSS, TS/JS | `tailwindcss-language-server` |\n| `svelte` | Svelte | `svelteserver` |\n| `vue-language-server` | Vue | `vue-language-server` |\n| `astro` | Astro | `astro-ls` |\n| `pyright` | Python | `pyright-langserver` |\n| `basedpyright` | Python | `basedpyright-langserver` |\n| `pylsp` | Python | `pylsp` |\n| `ruff` | Python (linter) | `ruff` |\n| `jdtls` | Java | `jdtls` |\n| `kotlin-lsp` | Kotlin | `kotlin-lsp` |\n| `metals` | Scala | `metals` |\n| `hls` | Haskell | `haskell-language-server-wrapper` |\n| `ocamllsp` | OCaml | `ocamllsp` |\n| `elixirls` | Elixir | `elixir-ls` |\n| `erlangls` | Erlang | `erlang_ls` |\n| `gleam` | Gleam | `gleam` |\n| `solargraph` | Ruby | `solargraph` |\n| `ruby-lsp` | Ruby | `ruby-lsp` |\n| `rubocop` | Ruby (linter) | `rubocop` |\n| `bashls` | Bash, Zsh | `bash-language-server` |\n| `lua-language-server` | Lua | `lua-language-server` |\n| `intelephense` | PHP | `intelephense` |\n| `phpactor` | PHP | `phpactor` |\n| `omnisharp` | C# | `omnisharp` |\n| `yamlls` | YAML | `yaml-language-server` |\n| `terraformls` | Terraform | `terraform-ls` |\n| `dockerls` | Dockerfile | `docker-langserver` |\n| `helm-ls` | Helm | `helm_ls` |\n| `nixd` | Nix | `nixd` |\n| `nil` | Nix | `nil` |\n| `ols` | Odin | `ols` |\n| `dartls` | Dart | `dart` |\n| `marksman` | Markdown | `marksman` |\n| `texlab` | LaTeX | `texlab` |\n| `graphql` | GraphQL | `graphql-lsp` |\n| `prismals` | Prisma | `prisma-language-server` |\n| `vimls` | Vim script | `vim-language-server` |\n| `emmet-language-server` | HTML, CSS, JSX | `emmet-language-server` |\n| `sourcekit-lsp` | Swift | `sourcekit-lsp` |\n| `swiftlint` | Swift (linter) | `swiftlint` |\n| `tlaplus` | TLA+ | `tlapm_lsp` |\n",
 	"marketplace.md": "# Marketplace plugin system\n\nThe marketplace system lets you discover, install, and manage plugins from Git-hosted catalogs. It is compatible with the Claude Code plugin registry format.\n\n## Quick start\n\n```\n/marketplace add anthropics/claude-plugins-official\n/marketplace install wordpress.com@claude-plugins-official\n```\n\nOr just type `/marketplace` with no arguments to open the interactive plugin browser.\n\n## Concepts\n\nA **marketplace** is a Git repository (or local directory) containing a catalog file at `.claude-plugin/marketplace.json`. The catalog lists available plugins with their sources, descriptions, and metadata.\n\nA **plugin** is a directory containing skills, commands, hooks, MCP servers, or LSP servers. Plugins are identified by `name@marketplace` (e.g. `code-review@claude-plugins-official`).\n\n**Scopes**: plugins can be installed at two scopes:\n\n- **user** (default) -- available in all projects, stored in `~/.omp/plugins/installed_plugins.json`\n- **project** -- available only in the current project, stored in `.omp/plugins/installed_plugins.json`\n\nProject-scoped installs shadow user-scoped installs of the same plugin.\n\n## Commands\n\n### Interactive mode\n\n| Command        | Effect                                    |\n| -------------- | ----------------------------------------- |\n| `/marketplace` | Open interactive plugin browser (install) |\n\n### Marketplace management\n\n| Command                      | Effect                                       |\n| ---------------------------- | -------------------------------------------- |\n| `/marketplace add <source>`  | Add a marketplace source                     |\n| `/marketplace remove <name>` | Remove a marketplace                         |\n| `/marketplace update [name]` | Re-fetch catalog(s); omit name to update all |\n| `/marketplace list`          | List configured marketplaces                 |\n\n### Plugin operations\n\n| Command                                                                   | Effect                             |\n| ------------------------------------------------------------------------- | ---------------------------------- |\n| `/marketplace discover [marketplace]`                                     | Browse available plugins           |\n| `/marketplace install [--force] [--scope user\\|project] name@marketplace` | Install a plugin                   |\n| `/marketplace uninstall [--scope user\\|project] name@marketplace`         | Uninstall a plugin                 |\n| `/marketplace installed`                                                  | List installed marketplace plugins |\n| `/marketplace upgrade [--scope user\\|project] [name@marketplace]`         | Upgrade one or all plugins         |\n\n### CLI equivalents\n\nThe same operations are available from the command line:\n\n```\nomp plugin marketplace add <source>\nomp plugin marketplace remove <name>\nomp plugin marketplace update [name]\nomp plugin marketplace list\nomp plugin discover [marketplace]\nomp plugin install [--force] [--scope user|project] name@marketplace\nomp plugin uninstall [--scope user|project] name@marketplace\nomp plugin upgrade [--scope user|project] [name@marketplace]\n```\n\n## Marketplace sources\n\nWhen you run `/marketplace add <source>`, the system classifies the source:\n\n| Source format                   | Type               | Example                                |\n| ------------------------------- | ------------------ | -------------------------------------- |\n| `owner/repo`                    | GitHub shorthand   | `anthropics/claude-plugins-official`   |\n| `https://...*.json`             | Direct catalog URL | `https://example.com/marketplace.json` |\n| `https://...*.git` or `git@...` | Git repository     | `https://github.com/org/repo.git`      |\n| `./path` or `~/path` or `/path` | Local directory    | `./my-marketplace`                     |\n\nThe system clones the repository (or reads the local directory), locates `.claude-plugin/marketplace.json`, validates it, and caches the catalog locally.\n\n## Catalog format (marketplace.json)\n\nA marketplace catalog lives at `.claude-plugin/marketplace.json` in the repository root:\n\n```json\n{\n  \"$schema\": \"https://anthropic.com/claude-code/marketplace.schema.json\",\n  \"name\": \"my-marketplace\",\n  \"owner\": {\n    \"name\": \"Your Name\",\n    \"email\": \"you@example.com\"\n  },\n  \"description\": \"A collection of plugins\",\n  \"plugins\": [\n    {\n      \"name\": \"my-plugin\",\n      \"description\": \"What this plugin does\",\n      \"source\": \"./plugins/my-plugin\",\n      \"category\": \"development\",\n      \"homepage\": \"https://github.com/you/my-plugin\"\n    }\n  ]\n}\n```\n\n### Required fields\n\n| Field        | Description                                                                                                      |\n| ------------ | ---------------------------------------------------------------------------------------------------------------- |\n| `name`       | Marketplace name. Lowercase alphanumeric, hyphens, and dots. Must start and end with alphanumeric. Max 64 chars. |\n| `owner.name` | Marketplace owner name                                                                                           |\n| `plugins`    | Array of plugin entries                                                                                          |\n\n### Plugin entry fields\n\n| Field         | Required | Description                                                      |\n| ------------- | -------- | ---------------------------------------------------------------- |\n| `name`        | yes      | Plugin name (same rules as marketplace name)                     |\n| `source`      | yes      | Where to find the plugin (see below)                             |\n| `description` | no       | Short description                                                |\n| `version`     | no       | Version string                                                   |\n| `author`      | no       | `{ name, email? }`                                               |\n| `homepage`    | no       | URL                                                              |\n| `category`    | no       | Category string (e.g. `development`, `productivity`, `security`) |\n| `tags`        | no       | Array of string tags                                             |\n| `strict`      | no       | Boolean                                                          |\n| `commands`    | no       | Slash commands provided                                          |\n| `agents`      | no       | Agents provided                                                  |\n| `hooks`       | no       | Hook definitions                                                 |\n| `mcpServers`  | no       | MCP server definitions                                           |\n| `lspServers`  | no       | LSP server definitions                                           |\n\n### Plugin source formats\n\nThe `source` field supports several formats:\n\n**Relative path** (within the marketplace repo):\n\n```json\n\"source\": \"./plugins/my-plugin\"\n```\n\n**Git repository URL**:\n\n```json\n\"source\": {\n  \"source\": \"url\",\n  \"url\": \"https://github.com/org/repo.git\",\n  \"sha\": \"abc123...\"\n}\n```\n\n**GitHub shorthand**:\n\n```json\n\"source\": {\n  \"source\": \"github\",\n  \"repo\": \"org/repo\",\n  \"ref\": \"main\",\n  \"sha\": \"abc123...\"\n}\n```\n\n**Git subdirectory** (monorepo):\n\n```json\n\"source\": {\n  \"source\": \"git-subdir\",\n  \"url\": \"https://github.com/org/monorepo.git\",\n  \"path\": \"plugins/my-plugin\",\n  \"ref\": \"main\",\n  \"sha\": \"abc123...\"\n}\n```\n\n**npm package**:\n\n```json\n\"source\": {\n  \"source\": \"npm\",\n  \"package\": \"@scope/my-plugin\",\n  \"version\": \"1.0.0\"\n}\n```\n\n## On-disk layout\n\n```\n~/.omp/\n  marketplaces.json              # Registry of added marketplaces\n  plugins/\n    installed_plugins.json       # User-scoped installed plugins\n    cache/\n      marketplaces/              # Cached marketplace catalogs\n      plugins/                   # Cached plugin directories\n\n<project>/.omp/\n  plugins/\n    installed_plugins.json       # Project-scoped installed plugins\n```\n\n## Naming rules\n\nMarketplace and plugin names must:\n\n- Start and end with a lowercase letter or digit\n- Contain only lowercase letters, digits, hyphens, and dots\n- Be at most 64 characters\n\nPlugin IDs (`name@marketplace`) must be at most 128 characters total.\n\nValid examples: `my-plugin`, `code-review`, `wordpress.com`, `ai-firstify`\nInvalid examples: `-bad`, `bad-`, `.bad`, `Bad`, `under_score`\n",
 	"mcp-config.md": "# MCP configuration in OMP\n\nThis guide explains how to add, edit, and validate MCP servers for the OMP coding agent.\n\nSource of truth in code:\n\n- Runtime config types: `packages/coding-agent/src/mcp/types.ts`\n- Config writer: `packages/coding-agent/src/mcp/config-writer.ts`\n- Loader + validation: `packages/coding-agent/src/mcp/config.ts`\n- Standalone `mcp.json` discovery: `packages/coding-agent/src/discovery/mcp-json.ts`\n- Schema: `packages/coding-agent/src/config/mcp-schema.json`\n\n## Preferred config locations\n\nOMP can discover MCP servers from multiple tools (`.claude/`, `.cursor/`, `.vscode/`, `opencode.json`, and more), but for OMP-native configuration you should usually use one of these files:\n\n- Project: `.omp/mcp.json`\n- User: `~/.omp/agent/mcp.json`\n\nOMP also accepts fallback standalone files in the project root:\n\n- `mcp.json`\n- `.mcp.json`\n\nUse `.omp/mcp.json` or `~/.omp/agent/mcp.json` when you want OMP to own the configuration. Use root `mcp.json` / `.mcp.json` only when you want a portable fallback file that other MCP clients may also read.\n\n## Add a schema reference\n\nAdd this line at the top of the file for editor autocomplete and validation:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {}\n}\n```\n\nOMP now writes this automatically when `/mcp add`, `/mcp enable`, `/mcp disable`, `/mcp reauth`, or other config-writing flows create or update an OMP-managed MCP file.\n\n## File shape\n\nOMP supports this top-level structure:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"server-name\": {\n      \"type\": \"stdio\",\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"some-mcp-server\"]\n    }\n  },\n  \"disabledServers\": [\"server-name\"]\n}\n```\n\nTop-level keys:\n\n- `$schema` — optional JSON Schema URL for tooling\n- `mcpServers` — map of server name to server config\n- `disabledServers` — user-level denylist used to turn off discovered servers by name; runtime loading reads this list from `~/.omp/agent/mcp.json`\n\nServer names must match `^[a-zA-Z0-9_.-]{1,100}$`.\n\n## Supported server fields\n\nShared fields for every transport:\n\n- `enabled?: boolean` — skip this server when `false`\n- `timeout?: number` — MCP request timeout in milliseconds; `0` disables client-side MCP timeouts\n- `auth?: { ... }` — auth metadata used by OMP for OAuth/API-key flows\n- `oauth?: { ... }` — explicit OAuth client settings used during auth/reauth\n\nSet `OMP_MCP_TIMEOUT_MS=0` to disable the client-side timeout for every MCP server in the current process. Set it to a positive millisecond value, such as `OMP_MCP_TIMEOUT_MS=120000`, to apply one global timeout without editing each server entry.\n\n### `stdio` transport\n\n`stdio` is the default when `type` is omitted.\n\nRequired:\n\n- `command: string`\n\nOptional:\n\n- `type?: \"stdio\"`\n- `args?: string[]`\n- `env?: Record<string, string>`\n- `cwd?: string`\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"filesystem\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@modelcontextprotocol/server-filesystem\",\n        \"/Users/alice/projects\",\n        \"/Users/alice/Documents\"\n      ]\n    }\n  }\n}\n```\n\nThis follows the official Filesystem MCP server package (`@modelcontextprotocol/server-filesystem`).