@gajae-code/coding-agent 0.2.3 → 0.2.4

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","REBRANDING_PLAN_260525.md","ai-schema-normalize.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","brand-assets.md","codebase-overview.md","compaction.md","environment-variables.md","fs-scan-cache-architecture.md","gjc-dogfood-skill-template.md","handoff-generation-pipeline.md","keybindings.md","lsp-config.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","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","theme.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/calc.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"];
+export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.md","REBRANDING_PLAN_260525.md","ai-schema-normalize.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","brand-assets.md","codebase-overview.md","compaction.md","environment-variables.md","fs-scan-cache-architecture.md","gjc-dogfood-skill-template.md","handoff-generation-pipeline.md","keybindings.md","lsp-config.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","onboarding-packet.md","onboarding-receipt.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","theme.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/calc.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"];
 
 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: `~/.gjc/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-openai-code    | 17                 | 112,243 | 151         |\n| gpt-5.5          | 2                  |  80,750 |  25         |\n| gpt-5.2-openai-code    | 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.",
@@ -28,8 +28,10 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"natives-rust-task-cancellation.md": "# Native Rust task execution and cancellation (`pi-natives`)\n\nThis document describes how `crates/pi-natives` schedules native work and how cancellation flows from JS options (`timeoutMs`, `AbortSignal`) into Rust execution.\n\n## Implementation files\n\n- `crates/pi-natives/src/task.rs`\n- `crates/pi-natives/src/grep.rs`\n- `crates/pi-natives/src/glob.rs`\n- `crates/pi-natives/src/fd.rs`\n- `crates/pi-natives/src/ast.rs`\n- `crates/pi-natives/src/shell.rs`\n- `crates/pi-natives/src/pty.rs`\n- `crates/pi-natives/src/html.rs`\n- `crates/pi-natives/src/image.rs`\n- `crates/pi-natives/src/clipboard.rs`\n- `crates/pi-natives/src/text.rs`\n- `crates/pi-natives/src/ps.rs`\n\n## Core primitives (`task.rs`)\n\n`task.rs` defines:\n\n1. `task::blocking(tag, cancel_token, work)`\n   - Wraps `napi::AsyncTask` / `Task`.\n   - `compute()` runs on libuv worker threads.\n   - Returns a JS `Promise<T>` for exported functions.\n   - Records a profiling sample through `profile_region(tag)`.\n\n2. `task::future(env, tag, work)`\n   - Wraps `env.spawn_future(...)`.\n   - Runs async work on Tokio's runtime.\n   - Returns `PromiseRaw<'env, T>`.\n   - Records a profiling sample through `profile_region(tag)`.\n\n3. `CancelToken` / `AbortToken` / `AbortReason`\n   - `CancelToken::new(timeout_ms, signal)` combines an optional deadline and optional JS `AbortSignal` converted from `Unknown`.\n   - `CancelToken::heartbeat()` is cooperative cancellation for blocking loops.\n   - `CancelToken::wait()` asynchronously waits for signal, timeout, or Ctrl-C.\n   - `CancelToken::emplace_abort_token()` creates an abortable flag when a later `Shell.abort()`/internal bridge needs one.\n   - `AbortToken::abort(reason)` lets external code request abort.\n\n## `blocking` vs `future`: execution model and selection\n\n### Use `task::blocking`\n\nUse when work is CPU-heavy or fundamentally synchronous/blocking:\n\n- regex/file scanning (`grep`, `glob`, `fuzzyFind`)\n- ast-grep search/edit worker work\n- PTY loop internals through `tokio::task::spawn_blocking`\n- image decode/resize/encode\n- HTML conversion\n- clipboard image read\n\nBehavior:\n\n- Work closure receives a cloned `CancelToken`.\n- Cancellation is only observed where code checks `ct.heartbeat()?`.\n- Closure `Err(...)` rejects the JS promise.\n\n### Use `task::future`\n\nUse when work must `await` async operations:\n\n- shell session orchestration (`Shell.run`, `executeShell`)\n- PTY outer promise (`PtySession.start`) before it enters `spawn_blocking`\n- task racing (`tokio::select!`) between completion and cancellation\n\nBehavior:\n\n- Future code can race normal completion against `ct.wait()`.\n- On cancel path, async implementations typically cancel subordinate machinery and may force-abort after a grace timeout.\n\n## JS API ↔ Rust export mapping (task/cancel relevant)\n\n| JS-facing API                           | Rust export                          | Scheduler                                                      | Cancellation hookup                                                                      |\n| --------------------------------------- | ------------------------------------ | -------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |\n| `grep(options, onMatch?)`               | `grep`                               | `task::blocking(\"grep\", ct, ...)`                              | `CancelToken::new(options.timeoutMs, options.signal)` + heartbeat checks                 |\n| `glob(options, onMatch?)`               | `glob`                               | `task::blocking(\"glob\", ct, ...)`                              | `CancelToken::new(...)` + heartbeat checks                                               |\n| `fuzzyFind(options)`                    | `fuzzy_find`                         | `task::blocking(\"fuzzy_find\", ct, ...)`                        | `CancelToken::new(...)` + heartbeat checks                                               |\n| `astGrep(options)` / `astEdit(options)` | ast exports                          | blocking worker path                                           | timeout/signal fields are accepted by options and checked cooperatively in worker loops  |\n| `Shell#run(options, onChunk?)`          | `Shell::run`                         | `task::future(env, \"shell.run\", ...)`                          | `ct.wait()` raced against run task; bridges to Tokio cancellation token and `AbortToken` |\n| `executeShell(options, onChunk?)`       | `execute_shell`                      | `task::future(env, \"shell.execute\", ...)`                      | same cancel race and 2s graceful window                                                  |\n| `PtySession#start(options, onChunk?)`   | `PtySession::start`                  | `task::future(env, \"pty.start\", ...)` + inner `spawn_blocking` | `CancelToken` checked in sync PTY loop via `heartbeat()`                                 |\n| `htmlToMarkdown(html, options?)`        | `html_to_markdown`                   | `task::blocking(\"html_to_markdown\", (), ...)`                  | none (`()` token)                                                                        |\n| `PhotonImage.parse/encode/resize`       | `PhotonImage::{parse,encode,resize}` | `task::blocking(...)`                                          | none (`()` token)                                                                        |\n| `readImageFromClipboard()`              | `read_image_from_clipboard`          | `task::blocking(\"clipboard.read_image\", (), ...)`              | none (`()` token)                                                                        |\n\n`text.rs`, `tokens.rs`, `keys.rs`, most `ps.rs` functions, and synchronous utility exports do not use `task::blocking`/`task::future` and therefore do not participate in this cancellation path.\n\n## Cancellation lifecycle and state transitions\n\n### `CancelToken` lifecycle\n\n```text\nCreated\n  ├─ no signal + no timeout  -> passive token\n  ├─ signal registered        -> AbortSignal callback can set AbortReason::Signal\n  └─ deadline set             -> timeout check becomes active\n\nRunning\n  ├─ heartbeat()/wait() sees signal   -> AbortReason::Signal\n  ├─ heartbeat()/wait() sees deadline -> AbortReason::Timeout\n  ├─ wait() sees Ctrl-C               -> AbortReason::User\n  └─ no abort                         -> continue\n\nAborted\n  └─ flag stores first observed cause for waiters; heartbeat formats it as \"Aborted: <reason>\"\n```\n\n### Before-start vs mid-execution cancellation\n\n- **Before start / before first cancellation check**:\n  - `task::future` users that race on `ct.wait()` can resolve cancellation once they enter `select!`.\n  - `task::blocking` users only observe cancellation when closure code reaches `heartbeat()`.\n\n- **Mid-execution**:\n  - `blocking`: next `heartbeat()` returns `Err(\"Aborted: ...\")`.\n  - `future`: `ct.wait()` branch wins `select!`, then code cancels subordinate async machinery.\n  - shell: cancellation triggers a Tokio cancellation token, waits up to 2 seconds, then aborts the task if needed.\n  - PTY: heartbeat failure or `kill()` terminates PTY child/process tree and drains output briefly.\n\n## Heartbeat expectations for long-running loops\n\n`heartbeat()` must run at predictable cadence in loops with unbounded or large work sets.\n\nObserved patterns:\n\n- `glob` filtering checks entries during scan/filter work.\n- `fd` scoring checks scanned candidates.\n- `grep` checks before/during expensive search and passes tokens into shared scan/cache helpers.\n- `run_pty_sync` checks every loop tick with a maximum 16ms wait cadence.\n\nPractical rule: no loop over external-size input should exceed a short bounded interval without a heartbeat.\n\n## Failure behavior and error propagation to JS\n\n### Blocking tasks\n\nError path:\n\n1. Closure returns `Err(napi::Error)` (including `heartbeat()` abort).\n2. `Task::compute()` returns `Err`.\n3. `AsyncTask` rejects JS promise.\n\nTypical error strings:\n\n- `Aborted: Timeout`\n- `Aborted: Signal`\n- domain errors (`Failed to decode image: ...`, `Conversion error: ...`, etc.)\n\n### Future tasks\n\nError path:\n\n1. Async body returns `Err(napi::Error)` or join failure is mapped (`... task failed: {err}`).\n2. `task::future`-spawned promise rejects.\n3. Shell and PTY command APIs model cancellation as structured results instead of rejection when the cancellation path wins: `exitCode` omitted, `cancelled` or `timedOut` set.\n\n### Cancellation reporting split\n\n- **Abort as error**: blocking exports using `heartbeat()?`.\n- **Abort as typed result**: shell/PTY command APIs that model cancellation in result structs.\n\nChoose one model per API and document it explicitly.\n\n## Common pitfalls\n\n1. **Missing heartbeat in blocking loops**\n   - Symptom: timeout/signal appears ignored until loop ends.\n   - Fix: add `ct.heartbeat()?` at loop top and before expensive per-item steps.\n\n2. **Long uncancelable sections**\n   - Symptom: cancellation latency spikes during single large call (decode, sort, compression, parser invocation, etc.).\n   - Fix: split work into chunks with heartbeat boundaries; if impossible, document latency.\n\n3. **Blocking async executor**\n   - Symptom: async API stalls when sync-heavy code runs directly in future.\n   - Fix: move CPU/sync blocks to `task::blocking` or `tokio::task::spawn_blocking`.\n\n4. **Inconsistent cancel semantics**\n   - Symptom: one API rejects on cancel, another resolves with flags, confusing callers.\n   - Fix: standardize per domain and keep docs aligned.\n\n5. **Forgetting cancellation bridge in nested async tasks**\n   - Symptom: outer token is cancelled but inner readers/subprocess tasks keep running.\n   - Fix: bridge cancellation to inner token/signal and enforce grace timeout + forced abort fallback.\n\n## Checklist for new cancellable exports\n\n1. Classify work correctly:\n   - CPU-bound or sync blocking -> `task::blocking`.\n   - async I/O / `await` orchestration -> `task::future`.\n\n2. Expose cancel inputs when needed:\n   - include `timeoutMs` and `signal` in `#[napi(object)]` options,\n   - create `let ct = task::CancelToken::new(timeout_ms, signal);`.\n\n3. Wire cancellation through all layers:\n   - blocking loops: `ct.heartbeat()?` at stable intervals,\n   - async orchestration: race with `ct.wait()` and cancel sub-tasks/tokens.\n\n4. Decide cancellation contract:\n   - reject promise with abort error, or\n   - resolve typed `{ cancelled, timedOut, ... }`,\n   - keep this contract consistent for the API family.\n\n5. Propagate failures with context:\n   - map errors via `Error::from_reason(format!(\"...: {err}\"))`,\n   - include stage-specific prefixes (`spawn`, `decode`, `wait`, etc.).\n\n6. Handle before-start and mid-flight cancellation:\n   - cancellation check/await must happen before expensive body and during long execution.\n\n7. Validate no executor misuse:\n   - no long sync work directly inside async futures without `spawn_blocking`/blocking task wrapper.\n",
 	"natives-shell-pty-process.md": "# Natives Shell, PTY, Process, and Key Internals\n\nThis document covers the execution/process/terminal primitives in `@gajae-code/natives`: `shell`, `pty`, `ps`, and `keys`, using the architecture terms from `docs/natives-architecture.md`.\n\n## Implementation files\n\n- `crates/pi-natives/src/shell.rs`\n- `crates/pi-natives/src/shell/windows.rs` (Windows-only PATH enrichment)\n- `crates/pi-natives/src/pty.rs`\n- `crates/pi-natives/src/ps.rs`\n- `crates/pi-natives/src/keys.rs`\n- `crates/pi-natives/src/task.rs`\n- `packages/natives/native/index.d.ts`\n\n## Layer ownership\n\n- **Package entrypoint** (`packages/natives/native/index.js`): loads the `.node` addon and exports generated N-API bindings.\n- **Rust N-API module layer** (`crates/pi-natives/src/*`): shell/PTY process execution, process-tree traversal/termination, and key-sequence parsing.\n- **Consumers** (`packages/coding-agent`, `packages/tui`): higher-level session policy, output artifact/minimizer handling, render policy, and UI key handling.\n\n## Shell subsystem (`shell`)\n\n### API model\n\nTwo execution modes are exposed:\n\n1. **One-shot** via `executeShell(options, onChunk?)`.\n2. **Persistent session** via `new Shell(options?)` then `shell.run(...)` repeatedly.\n\nBoth stream output through a threadsafe callback and return `{ exitCode?, cancelled, timedOut, minimized? }`.\n\n`ShellOptions` supports `sessionEnv`, `snapshotPath`, and optional output `minimizer`. `ShellExecuteOptions` supports command-scoped `env`, session-level `sessionEnv`, `snapshotPath`, timeout/signal, and optional minimizer. `ShellRunOptions` supports command, cwd, command-scoped env, timeout, and signal.\n\n### Session creation and environment model\n\nRust creates `brush_core::Shell` with:\n\n- non-interactive, non-login mode,\n- `no_profile` and `no_rc`,\n- `do_not_inherit_env: true`,\n- bash-mode builtins, with `exec` and `suspend` disabled,\n- explicit environment reconstruction from host env,\n- skip-list for shell-sensitive vars (`PS1`, `PWD`, `SHLVL`, bash function exports, etc.).\n\nSession env behavior:\n\n- `ShellOptions.sessionEnv` / one-shot `sessionEnv` is applied at session creation.\n- `ShellRunOptions.env` / one-shot `env` is command-scoped (`EnvironmentScope::Command`) and popped after the command.\n- `PATH` is merged specially on Windows with case-insensitive dedupe.\n- Windows-only path enrichment (`shell/windows.rs`) appends discovered Git-for-Windows paths when present and not already included.\n- `snapshotPath`, when present, is sourced during session creation with stdout/stderr/stdin wired to null files.\n\n### Runtime lifecycle and state transitions\n\nPersistent shell (`Shell.run`) uses this state machine:\n\n- **Idle/Uninitialized**: `session: None`.\n- **Running**: first `run()` lazily creates a session, stores an abort token, executes command.\n- **Completed + keepalive**: if execution control flow is normal, abort state is cleared and session is reused.\n- **Completed + teardown**: if control flow is loop/script/shell-exit related, session is dropped.\n- **Cancelled/Timed out**: run task is cancelled, grace wait is 2 seconds, task may be force-aborted, session is dropped if lock can be acquired.\n- **Error**: session is dropped.\n\nOne-shot shell (`executeShell`) always creates and drops a fresh session per call.\n\n### Streaming/output and minimizer behavior\n\n- Stdout/stderr are routed into a shared pipe and read concurrently.\n- Reader decodes UTF-8 incrementally; invalid byte sequences emit `U+FFFD` replacement chunks.\n- The command runs in a new process group policy.\n- Optional minimizer configuration can capture and rewrite output. When minimization occurs, the result includes `minimized` with filter name, replacement text, original text, and byte counts.\n- Consumers are responsible for persisting or displaying minimizer artifacts; the native result only carries the data.\n\n### Cancellation, timeout, and abort\n\n- `CancelToken` is constructed from `timeoutMs` and optional `AbortSignal`.\n- On cancellation/timeout, shell cancellation token is triggered, then task gets a 2-second graceful window before forced abort.\n- Structured result flags are used:\n  - timeout -> `exitCode` omitted, `timedOut: true`.\n  - abort signal / `Shell.abort()` -> `exitCode` omitted, `cancelled: true`.\n\n`Shell.abort()` behavior:\n\n- aborts the current running command for that `Shell` instance through the stored `AbortToken`,\n- resolves successfully even when nothing is running.\n\n### Failure behavior\n\nCommon surfaced errors include:\n\n- session init failures (`Failed to initialize shell`),\n- cwd errors (`Failed to set cwd`),\n- env set/pop failures,\n- snapshot source failures (`Failed to source snapshot`),\n- pipe creation/clone failures,\n- execution failure (`Shell execution failed: ...