\n\n### `http` transport\n\nRequired:\n\n- `type: \"http\"`\n- `url: string`\n\nOptional:\n\n- `headers?: Record<string, string>`\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"github\": {\n      \"type\": \"http\",\n      \"url\": \"https://api.githubcopilot.com/mcp/\"\n    }\n  }\n}\n```\n\nThis matches GitHub's hosted GitHub MCP server endpoint.\n\n### `sse` transport\n\nRequired:\n\n- `type: \"sse\"`\n- `url: string`\n\nOptional:\n\n- `headers?: Record<string, string>`\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"legacy-remote\": {\n      \"type\": \"sse\",\n      \"url\": \"https://example.com/mcp/sse\"\n    }\n  }\n}\n```\n\n`sse` is still supported for compatibility, but the MCP spec now prefers Streamable HTTP (`type: \"http\"`) for new servers.\n\n## Auth fields\n\nOMP understands two auth-related objects.\n\n### `auth`\n\n```json\n{\n  \"type\": \"oauth\" | \"apikey\",\n  \"credentialId\": \"optional-stored-credential-id\",\n  \"tokenUrl\": \"optional-token-endpoint\",\n  \"clientId\": \"optional-client-id\",\n  \"clientSecret\": \"optional-client-secret\"\n}\n```\n\nUse this when OMP should remember how to rehydrate credentials for a server.\n\n### `oauth`\n\n```json\n{\n  \"clientId\": \"...\",\n  \"clientSecret\": \"...\",\n  \"redirectUri\": \"...\",\n  \"callbackPort\": 3334,\n  \"callbackPath\": \"/oauth/callback\"\n}\n```\n\nUse this when the MCP server requires explicit OAuth client settings.\n\nSlack is the clearest current example. Slack's MCP server is hosted at `https://mcp.slack.com/mcp`, uses Streamable HTTP, and requires confidential OAuth with your Slack app's client credentials.\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"slack\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.slack.com/mcp\",\n      \"oauth\": {\n        \"clientId\": \"YOUR_SLACK_CLIENT_ID\",\n        \"clientSecret\": \"YOUR_SLACK_CLIENT_SECRET\"\n      },\n      \"auth\": {\n        \"type\": \"oauth\",\n        \"tokenUrl\": \"https://slack.com/api/oauth.v2.user.access\",\n        \"clientId\": \"YOUR_SLACK_CLIENT_ID\",\n        \"clientSecret\": \"YOUR_SLACK_CLIENT_SECRET\"\n      }\n    }\n  }\n}\n```\n\nRelevant Slack endpoints from Slack's docs:\n\n- MCP endpoint: `https://mcp.slack.com/mcp`\n- Authorization endpoint: `https://slack.com/oauth/v2_user/authorize`\n- Token endpoint: `https://slack.com/api/oauth.v2.user.access`\n\n## Common copy-paste examples\n\n### Filesystem server via stdio\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"filesystem\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@modelcontextprotocol/server-filesystem\",\n        \"/absolute/path/one\",\n        \"/absolute/path/two\"\n      ]\n    }\n  }\n}\n```\n\n### GitHub hosted server via HTTP\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"github\": {\n      \"type\": \"http\",\n      \"url\": \"https://api.githubcopilot.com/mcp/\"\n    }\n  }\n}\n```\n\n### GitHub local server via Docker\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"github\": {\n      \"command\": \"docker\",\n      \"args\": [\n        \"run\",\n        \"-i\",\n        \"--rm\",\n        \"-e\",\n        \"GITHUB_PERSONAL_ACCESS_TOKEN\",\n        \"ghcr.io/github/github-mcp-server\"\n      ],\n      \"env\": {\n        \"GITHUB_PERSONAL_ACCESS_TOKEN\": \"GITHUB_PERSONAL_ACCESS_TOKEN\"\n      }\n    }\n  }\n}\n```\n\nThis matches GitHub's official local Docker image `ghcr.io/github/github-mcp-server`.\n\n### Slack hosted server via OAuth\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"slack\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.slack.com/mcp\",\n      \"oauth\": {\n        \"clientId\": \"YOUR_SLACK_CLIENT_ID\",\n        \"clientSecret\": \"YOUR_SLACK_CLIENT_SECRET\"\n      },\n      \"auth\": {\n        \"type\": \"oauth\",\n        \"tokenUrl\": \"https://slack.com/api/oauth.v2.user.access\",\n        \"clientId\": \"YOUR_SLACK_CLIENT_ID\",\n        \"clientSecret\": \"YOUR_SLACK_CLIENT_SECRET\"\n      }\n    }\n  }\n}\n```\n\n## Secrets and variable resolution\n\nThis is the part that usually trips people up.\n\n### In `.omp/mcp.json` and `~/.omp/agent/mcp.json`\n\nBefore OMP launches a stdio server or makes an HTTP/SSE request, it resolves stdio `env` values and HTTP/SSE `headers` values like this:\n\n1. If a value starts with `!`, OMP runs the rest as a shell command with a 10s timeout and uses trimmed stdout.\n2. If the command fails, times out, or prints only whitespace, that `env`/`headers` entry is omitted.\n3. Otherwise OMP checks whether the value names an environment variable.\n4. If that environment variable is set to a non-empty value, OMP uses the environment value; otherwise it uses the string literally.\n\nExamples:\n\n```json\n{\n  \"env\": {\n    \"GITHUB_PERSONAL_ACCESS_TOKEN\": \"GITHUB_PERSONAL_ACCESS_TOKEN\"\n  },\n  \"headers\": {\n    \"X-MCP-Insiders\": \"true\"\n  }\n}\n```\n\nThat means this is valid and convenient for local secrets:\n\n- `\"GITHUB_PERSONAL_ACCESS_TOKEN\": \"GITHUB_PERSONAL_ACCESS_TOKEN\"` → copy from the current shell environment\n- `\"Authorization\": \"Bearer hardcoded-token\"` → use the literal value\n- `\"Authorization\": \"!printf 'Bearer %s' \\\"$GITHUB_TOKEN\\\"\"` → build the header from a command\n\n### In root `mcp.json` and `.mcp.json`\n\nThe standalone fallback loader also expands `${VAR}` and `${VAR:-default}` inside strings during discovery for `command`, `args`, `env`, `cwd`, `url`, `headers`, `auth`, and `oauth`.\n\nExample:\n\n```json\n{\n  \"mcpServers\": {\n    \"github\": {\n      \"type\": \"http\",\n      \"url\": \"https://api.githubcopilot.com/mcp/\",\n      \"headers\": {\n        \"Authorization\": \"Bearer ${GITHUB_TOKEN}\"\n      }\n    }\n  }\n}\n```\n\nIf you want the least surprising OMP behavior, prefer `.omp/mcp.json` or `~/.omp/agent/mcp.json` and use explicit env/header values.\n\n## `disabledServers`\n\n`disabledServers` is read from the user config file (`~/.omp/agent/mcp.json`) when a server is discovered from any source and you want OMP to ignore it without editing that other tool's config.\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"disabledServers\": [\"github\", \"slack\"]\n}\n```\n\n## `/mcp add` vs editing JSON directly\n\nUse `/mcp add` when you want guided setup.\n\nUse direct JSON editing when:\n\n- you need a transport or auth option the wizard does not prompt for yet\n- you want to paste a server definition from another MCP client\n- you want schema-backed validation in your editor\n\nAfter editing, use:\n\n- `/mcp reload` to rediscover and reconnect servers in the current session\n- `/mcp list` to see which config file a server came from\n- `/mcp test <name>` to test a single server\n- `/mcp reconnect <name>` to reconnect one server without rediscovering all configs\n- `/mcp resources`, `/mcp prompts`, and `/mcp notifications` to inspect non-tool MCP capabilities\n\n## Validation rules OMP enforces\n\nFrom `validateServerConfig()` in `packages/coding-agent/src/mcp/config.ts`:\n\n- `stdio` requires `command`\n- `http` and `sse` require `url`\n- a server cannot set both `command` and `url`\n- unknown `type` values are rejected\n\nPractical implications:\n\n- Omitting `type` means `stdio`\n- If you paste a remote server config and forget `\"type\": \"http\"`, OMP will treat it as `stdio` and complain that `command` is missing\n- `sse` remains valid for compatibility, but new hosted servers should usually be configured as `http`\n\n## Discovery and precedence\n\nOMP does not merge duplicate server definitions across files. Discovery providers are prioritized, and the higher-priority definition wins. Separately, `disabledServers` from `~/.omp/agent/mcp.json` can suppress a discovered server by name.\n\nIn practice:\n\n- prefer `.omp/mcp.json` or `~/.omp/agent/mcp.json` when you want an OMP-specific override\n- keep server names unique across tools when possible\n- use `disabledServers` in the user config when a third-party config keeps reintroducing a server you do not want\n\n## Troubleshooting\n\n### `Server \"name\": stdio server requires \"command\" field`\n\nYou probably omitted `type: \"http\"` on a remote server.\n\n### `Server \"name\": both \"command\" and \"url\" are set`\n\nPick one transport. OMP treats `command` as stdio and `url` as http/sse.\n\n### `/mcp add` worked but the server still does not connect\n\nThe JSON is valid, but the server may still be unreachable. Use `/mcp test <name>` and check whether:\n\n- the binary or Docker image exists\n- required environment variables are set\n- the remote URL is reachable\n- the OAuth or API token is valid\n\n### The server exists in another tool's config but not in OMP\n\nRun `/mcp list`. OMP discovers many third-party MCP files, but project-level loading can also be disabled via the `mcp.enableProjectConfig` setting, and a user-level `disabledServers` entry can suppress a server by name.\n\n## References\n\n- MCP transport spec: https://modelcontextprotocol.io/specification/2025-03-26/basic/transports\n- Filesystem server package: https://www.npmjs.com/package/@modelcontextprotocol/server-filesystem\n- GitHub MCP server: https://github.com/github/github-mcp-server\n- Slack MCP server docs: https://docs.slack.dev/ai/slack-mcp-server/\n",
@@ -28,6 +29,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"mcp-runtime-lifecycle.md": "# MCP runtime lifecycle\n\nThis document describes how MCP servers are discovered, connected, exposed as tools, refreshed, and torn down in the coding-agent runtime.\n\n## Lifecycle at a glance\n\n1. **SDK startup** calls `discoverAndLoadMCPTools()` (unless MCP is disabled).\n2. **Discovery** (`loadAllMCPConfigs`) resolves MCP server configs from capability sources, filters disabled/project/Exa entries, and preserves source metadata.\n3. **Manager connect phase** (`MCPManager.connectServers`) starts per-server connect + `tools/list` in parallel.\n4. **Fast startup gate** waits up to 250ms, then may return:\n   - fully loaded `MCPTool`s,\n   - failures per server,\n   - or cached `DeferredMCPTool`s for still-pending servers.\n5. **SDK wiring** merges MCP tools into runtime tool registry for the session.\n6. **Post-connect enrichment** best-effort loads resources, resource templates, prompts, and optional resource subscriptions.\n7. **Live session** can refresh MCP tools via `/mcp` flows (`disconnectAll` + rediscover + `session.refreshMCPTools`) and can reconnect individual servers on transport close or `/mcp reconnect`.\n8. **Teardown** happens when callers invoke `disconnectServer`/`disconnectAll`; manager also clears MCP tool/resource/prompt registrations for disconnected servers.\n\n## Discovery and load phase\n\n### Entry path from SDK\n\n`createAgentSession()` in `src/sdk.ts` performs MCP startup when `enableMCP` is true (default):\n\n- calls `discoverAndLoadMCPTools(cwd, { ... })`,\n- passes `authStorage`, cache storage, and `mcp.enableProjectConfig` setting,\n- always sets `filterExa: true`,\n- logs per-server load/connect errors,\n- stores returned manager in `toolSession.mcpManager` and session result.\n\nIf `enableMCP` is false, MCP discovery is skipped entirely.\n\n### Config discovery and filtering\n\n`loadAllMCPConfigs()` (`src/mcp/config.ts`) loads canonical MCP server items through capability discovery, then converts to legacy `MCPServerConfig`.\n\nFiltering behavior:\n\n- `enableProjectConfig: false` removes project-level entries (`_source.level === \"project\"`).\n- `enabled: false` servers are skipped before connect attempts.\n- Exa servers are filtered out by default and API keys are extracted for native Exa tool integration.\n\nResult includes both `configs` and `sources` (metadata used later for provider labeling).\n\n### Discovery-level failure behavior\n\n`discoverAndLoadMCPTools()` distinguishes two failure classes:\n\n- **Discovery hard failure** (exception from `manager.discoverAndConnect`, typically from config discovery): returns an empty tool set and one synthetic error `{ path: \".mcp.json\", error }`.\n- **Per-server runtime/connect failure**: manager returns partial success with `errors` map; other servers continue.\n\nSo startup does not fail the whole agent session when individual MCP servers fail.\n\n## Manager state model\n\n`MCPManager` tracks runtime lifecycle with separate registries:\n\n- `#connections: Map<string, MCPServerConnection>` — fully connected servers.\n- `#pendingConnections: Map<string, Promise<MCPServerConnection>>` — handshake in progress.\n- `#pendingToolLoads: Map<string, Promise<{ connection, serverTools }>>` — connected but tools still loading.\n- `#tools: CustomTool[]` — current MCP tool view exposed to callers.\n- `#sources: Map<string, SourceMeta>` — provider/source metadata even before connect completes.\n- `#pendingReconnections: Map<string, Promise<MCPServerConnection | null>>` — reconnects in progress after a dropped transport or explicit reconnect.\n- `#serverConfigs: Map<string, MCPServerConfig>` — original unresolved configs preserved so reconnect can re-resolve credentials without leaking resolved tokens.\n\n`getConnectionStatus(name)` derives status from these maps:\n\n- `connected` if in `#connections`,\n- `connecting` if pending connect, pending tool load, or pending reconnect,\n- `disconnected` otherwise.\n\n## Connection establishment and startup timing\n\n## Per-server connect pipeline\n\nFor each discovered server in `connectServers()`:\n\n1. store/update source metadata,\n2. skip if already connected/pending/reconnecting,\n3. validate transport fields (`validateServerConfig`),\n4. resolve auth/shell substitutions (`#resolveAuthConfig`),\n5. call `connectToServer(name, resolvedConfig)` with manager notification/request handlers,\n6. wire HTTP OAuth refresh and transport `onClose` reconnect handling,\n7. call `listTools(connection)`,\n8. cache tool definitions (`MCPToolCache.set`) best-effort,\n9. best-effort load resources, resource templates, prompts, and subscriptions after tools load.\n\n`connectToServer()` behavior (`src/mcp/client.ts`):\n\n- creates stdio or HTTP/SSE transport,\n- performs MCP `initialize`,\n- for HTTP/SSE, starts the optional background SSE listener before `notifications/initialized`,\n- sends `notifications/initialized`,\n- uses timeout (`OMP_MCP_TIMEOUT_MS`, `config.timeout`, or 30s default; `0` disables the client-side timeout),\n- closes transport on init failure.\n\n### Fast startup gate + deferred fallback\n\n`connectServers()` waits on a race between:\n\n- all connect/tool-load tasks settled, and\n- `STARTUP_TIMEOUT_MS = 250`.\n\nAfter 250ms:\n\n- fulfilled tasks become live `MCPTool`s,\n- rejected tasks produce per-server errors,\n- still-pending tasks:\n  - use cached tool definitions if available (`MCPToolCache.get`) to create `DeferredMCPTool`s,\n  - otherwise block until those pending tasks settle.\n\nThis is a hybrid startup model: fast return when cache is available, correctness wait when cache is not.\n\n### Background completion behavior\n\nEach pending `toolsPromise` also has a background continuation that eventually:\n\n- replaces that server’s tool slice in manager state via `#replaceServerTools`,\n- writes cache,\n- logs late failures only after startup (`allowBackgroundLogging`).\n\n## Tool exposure and live-session availability\n\n### Startup registration\n\n`discoverAndLoadMCPTools()` converts manager tools into `LoadedCustomTool[]` and decorates paths (`mcp:<server> via <providerName>` when known).\n\n`createAgentSession()` then pushes these tools into `customTools`, which are wrapped and added to the runtime tool registry with names like `mcp__<server>_<tool>`.\n\n### Tool calls\n\n- `MCPTool` calls tools through an already connected `MCPServerConnection`.\n- `DeferredMCPTool` waits for `waitForConnection(server)` before calling; this allows cached tools to exist before connection is ready.\n- Both attempt a reconnect + single retry for retriable connection failures.\n\nBoth return structured tool output and convert remaining transport/tool errors into `MCP error: ...` tool content (abort remains abort).\n\n## Refresh/reload paths (startup vs live reload)\n\n### Initial startup path\n\n- one-time discovery/load in `sdk.ts`,\n- tools are registered in initial session tool registry.\n\n### Interactive reload path\n\n`/mcp reload` path (`src/modes/controllers/mcp-command-controller.ts`) does:\n\n1. `mcpManager.disconnectAll()`,\n2. `mcpManager.discoverAndConnect()`,\n3. `session.refreshMCPTools(mcpManager.getTools())`.\n\n`session.refreshMCPTools()` (`src/session/agent-session.ts`) removes all `mcp__` tools, re-wraps latest MCP tools, and re-activates tool set so MCP changes apply without restarting session.\n\nThere is also a follow-up path for late connections: after waiting for a specific server, if status becomes `connected`, it re-runs `session.refreshMCPTools(...)` so newly available tools are rebound in-session.\n\n## Health, reconnect, and partial failure behavior\n\nCurrent runtime behavior is connection-event driven:\n\n- **No autonomous polling health monitor** in manager/client.\n- **Automatic reconnect is wired to `transport.onClose`** for managed connections.\n- Reconnect retries with backoff (`500`, `1000`, `2000`, `4000` ms), reloads tools, and notifies consumers on success.\n- Tool calls that see retriable connection errors also attempt one reconnect + retry.\n- Reconnect is also explicit via `/mcp reconnect <name>` or broader `/mcp reload`.\n\nOperationally:\n\n- one server failing does not remove tools from healthy servers,\n- connect/list failures are isolated per server,\n- stale tools may remain visible while reconnect is attempted; calls report MCP errors if recovery fails,\n- tool cache, resource/prompt loading, subscriptions, and background updates are best-effort (warnings/errors logged, no hard stop).\n\n## Teardown semantics\n\n### Server-level teardown\n\n`disconnectServer(name)`:\n\n- removes pending entries, source metadata, saved config, resource refresh/subscription state,\n- detaches `onClose` so explicit close does not trigger reconnect,\n- closes transport if connected,\n- filters manager tool state for names beginning with `mcp__${name}_`.\n\n### Global teardown\n\n`disconnectAll()`:\n\n- detaches `onClose` for all active transports, then closes them with `Promise.allSettled`,\n- clears pending maps, sources, saved configs, connections, subscriptions, resource refreshes, and manager tool list.\n\nIn current wiring, explicit teardown is used in MCP command flows (for reload/remove/disable). Startup stores the manager on the session; callers that need deterministic MCP shutdown should invoke manager disconnect methods.\n\n## Failure modes and guarantees\n\n| Scenario                                             | Behavior                                                                                                                  | Hard fail vs best-effort       |\n| ---------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------- | ------------------------------ |\n| Discovery throws (capability/config load path)       | Loader returns empty tools + synthetic `.mcp.json` error                                                                  | Best-effort session startup    |\n| Invalid server config                                | Server skipped with validation error entry                                                                                | Best-effort per server         |\n| Connect timeout/init failure                         | Server error recorded; others continue                                                                                    | Best-effort per server         |\n| `tools/list` still pending at startup with cache hit | Deferred tools returned immediately                                                                                       | Best-effort fast startup       |\n| `tools/list` still pending at startup without cache  | Startup waits for pending to settle                                                                                       | Hard wait for correctness      |\n| Late background tool-load failure                    | Logged after startup gate                                                                                                 | Best-effort logging            |\n| Runtime dropped transport                            | Manager attempts reconnect; stale tools remain while reconnecting and future calls may retry once or fail with MCP errors | Best-effort automatic recovery |\n\n## Public API surface\n\n`src/mcp/index.ts` re-exports loader/manager/client APIs for external callers. `src/sdk.ts` exposes `discoverMCPServers()` as a convenience wrapper returning the same loader result shape.\n\n## Implementation files\n\n- [`src/mcp/loader.ts`](../packages/coding-agent/src/mcp/loader.ts) — loader facade, discovery error normalization, `LoadedCustomTool` conversion.\n- [`src/mcp/manager.ts`](../packages/coding-agent/src/mcp/manager.ts) — lifecycle state registries, parallel connect/list flow, refresh/disconnect.\n- [`src/mcp/client.ts`](../packages/coding-agent/src/mcp/client.ts) — transport setup, initialize handshake, list/call/disconnect.\n- [`src/mcp/index.ts`](../packages/coding-agent/src/mcp/index.ts) — MCP module API exports.\n- [`src/sdk.ts`](../packages/coding-agent/src/sdk.ts) — startup wiring into session/tool registry.\n- [`src/mcp/config.ts`](../packages/coding-agent/src/mcp/config.ts) — config discovery/filtering/validation used by manager.\n- [`src/mcp/tool-bridge.ts`](../packages/coding-agent/src/mcp/tool-bridge.ts) — `MCPTool` and `DeferredMCPTool` runtime behavior.\n- [`src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts) — `refreshMCPTools` live rebinding.\n- [`src/modes/controllers/mcp-command-controller.ts`](../packages/coding-agent/src/modes/controllers/mcp-command-controller.ts) — interactive reload/reconnect flows.\n- [`src/task/executor.ts`](../packages/coding-agent/src/task/executor.ts) — subagent MCP proxying via parent manager connections.\n",
 	"mcp-server-tool-authoring.md": "# MCP server and tool authoring\n\nThis document explains how MCP server definitions become callable `mcp__*` tools in coding-agent, and what operators should expect when configs are invalid, duplicated, disabled, or auth-gated.\n\n## Architecture at a glance\n\n```text\nConfig sources (.omp/.claude/.cursor/.vscode/mcp.json, mcp.json, etc.)\n  -> discovery providers normalize to canonical MCPServer\n  -> capability loader dedupes by server name (higher provider priority wins)\n  -> loadAllMCPConfigs converts to MCPServerConfig + skips enabled:false\n  -> MCPManager connects/listTools (with auth/header/env resolution)\n  -> manager best-effort loads resources/prompts and subscribes to resource updates when enabled\n  -> MCPTool/DeferredMCPTool bridge exposes tools as mcp__<server>_<tool>\n  -> AgentSession.refreshMCPTools replaces live MCP tools immediately\n```\n\n## 1) Server config model and validation\n\n`src/mcp/types.ts` defines the authoring shape used by MCP config writers and runtime:\n\n- `stdio` (default when `type` missing): requires `command`, optional `args`, `env`, `cwd`\n- `http`: requires `url`, optional `headers`\n- `sse`: requires `url`, optional `headers` (kept for compatibility)\n- shared fields: `enabled`, `timeout`, `auth`, `oauth`\n\n`validateServerConfig()` (`src/mcp/config.ts`) enforces transport basics:\n\n- rejects configs that set both `command` and `url`\n- requires `command` for stdio\n- requires `url` for http/sse\n- rejects unknown `type`\n\n`config-writer.ts` applies this validation for add/update operations and also validates server names:\n\n- non-empty\n- max 100 chars\n- only `[a-zA-Z0-9_.-]`\n\n### Transport pitfalls\n\n- `type` omitted means stdio. If you intended HTTP/SSE but omitted `type`, `command` becomes mandatory.\n- `sse` is still accepted but treated as HTTP transport internally (`createHttpTransport`).\n- Validation is structural, not reachability: a syntactically valid URL can still fail at connect time.\n\n## 2) Discovery, normalization, and precedence\n\n### Capability-based discovery\n\n`loadAllMCPConfigs()` (`src/mcp/config.ts`) loads canonical `MCPServer` items via `loadCapability(mcpCapability.id)`.\n\nThe capability layer (`src/capability/index.ts`) then:\n\n1. loads providers in priority order\n2. dedupes by `server.name` (first win = highest priority)\n3. validates deduped items\n\nResult: duplicate server names across sources are not merged. One definition wins; lower-priority duplicates are shadowed.\n\n### `.mcp.json` and related files\n\nThe dedicated fallback provider in `src/discovery/mcp-json.ts` reads project-root `mcp.json` and `.mcp.json` (low priority).\n\nIn practice MCP servers also come from higher-priority providers (for example native `.omp/...` and tool-specific config dirs). Authoring guidance:\n\n- Prefer `.omp/mcp.json` (project) or `~/.omp/agent/mcp.json` (user) for explicit control.\n- Use root `mcp.json` / `.mcp.json` when you need fallback compatibility.\n- Reusing the same server name in multiple sources causes precedence shadowing, not merge.\n\n### Normalization behavior\n\n`convertToLegacyConfig()` (`src/mcp/config.ts`) maps canonical `MCPServer` to runtime `MCPServerConfig`.\n\nKey behavior:\n\n- transport inferred as `server.transport ?? (command ? \"stdio\" : url ? \"http\" : \"stdio\")`\n- disabled servers (`enabled === false`) are dropped before connection\n- optional fields are preserved when present\n\n### Environment expansion during discovery\n\n`mcp-json.ts` expands env placeholders in string fields with `expandEnvVarsDeep()`:\n\n- supports `${VAR}` and `${VAR:-default}`\n- unresolved values remain literal `${VAR}` strings\n\n`mcp-json.ts` also performs runtime type checks for user JSON and logs warnings for invalid `enabled`/`timeout` values instead of hard-failing the whole file.\n\n## 3) Auth and runtime value resolution\n\n`MCPManager.prepareConfig()`/`#resolveAuthConfig()` (`src/mcp/manager.ts`) is the final pre-connect pass.\n\n### OAuth credential injection\n\nIf config has:\n\n```ts\nauth: { type: \"oauth\", credentialId: \"...\" }\n```\n\nand credential exists in auth storage:\n\n- `http`/`sse`: injects `Authorization: Bearer <access_token>` header\n- `stdio`: injects `OAUTH_ACCESS_TOKEN` env var\n\nIf credential lookup fails, manager logs a warning and continues with unresolved auth.\n\n### Header/env value resolution\n\nBefore connect, manager resolves stdio `env` values and HTTP/SSE `headers` values via `resolveConfigValue()` (`src/config/resolve-config-value.ts`):\n\n- value starting with `!` => execute shell command, use trimmed stdout (cached)\n- failed, timed-out, or whitespace-only commands produce `undefined`, so that entry is omitted\n- otherwise, treat value as environment variable name first (`process.env[name]`), fallback to literal value\n\nOperational caveat: a mistyped `!` secret command can silently remove that header/env entry, producing downstream 401/403 or server startup failures. A mistyped environment variable name is sent literally unless that literal happens to be meaningful to the server.\n\n## 4) Tool bridge: MCP -> agent-callable tools\n\n`src/mcp/tool-bridge.ts` converts MCP tool definitions into `CustomTool`s.\n\n### Naming and collision domain\n\nTool names are generated as:\n\n```text\nmcp__<sanitized_server_name>_<sanitized_tool_name>\n```\n\nRules:\n\n- lowercases\n- non-`[a-z_]` chars become `_`\n- repeated underscores collapse\n- redundant `<server>_` prefix in tool name is stripped once\n\nThis avoids many collisions, but not all. Different raw names can still sanitize to the same identifier (for example `my-server` and `my.server` both sanitize similarly), and registry insertion is last-write-wins.