`),\n- task wrapper failures (`Shell execution task failed: ...`).\n\n## PTY subsystem (`pty`)\n\n### API model\n\n`new PtySession()` exposes:\n\n- `start(options, onChunk?) -> Promise<{ exitCode?, cancelled, timedOut }>`\n- `write(data)`\n- `resize(cols, rows)`\n- `kill()`\n\n`PtyStartOptions` supports `command`, optional `cwd`, optional `env`, `timeoutMs`, `signal`, `cols`, and `rows`.\n\n### Runtime lifecycle and state transitions\n\n`PtySession` state machine:\n\n- **Idle**: `core: None`.\n- **Reserved**: `start()` installs control channel synchronously (`core: Some`) before async work begins, so `write/resize/kill` become immediately valid.\n- **Running**: blocking PTY loop handles child state, reader events, cancellation heartbeat, and control messages.\n- **Terminal closed / drain**: child exit or cancellation starts a short reader drain window.\n- **Finalized**: `core` is always reset to `None` after start task completion (success or error).\n\nConcurrency guard:\n\n- starting while already running returns `PTY session already running`.\n\n### Spawn/attach/write/read/terminate patterns\n\n- PTY opened via `portable_pty::native_pty_system().openpty(...)`.\n- Command currently runs as `sh -lc <command>` with optional `cwd` and env overrides.\n- Default size is `120x40`; dimensions are clamped (`cols 20..400`, `rows 5..200`).\n- `write()` sends raw bytes to PTY stdin.\n- `resize()` sends a control message and clamps dimensions again.\n- `kill()` sends a control message that marks the run cancelled and terminates the child/process tree.\n\nOutput path:\n\n- dedicated reader thread reads master stream,\n- incremental UTF-8 decode emits `U+FFFD` for invalid bytes,\n- chunks forwarded through N-API threadsafe callback.\n\nTermination path:\n\n- Unix: terminate process group when known, terminate child tree, call child kill, then repeat with SIGKILL.\n- Non-Unix: terminate child tree, call child kill, then repeat with SIGKILL-equivalent process-tree helper.\n\n### Cancellation and timeout semantics\n\n- `timeoutMs` and `AbortSignal` feed a `CancelToken`.\n- Loop calls `ct.heartbeat()` periodically with a 16ms maximum wait cadence.\n- Timeout classification is based on the heartbeat error string containing `Timeout`.\n- Cancellation/kill starts a 300ms post-cancel drain window; normal child exit starts a 300ms post-exit drain window.\n\n### Failure behavior\n\nError surfaces include:\n\n- PTY allocation/open failure,\n- PTY spawn failure,\n- writer/reader acquisition failure,\n- child status/wait failures,\n- lock poisoning,\n- control-channel disconnection (`PTY session is no longer available`).\n\nControl call failures when not running:\n\n- `write/resize/kill` return `PTY session is not running`.\n\n## Process-tree subsystem (`ps`)\n\n### API model\n\n- `killTree(pid, signal) -> number`\n- `listDescendants(pid) -> number[]`\n\n### Platform-specific implementation\n\n- **Linux**: recursively reads `/proc/<pid>/task/<pid>/children`.\n- **macOS**: uses `libproc` `proc_listchildpids`.\n- **Windows**: snapshots process table with `CreateToolhelp32Snapshot`, builds parent->children map, terminates with `OpenProcess(PROCESS_TERMINATE)` + `TerminateProcess`.\n\n### Kill-tree behavior\n\n- Descendants are collected recursively.\n- Kill order is bottom-up (deepest descendants first).\n- Root pid is killed last.\n- Return value is count of successful terminations.\n\nSignal behavior:\n\n- POSIX: provided `signal` is passed to `kill`.\n- Windows: `signal` is ignored; termination is unconditional process terminate.\n\n### Failure behavior\n\nThis module is intentionally non-throwing at API surface for ordinary process misses:\n\n- missing/inaccessible process tree branches are skipped,\n- per-pid kill failures are counted as unsuccessful,\n- lookup miss typically yields `[]` from `listDescendants` and `0` from `killTree`.\n\n## Key parsing subsystem (`keys`)\n\n### API model\n\nExposed helpers:\n\n- `parseKey(data, kittyProtocolActive)`\n- `matchesKey(data, keyId, kittyProtocolActive)`\n- `parseKittySequence(data)`\n- `matchesKittySequence(data, expectedCodepoint, expectedModifier)`\n- `matchesLegacySequence(data, keyName)`\n\n### Parsing model\n\nThe parser combines:\n\n- direct single-byte mappings (`enter`, `tab`, `ctrl+<letter>`, printable ASCII),\n- O(1) legacy escape-sequence lookup (PHF map),\n- xterm `modifyOtherKeys` parsing,\n- Kitty protocol parsing (`CSI u`, `CSI ~`, `CSI 1;...<letter>`),\n- normalization to key IDs (`ctrl+c`, `shift+tab`, `pageUp`, `f5`, etc.).\n\nModifier handling:\n\n- only shift/alt/ctrl bits are compared for key matching,\n- lock bits are masked out before comparisons.\n\nLayout behavior:\n\n- base-layout fallback is intentionally constrained so remapped layouts do not create false matches for ASCII letters/symbols.\n\n### Failure behavior\n\n- Unrecognized or invalid sequences produce `null` from parse functions.\n- Match functions return `false` on parse failure or mismatch.\n- No thrown error surface for malformed key input.\n\n## JS API ↔ Rust export mapping\n\n### Shell + PTY + Process\n\n| JS API                            | Rust N-API export                      | Notes                                     |\n| --------------------------------- | -------------------------------------- | ----------------------------------------- |\n| `executeShell(options, onChunk?)` | `executeShell` (`execute_shell`)       | One-shot shell execution                  |\n| `new Shell(options?)`             | `Shell` class                          | Persistent shell session                  |\n| `shell.run(options, onChunk?)`    | `Shell::run`                           | Reuses session on keepalive control flow  |\n| `shell.abort()`                   | `Shell::abort`                         | Aborts active run for that shell instance |\n| `new PtySession()`                | `PtySession` class                     | Stateful PTY session                      |\n| `pty.start(options, onChunk?)`    | `PtySession::start`                    | Interactive PTY run                       |\n| `pty.write(data)`                 | `PtySession::write`                    | Raw stdin passthrough                     |\n| `pty.resize(cols, rows)`          | `PtySession::resize`                   | Clamped terminal dimensions               |\n| `pty.kill()`                      | `PtySession::kill`                     | Force-kills active PTY child              |\n| `killTree(pid, signal)`           | `killTree` (`kill_tree`)               | Children-first process tree termination   |\n| `listDescendants(pid)`            | `listDescendants` (`list_descendants`) | Recursive descendants listing             |\n\n### Keys\n\n| JS API                                         | Rust N-API export                                   | Notes                           |\n| ---------------------------------------------- | --------------------------------------------------- | ------------------------------- |\n| `matchesKittySequence(data, cp, mod)`          | `matchesKittySequence` (`matches_kitty_sequence`)   | Kitty codepoint+modifier match  |\n| `parseKey(data, kittyProtocolActive)`          | `parseKey` (`parse_key`)                            | Normalized key-id parser        |\n| `matchesLegacySequence(data, keyName)`         | `matchesLegacySequence` (`matches_legacy_sequence`) | Exact legacy sequence map check |\n| `parseKittySequence(data)`                     | `parseKittySequence` (`parse_kitty_sequence`)       | Structured Kitty parse result   |\n| `matchesKey(data, keyId, kittyProtocolActive)` | `matchesKey` (`matches_key`)                        | High-level key matcher          |\n\n## Abandoned session cleanup and finalization notes\n\n- **Shell persistent session**: if a run is cancelled/timed out/errors/non-keepalive control flow, Rust drops the internal session state. Successful normal runs keep the session for reuse.\n- **PTY session**: `core` is always cleared after `start()` finishes, including failure paths.\n- **No explicit JS finalizer-driven kill contract** is exposed by wrappers; cleanup is primarily tied to run completion/cancellation paths. Callers should use `timeoutMs`, `AbortSignal`, `shell.abort()`, or `pty.kill()` for deterministic teardown.\n",
 	"natives-text-search-pipeline.md": "# Natives Text/Search Pipeline\n\nThis document maps the `@gajae-code/natives` text/search/code surface from generated JS/TS exports to Rust N-API modules and back to JS result objects.\n\nTerminology follows `docs/natives-architecture.md`:\n\n- **Generated binding**: public API in `packages/natives/native/index.d.ts`.\n- **Rust module layer**: N-API exports in `crates/pi-natives/src/*`.\n- **Shared scan cache**: `fs_cache`-backed directory-entry cache used by discovery/search flows.\n\n## Implementation files\n\n- `packages/natives/native/index.d.ts`\n- `crates/pi-natives/src/grep.rs`\n- `crates/pi-natives/src/glob.rs`\n- `crates/pi-natives/src/glob_util.rs`\n- `crates/pi-natives/src/fs_cache.rs`\n- `crates/pi-natives/src/fd.rs`\n- `crates/pi-natives/src/ast.rs`\n- `crates/pi-natives/src/text.rs`\n- `crates/pi-natives/src/highlight.rs`\n- `crates/pi-natives/src/tokens.rs`\n\n## JS API ↔ Rust export mapping\n\n| JS API                                                                          | Rust export (`#[napi]`, snake_case -> camelCase) | Rust module    |\n| ------------------------------------------------------------------------------- | ------------------------------------------------ | -------------- |\n| `grep(options, onMatch?)`                                                       | `grep`                                           | `grep.rs`      |\n| `search(content, options)`                                                      | `search`                                         | `grep.rs`      |\n| `hasMatch(content, pattern, ignoreCase?, multiline?)`                           | `hasMatch`                                       | `grep.rs`      |\n| `fuzzyFind(options)`                                                            | `fuzzyFind`                                      | `fd.rs`        |\n| `glob(options, onMatch?)`                                                       | `glob`                                           | `glob.rs`      |\n| `invalidateFsScanCache(path?)`                                                  | `invalidateFsScanCache`                          | `fs_cache.rs`  |\n| `astGrep(options)`                                                              | `astGrep`                                        | `ast.rs`       |\n| `astEdit(options)`                                                              | `astEdit`                                        | `ast.rs`       |\n| `wrapTextWithAnsi(text, width, tabWidth)`                                       | `wrapTextWithAnsi`                               | `text.rs`      |\n| `truncateToWidth(text, maxWidth, ellipsis, pad, tabWidth)`                      | `truncateToWidth`                                | `text.rs`      |\n| `sliceWithWidth(line, startCol, length, strict, tabWidth)`                      | `sliceWithWidth`                                 | `text.rs`      |\n| `extractSegments(line, beforeEnd, afterStart, afterLen, strictAfter, tabWidth)` | `extractSegments`                                | `text.rs`      |\n| `visibleWidth(text, tabWidth)`                                                  | `visibleWidth`                                   | `text.rs`      |\n| `highlightCode(code, lang, colors)`                                             | `highlightCode`                                  | `highlight.rs` |\n| `supportsLanguage(lang)`                                                        | `supportsLanguage`                               | `highlight.rs` |\n| `getSupportedLanguages()`                                                       | `getSupportedLanguages`                          | `highlight.rs` |\n| `countTokens(input, encoding?)`                                                 | `countTokens`                                    | `tokens.rs`    |\n\n## Pipeline overview by subsystem\n\n## 1) Regex search (`grep`, `search`, `hasMatch`)\n\n### Input/options flow\n\n1. Callers invoke generated native exports directly; there is no package-local TS wrapper that renames `search` to `searchContent`.\n2. Rust option structs in `grep.rs` deserialize camelCase fields (`ignoreCase`, `maxCount`, `contextBefore`, `contextAfter`, `maxColumns`, `timeoutMs`).\n3. `grep` creates `CancelToken` from `timeoutMs` + `AbortSignal` and runs inside `task::blocking(\"grep\", ...)`.\n4. `search` and `hasMatch` operate on provided string/`Uint8Array` content and do not scan the filesystem.\n\n### Execution branches\n\n- **In-memory branch**\n  - `search` -> `search_sync` / search helpers over provided content bytes.\n  - `hasMatch` compiles/checks pattern against provided content and returns a boolean.\n  - No filesystem scan, no `fs_cache`.\n- **Single-file branch**\n  - `grep` resolves path, checks metadata is file, and searches that file.\n- **Directory branch**\n  - Optional cache lookup via `fs_cache::get_or_scan` when `cache: true`.\n  - Fresh scan via `fs_cache::force_rescan` when `cache: false`.\n  - Optional empty-result recheck when cached results are older than the empty-result recheck threshold.\n  - Entry filtering: file-only + optional glob filter (`glob_util`) + optional type filter mapping (`js`, `ts`, `rust`, etc.).\n\n### Search/collection semantics\n\n- Regex engine: `grep_regex::RegexMatcherBuilder` with `ignoreCase` and `multiline`.\n- Context resolution:\n  - `contextBefore/contextAfter` override legacy `context`.\n  - Non-content modes do not collect context.\n- Output modes:\n  - `content` -> one `GrepMatch` per hit.\n  - `count` and `filesWithMatches` map to count-style entries (`lineNumber=0`, `line=\"\"`, `matchCount` set).\n- Limits:\n  - Global `offset` and `maxCount` apply across files.\n  - Parallel path is used only when `maxCount` is unset and `offset == 0`; otherwise sequential path preserves deterministic global offset/limit semantics.\n\n### Result shaping back to JS\n\n- Rust `SearchResult`/`GrepResult` fields map to TS interfaces via N-API object conversion.\n- Counters are clamped before crossing N-API where needed.\n- `GrepResult.limitReached` is optional and emitted when true.\n- Streaming callback receives each shaped `GrepMatch` for content or count-style entries.\n\n### Failure behavior\n\n- `search` returns `SearchResult.error` for regex/search failures instead of throwing.\n- `grep` rejects on hard errors such as invalid path, invalid glob/regex, or cancellation timeout/abort.\n- `hasMatch` returns a boolean on success and throws on invalid pattern/UTF-8 conversion errors.\n- File open/search errors in multi-file scans are skipped per-file; scan continues.\n\n### Malformed regex handling\n\n`grep.rs` sanitizes braces before regex compile:\n\n- Invalid repetition-like braces are escaped (`{`/`}` -> `\\{`/`\\}`) when they cannot form `{N}`, `{N,}`, `{N,M}`.\n- This prevents common literal-template fragments (for example `${platform}`) from failing as malformed repetition.\n- Remaining invalid regex syntax still returns a regex error.\n\n## 2) File discovery (`glob`) and fuzzy path search (`fuzzyFind`)\n\n`glob` and `fuzzyFind` share `fs_cache` scans; matching logic differs.\n\n### `glob` flow\n\n1. Caller passes `GlobOptions` directly. `pattern` and `path` are required in the generated type.\n2. Rust resolves the search path and compiles pattern via `glob_util::compile_glob`.\n3. Entry source:\n   - `cache=true` -> `get_or_scan` + optional stale-empty `force_rescan`.\n   - `cache=false` -> `force_rescan(..., store=false)` (fresh only).\n4. Filtering:\n   - skip `.git` always;\n   - skip `node_modules` unless requested (`includeNodeModules`) or pattern mentions `node_modules`;\n   - apply glob match;\n   - apply file-type filter; symlink `file`/`dir` filters resolve target metadata.\n5. Optional sort by mtime descending (`sortByMtime`) before truncating to `maxResults`.\n\n### `fuzzyFind` flow\n\n1. Rust implementation lives in `fd.rs`; generated export is `fuzzyFind`.\n2. Shared scan source from `fs_cache` with the same cache/no-cache split and stale-empty recheck policy.\n3. Scoring:\n   - exact / starts-with / contains / subsequence-based fuzzy score;\n   - separator/punctuation-normalized scoring path;\n   - directory bonus and deterministic tie-break (`score desc`, then `path asc`).\n4. Symlink entries are excluded from fuzzy results.\n\n### Failure behavior\n\n- Invalid glob pattern returns an error from `glob_util::compile_glob`.\n- Search root must resolve to an existing directory for directory discovery flows.\n- Cancellation/timeouts propagate as abort errors via `CancelToken::heartbeat()` checks in loops.\n\n### Malformed glob handling\n\n`glob_util::build_glob_pattern` is tolerant:\n\n- normalizes `\\` to `/`,\n- auto-prefixes simple recursive patterns with `**/` when `recursive=true`,\n- auto-closes unbalanced `{...` alternation groups before compile.\n\n## 3) AST search/edit (`astGrep`, `astEdit`)\n\n`ast.rs` exposes syntax-aware code search and rewrite operations.\n\n- `astGrep(options)` returns matches with byte/line/column coordinates and optional metavariable bindings.\n- `astEdit(options)` returns replacement changes, per-file counts, searched/touched file counts, parse errors, and whether edits were applied.