\n\n### Schema mapping\n\n`tool-bridge.ts` passes each MCP `inputSchema` through `sanitizeSchemaForMCP()` before registering it as a `CustomTool` schema.\n\n### Execution mapping\n\n`MCPTool.execute()` / `DeferredMCPTool.execute()`:\n\n- calls MCP `tools/call`\n- flattens MCP content into displayable text\n- returns structured details (`serverName`, `mcpToolName`, provider metadata)\n- maps server-reported `isError` to `Error: ...` text result\n- attempts reconnect + one retry for retriable connection errors\n- maps remaining thrown transport/runtime failures to `MCP error: ...`\n- preserves abort semantics by translating AbortError into `ToolAbortError`\n\n## 5) Operator lifecycle: add/edit/remove and live updates\n\nInteractive mode exposes `/mcp` in `src/modes/controllers/mcp-command-controller.ts`.\n\nSupported operations:\n\n- `add` (wizard or quick-add)\n- `remove` / `rm`\n- `enable` / `disable`\n- `test`\n- `reauth` / `unauth`\n- `reconnect`\n- `reload`\n- `resources`, `prompts`, `notifications`\n- Smithery search/login/logout flows\n\nConfig writes are atomic (`writeMCPConfigFile`: temp file + rename).\n\nAfter changes, controller calls `#reloadMCP()`:\n\n1. `mcpManager.disconnectAll()`\n2. `mcpManager.discoverAndConnect()`\n3. `session.refreshMCPTools(mcpManager.getTools())`\n\n`refreshMCPTools()` replaces all `mcp__` registry entries and immediately re-activates the latest MCP tool set, so changes take effect without restarting the session.\n\n### Mode differences\n\n- **Interactive/TUI mode**: `/mcp` gives in-app UX (wizard, OAuth flow, connection status text, immediate runtime rebinding).\n- **SDK/headless integration**: `discoverAndLoadMCPTools()` (`src/mcp/loader.ts`) returns loaded tools + per-server errors; no `/mcp` command UX.\n\n## 6) User-visible error surfaces\n\nCommon error strings users/operators see:\n\n- add/update validation failures:\n  - `Invalid server config: ...`\n  - `Server \"<name>\" already exists in <path>`\n- quick-add argument issues:\n  - `Use either --url or -- <command...>, not both.`\n  - `--token requires --url (HTTP/SSE transport).`\n- connect/test failures:\n  - `Failed to connect to \"<name>\": <message>`\n  - timeout help text suggests increasing timeout\n  - auth help text for `401/403`\n- auth/OAuth flows:\n  - `Authentication required ... OAuth endpoints could not be discovered`\n  - `OAuth flow timed out. Please try again.`\n  - `OAuth authentication failed: ...`\n- disabled server usage:\n  - `Server \"<name>\" is disabled. Run /mcp enable <name> first.`\n\nBad source JSON in discovery is generally handled as warnings/logs; config-writer paths throw explicit errors.\n\n## 7) Practical authoring guidance\n\nFor robust MCP authoring in this codebase:\n\n1. Keep server names globally unique across all MCP-capable config sources.\n2. Prefer names that remain distinct after MCP tool-name sanitization to avoid generated `mcp__` collisions.\n3. Use explicit `type` to avoid accidental stdio defaults.\n4. Treat `enabled: false` as hard-off: server is omitted from runtime connect set.\n5. For OAuth configs, store a valid `credentialId`; otherwise auth injection is skipped.\n6. If using command-based secret resolution (`!cmd`), verify command output is stable and non-empty.\n\n## Implementation files\n\n- [`src/mcp/types.ts`](../packages/coding-agent/src/mcp/types.ts)\n- [`src/mcp/config.ts`](../packages/coding-agent/src/mcp/config.ts)\n- [`src/mcp/config-writer.ts`](../packages/coding-agent/src/mcp/config-writer.ts)\n- [`src/mcp/tool-bridge.ts`](../packages/coding-agent/src/mcp/tool-bridge.ts)\n- [`src/discovery/mcp-json.ts`](../packages/coding-agent/src/discovery/mcp-json.ts)\n- [`src/modes/controllers/mcp-command-controller.ts`](../packages/coding-agent/src/modes/controllers/mcp-command-controller.ts)\n- [`src/mcp/manager.ts`](../packages/coding-agent/src/mcp/manager.ts)\n- [`src/capability/index.ts`](../packages/coding-agent/src/capability/index.ts)\n- [`src/config/resolve-config-value.ts`](../packages/coding-agent/src/config/resolve-config-value.ts)\n- [`src/mcp/loader.ts`](../packages/coding-agent/src/mcp/loader.ts)\n",
 	"memory.md": "# Autonomous Memory\n\nWhen enabled, the agent automatically extracts durable knowledge from past sessions and injects a compact summary into each new session. Over time it builds a project-scoped memory store — technical decisions, recurring workflows, pitfalls — that carries forward without manual effort.\n\nDisabled by default. Enable via `/settings` or `config.yml`:\n\n```yaml\nmemories:\n  enabled: true\n```\n\n## Usage\n\n### What gets injected\n\nAt session start, if a memory summary exists for the current project, it is injected into the system prompt as a **Memory Guidance** block. The agent is instructed to:\n\n- Treat memory as heuristic context — useful for process and prior decisions, not authoritative on current repo state.\n- Cite the memory artifact path when memory changes the plan, and pair it with current-repo evidence before acting.\n- Prefer repo state and user instruction when they conflict with memory; treat conflicting memory as stale.\n\n### Reading memory artifacts\n\nThe agent can read memory files directly using `memory://` URLs with the `read` tool:\n\n| URL                                    | Content                             |\n| -------------------------------------- | ----------------------------------- |\n| `memory://root`                        | Compact summary injected at startup |\n| `memory://root/MEMORY.md`              | Full long-term memory document      |\n| `memory://root/skills/<name>/SKILL.md` | A generated skill playbook          |\n\n### `/memory` slash command\n\n| Subcommand            | Effect                                         |\n| --------------------- | ---------------------------------------------- |\n| `view`                | Show the current memory injection payload      |\n| `clear` / `reset`     | Delete all memory data and generated artifacts |\n| `enqueue` / `rebuild` | Force consolidation to run at next startup     |\n\n## How it works\n\nMemories are built by a background pipeline that runs at startup or when manually triggered via slash command.\n\n**Phase 1 — per-session extraction:** For each past session that has changed since it was last processed, a model reads the session history and extracts durable signal: technical decisions, constraints, resolved failures, recurring workflows. Sessions that are too recent, too old, or currently active are skipped. Each extraction produces a raw memory block and a short synopsis for that session.\n\n**Phase 2 — consolidation:** After extraction, a second model pass reads all per-session extractions and produces three outputs written to disk:\n\n- `MEMORY.md` — a curated long-term memory document\n- `memory_summary.md` — the compact text injected at session start\n- `skills/` — reusable procedural playbooks, each in its own subdirectory\n\nPhase 2 uses a lease to prevent double-running when multiple processes start simultaneously. Stale skill directories from prior runs are pruned automatically.\n\nAll output is scanned for secrets before being written to disk.\n\n### Extraction behavior\n\nMemory extraction and consolidation behavior is driven by static prompt files in `packages/coding-agent/src/prompts/memories/`.\n\n| File                  | Purpose                                     | Variables                                   |\n| --------------------- | ------------------------------------------- | ------------------------------------------- |\n| `stage_one_system.md` | System prompt for per-session extraction    | —                                           |\n| `stage_one_input.md`  | User-turn template wrapping session content | `{{thread_id}}`, `{{response_items_json}}`  |\n| `consolidation.md`    | Prompt for cross-session consolidation      | `{{raw_memories}}`, `{{rollout_summaries}}` |\n| `read_path.md`        | Memory guidance injected into live sessions | `{{memory_summary}}`                        |\n\n### Model selection\n\nMemory piggybacks on the model role system.\n\n| Phase                   | Role                                                                | Purpose                          |\n| ----------------------- | ------------------------------------------------------------------- | -------------------------------- |\n| Phase 1 (extraction)    | `default`                                                           | Per-session knowledge extraction |\n| Phase 2 (consolidation) | `smol` (falls back to `default`, then current/first registry model) | Cross-session synthesis          |\n\nIf the requested memory role is not configured, memory model resolution falls back to the `default` role, then the active session model, then the first model in the registry.\n\n## Configuration\n\n| Setting                               | Default | Description                                               |\n| ------------------------------------- | ------- | --------------------------------------------------------- |\n| `memories.enabled`                    | `false` | Master switch                                             |\n| `memories.maxRolloutAgeDays`          | `30`    | Sessions older than this are not processed                |\n| `memories.minRolloutIdleHours`        | `12`    | Sessions active more recently than this are skipped       |\n| `memories.maxRolloutsPerStartup`      | `64`    | Cap on sessions processed in a single startup             |\n| `memories.summaryInjectionTokenLimit` | `5000`  | Max tokens of the summary injected into the system prompt |\n\nAdditional tuning knobs (concurrency, lease durations, token budgets) are available in config for advanced use.\n\n## Key files\n\n- `packages/coding-agent/src/memories/index.ts` — pipeline orchestration, injection, slash command handling\n- `packages/coding-agent/src/memories/storage.ts` — SQLite-backed job queue and thread registry\n- `packages/coding-agent/src/prompts/memories/` — memory prompt templates\n- `packages/coding-agent/src/internal-urls/memory-protocol.ts` — `memory://` URL handler\n",
+	"mnemosyne-memory-backend.md": "# Mnemosyne memory backend\n\nOh My Pi can use `@oh-my-pi/pi-mnemosyne` as a local long-term memory backend.\n\nSet:\n\n```yaml\nmemory:\n  backend: mnemosyne\n```\n\nExample:\n\n```yaml\nmemory:\n  backend: mnemosyne\nmnemosyne:\n  scoping: per-project-tagged\n```\n\nWith this backend enabled, the coding agent:\n\n1. Opens a local Mnemosyne SQLite database.\n2. Recalls relevant memories into a `<memories>` block before the first model turn.\n3. Retains completed conversation turns into the same bank after agent turns.\n4. Uses the normal `/memory view`, `/memory clear`, and `/memory enqueue` commands through the shared memory backend interface.\n\nRecalled memory is background context, not instructions. Current user messages and tool output take precedence when they conflict.\n\n## Settings\n\n| Setting | Default | Description |\n| --- | --- | --- |\n| `memory.backend` | `off` | Set to `mnemosyne` to enable this backend. |\n| `mnemosyne.dbPath` | agent memories dir | Optional SQLite database path. |\n| `mnemosyne.bank` | project directory name | Base bank name passed to `Mnemosyne`; the coding-agent wrapper scopes from this base according to `mnemosyne.scoping`. |\n| `mnemosyne.scoping` | `per-project` | Memory visibility mode: `global` = one shared bank, `per-project` = isolated project memory, `per-project-tagged` = project-local writes plus global recall visibility. |\n| `mnemosyne.autoRecall` | `true` | Recall memory on the first turn of a session. |\n| `mnemosyne.autoRetain` | `true` | Retain completed turns automatically. |\n| `mnemosyne.retainEveryNTurns` | `4` | Minimum user turns between automatic retain writes. |\n| `mnemosyne.recallLimit` | `8` | Maximum recalled memories in the prompt block. |\n| `mnemosyne.recallContextTurns` | `3` | Prior user-bounded turns included in recall queries. |\n| `mnemosyne.recallMaxQueryChars` | `4000` | Maximum composed recall query length. |\n| `mnemosyne.injectionTokenLimit` | `5000` | Approximate token budget for memory prompt injection. |\n| `mnemosyne.debug` | `false` | Enable debug logging for backend failures. |\n| `mnemosyne.noEmbeddings` | `false` | Pass `noEmbeddings` to `Mnemosyne` and force FTS-only recall. |\n| `mnemosyne.embeddingModel` | env/default | Embedding model passed to `Mnemosyne`. |\n| `mnemosyne.embeddingApiUrl` | env/default | OpenAI-compatible embedding endpoint passed to `Mnemosyne`. |\n| `mnemosyne.embeddingApiKey` | env/default | Embedding API key passed to `Mnemosyne`. |\n| `mnemosyne.llmMode` | `smol` | `smol` uses the configured pi-ai smol model, `remote` uses the settings below, and `none` disables LLM calls. |\n| `mnemosyne.llmBaseUrl` | env/default | OpenAI-compatible LLM endpoint for `llmMode: remote`. |\n| `mnemosyne.llmApiKey` | env/default | LLM API key for `llmMode: remote`. |\n| `mnemosyne.llmModel` | env/default | LLM model id for `llmMode: remote`. |\n\n## Scoping\n\nThe coding-agent wrapper applies scoping on top of the underlying `Mnemosyne` package:\n\n- `global` uses one shared bank for every project.\n- `per-project` uses a separate bank per project.\n- `per-project-tagged` keeps writes project-local while recall can also read from shared global memory.\n\nThe combined project-plus-global behavior lives in the wrapper. The `@oh-my-pi/pi-mnemosyne` package itself still exposes banks and constructor options directly, including `bank` for selecting a bank name.\n## LLM and embeddings\n\nThe backend passes these settings to the `Mnemosyne` constructor; if a setting is omitted, Mnemosyne falls back to its `MNEMOSYNE_*` environment defaults. The backend does not download or run a local GGUF LLM. LLM-dependent paths use a configured pi-ai model, a dynamic completion function, a remote OpenAI-compatible endpoint, or deterministic no-LLM fallbacks.\n\nFTS-only:\n\n```yaml\nmemory:\n  backend: mnemosyne\nmnemosyne:\n  noEmbeddings: true\n```\n\nEquivalent constructor shape:\n\n```ts\nnew Mnemosyne({ noEmbeddings: true });\n```\n\nRemote embeddings:\n\n```yaml\nmnemosyne:\n  embeddingModel: text-embedding-3-small\n  embeddingApiUrl: https://api.openai.com/v1\n  embeddingApiKey: ${OPENAI_API_KEY}\n```\n\nEquivalent constructor shape:\n\n```ts\nnew Mnemosyne({\n  embeddingModel: \"text-embedding-3-small\",\n  embeddingApiUrl: \"https://api.openai.com/v1\",\n  embeddingApiKey,\n});\n```\n\nRemote LLM:\n\n```yaml\nmnemosyne:\n  llmMode: remote\n  llmBaseUrl: https://api.openai.com/v1\n  llmApiKey: ${OPENAI_API_KEY}\n  llmModel: gpt-4.1-mini\n```\n\nEquivalent constructor shapes:\n\n```ts\nnew Mnemosyne({ llm: { baseUrl, apiKey, model } });\nnew Mnemosyne({ llmBaseUrl: baseUrl, llmApiKey: apiKey, llmModel: model });\n```\n\nDynamic function LLM for rotating OAuth tokens:\n\n```ts\nnew Mnemosyne({\n  llm: async (prompt, opts) => {\n    const token = await getFreshOauthToken();\n    return await completeWithPiAi(prompt, {\n      token,\n      maxTokens: opts?.maxTokens,\n      temperature: opts?.temperature,\n    });\n  },\n});\n```\n\npi-ai smol model LLM:\n\n```yaml\nmnemosyne:\n  llmMode: smol\n```\n\nThe coding agent resolves its configured smol role and passes a dynamic completion function so every Mnemosyne LLM call can fetch the current provider credentials at call time:\n\n```ts\nnew Mnemosyne({\n  llm: async (prompt, opts) => completeSmolWithCurrentAuth(prompt, opts),\n});\n```\n\n## Operational notes\n\n- The default database lives under the agent memories directory in `mnemosyne/mnemosyne.db`.\n- `/memory clear` removes the active Mnemosyne SQLite database and sidecar WAL/SHM files.\n- `/memory enqueue` forces retention of the current session and runs Mnemosyne sleep/consolidation.\n- Subagents do not auto-retain separate transcript windows; parent sessions own durable retention.\n",
 	"models.md": "# Model and Provider Configuration (`models.yml`)\n\nThis document describes how the coding-agent currently loads models, applies overrides, resolves credentials, and chooses models at runtime.\n\n## What controls model behavior\n\nPrimary implementation files:\n\n- `src/config/model-registry.ts` — loads built-in + custom models, provider overrides, runtime discovery, auth integration\n- `src/config/model-resolver.ts` — parses model patterns and selects initial/smol/slow models\n- `src/config/settings-schema.ts` — model-related settings (`modelRoles`, provider transport preferences)\n- `src/session/auth-storage.ts` — API key + OAuth resolution order\n- `packages/ai/src/models.ts` and `packages/ai/src/types.ts` — built-in providers/models and `Model`/`compat` types\n\n## Config file location and legacy behavior\n\nDefault config path:\n\n- `~/.omp/agent/models.yml`\n\nLegacy behavior still present:\n\n- If `models.yml` is missing and `models.json` exists at the same location, it is migrated to `models.yml`.\n- Explicit `.json` / `.jsonc` config paths are still supported when passed programmatically to `ModelRegistry`.\n\n## `models.yml` shape\n\n```yaml\nproviders:\n  <provider-id>:\n    # provider-level config\nequivalence:\n  overrides:\n    <provider-id>/<model-id>: <canonical-model-id>\n  exclude:\n    - <provider-id>/<model-id>\n```\n\n`provider-id` is the canonical provider key used across selection and auth lookup.\n\n`equivalence` is optional and configures canonical model grouping on top of concrete provider models:\n\n- `overrides` maps an exact concrete selector (`provider/modelId`) to an official upstream canonical id\n- `exclude` opts a concrete selector out of canonical grouping\n\n## Provider-level fields\n\n```yaml\nproviders:\n  my-provider:\n    baseUrl: https://api.example.com/v1\n    apiKey: MY_PROVIDER_API_KEY\n    api: openai-completions\n    headers:\n      X-Team: platform\n    authHeader: true\n    auth: apiKey\n    disableStrictTools: false  # set true for Anthropic-compatible endpoints that reject the strict field\n    discovery:\n      type: ollama\n    modelOverrides:\n      some-model-id:\n        name: Renamed model\n    models:\n      - id: some-model-id\n        name: Some Model\n        api: openai-completions\n        reasoning: false\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 128000\n        maxTokens: 16384\n        headers:\n          X-Model: value\n        compat:\n          supportsStore: true\n          supportsDeveloperRole: true\n          supportsReasoningEffort: true\n          maxTokensField: max_completion_tokens\n          openRouterRouting:\n            only: [anthropic]\n          vercelGatewayRouting:\n            order: [anthropic, openai]\n          extraBody:\n            gateway: m1-01\n            controller: mlx\n```\n\n### Allowed provider/model `api` values\n\n- `openai-completions`\n- `openai-responses`\n- `openai-codex-responses`\n- `azure-openai-responses`\n- `anthropic-messages`\n- `google-generative-ai`\n- `google-vertex`\n\n### Allowed auth/discovery values\n\n- `auth`: `apiKey` (default), `none`, or `oauth`; for `models.yml` custom models, `oauth` is accepted by schema but does not waive the `apiKey` requirement\n- `discovery.type`: `ollama`, `llama.cpp`, `lm-studio`, `openai-models-list`, or `proxy`\n\n## Validation rules (current)\n\n### Full custom provider (`models` is non-empty)\n\nRequired:\n\n- `baseUrl`\n- `apiKey` unless `auth: none`\n- `api` at provider level or each model\n\n### Override-only provider (`models` missing or empty)\n\nMust define at least one of:\n\n- `baseUrl`\n- `headers`\n- `compat`\n- `disableStrictTools`\n- `modelOverrides`\n- `discovery`\n\n### Discovery\n\n- `discovery` requires provider-level `api`.\n\n### Model value checks\n\n- `id` required\n- `contextWindow` and `maxTokens` must be positive if provided\n\n## Merge and override order\n\nModelRegistry pipeline (on refresh):\n\n1. Load built-in providers/models from `@oh-my-pi/pi-ai`.\n2. Load `models.yml` custom config.\n3. Apply provider overrides (`baseUrl`, `headers`, `disableStrictTools`) to built-in models.\n4. Apply `modelOverrides` (per provider + model id).\n5. Merge custom `models`:\n   - same `provider + id` replaces existing\n   - otherwise append\n6. Load cached/runtime-discovered models (Ollama, llama.cpp, LM Studio, plus built-in provider managers), then re-apply model overrides.\n\n### Provider-model cache and static fingerprint\n\nCached per-provider model lists are persisted in the model-cache SQLite\ndatabase (schema v3) with a `static_fingerprint` column that hashes the\nstatic catalog slice merged into the row. When `resolveProviderModels`\nskips the network fetch and the fingerprint of the in-memory static\ncatalog matches the cached one, the cached rows are returned verbatim —\nthe static + dynamic merge is bypassed entirely. The fingerprint is\nmemoized per process via a WeakMap keyed by the static-models array\nreference, so repeated cold-start calls do not re-hash.\n\n## Canonical model equivalence and coalescing\n\nThe registry keeps every concrete provider model and then builds a canonical layer above them.\n\nCanonical ids are official upstream ids only, for example:\n\n- `claude-opus-4-6`\n- `claude-haiku-4-5`\n- `gpt-5.3-codex`\n\n### `models.yml` equivalence config\n\nExample:\n\n```yaml\nproviders:\n  zenmux:\n    baseUrl: https://api.zenmux.example/v1\n    apiKey: ZENMUX_API_KEY\n    api: openai-codex-responses\n    models:\n      - id: codex\n        name: Zenmux Codex\n        reasoning: true\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 200000\n        maxTokens: 32768\n\nequivalence:\n  overrides:\n    zenmux/codex: gpt-5.3-codex\n    p-codex/codex: gpt-5.3-codex\n  exclude:\n    - demo/codex-preview\n```\n\nBuild order for canonical grouping:\n\n1. exact user override from `equivalence.overrides`\n2. bundled official-id matches from built-in model metadata\n3. conservative heuristic normalization for gateway/provider variants\n4. fallback to the concrete model's own id\n\nCurrent heuristics are intentionally narrow:\n\n- embedded upstream prefixes can be stripped when present, for example `anthropic/...` or `openai/...`\n- dotted and dashed version variants can normalize only when they map to an existing official id, for example `4.6 -> 4-6`\n- ambiguous families or versions are not merged without a bundled match or explicit override\n\n### Canonical resolution behavior\n\nWhen multiple concrete variants share a canonical id, resolution uses:\n\n1. availability and auth\n2. `config.yml` `modelProviderOrder`\n3. existing registry/provider order if `modelProviderOrder` is unset\n\nDisabled or unauthenticated providers are skipped.\n\nSession state and transcripts continue to record the concrete provider/model that actually executed the turn.\n\nProvider defaults vs per-model overrides:\n\n- Provider `headers` are baseline.\n- Model `headers` override provider header keys.\n- `modelOverrides` can override model metadata (`name`, `reasoning`, `input`, `cost`, `contextWindow`, `maxTokens`, `headers`, `compat`, `contextPromotionTarget`).\n- `compat` is deep-merged for nested routing blocks (`openRouterRouting`, `vercelGatewayRouting`, `extraBody`).\n\n## Runtime discovery integration\n\n### Implicit Ollama discovery\n\nIf `ollama` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `ollama`\n- api: `openai-responses`\n- base URL: `OLLAMA_BASE_URL` or `http://127.0.0.1:11434`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls Ollama endpoints and normalizes discovered OpenAI-compatible models to `openai-responses`.\n\n### Implicit llama.cpp discovery\n\nIf `llama.cpp` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `llama.cpp`\n- api: `openai-responses`\n- base URL: `LLAMA_CPP_BASE_URL` or `http://127.0.0.1:8080`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls llama.cpp model endpoints and synthesizes model entries with local defaults.\n\n### Implicit LM Studio discovery\n\nIf `lm-studio` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `lm-studio`\n- api: `openai-completions`\n- base URL: `LM_STUDIO_BASE_URL` or `http://127.0.0.1:1234/v1`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery fetches models (`GET /models`) and synthesizes model entries with local defaults.\n\n### Explicit provider discovery\n\nYou can configure discovery yourself:\n\n```yaml\nproviders:\n  ollama:\n    baseUrl: http://127.0.0.1:11434\n    api: openai-responses\n    auth: none\n    discovery:\n      type: ollama\n\n  llama.cpp:\n    baseUrl: http://127.0.0.1:8080\n    api: openai-responses\n    auth: none\n    discovery:\n      type: llama.cpp\n```\n\n### Proxy discovery (`discovery.type: proxy`)\n\nFor Anthropic+OpenAI-compatible proxies (new-api / one-api / similar)\nthat expose both `/v1/messages` and `/v1/chat/completions` behind the same\nhost. Discovery hits `GET /v1/models` (10s timeout, OpenAI-style payload) and\nderives each model's `api` from the entry's `supported_endpoint_types`:\n\n- contains `\"anthropic\"` -> `api: anthropic-messages` (routes via `/v1/messages`)\n- contains `\"openai\"`    -> `api: openai-completions` (routes via `/v1/chat/completions`)\n- otherwise              -> falls back to provider-level `api` if set, else dropped\n\nProvider-level `api` is **optional** with `discovery.type: proxy` because the\nper-model wire is auto-detected. The Anthropic SDK strips a trailing `/v1`\nfrom `baseUrl` before appending `/v1/messages`, so a single discovery `baseUrl`\n(ending in `/v1`) round-trips correctly to both wires.\n\n```yaml\nproviders:\n  newapi-reseller:\n    baseUrl: https://api.example.com/v1\n    apiKey: xxxx\n    authHeader: true            # injects Authorization: Bearer for openai models\n    disableStrictTools: true    # most anthropic-fronted proxies reject `strict`\n    discovery:\n      type: proxy\n```\n\n### Extension provider registration\n\nExtensions can register providers at runtime (`pi.registerProvider(...)`), including:\n\n- model replacement/append for a provider\n- custom stream handler registration for new API IDs\n- custom OAuth provider registration\n\n## Auth and API key resolution order\n\nWhen requesting a key for a provider, effective order is:\n\n1. Runtime override (CLI `--api-key`)\n2. Stored API key credential in `agent.db`\n3. Stored OAuth credential in `agent.db` (with refresh)\n4. Environment variable mapping (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, etc.)\n5. ModelRegistry fallback resolver (provider `apiKey` from `models.yml`, env-name-or-literal semantics)\n\n`models.yml` `apiKey` behavior:\n\n- Value is first treated as an environment variable name.\n- If no env var exists, the literal string is used as the token.\n\nIf `authHeader: true` and provider `apiKey` is set, models get:\n\n- `Authorization: Bearer <resolved-key>` header injected.\n\nKeyless providers:\n\n- Providers marked `auth: none` are treated as available without credentials.\n- `getApiKey*` returns `kNoAuth` for them.\n\n### Broker mode\n\nWhen `OMP_AUTH_BROKER_URL` (or `auth.broker.url`) is set, the local SQLite credential store is replaced by `RemoteAuthCredentialStore`. Layers 2 and 3 above (stored API key / OAuth in `agent.db`) are served from a broker-supplied snapshot whose `refresh` tokens are redacted; expiry triggers `POST /v1/credential/:id/refresh` on the broker rather than a local refresh.