\n- `dryRun` defaults to true for edit options in the generated documentation.\n- Options include language override, path/glob/selector, strictness, limits, parse-error policy, `signal`, and `timeoutMs`.\n\nThese exports are direct native APIs used by tooling; they are not mediated by a TS wrapper in `packages/natives`.\n\n## 4) Shared scan/cache lifecycle (`fs_cache`)\n\n`fs_cache` stores scan results as normalized relative entries (`path`, `fileType`, optional `mtime`) keyed by:\n\n- canonical search root,\n- `include_hidden`,\n- `use_gitignore`.\n\n### Cache state transitions\n\n1. **Miss / disabled**\n   - TTL is `0` or key absent/expired -> fresh collection.\n2. **Hit**\n   - Entry age is within TTL -> return cached entries + `cache_age_ms`.\n3. **Stale-empty recheck**\n   - If query yields zero matches and cache age exceeds the empty-result threshold, force one rescan.\n4. **Invalidation**\n   - `invalidateFsScanCache(path?)`:\n     - no arg: clear all keys;\n     - path arg: remove keys for roots affected by that path.\n\n### Stale-result tradeoff\n\n- Cache favors low-latency repeated scans over immediate consistency.\n- TTL window can return stale positives/negatives.\n- Empty-result recheck reduces stale negatives for older cached scans at the cost of one extra scan.\n- Explicit invalidation is the intended correctness hook after file mutations.\n\n## 5) ANSI text utilities (`text`)\n\nThese are pure, in-memory utilities.\n\n### Boundaries and responsibilities\n\n- `text.rs` owns terminal-cell semantics:\n  - ANSI sequence parsing,\n  - grapheme-aware width and slicing,\n  - wrap/truncate/sanitize behavior,\n  - explicit tab-width parameter on width-sensitive APIs.\n- `grep.rs` line truncation (`maxColumns`) is separate:\n  - simple character-boundary truncation of matched lines with `...`,\n  - not ANSI-state-preserving and not terminal-cell width aware.\n\n### Key behaviors\n\n- `wrapTextWithAnsi`: wraps by visible width, carries active SGR codes across wrapped lines.\n- `truncateToWidth`: visible-cell truncation with ellipsis policy (`Unicode`, `Ascii`, `Omit`), optional right padding.\n- `sliceWithWidth`: column slicing with optional strict width enforcement.\n- `extractSegments`: extracts before/after segments around an overlay while restoring ANSI state for the `after` segment.\n- `sanitizeText` (ANSI/control/surrogate stripping with line-ending normalization) no longer lives in `text.rs`; it moved to `@gajae-code/utils` as a pure-JS implementation in `packages/utils/src/sanitize-text.ts`. The native binding was removed in the same change because the JS version was competitive on the benchmarked workloads, and keeping a Rust copy forced every caller (including `pi-utils`) to pull in `@gajae-code/natives`.\n- `visibleWidth`: counts visible terminal cells using caller-supplied tab width.\n\n### Failure behavior\n\nText functions generally return deterministic transformed output; errors are limited to N-API argument/string conversion boundaries.\n\n## 6) Syntax highlighting (`highlight`)\n\n`highlight.rs` is pure transformation; it does not use the filesystem scan cache.\n\n### Flow\n\n1. Caller passes `code`, optional `lang`, and ANSI color palette.\n2. Rust resolves syntax by token/name lookup, extension lookup, alias table fallback, then plain-text fallback.\n3. Each line is parsed with syntect `ParseState` and scope stack.\n4. Scopes map to semantic color categories and ANSI color codes are injected/reset.\n\n### Failure behavior\n\n- Per-line parse failure does not fail the call: that line is appended unhighlighted and processing continues.\n- Unknown/unsupported language falls back to plain text syntax.\n\n## 7) Token counting (`tokens`)\n\n`countTokens(input, encoding?)` is an in-memory utility.\n\n- `input` may be a single string or an array of strings.\n- Arrays return one aggregate count and are encoded in parallel in Rust.\n- Default encoding is `O200kBase`; `Cl100kBase` is also available.\n- The implementation uses ordinary tokenization, not special-token handling.\n\n## Pure utility vs filesystem-dependent flows\n\n| Flow                         | Filesystem access | Shared cache         | Notes                                         |\n| ---------------------------- | ----------------- | -------------------- | --------------------------------------------- |\n| `search` / `hasMatch`        | No                | No                   | regex on provided bytes/string only           |\n| `text` module functions      | No                | No                   | ANSI/width/sanitization only                  |\n| `highlight` module functions | No                | No                   | syntax + ANSI coloring only                   |\n| `countTokens`                | No                | No                   | tokenization only                             |\n| `astGrep` / `astEdit`        | Yes               | No                   | syntax-aware file search/edit                 |\n| `glob`                       | Yes               | Optional             | directory scans + glob filtering              |\n| `fuzzyFind`                  | Yes               | Optional             | directory scans + fuzzy scoring               |\n| `grep` (file/dir path)       | Yes               | Optional in dir mode | ripgrep over files, optional filters/callback |\n\n## End-to-end lifecycle summary\n\n1. Caller invokes generated native export with typed options.\n2. Rust validates/normalizes options and builds matcher/search config.\n3. For filesystem flows, entries are scanned (cache hit/miss/rescan where applicable) then filtered/scored/searched.\n4. Worker loops periodically call cancel heartbeat; timeout/abort can terminate execution.\n5. Rust shapes outputs into N-API objects (`lineNumber`, `matchCount`, `limitReached`, etc.).\n6. Generated bindings return typed JS objects and optional per-match callbacks for `grep`/`glob`.\n",
-	"non-compaction-retry-policy.md": "# Non-compaction auto-retry policy\n\nThis document describes the standard API-error retry path in `AgentSession`.\n\nIt explicitly excludes context-overflow recovery via auto-compaction. Overflow is handled by compaction logic and is documented separately in [`compaction.md`](../docs/compaction.md).\n\n## Implementation files\n\n- [`../src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts)\n- [`../src/config/settings-schema.ts`](../packages/coding-agent/src/config/settings-schema.ts)\n- [`../src/modes/controllers/event-controller.ts`](../packages/coding-agent/src/modes/controllers/event-controller.ts)\n- [`../src/modes/rpc/rpc-mode.ts`](../packages/coding-agent/src/modes/rpc/rpc-mode.ts)\n- [`../src/modes/rpc/rpc-client.ts`](../packages/coding-agent/src/modes/rpc/rpc-client.ts)\n- [`../src/modes/rpc/rpc-types.ts`](../packages/coding-agent/src/modes/rpc/rpc-types.ts)\n\n## Scope boundary vs compaction\n\nRetry and compaction are checked from the same `agent_end` path, but they are intentionally separated:\n\n1. `agent_end` inspects the last assistant message.\n2. `#isRetryableError(...)` runs first.\n3. If retry is initiated, compaction checks are skipped for that turn.\n4. Context-overflow errors are hard-excluded from retry classification (`isContextOverflow(...)` short-circuits retry).\n5. Overflow therefore falls through to `#checkCompaction(...)` instead of standard retry.\n\nSo: overload/rate/server/network-style failures use this retry policy; context-window overflow uses compaction recovery.\n\n## Retry classification\n\n`#isRetryableError(...)` requires all of the following:\n\n- assistant `stopReason === \"error\"`\n- `errorMessage` exists\n- message is **not** context overflow\n- `errorMessage` matches transient transport/envelope patterns or `isUsageLimitError(...)`\n\nCurrent retryable inputs are regex/string-classified:\n\n- transient transport/envelope failures, including Anthropic stream-envelope failures before `message_start`\n- overloaded/provider-returned-error wording\n- rate limit / usage limit / too many requests\n- HTTP-like server classes: 429, 500, 502, 503, 504\n- service unavailable / server/internal error\n- provider-suggested retry wording, including OpenAI `retry your request` failures\n- network/connection/socket failures, refused/closed connections, upstream connect/reset-before-headers, socket hang up, timeout/timed out, fetch failed, terminated, retry delay wording, and unexpected socket close messages\n\nThis is string-pattern classification, not typed provider error codes.\n\n## Retry lifecycle and state transitions\n\nSession state used by retry:\n\n- `#retryAttempt: number` (`0` means idle)\n- `#retryPromise: Promise<void> | undefined` (tracks in-progress retry lifecycle)\n- `#retryResolve: (() => void) | undefined` (resolves `#retryPromise`)\n- `#retryAbortController: AbortController | undefined` (cancels backoff sleep)\n\nFlow (`#handleRetryableError`):\n\n1. Read `retry` settings group.\n2. If `retry.enabled === false`, stop immediately (`false`, no retry started).\n3. Increment `#retryAttempt`.\n4. Create `#retryPromise` once (first attempt in a chain).\n5. If attempt exceeded `retry.maxRetries`, emit final failure event and stop.\n6. Compute base delay: `retry.baseDelayMs * 2^(attempt-1)`.\n7. For usage-limit errors, parse retry hints and call auth storage (`markUsageLimitReached(...)`); if credential switching succeeds, force delay to `0`, otherwise use a larger retry-after/backoff hint when present.\n8. If no credential switch occurred, suppress the current model selector for cooldown, try configured retry model fallback chains, and force delay to `0` on model switch.\n9. Emit `auto_retry_start`.\n10. Remove the trailing assistant error message from agent runtime state (kept in persisted session history).\n11. Sleep with abort support.\n12. Schedule `agent.continue()` through the post-prompt task scheduler (`delayMs: 1`) for the same prompt generation.\n\n### What resets retry counters\n\n`#retryAttempt` resets to `0` in these cases:\n\n- first successful non-error, non-aborted assistant message after retries started (emits `auto_retry_end { success: true }`)\n- retry cancellation during backoff sleep\n- max retries exceeded path\n\n`#retryPromise` resolves/clears when retry chain ends (success, cancellation, or max-exceeded), via `#resolveRetry()`.\n\n## Backoff and max-attempt semantics\n\nSettings:\n\n- `retry.enabled` (default `true`)\n- `retry.maxRetries` (default `3`)\n- `retry.baseDelayMs` (default `2000`)\n\nAttempt numbering:\n\n- attempt counter is incremented before max-check\n- start events use current attempt (1-based)\n- max-exceeded end event reports `attempt: this.#retryAttempt - 1` (last attempted retry count)\n\nBackoff sequence with default settings:\n\n- attempt 1: 2000 ms\n- attempt 2: 4000 ms\n- attempt 3: 8000 ms\n\nDelay override inputs can come from parsed retry headers (`retry-after-ms`, `retry-after`, `x-ratelimit-reset-ms`, `x-ratelimit-reset`) or usage-limit backoff. Credential/model fallback switches set delay to `0`; otherwise parsed hints can extend the exponential local delay.\n\n## Abort mechanics\n\n### Explicit retry abort\n\n`abortRetry()`:\n\n- aborts `#retryAbortController` (if present)\n- resolves retry promise (`#resolveRetry()`) so awaiters are unblocked\n\nIf abort hits while sleeping, catch path emits:\n\n- `auto_retry_end { success: false, finalError: \"Retry cancelled\" }`\n- resets attempt/controller\n\n### Global operation abort interaction\n\n`abort()` calls `abortRetry()` before aborting the active agent stream. This guarantees retry backoff is cancelled when user issues a general abort.\n\n### TUI interaction\n\nOn `auto_retry_start`, EventController:\n\n- swaps `Esc` handler to `session.abortRetry()`\n- renders loader text: `Retrying (attempt/maxAttempts) in Ns… (esc to cancel)`\n\nOn `auto_retry_end`, it restores prior `Esc` handler and clears loader state.\n\n## Streaming and prompt completion behavior\n\n`prompt()` ultimately waits on `#waitForRetry()` after `agent.prompt(...)` returns.\n\nEffect:\n\n- a prompt call does not fully resolve until any started retry chain finishes (success/failure/cancel)\n- retry lifecycle is part of one logical prompt execution boundary\n\nThis prevents callers from treating a retrying turn as complete too early.\n\n## Controls: settings and RPC\n\n### Configuration knobs\n\nDefined in settings schema under retry group:\n\n- `retry.enabled`\n- `retry.maxRetries`\n- `retry.baseDelayMs`\n- `retry.fallbackChains`\n- `retry.fallbackRevertPolicy` (`\"cooldown-expiry\"` by default; `\"never\"` disables automatic restoration)\n\nProgrammatic toggles in session:\n\n- `setAutoRetryEnabled(enabled)` writes `retry.enabled`\n- `autoRetryEnabled` reads `retry.enabled`\n- `isRetrying` reports whether retry lifecycle promise is active\n\n### RPC controls\n\nRPC command surface:\n\n- `set_auto_retry` → `session.setAutoRetryEnabled(command.enabled)`\n- `abort_retry` → `session.abortRetry()`\n\nClient helpers:\n\n- `RpcClient.setAutoRetry(enabled)`\n- `RpcClient.abortRetry()`\n\nBoth commands return success responses; retry progress/failure details come from streamed session events, not command response payloads.\n\n## Event emission and failure surfacing\n\nSession-level retry events:\n\n- `auto_retry_start { attempt, maxAttempts, delayMs, errorMessage }`\n- `auto_retry_end { success, attempt, finalError? }`\n- `retry_fallback_applied { from, to, role }`\n- `retry_fallback_succeeded { model, role }`\n\nPropagation:\n\n- emitted through `AgentSession.subscribe(...)`\n- forwarded to extension runner as extension events\n- in RPC mode, forwarded directly as JSON event objects (`session.subscribe(event => output(event))`)\n- in TUI, consumed by `EventController` for loader/error UI\n\nFinal failure surfacing:\n\n- On max-exceeded or cancellation, `auto_retry_end.success === false`\n- TUI shows: `Retry failed after N attempts: <finalError>`\n- Extensions/hooks receive `auto_retry_end` with same fields\n- RPC consumers receive same event object on stdout stream\n\n## Permanent stop conditions\n\nRetry stops and will not auto-continue when any of these occur:\n\n- `retry.enabled` is false\n- error is not retry-classified\n- error is context overflow (delegated to compaction path)\n- max retries exceeded\n- user cancels retry (`abort_retry` or `Esc` during retry loader)\n- global abort (`abort`) cancels retry first\n\nA new retry chain can still start later on a future retryable error after counters reset.\n\n## Operational caveats\n\n- Classification is regex text matching; provider-specific structured errors are not used here.\n- Retry strips the failing assistant error from **runtime context** before re-continue, but session history still keeps that error entry.\n- `RpcSessionState` currently exposes `autoCompactionEnabled` but not an `autoRetryEnabled` field; RPC callers must track their own toggle state or query settings through other APIs.\n- Model fallback changes append temporary `model_change` entries and may later restore the primary model when its cooldown expires, depending on `retry.fallbackRevertPolicy`.\n",