\n\n`AuthStorage.setConfigApiKey` lets a `models.yml` `apiKey` win over a broker-resolved OAuth token without overriding a runtime `--api-key`. See [`auth-broker-gateway.md`](./auth-broker-gateway.md) for the full broker / gateway design and env surface (`OMP_AUTH_BROKER_URL`, `OMP_AUTH_BROKER_TOKEN`, `auth.broker.url`, `auth.broker.token`).\n\n## Model availability vs all models\n\n- `getAll()` returns the loaded model registry (built-in + merged custom + discovered).\n- `getAvailable()` filters to models that are keyless or have resolvable auth.\n\nSo a model can exist in registry but not be selectable until auth is available.\n\n## Runtime model resolution\n\n### CLI and pattern parsing\n\n`model-resolver.ts` supports:\n\n- exact `provider/modelId`\n- exact canonical model id\n- exact model id (provider inferred)\n- fuzzy/substring matching\n- glob scope patterns in `--models` (e.g. `openai/*`, `*sonnet*`)\n- optional `:thinkingLevel` suffix (`off|minimal|low|medium|high|xhigh`)\n\n`--provider` is legacy; `--model` is preferred.\n\nResolution precedence for exact selectors:\n\n1. exact `provider/modelId` bypasses coalescing\n2. exact canonical id resolves through the canonical index\n3. exact bare concrete id still works\n4. fuzzy and glob matching run after the exact paths\n\n### Initial model selection priority\n\n`findInitialModel(...)` uses this order:\n\n1. explicit CLI provider+model\n2. first scoped model (if not resuming)\n3. saved default provider/model\n4. known provider defaults (e.g. OpenAI/Anthropic/etc.) among available models\n5. first available model\n\n### Role aliases and settings\n\nSupported model roles:\n\n- `default`, `smol`, `slow`, `vision`, `plan`, `designer`, `commit`, `task`\n\nRole aliases like `pi/smol` expand through `settings.modelRoles`. Each role value can also append a thinking selector such as `:minimal`, `:low`, `:medium`, or `:high`.\n\nIf a role points at another role, the target model still inherits normally and any explicit suffix on the referring role wins for that role-specific use.\n\nRelated settings:\n\n- `modelRoles` (record)\n- `enabledModels` (scoped pattern list)\n- `modelProviderOrder` (global canonical-provider precedence)\n- `providers.kimiApiFormat` (`openai` or `anthropic` request format)\n- `providers.openaiWebsockets` (`auto|off|on` websocket preference for OpenAI Codex transport)\n\n`modelRoles` may store either:\n\n- `provider/modelId` to pin a concrete provider variant\n- a canonical id such as `gpt-5.3-codex` to allow provider coalescing\n\nFor `enabledModels` and CLI `--models`:\n\n- exact canonical ids expand to all concrete variants in that canonical group\n- explicit `provider/modelId` entries stay exact\n- globs and fuzzy matches still operate on concrete models\n\nGlobal `enabledModels` and `disabledProviders` entries may also be scoped to a path prefix:\n\n```yaml\nenabledModels:\n  - claude-sonnet-4-5\n  - path: ~/work\n    models:\n      - anthropic/claude-opus-4-5\ndisabledProviders:\n  - ollama\n  - path: ~/private\n    providers:\n      - anthropic\n```\n\nString entries apply everywhere. Scoped entries apply when the current working directory is the configured path or one of its subdirectories. Use `path`, `paths`, `pathPrefix`, or `pathPrefixes`; use `models` for `enabledModels`, `providers` for `disabledProviders`, or `values` for either.\n\n## `/model` and `--list-models`\n\nBoth surfaces keep provider-prefixed models visible and selectable.\n\nThey now also expose canonical/coalesced models:\n\n- `/model` includes a canonical view alongside provider tabs\n- `--list-models` prints a canonical section plus the concrete provider rows\n\nSelecting a canonical entry stores the canonical selector. Selecting a provider row stores the explicit `provider/modelId`.\n\n## Context promotion (model-level fallback chains)\n\nContext promotion is an overflow recovery mechanism for small-context variants (for example `*-spark`) that automatically promotes to a larger-context sibling when the API rejects a request with a context length error.\n\n### Trigger and order\n\nWhen a turn fails with a context overflow error (e.g. `context_length_exceeded`), `AgentSession` attempts promotion **before** falling back to compaction:\n\n1. If `contextPromotion.enabled` is true, resolve a promotion target (see below).\n2. If a target is found, switch to it and retry the request — no compaction needed.\n3. If no target is available, fall through to auto-compaction on the current model.\n\n### Target selection\n\nSelection is model-driven, not role-driven:\n\n1. `currentModel.contextPromotionTarget` (if configured)\n2. smallest larger-context model on the same provider + API\n\nCandidates are ignored unless credentials resolve (`ModelRegistry.getApiKey(...)`).\n\n### OpenAI Codex websocket handoff\n\nIf switching from/to `openai-codex-responses`, session provider state key `openai-codex-responses` is closed before model switch. This drops websocket transport state so the next turn starts clean on the promoted model.\n\n### Persistence behavior\n\nPromotion uses temporary switching (`setModelTemporary`):\n\n- recorded as a temporary `model_change` in session history\n- does not rewrite saved role mapping\n\n### Configuring explicit fallback chains\n\nConfigure fallback directly in model metadata via `contextPromotionTarget`.\n\n`contextPromotionTarget` accepts either:\n\n- `provider/model-id` (explicit)\n- `model-id` (resolved within current provider)\n\nExample (`models.yml`) for Spark -> non-Spark on the same provider:\n\n```yaml\nproviders:\n  openai-codex:\n    modelOverrides:\n      gpt-5.3-codex-spark:\n        contextPromotionTarget: openai-codex/gpt-5.3-codex\n```\n\nThe built-in model generator also assigns this automatically for `*-spark` models when a same-provider base model exists.\n\n## Compatibility and routing fields\n\nThe `compat` block on a provider or model overrides the URL-based auto-detection in `packages/ai/src/providers/openai-completions-compat.ts`. It is validated by `OpenAICompatSchema` in `packages/coding-agent/src/config/model-registry.ts` and consumed by every `openai-completions` transport (`packages/ai/src/providers/openai-completions.ts`). The canonical type is `OpenAICompat` in `packages/ai/src/types.ts`.\n\n`models.yml` accepts the following keys (all optional; unset falls back to URL detection):\n\nRequest shaping:\n\n- `supportsStore` — emit `store: false` on requests. Default: auto (off for non-standard endpoints).\n- `supportsDeveloperRole` — use the `developer` system role for reasoning models instead of `system`. Default: auto.\n- `supportsUsageInStreaming` — send `stream_options: { include_usage: true }` to receive token usage on streaming responses. Default: `true`.\n- `maxTokensField` — `\"max_completion_tokens\"` or `\"max_tokens\"`. Default: auto.\n- `supportsToolChoice` — emit the `tool_choice` parameter when the caller forces a specific tool. Default: `true`. Set `false` for endpoints that 400 on `tool_choice` (e.g. DeepSeek when reasoning is on).\n- `disableReasoningOnForcedToolChoice` — drop `reasoning_effort` / OpenRouter `reasoning` whenever `tool_choice` forces a call. Default: auto (Kimi/Anthropic-fronted endpoints).\n- `extraBody` — extra top-level fields merged into every request body (gateway hints, controller selectors, etc.).\n\nReasoning / thinking:\n\n- `supportsReasoningEffort` — accept `reasoning_effort`. Default: auto (off for Grok and zAI).\n- `reasoningEffortMap` — partial map from internal effort levels (`minimal|low|medium|high|xhigh`) to provider-specific strings (e.g. DeepSeek maps `xhigh -> \"max\"`).\n- `thinkingFormat` — request shape for thinking: `\"openai\"` (`reasoning_effort`), `\"openrouter\"` (`reasoning: { effort }`), `\"zai\"` (`thinking: { type: \"enabled\" }`), `\"qwen\"` (top-level `enable_thinking`), or `\"qwen-chat-template\"` (`chat_template_kwargs.enable_thinking`). Default: `\"openai\"`.\n- `reasoningContentField` — assistant field carrying chain-of-thought: `\"reasoning_content\"`, `\"reasoning\"`, or `\"reasoning_text\"`. Default: auto.\n- `requiresReasoningContentForToolCalls` — assistant tool-call turns must round-trip the reasoning field (DeepSeek-R1, Kimi, OpenRouter when reasoning is on). Default: `false`.\n- `requiresAssistantContentForToolCalls` — assistant tool-call turns must include non-empty text content (Kimi). Default: `false`.\n\nTool / message normalization:\n\n- `requiresToolResultName` — tool-result messages need a `name` field (Mistral). Default: auto.\n- `requiresAssistantAfterToolResult` — a user message after a tool result needs an assistant turn in between. Default: auto.\n- `requiresThinkingAsText` — convert thinking blocks to text wrapped in `<thinking>` delimiters (Mistral). Default: auto.\n- `requiresMistralToolIds` — normalize tool-call ids to exactly 9 alphanumeric chars. Default: auto.\n- `supportsStrictMode` — accept the per-tool `strict` field on tool schemas. Default: conservative auto-detect per provider/baseUrl.\n- `toolStrictMode` — `\"all_strict\"` forces strict on every tool, `\"none\"` forces it off; unset keeps the existing per-tool mixed behavior.\n\nGateway routing (only applied when `baseUrl` matches the gateway):\n\n- `openRouterRouting.only` / `openRouterRouting.order` — provider routing on `openrouter.ai` (see <https://openrouter.ai/docs/provider-routing>).\n- `vercelGatewayRouting.only` / `vercelGatewayRouting.order` — provider routing on `ai-gateway.vercel.sh` (see <https://vercel.com/docs/ai-gateway/models-and-providers/provider-options>).\n\nProvider-level `compat` is the baseline; per-model `compat` is deep-merged on top, with `openRouterRouting`, `vercelGatewayRouting`, and `extraBody` merged as nested objects.\n\n### Anthropic compatibility (`anthropic-messages`)\n\nFor `anthropic-messages` models the runtime uses a separate `AnthropicCompat` shape (`packages/ai/src/types.ts`). The `models.yml` schema currently exposes only the strict-tools opt-out as a top-level provider field (see below); the remaining Anthropic-side knobs (`disableAdaptiveThinking`, `supportsEagerToolInputStreaming`, `supportsLongCacheRetention`) are set by built-in catalog metadata and are not user-configurable from `models.yml`.\n\n### Strict tool schemas (`disableStrictTools`)\n\nAnthropic's API supports a `strict` field on tool definitions that forces the model to always follow the provided schema exactly. This is enabled by default for all `anthropic-messages` providers because it guarantees schema conformance in agentic systems.\n\nThird-party providers that front the Anthropic API (AWS Bedrock, Azure, self-hosted proxies) do not always implement this field and will reject requests that include it. Set `disableStrictTools: true` at the provider level to opt out:\n\n```yaml\nproviders:\n  bedrock-anthropic:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com/anthropic\n    apiKey: AWS_BEARER_TOKEN\n    api: anthropic-messages\n    disableStrictTools: true\n    models:\n      - id: claude-sonnet-4-20250514\n        name: Claude Sonnet 4 (Bedrock)\n        input: [text, image]\n        contextWindow: 200000\n        maxTokens: 16384\n        cost:\n          input: 3.00\n          output: 15.00\n          cacheRead: 0.30\n          cacheWrite: 3.75\n```\n\n`disableStrictTools` is a provider-level flag that applies to all models in the provider.\n\nTool schemas going on the wire are normalized by the unified flow in\n`packages/ai/src/utils/schema/normalize.ts` (Google/CCA/MCP dispatchers\nplus the OpenAI strict-mode sanitize+enforce pipeline). See\n[`ai-schema-normalize.md`](./ai-schema-normalize.md) for the strict-mode\nedge cases (local `$ref` inlining, single-item `allOf` collapse,\n`anyOf`-wrapper description hoist, enum/const primitive-type inference)\nand the per-provider dispatcher mapping.\n## Practical examples\n\n### Local OpenAI-compatible endpoint (no auth)\n\n```yaml\nproviders:\n  local-openai:\n    baseUrl: http://127.0.0.1:8000/v1\n    auth: none\n    api: openai-completions\n    models:\n      - id: Qwen/Qwen2.5-Coder-32B-Instruct\n        name: Qwen 2.5 Coder 32B (local)\n```\n\n### Hosted proxy with env-based key\n\n```yaml\nproviders:\n  anthropic-proxy:\n    baseUrl: https://proxy.example.com/anthropic\n    apiKey: ANTHROPIC_PROXY_API_KEY\n    api: anthropic-messages\n    authHeader: true\n    disableStrictTools: true  # if the proxy doesn't support strict tool schemas\n    models:\n      - id: claude-sonnet-4-20250514\n        name: Claude Sonnet 4 (Proxy)\n        reasoning: true\n        input: [text, image]\n```\n\n### Override built-in provider route + model metadata\n\n```yaml\nproviders:\n  openrouter:\n    baseUrl: https://my-proxy.example.com/v1\n    headers:\n      X-Team: platform\n    modelOverrides:\n      anthropic/claude-sonnet-4:\n        name: Sonnet 4 (Corp)\n        compat:\n          openRouterRouting:\n            only: [anthropic]\n```\n\n## Legacy consumer caveat\n\nMost model configuration now flows through `models.yml` via `ModelRegistry`. Explicit `.json` / `.jsonc` paths remain supported only when passed programmatically to `ModelRegistry`; the default user config is `~/.omp/agent/models.yml`.\n\n## Failure mode\n\nIf `models.yml` fails schema or validation checks:\n\n- registry keeps operating with built-in models\n- error is exposed via `ModelRegistry.getError()` and surfaced in UI/notifications\n",
 	"natives-addon-loader-runtime.md": "# Natives Addon Loader Runtime\n\nThis document covers the runtime loader shipped by `@oh-my-pi/pi-natives`: how `native/index.js` decides which `.node` file to require, how compiled-binary embedded payloads are extracted, and what startup failures report.\n\n## Implementation files\n\n- `packages/natives/native/index.js`\n- `packages/natives/native/loader-state.js`\n- `packages/natives/native/embedded-addon.js`\n- `packages/natives/scripts/embed-native.ts`\n- `packages/natives/package.json`\n\n## Scope and responsibility\n\nThe loader is intentionally narrow:\n\n- Build a platform/CPU-aware candidate list for addon filenames and directories.\n- Treat an embedded-addon manifest as the authoritative compiled-binary signal when present.\n- Optionally materialize an embedded addon into a versioned per-user cache directory.\n- Attempt candidates in deterministic order and return the first addon that `require(...)` loads.\n\nThe current loader does **not** run a separate `validateNative(...)` export-presence gate. API shape is provided by the generated N-API binding file (`native/index.d.ts`) and the loaded addon itself. A stale binary therefore normally fails as a missing property or native load error rather than as a custom \"missing exports\" validation error.\n\n## Runtime inputs and derived state\n\nAt module initialization, `native/index.js` computes:\n\n- **Platform tag**: `${process.platform}-${process.arch}` (for example `darwin-arm64`).\n- **Package version**: from `packages/natives/package.json`.\n- **Core directories**:\n  - `nativeDir`: package-local `packages/natives/native`.\n  - `execDir`: directory containing `process.execPath`.\n  - `versionedDir`: `<getNativesDir()>/<packageVersion>`.\n  - `userDataDir` fallback:\n    - Windows: `%LOCALAPPDATA%/omp` or `%USERPROFILE%/AppData/Local/omp`.\n    - Non-Windows: `~/.local/bin`.\n- **Natives cache root** (`getNativesDir()`):\n  - if `$XDG_DATA_HOME/omp` exists, `$XDG_DATA_HOME/omp/natives`;\n  - otherwise `~/.omp/natives`.\n- **Compiled-binary mode** (`detectCompiledBinary`): true if any of:\n  - embedded-addon manifest is non-null,\n  - `PI_COMPILED` env var is set,\n  - `import.meta.url` contains Bun embedded markers (`$bunfs`, `~BUN`, `%7EBUN`).\n- **Variant override**: `PI_NATIVE_VARIANT` (`modern`/`baseline` only; invalid values ignored).\n- **Selected variant**: explicit override, otherwise runtime AVX2 detection on x64 (`modern` if AVX2, else `baseline`).\n\n## Platform support and tag resolution\n\n`SUPPORTED_PLATFORMS` is fixed to:\n\n- `linux-x64`\n- `linux-arm64`\n- `darwin-x64`\n- `darwin-arm64`\n- `win32-x64`\n\nUnsupported platforms are not rejected before probing. The loader first tries the computed candidate paths. If all fail and `platformTag` is unsupported, it throws an unsupported-platform error listing supported tags.\n\n## Variant selection (`modern` / `baseline` / default)\n\n### x64 behavior\n\n1. `PI_NATIVE_VARIANT=modern|baseline` wins when valid.\n2. Otherwise AVX2 support is detected:\n   - Linux: scan `/proc/cpuinfo` for `avx2`.\n   - macOS: `sysctl -n machdep.cpu.leaf7_features`, then `machdep.cpu.features`.\n   - Windows: PowerShell `[System.Runtime.Intrinsics.X86.Avx2]::IsSupported`.\n3. AVX2 selects `modern`; unavailable or undetectable AVX2 selects `baseline`.\n\n### Non-x64 behavior\n\nNo variant suffix is used; the filename is `pi_natives.<platform>-<arch>.node`.\n\n### Filename construction\n\n`loader-state.js#getAddonFilenames` returns:\n\n- Non-x64 or no variant: `pi_natives.<tag>.node`\n- x64 + `modern`:\n  1. `pi_natives.<tag>-modern.node`\n  2. `pi_natives.<tag>-baseline.node`\n  3. `pi_natives.<tag>.node`\n- x64 + `baseline`:\n  1. `pi_natives.<tag>-baseline.node`\n  2. `pi_natives.<tag>.node`\n\nThe default unsuffixed fallback remains part of the x64 candidate list.\n\n## Candidate path construction and fallback ordering\n\n`resolveLoaderCandidates(...)` expands every filename across directories, then de-duplicates while preserving first occurrence order.\n\n### Non-compiled runtime\n\nFor each filename, candidates are:\n\n1. `<nativeDir>/<filename>`\n2. `<execDir>/<filename>`\n\n### Compiled runtime\n\nFor each filename, candidates are:\n\n1. `<versionedDir>/<filename>`\n2. `<userDataDir>/<filename>`\n3. `<nativeDir>/<filename>`\n4. `<execDir>/<filename>`\n\nAt load time, an extracted embedded candidate, when produced, is prepended ahead of these de-duplicated candidates.\n\n## Embedded addon extraction lifecycle\n\n`embedded-addon.js` is generated by `scripts/embed-native.ts`. The reset stub exports `embeddedAddon = null`. A populated manifest has:\n\n- `platformTag`\n- `version`\n- `files[]` entries with `variant`, `filename`, and `filePath`\n\nExtraction (`maybeExtractEmbeddedAddon`) runs only when:\n\n1. compiled-binary mode is true,\n2. `embeddedAddon` is non-null,\n3. manifest `platformTag` equals the runtime platform tag,\n4. manifest `version` equals the package version,\n5. a variant-appropriate embedded file exists.\n\nVariant file selection:\n\n- Non-x64: prefer `default`, then first available file.\n- x64 + `modern`: prefer `modern`, fallback to `baseline`.\n- x64 + `baseline`: require `baseline`.\n\nMaterialization:\n\n1. Ensure `<versionedDir>` exists.\n2. Reuse `<versionedDir>/<selected filename>` if it already exists.\n3. Otherwise read `selectedEmbeddedFile.filePath` and write the target path.\n4. Return the target path as the first candidate.\n\nDirectory creation or write failures are appended to the loader error list; probing continues through normal candidates.\n\n## Lifecycle and state transitions\n\n```text\nInit\n  -> Load package metadata and embedded-addon manifest\n  -> Compute platform/version/variant/filenames/candidate paths\n  -> (compiled + embedded manifest matches?)\n       yes -> try extract to versionedDir (record errors, continue)\n       no  -> skip extraction\n  -> For each runtime candidate in order:\n       require(candidate)\n       -> success: return addon exports (READY)\n       -> failure: record error, continue\n  -> none loaded:\n       if unsupported platform tag -> throw Unsupported platform\n       else -> throw Failed to load (tried-path diagnostics + hints)\n```\n\n## Failure behavior and diagnostics\n\n### Unsupported platform\n\nIf all candidates fail and `platformTag` is not supported, the loader throws:\n\n- `Unsupported platform: <tag>`\n- supported platform list\n- issue-reporting guidance\n\n### No loadable candidate\n\nIf the platform is supported but no candidate can be loaded, the final error includes:\n\n- `Failed to load pi_natives native addon for <platformTag>` or `<platformTag> (<variant>)`\n- every attempted path with the corresponding `require(...)` error\n- mode-specific remediation hints\n\n### Compiled-binary startup failures\n\nCompiled mode diagnostics include:\n\n- expected versioned cache target paths (`<versionedDir>/<filename>`),\n- remediation to delete the versioned cache and rerun,\n- direct release download `curl` commands for each expected filename.\n\n### Non-compiled startup failures\n\nNormal package/runtime diagnostics include:\n\n- reinstall hint (`bun install @oh-my-pi/pi-natives`),\n- local rebuild command (`bun --cwd=packages/natives run build`),\n- optional x64 variant build hint (`TARGET_VARIANT=baseline|modern bun --cwd=packages/natives run build`).\n",
 	"natives-architecture.md": "# Natives Architecture\n\n`@oh-my-pi/pi-natives` is now a two-layer package around a loader:\n\n1. **CommonJS loader/package entrypoint** resolves and loads the correct `.node` addon and patches generated enum objects onto the export object.\n2. **Rust N-API module layer** implements the exported functions/classes and emits the generated TypeScript declarations.\n\nThis document is the foundation for deeper module-level docs.\n\n## Implementation files\n\n- `packages/natives/native/index.js`\n- `packages/natives/native/index.d.ts`\n- `packages/natives/native/loader-state.js`\n- `packages/natives/native/embedded-addon.js`\n- `packages/natives/scripts/build-native.ts`\n- `packages/natives/scripts/embed-native.ts`\n- `packages/natives/scripts/gen-enums.ts`\n- `packages/natives/package.json`\n- `crates/pi-natives/src/lib.rs`\n\n## Package entrypoint and public surface\n\n`packages/natives/package.json` points directly at generated native bindings:\n\n- `main`: `./native/index.js`\n- `types`: `./native/index.d.ts`\n- `exports[\".\"].types`: `./native/index.d.ts`\n- `exports[\".\"].import`: `./native/index.js`\n\nThere is no current `packages/natives/src` TypeScript wrapper layer. Consumers import functions/classes/enums directly from `@oh-my-pi/pi-natives`; the type contract is the generated `native/index.d.ts` plus enum exports appended by `scripts/gen-enums.ts`.\n\nCurrent capability groups in the generated API include:\n\n- **Search/text/code primitives**: `grep`, `search`, `hasMatch`, `fuzzyFind`, `glob`, `astGrep`, `astEdit`, text width/slicing/wrapping/sanitization, syntax highlighting, token counting.\n- **Execution/process/terminal primitives**: `executeShell`, `Shell`, `PtySession`, process-tree helpers, key parsing.\n- **System/media/conversion primitives**: clipboard, image resize/encode/SIXEL, HTML-to-Markdown, macOS appearance/power helpers, work profiling, Windows ProjFS overlay helpers.\n\n## Loader layer\n\n`packages/natives/native/index.js` owns runtime addon selection and optional embedded extraction.\n\n### Candidate resolution model\n\n- Platform tag is `${process.platform}-${process.arch}`.\n- Supported tags are currently:\n  - `linux-x64`\n  - `linux-arm64`\n  - `darwin-x64`\n  - `darwin-arm64`\n  - `win32-x64`\n- x64 can use CPU variants:\n  - `modern` (AVX2-capable)\n  - `baseline` (fallback)\n- Non-x64 uses the default filename without a variant suffix.\n\nFilename strategy:\n\n- Default: `pi_natives.<platform>-<arch>.node`\n- x64 variant: `pi_natives.<platform>-<arch>-modern.node` or `...-baseline.node`\n- x64 runtime fallback includes the unsuffixed default filename after variant candidates.\n\n### Platform-specific variant detection\n\nFor x64, variant selection uses:\n\n- Linux: `/proc/cpuinfo`\n- macOS: `sysctl -n machdep.cpu.leaf7_features`, then `machdep.cpu.features`\n- Windows: PowerShell check for `System.Runtime.Intrinsics.X86.Avx2`\n\n`PI_NATIVE_VARIANT` can force `modern` or `baseline`; invalid values are ignored.\n\n### Binary distribution and extraction model\n\n`packages/natives/package.json` publishes `native/`, which contains the loader, generated declarations, generated enum patch, embedded-addon manifest stub, and prebuilt `.node` artifacts.\n\nFor compiled binaries, loader behavior is:\n\n1. Check versioned user cache path: `<getNativesDir()>/<packageVersion>/...`.\n2. Check legacy compiled-binary location:\n   - Windows: `%LOCALAPPDATA%/omp` (fallback `%USERPROFILE%/AppData/Local/omp`)\n   - non-Windows: `~/.local/bin`\n3. Fall back to packaged `native/` and executable directory candidates.\n\n`getNativesDir()` uses `$XDG_DATA_HOME/omp/natives` when `$XDG_DATA_HOME/omp` exists; otherwise it uses `~/.omp/natives`.\n\nIf a populated embedded addon manifest is present, it is also treated as a compiled-binary signal. The loader can extract the matching embedded `.node` into the versioned cache directory before candidate probing.\n\n### Failure modes\n\nLoader failures are explicit:\n\n- **Unsupported platform tag**: after failed probing, throws with supported platform list.\n- **No loadable candidate**: throws with all attempted paths and remediation hints.\n- **Embedded extraction errors**: directory/write failures are recorded and included in final load diagnostics if no candidate loads.\n\nThe current loader does not perform a separate post-`require` export validation pass.\n\n## Rust N-API module layer\n\n`crates/pi-natives/src/lib.rs` declares exported module ownership:\n\n- `appearance`\n- `ast`\n- `clipboard`\n- `fd`\n- `fs_cache`\n- `glob`\n- `glob_util`\n- `grep`\n- `highlight`\n- `html`\n- `image`\n- `keys`\n- `language`\n- `power`\n- `prof`\n- `projfs_overlay`\n- `ps`\n- `pty`\n- `shell`\n- `task`\n- `text`\n- `tokens`\n- `utils` (crate-private helpers)\n\nN-API exports are generated from Rust `#[napi]` functions/classes/objects/enums. Snake_case Rust names are exposed as camelCase JavaScript names unless explicitly configured by napi-rs.\n\n## Ownership boundaries\n\n- **Loader/package ownership (`packages/natives/native`, `packages/natives/scripts`)**\n  - runtime binary selection\n  - CPU variant selection and override handling\n  - compiled-binary embedded extraction\n  - generated TypeScript declarations and enum export patching\n- **Rust ownership (`crates/pi-natives/src`)**\n  - algorithmic and system-level implementation\n  - platform-native behavior and performance-sensitive logic\n  - N-API symbol implementation consumed directly by package callers\n- **Consumer ownership (`packages/coding-agent`, `packages/tui`)**\n  - user-facing policy and fallbacks that are not built into the native API\n  - higher-level rendering, artifact, shell-session, and command behavior\n\n## Runtime flow (high level)\n\n1. Consumer imports from `@oh-my-pi/pi-natives`.\n2. `native/index.js` computes platform/arch/variant and candidate paths.\n3. Optional embedded binary extraction occurs for compiled distributions.\n4. The first `require(candidate)` that succeeds becomes the exported addon object.\n5. Generated enum objects are appended to `module.exports`.\n6. Caller invokes generated N-API functions/classes directly.\n\n## Glossary\n\n- **Native addon**: A `.node` binary loaded via Node-API (N-API).\n- **Platform tag**: Runtime tuple `platform-arch` (for example `darwin-arm64`).\n- **Variant**: x64 CPU-specific build flavor (`modern` AVX2, `baseline` fallback).\n- **Generated binding declaration**: `native/index.d.ts` emitted by napi-rs during `build-native.ts`.\n- **Compiled binary mode**: Runtime mode where the CLI is bundled and native addons are resolved from embedded/cache paths before package-local paths.\n- **Embedded addon**: Build artifact metadata and file references generated into `native/embedded-addon.js` so compiled binaries can extract matching `.node` payloads.\n",