+	"non-compaction-retry-policy.md": "# Non-compaction auto-retry policy\n\nThis document describes the standard API-error retry path in `AgentSession`.\n\nIt explicitly excludes context-overflow recovery via auto-compaction. Overflow is handled by compaction logic and is documented separately in [`compaction.md`](../docs/compaction.md).\n\n## Implementation files\n\n- [`../src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts)\n- [`../src/config/settings-schema.ts`](../packages/coding-agent/src/config/settings-schema.ts)\n- [`../src/modes/controllers/event-controller.ts`](../packages/coding-agent/src/modes/controllers/event-controller.ts)\n- [`../src/modes/rpc/rpc-mode.ts`](../packages/coding-agent/src/modes/rpc/rpc-mode.ts)\n- [`../src/modes/rpc/rpc-client.ts`](../packages/coding-agent/src/modes/rpc/rpc-client.ts)\n- [`../src/modes/rpc/rpc-types.ts`](../packages/coding-agent/src/modes/rpc/rpc-types.ts)\n\n## Scope boundary vs compaction\n\nRetry and compaction are checked from the same `agent_end` path, but they are intentionally separated:\n\n1. `agent_end` inspects the last assistant message.\n2. `#isRetryableError(...)` runs first.\n3. If retry is initiated, compaction checks are skipped for that turn.\n4. Context-overflow errors are hard-excluded from retry classification (`isContextOverflow(...)` short-circuits retry).\n5. Overflow therefore falls through to `#checkCompaction(...)` instead of standard retry.\n\nSo: overload/rate/server/network-style failures use this retry policy; context-window overflow uses compaction recovery.\n\n## Retry classification\n\n`#isRetryableError(...)` requires all of the following:\n\n- assistant `stopReason === \"error\"`\n- `errorMessage` exists\n- message is **not** context overflow\n- `errorMessage` matches transient transport/envelope patterns or `isUsageLimitError(...)`\n\nCurrent retryable inputs are regex/string-classified:\n\n- transient transport/envelope failures, including Anthropic stream-envelope failures before `message_start`\n- overloaded/provider-returned-error wording\n- rate limit / usage limit / too many requests\n- HTTP-like server classes: 429, 500, 502, 503, 504\n- service unavailable / server/internal error\n- provider-suggested retry wording, including OpenAI `retry your request` failures\n- network/connection/socket failures, refused/closed connections, upstream connect/reset-before-headers, socket hang up, timeout/timed out, fetch failed, terminated, retry delay wording, and unexpected socket close messages\n\nThis is string-pattern classification, not typed provider error codes.\n\n## Retry lifecycle and state transitions\n\nSession state used by retry:\n\n- `#retryAttempt: number` (`0` means idle)\n- `#retryPromise: Promise<void> | undefined` (tracks in-progress retry lifecycle)\n- `#retryResolve: (() => void) | undefined` (resolves `#retryPromise`)\n- `#retryAbortController: AbortController | undefined` (cancels backoff sleep)\n\nFlow (`#handleRetryableError`):\n\n1. Read `retry` settings group.\n2. If `retry.enabled === false`, stop immediately (`false`, no retry started).\n3. Increment `#retryAttempt`.\n4. Create `#retryPromise` once (first attempt in a chain).\n5. If attempt exceeded `retry.maxRetries`, emit final failure event and stop.\n6. Compute base delay: `retry.baseDelayMs * 2^(attempt-1)`.\n7. For usage-limit errors, parse retry hints and call auth storage (`markUsageLimitReached(...)`); if credential switching succeeds, force delay to `0`, otherwise use a larger retry-after/backoff hint when present.\n8. If no credential switch occurred, suppress the current model selector for cooldown, try configured retry model fallback chains, and force delay to `0` on model switch.\n9. Emit `auto_retry_start`.\n10. Remove the trailing assistant error message from agent runtime state (kept in persisted session history).\n11. Sleep with abort support.\n12. Schedule `agent.continue()` through the post-prompt task scheduler (`delayMs: 1`) for the same prompt generation.\n\n### What resets retry counters\n\n`#retryAttempt` resets to `0` in these cases:\n\n- first successful non-error, non-aborted assistant message after retries started (emits `auto_retry_end { success: true }`)\n- retry cancellation during backoff sleep\n- max retries exceeded path\n\n`#retryPromise` resolves/clears when retry chain ends (success, cancellation, or max-exceeded), via `#resolveRetry()`.\n\n## Backoff and max-attempt semantics\n\nSettings:\n\n- `retry.enabled` (default `true`)\n- `retry.maxRetries` (default `3`)\n- `retry.baseDelayMs` (default `2000`)\n- `retry.maxDelayMs` (default `300000`)\n- `retry.requestMaxRetries` (default `5`) — provider request retries before a stream is established; counts retries, not the initial request\n- `retry.streamMaxRetries` (default `5`) — provider stream replay retries for replay-safe transient stream failures; counts retries, not the initial stream attempt\n\nAttempt numbering:\n\n- attempt counter is incremented before max-check\n- start events use current attempt (1-based)\n- max-exceeded end event reports `attempt: this.#retryAttempt - 1` (last attempted retry count)\n\nBackoff sequence with default settings:\n\n- attempt 1: 2000 ms\n- attempt 2: 4000 ms\n- attempt 3: 8000 ms\n\nDelay override inputs can come from parsed retry headers (`retry-after-ms`, `retry-after`, `x-ratelimit-reset-ms`, `x-ratelimit-reset`) or usage-limit backoff. Credential/model fallback switches set delay to `0`; otherwise parsed hints can extend the exponential local delay.\n\n## Abort mechanics\n\n### Explicit retry abort\n\n`abortRetry()`:\n\n- aborts `#retryAbortController` (if present)\n- resolves retry promise (`#resolveRetry()`) so awaiters are unblocked\n\nIf abort hits while sleeping, catch path emits:\n\n- `auto_retry_end { success: false, finalError: \"Retry cancelled\" }`\n- resets attempt/controller\n\n### Global operation abort interaction\n\n`abort()` calls `abortRetry()` before aborting the active agent stream. This guarantees retry backoff is cancelled when user issues a general abort.\n\n### TUI interaction\n\nOn `auto_retry_start`, EventController:\n\n- swaps `Esc` handler to `session.abortRetry()`\n- renders loader text: `Retrying (attempt/maxAttempts) in Ns… (esc to cancel)`\n\nOn `auto_retry_end`, it restores prior `Esc` handler and clears loader state.\n\n## Streaming and prompt completion behavior\n\n`prompt()` ultimately waits on `#waitForRetry()` after `agent.prompt(...)` returns.\n\nEffect:\n\n- a prompt call does not fully resolve until any started retry chain finishes (success/failure/cancel)\n- retry lifecycle is part of one logical prompt execution boundary\n\nThis prevents callers from treating a retrying turn as complete too early.\n\n## Controls: settings and RPC\n\n### Configuration knobs\n\nDefined in settings schema under retry group:\n\n- `retry.enabled`\n- `retry.maxRetries`\n- `retry.baseDelayMs`\n- `retry.fallbackChains`\n- `retry.fallbackRevertPolicy` (`\"cooldown-expiry\"` by default; `\"never\"` disables automatic restoration)\n\nProgrammatic toggles in session:\n\n- `setAutoRetryEnabled(enabled)` writes `retry.enabled`\n- `autoRetryEnabled` reads `retry.enabled`\n- `isRetrying` reports whether retry lifecycle promise is active\n\n### RPC controls\n\nRPC command surface:\n\n- `set_auto_retry` → `session.setAutoRetryEnabled(command.enabled)`\n- `abort_retry` → `session.abortRetry()`\n\nClient helpers:\n\n- `RpcClient.setAutoRetry(enabled)`\n- `RpcClient.abortRetry()`\n\nBoth commands return success responses; retry progress/failure details come from streamed session events, not command response payloads.\n\n## Event emission and failure surfacing\n\nSession-level retry events:\n\n- `auto_retry_start { attempt, maxAttempts, delayMs, errorMessage }`\n- `auto_retry_end { success, attempt, finalError? }`\n- `retry_fallback_applied { from, to, role }`\n- `retry_fallback_succeeded { model, role }`\n\nPropagation:\n\n- emitted through `AgentSession.subscribe(...)`\n- forwarded to extension runner as extension events\n- in RPC mode, forwarded directly as JSON event objects (`session.subscribe(event => output(event))`)\n- in TUI, consumed by `EventController` for loader/error UI\n\nFinal failure surfacing:\n\n- On max-exceeded or cancellation, `auto_retry_end.success === false`\n- TUI shows: `Retry failed after N attempts: <finalError>`\n- Extensions/hooks receive `auto_retry_end` with same fields\n- RPC consumers receive same event object on stdout stream\n\n## Permanent stop conditions\n\nRetry stops and will not auto-continue when any of these occur:\n\n- `retry.enabled` is false\n- error is not retry-classified\n- error is context overflow (delegated to compaction path)\n- max retries exceeded\n- user cancels retry (`abort_retry` or `Esc` during retry loader)\n- global abort (`abort`) cancels retry first\n\nA new retry chain can still start later on a future retryable error after counters reset.\n\n## Operational caveats\n\n- Classification is regex text matching; provider-specific structured errors are not used here.\n- Retry strips the failing assistant error from **runtime context** before re-continue, but session history still keeps that error entry.\n- `RpcSessionState` currently exposes `autoCompactionEnabled` but not an `autoRetryEnabled` field; RPC callers must track their own toggle state or query settings through other APIs.\n- Model fallback changes append temporary `model_change` entries and may later restore the primary model when its cooldown expires, depending on `retry.fallbackRevertPolicy`.\n\n## Provider request/stream retry budgets\n\nThe provider budgets are deliberately separate from session auto-retry:\n\n```yaml\nretry:\n  requestMaxRetries: 4\n  streamMaxRetries: 100\n```\n\n`requestMaxRetries` maps to provider SDK/fetch retry counts for request setup failures such as retryable 5xx/408/429/network errors. `streamMaxRetries` maps to provider-specific stream replay loops that are safe to repeat without duplicating visible assistant output. Providers that cannot safely replay a stream continue to surface the terminal error so the session-level auto-retry layer can decide whether to retry the turn.\n\nFail-fast cases stay fail-fast: invalid credentials (after any credential-refresh path is exhausted), unsupported model/provider configuration, malformed requests, context overflow, explicit user aborts, and permanent quota failures are not treated as transient provider budget candidates.\n",
 	"notebook-tool-runtime.md": "# Notebook tool runtime internals\n\nThis document describes the current `notebook` tool implementation and its relationship to the kernel-backed Python runtime.\n\nThe critical distinction: **`notebook` is a JSON notebook editor, not a notebook executor**. It edits `.ipynb` cell sources directly; it does not start or talk to a Python kernel.\n\n## Implementation files\n\n- [`src/tools/notebook.ts`](../packages/coding-agent/src/tools/notebook.ts)\n- [`src/eval/py/executor.ts`](../packages/coding-agent/src/eval/py/executor.ts)\n- [`src/eval/py/kernel.ts`](../packages/coding-agent/src/eval/py/kernel.ts)\n- [`src/session/streaming-output.ts`](../packages/coding-agent/src/session/streaming-output.ts)\n- [`src/tools/eval.ts`](../packages/coding-agent/src/tools/eval.ts)\n\n## 1) Runtime boundary: editing vs executing\n\n## `notebook` tool (`src/tools/notebook.ts`)\n\n- Supports `action: edit | insert | delete` on a `.ipynb` file.\n- Resolves path relative to session CWD (`resolveToCwd`).\n- Loads notebook JSON, validates `cells` array, validates `cell_index` bounds.\n- Applies source edits in-memory and writes full notebook JSON back with `JSON.stringify(notebook, null, 1)`.\n- Returns textual summary + structured `details` (`action`, `cellIndex`, `cellType`, `totalCells`, `cellSource`).\n\nNo kernel lifecycle exists in this tool:\n\n- no gateway acquisition\n- no kernel session ID\n- no `execute_request`\n- no stream chunks from kernel channels\n- no rich display capture (`image/png`, JSON display, status MIME)\n\n## Notebook-like execution path (`src/tools/eval.ts` + `src/eval/py/*`)\n\nWhen the agent needs to run cell-style Python code (sequential cells, persistent state, rich displays), that goes through the **`eval` tool** with `language: \"python\"`, not `notebook`.\n\nThat path is where kernel modes, restart/cancel behavior, chunk streaming, and output artifact truncation live.\n\n## 2) Notebook cell handling semantics (`notebook` tool)\n\n## Source normalization\n\n`content` is split into `source: string[]` with newline preservation:\n\n- each non-final line keeps trailing `\\n`\n- final line has no forced trailing newline\n\nThis mirrors notebook JSON conventions and avoids accidental line concatenation on later edits.\n\n## Action behavior\n\n- `edit`\n  - replaces `cells[cell_index].source`\n  - preserves existing `cell_type`\n- `insert`\n  - inserts at `[0..cellCount]`\n  - `cell_type` defaults to `code`\n  - code cells initialize `execution_count: null` and `outputs: []`\n  - markdown cells initialize only `metadata` + `source`\n- `delete`\n  - removes `cells[cell_index]`\n  - returns removed `source` in details for renderer preview\n\n## Error surfaces\n\nHard failures are thrown for:\n\n- missing notebook file\n- invalid JSON\n- missing/non-array `cells`\n- out-of-range index (insert and non-insert have different valid ranges)\n- missing `content` for `edit`/`insert`\n\nThese become `Error:` tool responses upstream; renderer uses notebook path + formatted error text.\n\n## 3) Kernel session semantics (where they actually exist)\n\nKernel semantics are implemented in `executePython` / `PythonKernel` and apply to the Python backend of the `eval` tool.\n\n## Modes\n\n`PythonKernelMode`:\n\n- `session` (default)\n  - kernels cached in `kernelSessions` map\n  - max 4 sessions; oldest evicted on overflow\n  - idle/dead cleanup every 30s, timeout after 5 minutes\n  - per-session queue serializes execution (`session.queue`)\n- `per-call`\n  - creates kernel for request\n  - executes\n  - always shuts down kernel in `finally`\n\n## Reset behavior\n\n`eval` passes `reset` only for the first cell in a multi-cell Python call; later cells always run with `reset: false`.\n\n## Kernel death / restart / retry\n\nIn session mode (`withKernelSession`):\n\n- dead kernel detected by heartbeat (`kernel.isAlive()` check every 5s) or execute failure.\n- pre-run dead state triggers `restartKernelSession`.\n- execute-time crash path retries once: restart kernel, rerun handler.\n- `restartCount > 1` in same session throws `Python kernel restarted too many times in this session`.\n\nStartup retry behavior:\n\n- shared gateway kernel creation retries once on `SharedGatewayCreateError` with HTTP 5xx.\n\nResource exhaustion recovery:\n\n- detects `EMFILE`/`ENFILE`/\"Too many open files\" style failures\n- clears tracked sessions\n- calls `shutdownSharedGateway()`\n- retries kernel session creation once\n\n## 4) Environment/session variable injection\n\nKernel startup receives the optional session file path from executor:\n\n- `GJC_SESSION_FILE` (session state file path)\n\n`PythonKernel.#initializeKernelEnvironment(...)` then runs init script inside kernel to:\n\n- `os.chdir(cwd)`\n- inject env entries into `os.environ`\n- prepend cwd to `sys.path` if missing\n\nImplication:\n\n- prelude helpers that read session context rely on this env var in Python process state.\n\n## 5) Streaming/chunk and display handling (kernel-backed path)\n\nThe kernel client processes Jupyter protocol messages per execution:\n\n- `stream` -> text chunk to `onChunk`\n- `execute_result` / `display_data` ->\n  - display text chosen by MIME precedence: `text/markdown` > `text/plain` > converted `text/html`\n  - structured outputs captured separately:\n    - `application/json` -> `{ type: \"json\" }`\n    - `image/png` -> `{ type: \"image\" }`\n    - `application/x-gjc-status` -> `{ type: \"status\" }` (no text emission)\n- `error` -> traceback text pushed to chunk stream + structured error metadata\n- `input_request` -> emits stdin warning text, sends empty `input_reply`, marks stdin requested\n- completion waits for both `execute_reply` and kernel `status=idle`\n\nCancellation/timeout:\n\n- abort signal triggers `interrupt()` (REST `/interrupt` + control-channel `interrupt_request`)\n- result marks `cancelled=true`\n- timeout path annotates output with `Command timed out after <n> seconds`\n\n## 6) Truncation and artifact behavior\n\n`OutputSink` in `src/session/streaming-output.ts` is used by kernel execution paths (`executeWithKernel`):\n\n- sanitizes every chunk (`sanitizeText`)\n- tracks total/output lines and bytes\n- optional artifact spill file (`artifactPath`, `artifactId`)\n- when in-memory buffer exceeds threshold (`DEFAULT_MAX_BYTES` unless overridden):\n  - marks truncated\n  - keeps tail bytes in memory (UTF-8 safe boundary)\n  - can spill full stream to artifact sink\n\n`dump()` returns:\n\n- visible output text (possibly tail-truncated)\n- truncation flag + counts\n- artifact ID (for `artifact://<id>` references)\n\n`eval` converts this metadata into result truncation notices and TUI warnings.\n\n`notebook` tool does **not** use `OutputSink`; it has no stream/artifact truncation pipeline because it does not execute code.\n\n## 7) Renderer assumptions and formatting\n\n## Notebook renderer (`notebookToolRenderer`)\n\n- call view: status line with action + notebook path + cell/type metadata\n- result view:\n  - success summary derived from `details`\n  - `cellSource` rendered via `renderCodeCell`\n  - markdown cells set language hint `markdown`; other cells have no explicit language override\n  - collapsed code preview limit is `PREVIEW_LIMITS.COLLAPSED_LINES * 2`\n  - supports expanded mode via shared render options\n  - uses render cache keyed by width + expanded state\n\nError rendering assumption:\n\n- if first text content starts with `Error:`, renderer formats as notebook error block.\n\n## Python renderer (for actual execution output)\n\nKernel-backed execution rendering expects:\n\n- per-cell status transitions (`pending/running/complete/error`)\n- optional structured status event section\n- optional JSON output trees\n- truncation warnings + optional `artifact://<id>` pointer\n\nThis renderer behavior is unrelated to `notebook` JSON editing results except that both reuse shared TUI primitives.\n\n## 8) Divergence from eval Python backend behavior\n\nIf \"plain Python execution\" means the `eval` tool with `language: \"python\"`:\n\n- `eval` executes code in a kernel, persists state by mode, streams chunks, captures rich displays, handles interrupts/timeouts, and supports output truncation/artifacts.\n- `notebook` performs deterministic notebook JSON mutations only; no execution, no kernel state, no chunk stream, no display outputs, no artifact pipeline.\n\nIf a workflow needs both:\n\n1. edit notebook source with `notebook`\n2. execute code cells via `eval` with `language: \"python\"` (manually passing code), not through `notebook`\n\nCurrent implementation does not provide a single tool that both mutates `.ipynb` and executes notebook cells through kernel context.\n",
+	"onboarding-packet.md": "# Gajae-Code Onboarding Packet\n\nThis packet is a docs-only, public-safe context seed for the `gajae-code` repository as inspected on 2026-06-01. It is intentionally a no-new-skill artifact: not a new workflow skill, command, agent, configuration surface, issue template, or runtime behavior.\n\n## Purpose in one paragraph\n\nGajae-Code is the `gjc` coding-agent CLI and supporting monorepo. The product centers on a small public workflow loop: clarify with `deep-interview`, plan with `ralplan`, execute and verify through `ultragoal`, and use `team` only when parallel tmux workers are useful. The main product package is `packages/coding-agent/`; supporting packages provide LLM/provider access, agent runtime, TUI rendering, native helpers, stats, utilities, benchmarks, and Python RPC/bot integrations.\n\n## Fixed public surface\n\nKeep this invariant front-and-center when onboarding to the repo:\n\n- Default workflow skills: `deep-interview`, `ralplan`, `team`, `ultragoal`.\n- Public role agents: `executor`, `architect`, `planner`, `critic`.\n- Bundled default workflow skill sources live under `packages/coding-agent/src/defaults/gjc/skills/`.\n- Bundled role-agent prompt sources live under `packages/coding-agent/src/prompts/agents/`.\n- Runtime state, specs, plans, goals, team state, and local overrides belong under `.gjc/` for the product and `.omx/` only for this agent-run orchestration.\n\nDo not add a fifth default skill, fifth public role agent, new command, new config surface, or feature-intake behavior unless that product decision has already been made and the default-surface gates are updated.\n\n## Primary entrypoints\n\n| Area             | Repo-relative path                                   | Why it matters                                                                                    |\n| ---------------- | ---------------------------------------------------- | ------------------------------------------------------------------------------------------------- |\n| CLI bootstrap    | `packages/coding-agent/src/cli.ts`                   | Registers top-level CLI commands and routes default launch behavior.                              |\n| Session launch   | `packages/coding-agent/src/main.ts`                  | Converts CLI/runtime settings into agent-session creation and mode dispatch.                      |\n| Agent assembly   | `packages/coding-agent/src/sdk.ts`                   | Loads settings, default skills, rules, tools, auth/model state, system prompt, and agent runtime. |\n| Built-in tools   | `packages/coding-agent/src/tools/index.ts`           | Registers file, shell, edit, search, browser, task/subagent, memory, and related tools.           |\n| Default skills   | `packages/coding-agent/src/defaults/gjc-defaults.ts` | Embeds and installs the four default workflow skills plus deep-interview fragments.               |\n| Role agents      | `packages/coding-agent/src/task/agents.ts`           | Embeds bundled task-agent prompts; tests enforce public role-agent expectations.                  |\n| Product overview | `README.md`                                          | Explains installation, product story, fixed workflow surface, and development entry commands.     |\n| Architecture map | `docs/codebase-overview.md`                          | Public package map and runtime-flow reference.                                                    |\n\n## Package map\n\n- `packages/coding-agent/` — main `gjc` CLI, workflows, session runtime, tool registry, discovery, settings, prompts, and tests.\n- `packages/ai/` — provider/model boundary, streaming, auth, model registry, retries, and provider integrations.\n- `packages/agent/` — stateful agent loop and append-only context runtime.\n- `packages/tui/` — terminal UI framework and rendering primitives.\n- `packages/natives/` plus `crates/*` — native helpers, Rust/N-API bindings, shell/PTY, text search, AST, filesystem, and media utilities.\n- `packages/utils/` — shared TypeScript utilities, logging, formatting, process helpers, JSON/frontmatter, and sanitization.\n- `packages/stats/` — local observability dashboard and session/model usage aggregation.\n- `packages/swarm-extension/` — optional YAML/DAG multi-agent extension outside the fixed default workflow surface.\n- `packages/typescript-edit-benchmark/` — TypeScript edit benchmark tooling.\n- `python/gjc-rpc/` — Python client for `gjc --mode rpc`.\n- `python/robogjc/` — GitHub triage/fix bot that drives `gjc --mode rpc`; this subtree has its own `AGENTS.md`.\n\n## Build, test, and validation commands\n\nPrefer targeted checks first, then broader checks when code changes justify them. For this docs-only packet, lightweight validation is enough.\n\n| Command                                                               | Scope                               | When to use                                                                 |\n| --------------------------------------------------------------------- | ----------------------------------- | --------------------------------------------------------------------------- |\n| `bun install`                                                         | Workspace dependencies              | Initial local setup.                                                        |\n| `bun run install:defaults`                                            | Local default install               | Installs source-bundled default workflow definitions for local development. |\n| `bun packages/coding-agent/src/cli.ts --help`                         | CLI smoke/discovery                 | Fast source checkout CLI sanity check.                                      |\n| `bun run check:ts`                                                    | Type/lint/default UI checks         | Broad TypeScript validation; heavier than docs-only changes.                |\n| `bun run test`                                                        | Full TS + Rust tests                | Broad regression check; use for runtime/product changes.                    |\n| `bun run ci:test:smoke`                                               | CLI version/help/stats worker smoke | Useful before release/install changes.                                      |\n| `bun scripts/check-visible-definitions.ts`                            | Default surface gate                | Required after workflow-definition changes.                                 |\n| `bun scripts/verify-g002-gates.ts`                                    | Rebrand/default-surface gate        | Required after workflow-definition or public-surface changes.               |\n| `bun scripts/rebrand-inventory.ts --strict`                           | Rebrand inventory gate              | Required after workflow-definition or public-surface changes.               |\n| `bun test packages/coding-agent/test/default-gjc-definitions.test.ts` | Four-skills/four-agents contract    | Required after default workflow/agent surface changes.                      |\n\nRepository rule: do not run `tsc` or `npx tsc`; use the Bun scripts above.\n\n## Danger zones\n\n- **Default surface expansion:** `packages/coding-agent/src/defaults/gjc/skills/`, `packages/coding-agent/src/defaults/gjc-defaults.ts`, `packages/coding-agent/src/prompts/agents/`, and model-assignment tests are contract-heavy. Changes here can accidentally alter the fixed four-skills/four-agents shape.\n- **CLI commands:** `packages/coding-agent/src/cli.ts` and `packages/coding-agent/src/commands/` define visible behavior. Adding commands or aliases is a product-surface change.\n- **Runtime/session assembly:** `packages/coding-agent/src/main.ts`, `packages/coding-agent/src/sdk.ts`, discovery, settings, tools, and system-prompt paths can affect every session.\n- **TUI/logging:** Avoid `console.log`, `console.warn`, or `console.error` inside `packages/coding-agent/`; use the centralized logger to avoid corrupting TUI rendering.\n- **Secrets/auth/config:** Keep `docs/secrets.md`, auth broker/gateway code, settings, and environment-variable docs public-safe. Do not expose tokens or private infrastructure.\n- **Native/Rust build:** `packages/natives/` and `crates/*` can require platform-specific toolchains and CI artifact behavior.\n- **Python bot subtree:** `python/robogjc/` has its own local instructions and trust boundaries.\n- **Generated model data:** Do not edit `packages/ai/src/models.json` directly; update generators/descriptors/resolvers and regenerate with `bun --cwd=packages/ai run generate-models`.\n\n## Unknowns worth preserving\n\n- Which onboarding packet shape will be most useful for future `gjc` context ingestion is still an experiment, not a product contract.\n- Public issue #158 / `gajae-deep-onboarding` context is summarized only from the user-provided prompt in this run; this packet does not add issue intake or feature workflow behavior.\n- Full CI may depend on runner/system dependencies and native artifacts; docs-only changes usually do not need the full matrix locally.\n- Some packages contain internal or hidden utility prompts/agents beyond the four public role agents. Public-facing docs should keep the four-role contract clear.\n\n## First safe tasks for a new contributor or agent\n\n1. Read `README.md`, `docs/codebase-overview.md`, and this packet.\n2. Run `bun packages/coding-agent/src/cli.ts --help` for a fast CLI surface check after dependencies are installed.\n3. For docs-only edits, run formatting/check commands that do not mutate runtime behavior.\n4. For default-surface edits, run the four required gates listed in the command table before claiming completion.\n5. For package code edits, start with the nearest package test, then escalate to `bun run check:ts` or `bun run test` as risk increases.\n6. Before changing `packages/coding-agent/src/defaults/gjc/skills/`, `packages/coding-agent/src/prompts/agents/`, `packages/coding-agent/src/commands/`, or config/settings paths, write down whether the change alters public surface area.\n\n## Context seed checklist\n\nA future agent can use this packet as context if it preserves these constraints:\n\n- Keep changes public-safe and repo-relative.\n- Prefer docs and tests over new runtime abstractions for onboarding experiments.\n- Treat the fixed four-skills/four-agents shape as a product constraint.\n- Verify claims with repo files before summarizing them.\n- Report validation evidence and caveats instead of implying hidden automation.\n",
+	"onboarding-receipt.md": "# Onboarding Packet Receipt\n\n- Date: 2026-06-01\n- Scope: docs-only no-new-skill onboarding packet experiment for this repository.\n- Output files:\n  - `docs/onboarding-packet.md`\n  - `docs/onboarding-receipt.md`\n- Public-safe boundary: no secrets, tokens, hidden prompts, private infrastructure, internal ops, or private paths beyond repo-relative paths.\n- Product boundary: no new skill, command, agent slot, issue, config, or runtime behavior.\n\n## Evidence inspected\n\n- `README.md`\n- `docs/codebase-overview.md`\n- `package.json`\n- `packages/coding-agent/package.json`\n- `packages/coding-agent/src/cli.ts`\n- `packages/coding-agent/src/main.ts`\n- `packages/coding-agent/src/sdk.ts`\n- `packages/coding-agent/src/defaults/gjc-defaults.ts`\n- `packages/coding-agent/src/task/agents.ts`\n- `packages/coding-agent/test/default-gjc-definitions.test.ts`\n- `.github/workflows/ci.yml`\n- `.github/workflows/dev-ci.yml`\n\n## Result\n\nThe packet records repo purpose, package layout, main entrypoints, build/test commands, danger zones, unknowns, and first safe tasks without changing the product surface. It is suitable as a public context seed for future onboarding experiments, not as a feature intake mechanism.\n\n## Caveats\n\n- The attempted `omx question --input '<json>' --json` interview round failed before user input because the runtime reported no attached tmux client; no human answer was inferred from that failed call.\n- Public issue context is limited to the user-provided prompt summary for this run.\n- Full CI was not required for the docs-only artifact unless later code/runtime files change.\n",
 	"porting-from-pi-mono.md": "# Porting From pi-mono: A Practical Merge Guide\n\nThis guide is a repeatable checklist for porting changes from pi-mono into this repo.\nUse it for any merge: single file, feature branch, or full release sync.\n\n## Last Sync Point (historical upstream marker)\n\n**Commit:** `b21b42d032919de2f2e6920a76fa9a37c3920c0a`\n**Date:** 2026-03-22\n\nUpdate this section after each sync; do not reuse the previous range. This commit is an upstream pi-mono marker and may not exist in this repo's local object database.\n\nWhen starting a new sync, generate patches from this commit forward in a pi-mono checkout or remote that contains the commit:\n\n```bash\ngit format-patch b21b42d032919de2f2e6920a76fa9a37c3920c0a..HEAD --stdout > changes.patch\n```\n\n## 0) Define the scope\n\n- Identify the upstream reference (commit, tag, or PR).\n- List the packages or folders you plan to touch.\n- Decide which features are in-scope and which are intentionally skipped.\n\n## 1) Bring code over safely\n\n- Prefer a clean, focused diff rather than a wholesale copy.\n- Avoid copying built artifacts or generated files.\n- If upstream added new files, add them explicitly and review contents.\n\n## 2) Match import extension conventions\n\nMost runtime TypeScript sources omit `.js` in internal imports, but several current entrypoints and tool modules keep `.js` for ESM/runtime compatibility. Follow the surrounding file and package export style; do not blanket-strip or blanket-add extensions.\n\n- In `packages/coding-agent` runtime sources, prefer extensionless internal imports when the surrounding module does, but preserve existing `.js` imports in files that already require them.\n- In `packages/tui/test` and `packages/natives/bench`, keep `.js` where surrounding files already use it.\n- Keep real file extensions when required by tooling or import assertions (e.g., `.json`, `.css`, `.md` text embeds).\n- Example: `import { x } from \"./foo.js\";` → `import { x } from \"./foo\";` only when that package/file convention is extensionless.\n\n## 3) Replace import scopes\n\nUpstream uses different package scopes. Replace them consistently.\n\n- Replace old scopes with the local scope used here.\n- Examples (adjust to match the actual packages you are porting):\n  - `@mariozechner/gajae-code` → `@gajae-code/coding-agent`\n  - `@mariozechner/pi-agent-core` → `@gajae-code/agent-core`\n  - `@mariozechner/pi-tui` → `@gajae-code/tui`\n  - `@mariozechner/pi-ai` → `@gajae-code/ai`\n\n## 4) Use Bun APIs where they improve on Node\n\nWe run on Bun, but the current source intentionally mixes Bun APIs with small Node standard-library APIs. Replace Node APIs only when Bun provides a clearer, safer, or simpler implementation; do not mechanically rewrite every Node import.\n\n**Prefer replacing when porting new code:**\n\n- Process spawning: prefer Bun Shell `$` for simple commands; use `Bun.spawn`/`Bun.spawnSync` for streaming or process control. Keep existing `child_process` only where its exact semantics are needed.\n- HTTP clients: `node-fetch`, `axios` → native `fetch`\n- SQLite: `better-sqlite3` → `bun:sqlite`\n- Env loading: `dotenv` → Bun loads `.env` automatically\n- Runtime text/assets: prefer Bun imports such as `with { type: \"text\" }` or `Bun.file()` over copy steps or bundled fallback file reads.\n\n**DO NOT replace (these work fine in Bun):**\n\n- `os.homedir()` — do NOT replace with `Bun.env.HOME` or literal `\"~\"`\n- `os.tmpdir()` — do NOT replace with `Bun.env.TMPDIR || \"/tmp\"` or hardcoded paths\n- `fs.mkdtempSync()` — do NOT replace with manual path construction\n- `path.join()`, `path.resolve()`, etc. — these are fine\n\n**Import style:** Use the `node:` prefix for Node standard-library imports. Namespace imports are common, but named imports are acceptable where the surrounding code already uses them.\n\n**Additional Bun conventions:**\n\n- Prefer Bun Shell `$` for short, non-streaming commands; use `Bun.spawn` only when you need streaming I/O or process control.\n- Use `Bun.file()`/`Bun.write()` for simple files and `node:fs/promises` for directory-oriented operations. Existing synchronous `node:fs` calls are acceptable when the calling flow is intentionally synchronous.\n- Avoid `Bun.file().exists()` checks; use `isEnoent` handling in try/catch.\n- Prefer `Bun.sleep(ms)` over `setTimeout` wrappers.\n\n**Wrong:**\n\n```typescript\n// BROKEN: env vars may be undefined, \"~\" is not expanded\nconst home = Bun.env.HOME || \"~\";\nconst tmp = Bun.env.TMPDIR || \"/tmp\";\n```\n\n**Correct:**\n\n```typescript\nimport * as os from \"node:os\";\nimport * as fs from \"node:fs\";\nimport * as path from \"node:path\";\n\nconst configDir = path.join(os.homedir(), \".config\", \"myapp\");\nconst tempDir = fs.mkdtempSync(path.join(os.tmpdir(), \"myapp-\"));\n```\n\n## 5) Prefer Bun embeds (no copying)\n\nDo not add new runtime asset copy steps. Keep assets in repo and prefer Bun embeds/imports; preserve existing explicit generation workflows such as `packages/coding-agent/src/export/html/template.generated.ts`.\n\n- If upstream copies assets into a dist folder, replace with Bun-friendly embeds.\n- Prompts are static `.md` files; use Bun text imports (`with { type: \"text\" }`) and Handlebars instead of inline prompt strings.\n- Use `import.meta.dir` + `Bun.file` to load adjacent non-text resources.\n- Keep assets in-repo and let the bundler include them.\n- Eliminate copy scripts unless the user explicitly requests them or the package already has an intentional generation step.\n- If upstream reads a bundled fallback file at runtime, replace filesystem reads with a Bun text embed import unless the current package already uses a generated asset pipeline.\n  - Example (provider instructions fallback):\n    - `const FALLBACK_PROMPT_PATH = join(import.meta.dir, \"openai-code-instructions.md\");` -> removed\n    - `import FALLBACK_INSTRUCTIONS from \"./openai-code-instructions.md\" with { type: \"text\" };`\n    - Use `return FALLBACK_INSTRUCTIONS;` instead of `readFileSync(FALLBACK_PROMPT_PATH, \"utf8\")`\n\n## 6) Port `package.json` carefully\n\nTreat `package.json` as a contract. Merge intentionally.\n\n- Keep existing `name`, `version`, `type`, `exports`, and `bin` unless the port requires changes.