package/src/internal-urls/local-protocol.ts

@@ -5,7 +5,7 @@ import { isEnoent } from "@oh-my-pi/pi-utils";
 import { AgentRegistry } from "../registry/agent-registry";
 import { parseInternalUrl } from "./parse";
 import { validateRelativePath } from "./skill-protocol";
-import type { InternalResource, InternalUrl, ProtocolHandler } from "./types";
+import type { InternalResource, InternalUrl, ProtocolHandler, UrlCompletion } from "./types";
 
 export interface LocalProtocolOptions {
 	getArtifactsDir?: () => string | null;
@@ -246,4 +246,17 @@ export class LocalProtocolHandler implements ProtocolHandler {
 			notes: ["Use write path local://<file> to persist large intermediate artifacts across turns."],
 		};
 	}
+
+	async complete(): Promise<UrlCompletion[]> {
+		const opts = LocalProtocolHandler.resolveOptions();
+		if (!opts) return [];
+		const localRoot = path.resolve(resolveLocalRoot(opts));
+		try {
+			const files = await listFilesRecursively(localRoot);
+			return files.map(value => ({ value }));
+		} catch (err) {
+			if (isEnoent(err)) return [];
+			throw err;
+		}
+	}
 }

package/src/internal-urls/memory-protocol.ts

@@ -4,7 +4,7 @@ import { getAgentDir, isEnoent } from "@oh-my-pi/pi-utils";
 import { getMemoryRoot } from "../memories";
 import { AgentRegistry } from "../registry/agent-registry";
 import { validateRelativePath } from "./skill-protocol";
-import type { InternalResource, InternalUrl, ProtocolHandler } from "./types";
+import type { InternalResource, InternalUrl, ProtocolHandler, UrlCompletion } from "./types";
 
 const DEFAULT_MEMORY_FILE = "memory_summary.md";
 const MEMORY_NAMESPACE = "root";
@@ -161,4 +161,9 @@ export class MemoryProtocolHandler implements ProtocolHandler {
 
 		throw new Error(`Memory file not found: ${url.href}`);
 	}
+
+	async complete(): Promise<UrlCompletion[]> {
+		if (memoryRootsFromRegistry().length === 0) return [];
+		return [{ value: MEMORY_NAMESPACE, description: "Project memory summary" }];
+	}
 }

package/src/internal-urls/omp-protocol.ts

@@ -9,7 +9,7 @@
  */
 import * as path from "node:path";
 import { EMBEDDED_DOC_FILENAMES, EMBEDDED_DOCS } from "./docs-index.generated";
-import type { InternalResource, InternalUrl, ProtocolHandler } from "./types";
+import type { InternalResource, InternalUrl, ProtocolHandler, UrlCompletion } from "./types";
 
 /**
  * Handler for omp:// URLs.
@@ -33,6 +33,10 @@ export class OmpProtocolHandler implements ProtocolHandler {
 		return this.#readDoc(filename, url);
 	}
 
+	async complete(): Promise<UrlCompletion[]> {
+		return EMBEDDED_DOC_FILENAMES.map(value => ({ value }));
+	}
+
 	async #listDocs(url: InternalUrl): Promise<InternalResource> {
 		if (EMBEDDED_DOC_FILENAMES.length === 0) {
 			throw new Error("No documentation files found");

package/src/internal-urls/router.ts

@@ -15,7 +15,7 @@ import { OmpProtocolHandler } from "./omp-protocol";
 import { parseInternalUrl } from "./parse";
 import { RuleProtocolHandler } from "./rule-protocol";
 import { SkillProtocolHandler } from "./skill-protocol";
-import type { InternalResource, InternalUrl, ProtocolHandler, ResolveContext } from "./types";
+import type { InternalResource, InternalUrl, ProtocolHandler, ResolveContext, UrlCompletion } from "./types";
 import { VaultProtocolHandler } from "./vault-protocol";
 
 export class InternalUrlRouter {
@@ -66,6 +66,25 @@ export class InternalUrlRouter {
 		return this.#handlers.has(match[1].toLowerCase());
 	}
 
+	/** Schemes whose handler supports host/path autocomplete. */
+	completionSchemes(): string[] {
+		const schemes: string[] = [];
+		for (const [scheme, handler] of this.#handlers) {
+			if (handler.complete) schemes.push(scheme);
+		}
+		return schemes;
+	}
+
+	/**
+	 * Candidate completions for the host/path portion of `scheme://<query>`.
+	 * Returns `null` when the scheme is unknown or does not support completion.
+	 */
+	async complete(scheme: string, query: string): Promise<UrlCompletion[] | null> {
+		const handler = this.#handlers.get(scheme.toLowerCase());
+		if (!handler?.complete) return null;
+		return handler.complete(query);
+	}
+
 	async resolve(input: string, context?: ResolveContext): Promise<InternalResource> {
 		const parsed = parseInternalUrl(input);
 		const scheme = parsed.protocol.replace(/:$/, "").toLowerCase();

package/src/internal-urls/rule-protocol.ts

@@ -5,7 +5,7 @@
  * - rule://<name> - Reads rule content
  */
 import { getActiveRules } from "../capability/rule";
-import type { InternalResource, InternalUrl, ProtocolHandler } from "./types";
+import type { InternalResource, InternalUrl, ProtocolHandler, UrlCompletion } from "./types";
 
 export class RuleProtocolHandler implements ProtocolHandler {
 	readonly scheme = "rule";
@@ -35,4 +35,11 @@ export class RuleProtocolHandler implements ProtocolHandler {
 			notes: [],
 		};
 	}
+
+	async complete(): Promise<UrlCompletion[]> {
+		return getActiveRules().map(rule => ({
+			value: rule.name,
+			...(rule.description ? { description: rule.description } : {}),
+		}));
+	}
 }

package/src/internal-urls/skill-protocol.ts

@@ -9,7 +9,7 @@
  */
 import * as path from "node:path";
 import { getActiveSkills } from "../extensibility/skills";
-import type { InternalResource, InternalUrl, ProtocolHandler } from "./types";
+import type { InternalResource, InternalUrl, ProtocolHandler, UrlCompletion } from "./types";
 
 function getContentType(filePath: string): InternalResource["contentType"] {
 	const ext = path.extname(filePath).toLowerCase();
@@ -86,4 +86,11 @@ export class SkillProtocolHandler implements ProtocolHandler {
 			notes: [],
 		};
 	}
+
+	async complete(): Promise<UrlCompletion[]> {
+		return getActiveSkills().map(skill => ({
+			value: skill.name,
+			...(skill.description ? { description: skill.description } : {}),
+		}));
+	}
 }

package/src/internal-urls/types.ts

@@ -32,6 +32,22 @@ export interface InternalResource {
 	immutable?: boolean;
 }
 
+/**
+ * A single autocomplete candidate for the host/path portion of a `scheme://`
+ * URL, produced by {@link ProtocolHandler.complete}.
+ */
+export interface UrlCompletion {
+	/**
+	 * The text that follows `scheme://` for this candidate (e.g. `humanizer`,
+	 * `subdir/data.json`, `root`). The caller renders it as `scheme://<value>`.
+	 */
+	value: string;
+	/** Human-facing label for the dropdown. Defaults to {@link value}. */
+	label?: string;
+	/** Optional one-line description shown beside the candidate. */
+	description?: string;
+}
+
 /**
  * Parsed internal URL with preserved host casing.
  */
@@ -107,4 +123,15 @@ export interface ProtocolHandler {
 	 * surfaces a clear "not writable" error when invoked against them.
 	 */
 	write?(url: InternalUrl, content: string, context?: WriteContext): Promise<void>;
+	/**
+	 * Optional autocomplete hook. Returns candidate completions for the
+	 * host/path portion of a `scheme://` URL while the user composes a prompt.
+	 *
+	 * Implementations **MUST** be fast and local — this runs on every keystroke.
+	 * Schemes backed by network or external CLIs (issue://, pr://, vault://,
+	 * mcp://) omit it. The caller fuzzy-filters the returned set against the
+	 * partially typed `query`, so handlers return their full (bounded) candidate
+	 * list; `query` is provided only so handlers can scope expensive enumeration.
+	 */
+	complete?(query: string): Promise<UrlCompletion[]>;
 }

package/src/lsp/render.ts

@@ -103,7 +103,7 @@ export function renderResult(
 	args?: LspParams,
 ): Component {
 	const content = result.content?.[0];
-	if (!content || content.type !== "text" || !("text" in content) || !content.text) {
+	if (content?.type !== "text" || !("text" in content) || !content.text) {
 		const icon = formatStatusIcon("warning", theme, options.spinnerFrame);
 		const header = `${icon} LSP`;
 		return new Text([header, theme.fg("dim", "No result")].join("\n"), 0, 0);

package/src/mcp/oauth-flow.ts

@@ -42,7 +42,7 @@ function getUriPort(uri: URL): number {
 
 function validateRedirectConfig(config: MCPOAuthConfig, redirectUri: string | undefined): void {
 	const parsed = parseRedirectUri(redirectUri);
-	if (!parsed || parsed.protocol !== "https:" || !isLoopbackHostname(parsed.hostname)) {
+	if (parsed?.protocol !== "https:" || !isLoopbackHostname(parsed.hostname)) {
 		return;
 	}
 
@@ -63,7 +63,7 @@ function resolveCallbackPort(callbackPort: number | undefined, redirectUri: stri
 	if (callbackPort !== undefined) return callbackPort;
 
 	const parsed = parseRedirectUri(redirectUri);
-	if (!parsed || parsed.protocol !== "http:" || !isLoopbackHostname(parsed.hostname)) {
+	if (parsed?.protocol !== "http:" || !isLoopbackHostname(parsed.hostname)) {
 		return DEFAULT_PORT;
 	}
 

package/src/memory-backend/index.ts

@@ -1,3 +1,4 @@
+export * from "../mnemosyne";
 export * from "./local-backend";
 export * from "./off-backend";
 export * from "./resolve";