\n- Replace npm/node scripts with Bun equivalents (e.g., `bun check`, `bun test`).\n- Ensure dependencies use the correct scope.\n- Do not downgrade dependencies to fix type errors; upgrade instead.\n- Validate workspace package links and `peerDependencies`.\n\n## 7) Align code style and tooling\n\n- Keep existing formatting conventions.\n- Do not introduce `any` unless required.\n- Avoid dynamic imports unless they are required for optional dependencies, startup cost, or runtime-only modules; prefer top-level imports otherwise.\n- Never build prompts in code; prompts are static `.md` files rendered with Handlebars.\n- In `packages/coding-agent`, use `logger` from `@gajae-code/utils` for internal/runtime logging; CLI command files may use `console.*` for intentional user-facing output.\n- Use `Promise.withResolvers()` instead of `new Promise((resolve, reject) => ...)`.\n- Prefer ES `#` private fields for new encapsulated state. Constructor parameter properties already exist in current code and are acceptable; do not churn unrelated access modifiers while porting.\n- Prefer existing helpers and utilities over new ad-hoc code.\n  Preserve Bun-first infrastructure changes already made in this repo:\n  - Runtime is Bun (no Node entry points for the main CLI).\n  - Package manager is Bun (no npm lockfiles).\n  - Heavy Node APIs should not be introduced casually; current source still uses selected Node APIs (`node:crypto`, `node:readline`, synchronous `node:fs`, and `child_process`) where they fit provider, CLI, or process-control semantics.\n  - Lightweight Node APIs (`os.homedir`, `os.tmpdir`, `fs.mkdtempSync`, `path.*`) are kept.\n  - CLI shebangs use `bun` (not `node`, not `tsx`).\n  - TypeScript packages generally use source files directly; `@gajae-code/natives` exports generated native bindings from `packages/natives/native`.\n  - CI workflows run Bun for install/check/test.\n\n## 8) Remove old compatibility layers\n\nUnless requested, remove upstream compatibility shims.\n\n- Delete old APIs that were replaced.\n- Update all call sites to the new API directly.\n- Do not keep `*_v2` or parallel versions.\n\n## 9) Update docs and references\n\n- Replace pi-mono repo links where appropriate.\n- Update examples to use Bun and correct package scopes.\n- Ensure README instructions still match the current repo behavior.\n\n## 10) Validate the port\n\nRun the standard checks after changes:\n\n- `bun check`\n\nIf the repo already has failing checks unrelated to your changes, call that out.\nTests use Bun's runner (not Vitest), but only run `bun test` when explicitly requested.\n\n## 11) Protect improved features (regression trap list)\n\nIf you already improved behavior locally, treat those as **non‑negotiable**. Before porting, write down\nthe improvements and add explicit checks so they don’t get lost in the merge.\n\n- **Freeze the expected behavior**: add a short “before/after” note for each improvement (inputs, outputs,\n  defaults, edge cases). This prevents silent rollback.\n- **Map old → new APIs**: if upstream renamed concepts (hooks → extensions, custom tools → tools, etc.),\n  ensure every old entry point still wires through. One missed flag or export equals lost functionality.\n- **Verify exports**: check `package.json` `exports`, public types, and barrel files. Upstream ports often\n  forget to re-export local additions.\n- **Cover non‑happy paths**: if you fixed error handling, timeouts, or fallback logic, add a test or at\n  least a manual checklist that exercises those paths.\n- **Check defaults and config merge order**: improvements often live in defaults. Confirm new defaults\n  didn’t revert (e.g., new config precedence, disabled features, tool lists).\n- **Audit env/shell behavior**: if you fixed execution or sandboxing, verify the new path still uses your\n  sanitized env and does not reintroduce alias/function overrides.\n- **Re-run targeted samples**: keep a minimal set of \"known good\" examples and run them after the port\n  (CLI flags, extension registration, tool execution).\n\n## 12) Detect and handle reworked code\n\nBefore porting a file, check if upstream significantly refactored it:\n\n```bash\n# Compare the file you're about to port against what you have locally\ngit diff HEAD upstream/main -- path/to/file.ts\n```\n\nIf the diff shows the file was **reworked** (not just patched):\n\n- New abstractions, renamed concepts, merged modules, changed data flow\n\nThen you must **read the new implementation thoroughly** before porting. Blind merging of reworked code loses functionality because:\n\nNote: interactive mode was recently split into controllers/utils/types. When backporting related changes, port updates into the individual files we created and ensure `interactive-mode.ts` wiring stays in sync.\n\n1. **Defaults change silently** - A new variable `defaultFoo = [a, b]` may replace an old `getAllFoo()` that returned `[a, b, c, d, e]`.\n\n2. **API options get dropped** - When systems merge (e.g., `hooks` + `customTools` → `extensions`), old options may not wire through to the new implementation.\n\n3. **Code paths go stale** - A renamed concept (e.g., `hookMessage` → `custom`) needs updates in every switch statement, type guard, and handler—not just the definition.\n\n4. **Context/capabilities shrink** - Old APIs may have exposed `{ logger, typebox, pi }` that new APIs forgot to include.\n\n### Semantic porting process\n\nWhen upstream reworked a module:\n\n1. **Read the old implementation** - Understand what it did, what options it accepted, what it exposed.\n\n2. **Read the new implementation** - Understand the new abstractions and how they map to old behavior.\n\n3. **Verify feature parity** - For each capability in the old code, confirm the new code preserves it or explicitly removes it.\n\n4. **Grep for stragglers** - Search for old names/concepts that may have been missed in switch statements, handlers, UI components.\n\n5. **Test the boundaries** - CLI flags, SDK options, event handlers, default values—these are where regressions hide.\n\n### Quick checks\n\n```bash\n# Find all uses of an old concept that may need updating\nrg \"oldConceptName\" --type ts\n\n# Compare default values between versions\ngit show upstream/main:path/to/file.ts | rg \"default|DEFAULT\"\n\n# Check if all enum/union values have handlers\nrg \"case \\\"\" path/to/file.ts\n```\n\n## 13) Quick audit checklist\n\nUse this as a final pass before you finish:\n\n- [ ] Import extensions follow the local package convention (no blanket `.js` stripping)\n- [ ] No newly introduced Node-only APIs unless they match an existing justified pattern\n- [ ] All package scopes updated\n- [ ] `package.json` scripts use Bun\n- [ ] Prompts are `.md` text imports (no inline prompt strings)\n- [ ] No internal/runtime `console.*` in coding-agent; CLI user-facing output is intentional\n- [ ] Assets load via Bun embed/import patterns, or through an existing intentional generation pipeline\n- [ ] Tests or checks run (or explicitly noted as blocked)\n- [ ] No functionality regressions (see sections 11-12)\n\n## 14) Commit message format\n\nWhen committing a backport, follow the repo format `<type>(scope): <past-tense description>` and keep the commit\nrange in the title.\n\n```\nfix(coding-agent): backported pi-mono changes (<from>..<to>)\n\npackages/<package>:\n- <type>: <description>\n- <type>: <description> (#<issue> by @<contributor>)\n\npackages/<other-package>:\n- <type>: <description>\n```\n\n**Example:**\n\n```\nfix(coding-agent): backported pi-mono changes (9f3eef65f..52532c7c0)\n\npackages/ai:\n- fix: handle \"sensitive\" stop reason from Anthropic API\n- fix: normalize tool call IDs with special characters for Responses API\n- fix: add overflow detection for Bedrock, MiniMax, Kimi providers\n- fix: 429 status is rate limiting, not context overflow\n\npackages/tui:\n- fix: refactored autocomplete state tracking\n- fix: file autocomplete should not trigger on empty text\n- fix: configurable autocomplete max visible items\n- fix: improved table column width calculation with word-aware wrapping\n\npackages/coding-agent:\n- fix: preserve external config.yml edits on save (#1046 by @nicobailonMD)\n- fix: resolve macOS NFD and curly quote variants in file paths\n```\n\n**Rules:**\n\n- Group changes by package\n- Use conventional commit types (`fix`, `feat`, `refactor`, `perf`, `docs`)\n- Include upstream issue/PR numbers and contributor attribution for external contributions\n- The commit range in the title helps track sync points\n\n## 15) Intentional Divergences\n\nOur fork has architectural decisions that differ from upstream. **Do not port these upstream patterns:**\n\n### UI Architecture\n\n| Upstream                                    | Our Fork                                                  | Reason                                                                |\n| ------------------------------------------- | --------------------------------------------------------- | --------------------------------------------------------------------- |\n| `FooterDataProvider` class                  | `StatusLineComponent`                                     | Simpler, integrated status line                                       |\n| `ctx.ui.setHeader()` / `ctx.ui.setFooter()` | No-op stubs in current extension contexts                 | Not currently wired to replace the TUI status/header UI               |\n| `ctx.ui.setEditorComponent()`               | No-op stubs in current extension contexts                 | Custom editor replacement is not currently wired                      |\n| `InteractiveModeOptions` options object     | Positional constructor args (options type still exported) | Keep constructor signature; update the type when upstream adds fields |\n\n### Component Naming\n\n| Upstream                     | Our Fork                |\n| ---------------------------- | ----------------------- |\n| `extension-input.ts`         | `hook-input.ts`         |\n| `extension-selector.ts`      | `hook-selector.ts`      |\n| `ExtensionInputComponent`    | `HookInputComponent`    |\n| `ExtensionSelectorComponent` | `HookSelectorComponent` |\n\n### API Naming\n\n| Upstream                                 | Our Fork                                 | Notes                                     |\n| ---------------------------------------- | ---------------------------------------- | ----------------------------------------- |\n| `sessionManager.appendSessionInfo(name)` | `sessionManager.setSessionName(name)`    | We use `sessionName` throughout           |\n| `sessionManager.getSessionName()`        | `sessionManager.getSessionName()`        | Same (we unified to match upstream's RPC) |\n| `agent.sessionName` / `setSessionName()` | `agent.sessionName` / `setSessionName()` | Same                                      |\n\n### File Consolidation\n\n| Upstream                                           | Our Fork                                                  | Reason                                        |\n| -------------------------------------------------- | --------------------------------------------------------- | --------------------------------------------- |\n| `clipboard.ts` + `clipboard-image.ts` (tool files) | `src/utils/clipboard.ts` backed by `@gajae-code/natives` | Native implementation with a small TS wrapper |\n\n### Test Framework\n\n| Upstream                  | Our Fork                      |\n| ------------------------- | ----------------------------- |\n| `vitest` with `vi.mock()` | `bun:test` with `vi` from bun |\n| `node:test` assertions    | `expect()` matchers           |\n\n### Tool Architecture\n\n| Upstream                            | Our Fork                                                                                                      | Notes                                                     |\n| ----------------------------------- | ------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------- |\n| `createTool(cwd: string, options?)` | `createTools(session: ToolSession)` via `BUILTIN_TOOLS` registry                                              | Tool factories accept `ToolSession` and can return `null` |\n| Per-tool `*Operations` interfaces   | Only current per-tool override interfaces remain (for example `FindOperations`)                               | Used for SSH/remote overrides where present               |\n| Node.js `fs/promises` everywhere    | Bun file APIs for simple file writes/reads, `node:fs/promises` for dirs, selected sync `node:fs` where needed | Prefer Bun APIs when they simplify                        |\n\n### Auth Storage\n\n| Upstream                        | Our Fork                                    | Notes                                        |\n| ------------------------------- | ------------------------------------------- | -------------------------------------------- |\n| `proper-lockfile` + `auth.json` | `agent.db` (bun:sqlite)                     | Credentials stored exclusively in `agent.db` |\n| Single credential per provider  | Multi-credential with round-robin selection | Session affinity and backoff logic preserved |\n\n### Extensions\n\n| Upstream                      | Our Fork                                          |\n| ----------------------------- | ------------------------------------------------- |\n| `jiti` for TypeScript loading | Native Bun `import()`                             |\n| `pkg.pi` manifest field       | `pkg.gjc` preferred; fallback to `pkg.pi` remains |\n\n### Skip These Upstream Features\n\nWhen porting, **skip** these files/features entirely:\n\n- `footer-data-provider.ts` — we use StatusLineComponent\n- `clipboard-image.ts` — image clipboard support is exposed through `src/utils/clipboard.ts` backed by `@gajae-code/natives`\n- GitHub workflow files — we have our own CI\n- `models.generated.ts` — auto-generated, regenerate locally (as models.json instead)\n\n### Features We Added (Preserve These)\n\nThese exist in our fork but not upstream. **Never overwrite:**\n\n- `StatusLineComponent` in interactive mode\n- Multi-credential auth with session affinity\n- Capability-based discovery system (`defineCapability`, `registerProvider`, `loadCapability`, `skillCapability`, etc.)\n- MCP/Exa/SSH integrations\n- LSP writethrough for format-on-save\n- Bash interception (`checkBashInterception`)\n- Fuzzy path suggestions in read tool\n",
 	"porting-to-natives.md": "# Porting to pi-natives (N-API) — Field Notes\n\nThis is a practical guide for moving hot paths into `crates/pi-natives` and wiring them through the generated native package entrypoint. It exists to avoid the same failures happening twice.\n\n## When to port\n\nPort when any of these are true:\n\n- The hot path runs in render loops, tight UI updates, or large batches.\n- JS allocations dominate (string churn, regex backtracking, large arrays).\n- You already have a JS baseline and can benchmark both versions side by side.\n- The work is CPU-bound or blocking I/O that can run on the libuv thread pool.\n- The work is async I/O that can run on Tokio's runtime (for example shell execution).\n\nRust is reserved for native bindings, native OS/process/filesystem integration, and measured hot paths. New crates or Rust source trees must have an explicit native/performance rationale in `scripts/check-rust-scope.ts`; keep product policy, orchestration, and glue code in TypeScript unless the benchmark or native boundary justifies moving it.\n\nAvoid ports that depend on JS-only state or dynamic imports. N-API exports should be data-in/data-out. Long-running work should go through `task::blocking` (CPU-bound/blocking I/O) or `task::future` (async I/O) with cancellation where the caller needs `timeoutMs` or `AbortSignal`.\n\n## Current package shape\n\n`@gajae-code/natives` no longer has a `packages/natives/src/<module>` TypeScript wrapper layer. The package root points at generated native artifacts:\n\n- runtime entry: `packages/natives/native/index.js`\n- types entry: `packages/natives/native/index.d.ts`\n- loader helpers: `packages/natives/native/loader-state.js`\n- embedded manifest: `packages/natives/native/embedded-addon.js`\n\nConsumers import directly from `@gajae-code/natives`. The generated declarations are produced during `bun --cwd=packages/natives run build`.\n\n## Anatomy of a native export\n\n**Rust side:**\n\n- Implementation lives in `crates/pi-natives/src/<module>.rs`.\n- If you add a new module, register it in `crates/pi-natives/src/lib.rs`.\n- Export with `#[napi]`; snake_case exports are converted to camelCase automatically. Use explicit JS names only for true aliases/non-default names. Use `#[napi(object)]` for object-shaped structs.\n- For CPU-bound or blocking work, use `task::blocking(tag, cancel_token, work)`.\n- For async work that needs Tokio, use `task::future(env, tag, work)`.\n- Pass a `CancelToken` when the API exposes `timeoutMs` or `AbortSignal`, and call `heartbeat()` inside long loops.\n\n**Package/build side:**\n\n- `packages/natives/scripts/build-native.ts` runs napi-rs, installs the `.node` artifact, copies generated `index.js`/`index.d.ts`, and appends enum runtime exports.\n- `packages/natives/native/index.js` is the loader that chooses a candidate `.node` file and returns the loaded addon.\n- `packages/natives/package.json` exposes only the package root (`@gajae-code/natives`).\n\n**Consumer side:**\n\n- Update direct imports/callsites in `packages/coding-agent` or `packages/tui` when the new export replaces a JS implementation.\n- Keep higher-level policy in consumers unless it belongs in the native primitive itself.\n\n## Porting checklist\n\n1. **Add the Rust implementation**\n\n- Put the core logic in a plain Rust function.\n- If it is a new module, add it to `crates/pi-natives/src/lib.rs`.\n- Expose it with `#[napi]` so the default snake_case -> camelCase mapping stays consistent.\n- Keep signatures owned and simple: `String`, `Vec<String>`, `Uint8Array`, `Either<JsString, Uint8Array>`, or `#[napi(object)]` structs.\n- For CPU-bound or blocking work, use `task::blocking`; for async work, use `task::future`.\n- If exposing cancellation, include `timeout_ms: Option<u32>` and `signal: Option<Unknown<'env>>` in options, create `CancelToken::new(...)`, and heartbeat in long loops.\n\n2. **Build generated bindings**\n\n- Run `bun --cwd=packages/natives run build`.\n- Confirm the generated `packages/natives/native/index.d.ts` includes the new export with the intended JS name/signature.\n- Confirm `packages/natives/native/index.js` still has generated enum exports appended when enum changes are involved.\n\n3. **Update consumers**\n\n- Import the new export directly from `@gajae-code/natives`.\n- Replace only callsites where the native implementation is faster/equivalent and preserves behavior.\n- Remove obsolete JS implementation code in the same change when the native path becomes canonical.\n\n4. **Add benchmarks**\n\n- Put benchmarks next to the owning package (`packages/tui/bench`, `packages/natives/bench`, or `packages/coding-agent/bench`).\n- Include a JS baseline and native version in the same run.\n- Use `Bun.nanoseconds()` and a fixed iteration count.\n- Keep benchmark inputs realistic for the hot path.\n\n5. **Run focused verification**\n\n- Build the native package.\n- Run the benchmark.\n- Run the narrow tests or scenario covering the changed export/callsites.\n\n## Pain points and how to avoid them\n\n### 1) Stale platform/variant artifacts\n\nThe loader probes platform-tagged artifacts in deterministic order. For x64, selected variant candidates are tried before the unsuffixed default fallback:\n\n- `modern`: `pi_natives.<tag>-modern.node`, then `...-baseline.node`, then `pi_natives.<tag>.node`.\n- `baseline`: `pi_natives.<tag>-baseline.node`, then `pi_natives.<tag>.node`.\n\nNon-x64 uses `pi_natives.<tag>.node`.\n\nCompiled binaries also probe `<getNativesDir()>/<version>/...` and a legacy user-data directory before package/executable locations. If any earlier candidate is stale, a new export may appear missing.\n\n**Fix:** remove stale candidate/cache files and rebuild.\n\n```bash\nrm packages/natives/native/pi_natives.<platform>-<arch>.node\nrm packages/natives/native/pi_natives.<platform>-<arch>-modern.node\nrm packages/natives/native/pi_natives.<platform>-<arch>-baseline.node\nbun --cwd=packages/natives run build\n```\n\nFor compiled binaries, delete the versioned addon cache shown in the loader error (normally under `~/.gjc/natives/<version>` unless `$XDG_DATA_HOME/gjc` is used).\n\n### 2) Generated types do not match loaded binary\n\nThis can happen when `native/index.d.ts` was regenerated but the `.node` file being loaded is stale or from a different platform/variant.\n\nVerify the loaded export set from the actual candidate path:\n\n```bash\nbun -e 'const tag = `${process.platform}-${process.arch}`; const mod = require(`./packages/natives/native/pi_natives.${tag}.node`); console.log(Object.keys(mod).sort())'\n```\n\nFix the build/candidate mismatch. Do not paper over it with optional consumer checks if the export is required.\n\n### 3) Rust signature mismatch\n\nKeep N-API signatures simple and owned. Avoid borrowed references like `&str` in public exports. If you need structured data, use `#[napi(object)]` structs. If you need callbacks, use napi-rs `ThreadsafeFunction` and keep callback error/value behavior explicit.\n\n### 4) Enum runtime exports\n\nnapi-rs declarations alone are not enough for JS callers that use enum objects at runtime. `scripts/gen-enums.ts` appends enum objects to `native/index.js`. If you add or change a native enum, verify both `native/index.d.ts` and the generated enum export block in `native/index.js`.\n\n### 5) Benchmarking mistakes\n\n- Do not compare different inputs or allocations.\n- Keep JS and native using identical input arrays.\n- Run both in the same benchmark file to avoid skew.\n- Include enough iterations to smooth startup noise, but keep inputs realistic.\n\n## Benchmark template\n\n```ts\nconst ITERATIONS = 2000;\n\nfunction bench(name: string, fn: () => void): number {\n  const start = Bun.nanoseconds();\n  for (let i = 0; i < ITERATIONS; i++) fn();\n  const elapsed = (Bun.nanoseconds() - start) / 1e6;\n  console.log(\n    `${name}: ${elapsed.toFixed(2)}ms total (${(elapsed / ITERATIONS).toFixed(6)}ms/op)`,\n  );\n  return elapsed;\n}\n\nbench(\"feature/js\", () => {\n  jsImpl(sample);\n});\n\nbench(\"feature/native\", () => {\n  nativeImpl(sample);\n});\n```\n\n## Verification checklist\n\n- Generated `native/index.d.ts` includes the new export and intended TS signature.\n- The loaded `.node` file's `Object.keys(require(candidate))` includes the new export.\n- Runtime enum objects are present when the change adds/changes enums.\n- Bench numbers are recorded in the PR/notes.\n- Call sites are updated only if native is faster/equal and behavior-compatible.\n- Obsolete JS code is removed when the native implementation becomes canonical.\n\n## Rule of thumb\n\n- If native is slower, do not switch callsites. Keep or remove the export based on whether it has a near-term owner.\n- If native is faster and behavior-compatible, switch callsites and keep a benchmark to catch regressions.\n",
 	"provider-streaming-internals.md": "# Provider streaming internals\n\nThis document explains how token/tool streaming is normalized in `@gajae-code/ai`, then propagated through `@gajae-code/agent-core` and `coding-agent` session events.\n\n## End-to-end flow\n\n1. `streamSimple()` (`packages/ai/src/stream.ts`) maps generic options and dispatches to a provider stream function.\n2. Provider stream functions translate provider-native stream events into the unified `AssistantMessageEvent` sequence. Current built-ins include Anthropic, OpenAI Responses/Completions/OpenAI code/Azure Responses, Google Gemini/Gemini CLI/Vertex, Bedrock Converse, Ollama, Cursorand GitLab Duo/Kimi wrappers.\n3. Each provider pushes events into `AssistantMessageEventStream` (`packages/ai/src/utils/event-stream.ts`), which throttles delta events and exposes:\n   - async iteration for incremental updates\n   - `result()` for final `AssistantMessage`\n4. `agentLoop` (`packages/agent/src/agent-loop.ts`) consumes those events, mutates in-flight assistant state, and emits `message_update` events carrying the raw `assistantMessageEvent`.\n5. `AgentSession` (`packages/coding-agent/src/session/agent-session.ts`) subscribes to agent events, persists messages, and applies session behaviors (retry, compaction, TTSR, streaming-edit abort checks).\n\n## Unified stream contract in `@gajae-code/ai`\n\nAll providers emit the same shape (`AssistantMessageEvent` in `packages/ai/src/types.ts`):\n\n- `start`\n- content block lifecycle triplets:\n  - text: `text_start` → `text_delta`\\* → `text_end`\n  - thinking: `thinking_start` → `thinking_delta`\\* → `thinking_end`\n  - tool call: `toolcall_start` → `toolcall_delta`\\* → `toolcall_end`\n- terminal event:\n  - `done` with `reason: \"stop\" | \"length\" | \"toolUse\"`\n  - or `error` with `reason: \"aborted\" | \"error\"`\n\n`AssistantMessageEventStream` guarantees:\n\n- final result is resolved by terminal event (`done` or `error`)\n- deltas are batched/throttled (~50ms)\n- buffered deltas are flushed before non-delta events and before completion\n\n## Delta throttling and harmonization behavior\n\n`AssistantMessageEventStream` treats `text_delta`, `thinking_delta`, and `toolcall_delta` as mergeable events:\n\n- buffered deltas are merged only when **type + contentIndex** match\n- merge keeps the latest `partial` snapshot\n- non-delta events force immediate flush\n\nThis smooths high-frequency provider streams for TUI/event consumers, but is not provider backpressure: providers still produce at full speed, while the local stream buffers.\n\n## Provider normalization details\n\n## Anthropic (`anthropic-messages`)\n\nSource: `packages/ai/src/providers/anthropic.ts`\n\nNormalization points:\n\n- `message_start` initializes usage (input/output/cache tokens)\n- `content_block_start` maps to text/thinking/toolcall starts\n- `content_block_delta` maps:\n  - `text_delta` → `text_delta`\n  - `thinking_delta` → `thinking_delta`\n  - `input_json_delta` → `toolcall_delta`\n  - `signature_delta` updates `thinkingSignature` only (no event)\n- `content_block_stop` emits corresponding `*_end`\n- `message_delta.stop_reason` maps via `mapStopReason()`\n\nTool-call argument streaming:\n\n- each tool block carries internal `partialJson`\n- every JSON delta appends to `partialJson`\n- `arguments` are reparsed on each delta via `parseStreamingJson()`\n- `toolcall_end` reparses once more, then strips `partialJson`\n\n## OpenAI Responses family (`openai-responses`, `openai-code-responses`, `azure-openai-responses`)\n\nSources: `packages/ai/src/providers/openai-responses.ts`, `openai-code-responses.ts`, and `azure-openai-responses.ts`\n\nNormalization points:\n\n- `response.output_item.added` starts reasoning/text/function-call blocks\n- reasoning summary events (`response.reasoning_summary_text.delta`) become `thinking_delta`\n- output/refusal deltas become `text_delta`\n- `response.function_call_arguments.delta` becomes `toolcall_delta`\n- `response.output_item.done` emits `thinking_end` / `text_end` / `toolcall_end`\n- `response.completed` maps status to stop reason and usage\n\nTool-call argument streaming:\n\n- same `partialJson` accumulation pattern as Anthropic\n- providers that send only `response.function_call_arguments.done` still populate final args\n- tool call IDs are normalized as `\"<call_id>|<item_id>\"`\n\n## Google Generative AI (`google-generative-ai`)\n\nSource: `packages/ai/src/providers/google.ts`\n\nNormalization points:\n\n- iterates `candidate.content.parts`\n- text parts are split into thinking vs text by `isThinkingPart(part)`\n- block transitions close previous block before starting a new one\n- `part.functionCall` is treated as a complete tool call (start/delta/end emitted immediately)\n- finish reason mapped by `mapStopReason()` from `google-shared.ts`\n\nTool-call argument streaming:\n\n- function call args arrive as structured object, not incremental JSON text\n- implementation emits one synthetic `toolcall_delta` containing `JSON.stringify(arguments)`\n- no partial JSON parser needed for Google in this path\n\n## Partial tool-call JSON accumulation and recovery\n\nShared behavior for Anthropic/OpenAI Responses uses `parseStreamingJson()` (`packages/ai/src/utils/json-parse.ts`):\n\n1. try `JSON.parse`\n2. fallback to `partial-json` parser for incomplete fragments\n3. if both fail, return `{}`\n\nImplications:\n\n- malformed or truncated argument deltas do not crash stream processing immediately\n- in-progress `arguments` may temporarily be `{}`\n- later valid deltas can recover structured arguments because parsing is retried on every append\n- final `toolcall_end` performs one more parse attempt before emission\n\n## Stop reasons vs transport/runtime errors\n\nProvider stop reasons are mapped to normalized `stopReason`:\n\n- Anthropic: `end_turn`→`stop`, `max_tokens`→`length`, `tool_use`→`toolUse`, safety/refusal cases→`error`\n- OpenAI Responses: `completed`→`stop`, `incomplete`→`length`, `failed/cancelled`→`error`\n- Google: `STOP`→`stop`, `MAX_TOKENS`→`length`, safety/prohibited/malformed-function-call classes→`error`\n\nError semantics are split in two stages:\n\n1. **Model completion semantics** (provider reported finish reason/status)\n2. **Transport/runtime failure** (network/client/parser/abort exceptions)\n\nIf provider stream throws or signals failure, each provider wrapper catches and emits terminal `error` event with:\n\n- `stopReason = \"aborted\"` when abort signal is set\n- otherwise `stopReason = \"error\"`\n- `errorMessage = formatErrorMessageWithRetryAfter(error)`\n\n## Malformed chunk / SSE parse failure behavior\n\nFor these provider paths, chunk/SSE framing is handled by vendor SDK streams (Anthropic SDK, OpenAI SDK, Google SDK). This code does not implement a custom SSE decoder here.\n\nObserved behavior in current implementation:\n\n- malformed chunk/SSE parsing at SDK level surfaces as an exception or stream `error` event\n- provider wrapper converts that into unified terminal `error` event\n- no provider-specific resume/retry inside the stream function itself\n- higher-level retries are handled in `AgentSession` auto-retry logic (message-level retry, not stream-chunk replay)\n\n## Cancellation boundaries\n\nCancellation is layered:\n\n- AI provider request: `options.signal` is passed into provider client stream call.\n- Provider wrapper: after stream loop, aborted signal forces error path (`\"Request was aborted\"`).\n- Agent loop: checks `signal.aborted` before handling each provider event and can synthesize an aborted assistant message from the latest partial.\n- Session/agent controls: `AgentSession.abort()` -> `agent.abort()` -> shared abort controller cancellation.\n\nTool execution cancellation is separate from model stream cancellation:\n\n- tool runners use `AbortSignal.any([agentSignal, steeringAbortSignal])`\n- steering interrupts can abort remaining tool execution while preserving already-produced tool results\n\n## Backpressure boundaries\n\nThere is no hard backpressure mechanism between provider SDK stream and downstream consumers:\n\n- `EventStream` uses in-memory queues with no max size\n- throttling reduces UI update rate but does not slow provider intake\n- if consumers lag significantly, queued events can grow until completion\n\nCurrent design favors responsiveness and simple ordering over bounded-buffer flow control.\n\n## How stream events surface as agent/session events\n\n`agentLoop.streamAssistantResponse()` bridges `AssistantMessageEvent` to `AgentEvent`:\n\n- on `start`: pushes placeholder assistant message and emits `message_start`\n- on block events (`text_*`, `thinking_*`, `toolcall_*`): updates last assistant message, emits `message_update` with raw `assistantMessageEvent`\n- on terminal (`done`/`error`): resolves final message from `response.result()`, emits `message_end`\n\n`AgentSession` then consumes those events for session-level behaviors:\n\n- TTSR watches `message_update.assistantMessageEvent` for `text_delta`, `thinking_delta`, and `toolcall_delta`\n- streaming edit guard inspects `toolcall_delta`/`toolcall_end` on `edit` calls and can abort early\n- persistence writes finalized messages at `message_end`\n- auto-retry examines assistant `stopReason === \"error\"` plus `errorMessage` heuristics\n\n## Unified vs provider-specific responsibilities\n\nUnified (common contract):\n\n- event shape (`AssistantMessageEvent`)\n- final result extraction (`done`/`error`)\n- delta throttling + merge rules\n- agent/session event propagation model\n\nProvider-specific (not fully abstracted):\n\n- upstream event taxonomies and mapping logic\n- stop-reason translation tables\n- tool-call ID conventions\n- reasoning/thinking block semantics and signatures\n- usage token semantics and availability timing\n- message conversion constraints per API\n\n## Implementation files\n\n- [`../../ai/src/stream.ts`](../packages/ai/src/stream.ts) — provider dispatch, option mapping, API key/session plumbing, custom API dispatch, and provider-specific credential handling.\n- [`../../ai/src/utils/event-stream.ts`](../packages/ai/src/utils/event-stream.ts) — generic stream queue + assistant delta throttling.\n- [`../../ai/src/utils/json-parse.ts`](../packages/ai/src/utils/json-parse.ts) — partial JSON parsing for streamed tool arguments.\n- [`../../ai/src/providers/anthropic.ts`](../packages/ai/src/providers/anthropic.ts) — Anthropic event translation and tool JSON delta accumulation.\n- [`../../ai/src/providers/openai-responses.ts`](../packages/ai/src/providers/openai-responses.ts), [`openai-code-responses.ts`](../packages/ai/src/providers/openai-code-responses.ts), [`azure-openai-responses.ts`](../packages/ai/src/providers/azure-openai-responses.ts) — Responses-family event translation and status mapping.\n- [`../../ai/src/providers/google.ts`](../packages/ai/src/providers/google.ts), [`google-gemini-cli.ts`](../packages/ai/src/providers/google-gemini-cli.ts), [`google-vertex.ts`](../packages/ai/src/providers/google-vertex.ts) — Gemini stream chunk-to-block translation variants.\n- [`../../ai/src/providers/google-shared.ts`](../packages/ai/src/providers/google-shared.ts) — Gemini finish-reason mapping and shared conversion rules.\n- [`../../ai/src/providers/amazon-bedrock.ts`](../packages/ai/src/providers/amazon-bedrock.ts), [`openai-completions.ts`](../packages/ai/src/providers/openai-completions.ts), [`ollama.ts`](../packages/ai/src/providers/ollama.ts), [`cursor.ts`](../packages/ai/src/providers/cursor.ts) — additional built-in stream adapters using the same event contract.\n- [`../../agent/src/agent-loop.ts`](../packages/agent/src/agent-loop.ts) — provider stream consumption and `message_update` bridging.\n- [`../src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts) — session-level handling of streaming updates, abort, retry, and persistence.\n",

package/src/memories/index.ts

@@ -12,6 +12,7 @@ import consolidationTemplate from "../prompts/memories/consolidation.md" with {
 import readPathTemplate from "../prompts/memories/read-path.md" with { type: "text" };
 import stageOneInputTemplate from "../prompts/memories/stage_one_input.md" with { type: "text" };
 import stageOneSystemTemplate from "../prompts/memories/stage_one_system.md" with { type: "text" };
+import unavailableTemplate from "../prompts/memories/unavailable.md" with { type: "text" };
 import type { AgentSession } from "../session/agent-session";
 import {
 	claimStage1Jobs,
@@ -153,20 +154,20 @@ export async function buildMemoryToolDeveloperInstructions(
 ): Promise<string | undefined> {
 	const cfg = loadMemoryConfig(settings);
 	if (!cfg.enabled) return undefined;
-	const memoryRoot = getMemoryRoot(agentDir, session?.sessionManager.getCwd() ?? settings.getCwd());
+	const memoryRoot = getMemoryRoot(agentDir, session?.sessionManager?.getCwd() ?? settings.getCwd());
 	const summaryPath = path.join(memoryRoot, "memory_summary.md");
 
 	let text: string;
 	try {
 		text = await Bun.file(summaryPath).text();
 	} catch {
-		return undefined;
+		return unavailableTemplate;
 	}
 
 	const summary = text.trim();
-	if (!summary) return undefined;
+	if (!summary) return unavailableTemplate;
 	const truncated = truncateByApproxTokens(summary, cfg.summaryInjectionTokenLimit);
-	if (!truncated.trim()) return undefined;
+	if (!truncated.trim()) return unavailableTemplate;
 
 	return prompt.render(readPathTemplate, {
 		memory_summary: truncated,

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

@@ -21,7 +21,7 @@ import type {
 	StatusLineSeparatorStyle,
 } from "../../config/settings-schema";
 import { SETTING_TABS, TAB_METADATA } from "../../config/settings-schema";
-import { getSelectListTheme, getSettingsListTheme, theme } from "../../modes/theme/theme";
+import { getCurrentThemeName, getSelectListTheme, getSettingsListTheme, theme } from "../../modes/theme/theme";
 import { matchesAppInterrupt } from "../../modes/utils/keybinding-matchers";
 import { getTabBarTheme } from "../shared";
 import { DynamicBorder } from "./dynamic-border";
@@ -200,6 +200,10 @@ export interface StatusLinePreviewSettings {
 export interface SettingsCallbacks {
 	/** Called when any setting value changes */
 	onChange: (path: SettingPath, newValue: unknown) => void;
+	/** Called for theme preview while browsing theme settings */
+	onThemePreview?: (theme: string) => void | Promise<void>;
+	/** Called to restore the rendered theme when theme settings preview is cancelled */
+	onThemePreviewCancel?: (theme: string) => void | Promise<void>;
 	/** Called for status line preview while configuring */
 	onStatusLinePreview?: (settings: StatusLinePreviewSettings) => void;
 	/** Get current rendered status line for inline preview */
@@ -217,7 +221,6 @@ export interface SettingsCallbacks {
 export class SettingsSelectorComponent extends Container {
 	#tabBar: TabBar;
 	#currentList: SettingsList | null = null;
-	#currentSubmenu: Container | null = null;
 	#pluginComponent: PluginSettingsComponent | null = null;
 	#statusPreviewContainer: Container | null = null;
 	#statusPreviewText: Text | null = null;
@@ -374,10 +377,15 @@ export class SettingsSelectorComponent extends Container {
 		let onPreview: ((value: string) => void | Promise<void>) | undefined;
 		let onPreviewCancel: (() => void) | undefined;
 
-		// Theme selection is confirm-only: moving through the list must not mutate
-		// the rendered theme while the displayed/persisted setting still names
-		// the previous value. Confirmation persists through Settings hooks.
-		if (def.path === "statusLine.preset") {
+		if (def.path === "theme.dark" || def.path === "theme.light") {
+			const activeThemeBeforePreview = getCurrentThemeName() ?? currentValue;
+			onPreview = value => {
+				return this.callbacks.onThemePreview?.(value);
+			};
+			onPreviewCancel = () => {
+				return this.callbacks.onThemePreviewCancel?.(activeThemeBeforePreview);
+			};
+		} else if (def.path === "statusLine.preset") {
 			onPreview = value => {
 				const presetDef = getPreset(
 					value as "default" | "minimal" | "compact" | "full" | "nerd" | "ascii" | "custom",
@@ -612,17 +620,20 @@ export class SettingsSelectorComponent extends Container {
 			return;
 		}
 
-		// Escape at top level cancels
-		if (matchesAppInterrupt(data) && !this.#currentSubmenu) {
-			this.callbacks.onCancel();
-			return;
-		}
-
-		// Pass to current content
+		// Pass to current content. SettingsList owns Escape routing so open
+		// submenus can run their cancel/restore callbacks before closing.
 		if (this.#currentList) {
 			this.#currentList.handleInput(data);
-		} else if (this.#pluginComponent) {
+			return;
+		}
+		if (this.#pluginComponent) {
 			this.#pluginComponent.handleInput(data);
+			return;
+		}
+
+		// Fallback for future top-level content that does not own cancellation.
+		if (matchesAppInterrupt(data)) {
+			this.callbacks.onCancel();
 		}
 	}
 }

package/src/modes/controllers/command-controller.ts

@@ -585,7 +585,7 @@ export class CommandController {
 		if (action === "view") {
 			const payload = await backend.buildDeveloperInstructions(agentDir, this.ctx.settings, this.ctx.session);
 			if (!payload) {
-				this.ctx.showWarning("Memory payload is empty (memory backend off, disabled, or no memory available).");
+				this.ctx.showWarning("Memory payload is empty; durable memory is unavailable or unconfirmed.");
 				return;
 			}
 			this.ctx.chatContainer.addChild(new Spacer(1));

package/src/modes/controllers/selector-controller.ts

@@ -17,7 +17,11 @@ import {
 } from "../../extensibility/plugins/marketplace";
 import {
 	getAvailableThemes,
+	getCurrentThemeName,
+	getDetectedThemeSettingsPath,
 	getSymbolTheme,
+	previewTheme,
+	restoreThemePreview,
 	setColorBlindMode,
 	setSymbolPreset,
 	setTheme,
@@ -47,6 +51,7 @@ import {
 import { SessionObserverOverlayComponent } from "../components/session-observer-overlay";
 import { SessionSelectorComponent } from "../components/session-selector";
 import { SettingsSelectorComponent } from "../components/settings-selector";
+import { ThemeSelectorComponent } from "../components/theme-selector";
 import { ToolExecutionComponent } from "../components/tool-execution";
 import { TreeSelectorComponent } from "../components/tree-selector";
 import { UserMessageSelectorComponent } from "../components/user-message-selector";
@@ -62,6 +67,10 @@ const CALLBACK_SERVER_PROVIDERS = new Set<OAuthProvider>([
 
 const MANUAL_LOGIN_TIP = "Tip: You can complete pairing with /login <redirect URL>.";
 
+function isThemePreviewSuperseded(result: { success: boolean; error?: string }): boolean {
+	return !result.success && result.error?.includes("superseded by a newer request") === true;
+}
+
 function formatProviderOnboardingCommandGuide(): string {
 	return [
 		"Provider preset setup:",
@@ -134,6 +143,22 @@ export class SelectorController {
 					},
 					{
 						onChange: (id, value) => this.handleSettingChange(id, value),
+						onThemePreview: themeName => {
+							return previewTheme(themeName).then(result => {
+								if (!result.success && result.error && !isThemePreviewSuperseded(result)) {
+									this.ctx.showError(`Failed to preview theme: ${result.error}`);
+								}
+								this.#refreshThemeUi();
+							});
+						},
+						onThemePreviewCancel: themeName => {
+							return restoreThemePreview(themeName).then(result => {
+								if (!result.success && result.error && !isThemePreviewSuperseded(result)) {
+									this.ctx.showError(`Failed to restore theme preview: ${result.error}`);
+								}
+								this.#refreshThemeUi();
+							});
+						},
 						onStatusLinePreview: previewSettings => {
 							// Update status line with preview settings
 							this.ctx.statusLine.updateSettings({
@@ -177,6 +202,48 @@ export class SelectorController {
 		});
 	}
 
+	#refreshThemeUi(): void {
+		this.ctx.statusLine.invalidate();
+		this.ctx.updateEditorTopBorder();
+		this.ctx.ui.requestRender();
+	}
+
+	showThemeSelector(): void {
+		getAvailableThemes().then(availableThemes => {
+			const initialTheme = getCurrentThemeName() ?? "red-claw";
+			this.showSelector(done => {
+				const selector = new ThemeSelectorComponent(
+					initialTheme,
+					availableThemes,
+					themeName => {
+						const settingPath = getDetectedThemeSettingsPath();
+						settings.set(settingPath, themeName);
+						this.#refreshThemeUi();
+						done();
+					},
+					() => {
+						void restoreThemePreview(initialTheme).then(result => {
+							if (!result.success && result.error) {
+								this.ctx.showError(`Failed to restore theme preview: ${result.error}`);
+							}
+							this.#refreshThemeUi();
+						});
+						done();
+					},
+					themeName => {
+						void previewTheme(themeName).then(result => {
+							if (!result.success && result.error) {
+								this.ctx.showError(`Failed to preview theme: ${result.error}`);
+							}
+							this.#refreshThemeUi();
+						});
+					},
+				);
+				return { component: selector, focus: selector };
+			});
+		});
+	}
+
 	showHistorySearch(): void {
 		const historyStorage = this.ctx.historyStorage;
 		if (!historyStorage) return;

package/src/modes/interactive-mode.ts

@@ -1281,7 +1281,16 @@ export class InteractiveMode implements InteractiveModeContext {
 		reason?: "completed" | "paused" | "dropped";
 	}): Promise<void> {
 		const previousTools = this.#goalModePreviousTools;
-		if (this.goalModeEnabled && previousTools) {
+		// Drop keeps the `goal` tool callable so the agent can immediately create a new
+		// goal in the same session without a leader-side cleanup. Complete (and pause)
+		// exit goal mode and restore the pre-goal tool set even when the goal_updated
+		// event has already cleared goalModeEnabled (see #completeGoalFromTool emitting
+		// state.enabled = false before #exitGoalMode runs). Spec: deep-interview-ultragoal-goal-tool-wiring AC1+AC2.
+		const shouldRestoreTools =
+			previousTools &&
+			options?.reason !== "dropped" &&
+			(this.goalModeEnabled || options?.reason === "completed" || options?.paused === true);
+		if (shouldRestoreTools) {
 			await this.session.setActiveToolsByName(previousTools);
 		}
 		const currentState = this.session.getGoalModeState();
@@ -2339,6 +2348,10 @@ export class InteractiveMode implements InteractiveModeContext {
 		this.#selectorController.showSettingsSelector();
 	}
 
+	showThemeSelector(): void {
+		this.#selectorController.showThemeSelector();
+	}
+
 	showHistorySearch(): void {
 		this.#selectorController.showHistorySearch();
 	}