pi-cursor-sdk 0.1.17 → 0.1.19

package/CHANGELOG.md

@@ -1,5 +1,67 @@
 # Changelog
 
+## Unreleased
+
+## 0.1.19 - 2026-05-25
+
+### Added
+
+- Add maintainer Cursor SDK event capture probes, `npm run debug:sdk-events` and `npm run debug:provider-events`, with structured artifacts for SDK callbacks, stream events, provider decisions, bridge diagnostics, drain timelines, final partials, wait results, conversations, and optional pi session snapshots.
+- Add display-only replay for Cursor SDK `semSearch` and `recordScreen` activity, including distinct labels for semantic codebase search versus web search.
+- Add recognizable Cursor web search/fetch activity cards for SDK MCP/host completions and local Cursor transcript `webSearchToolCall` / `webFetchToolCall` records.
+- Surface incomplete started Cursor SDK tool calls as bounded neutral `Cursor … did not complete` cards or traces, including safe reasons for missing completion, abort, SDK failure, and run-drain cleanup while preserving #52 maintainer debug artifacts and excluding bridge-owned `pi__*` calls.
+- Add low-noise pending lifecycle visibility for long-running Cursor tools, delayed so fast start/complete pairs coalesce into completed replay cards instead of duplicate permanent start cards.
+- Render unknown future Cursor SDK tools as neutral bounded Cursor activity cards, while keeping explicit known-tool replay/transcript formatting authoritative.
+
+### Changed
+
+- Add a Cursor tool-tail guard and periodic session-agent rebootstrap so pooled local Cursor sessions recover from stale tool-tail or long incremental-send chains without losing the pi-facing session contract.
+- Refactor Cursor session send planning into `src/cursor-session-send-policy.ts` and document the new session-agent/send-policy ownership in `AGENTS.md`.
+- Improve collapsed summaries and bounded transcript text for neutral Cursor activity replay cards, including MCP, task, image, plan/todo, semantic search, record screen, web search/fetch, and future/unknown tools.
+- Document the SDK ToolType replay matrix, alias normalization, replay boundaries, and known SDK reporting limits for web search/fetch, future tools, and abort exceptions.
+- Route incomplete started-tool visibility through the same native replay disposition used by completed replay, so inactive, conflicting, non-native, and bridge-only contexts fall back to safe traces instead of invalid `cursor` tool-use turns.
+- Harden Cursor lifecycle and incomplete-tool labels to scrub commands, URLs, absolute paths, key/flag path values, and secrets before showing user-visible activity.
+- Remove the 4096-message local Cursor transcript counting cap so web-tool transcript fallback can work in very long reused local Cursor sessions.
+
+### Fixed
+
+- Fix replay JSONL scan false positives from successful read results and document JSONL replay scan semantics for maintainer smoke triage.
+- Suppress duplicate pi `AGENTS.md` injection on Cursor models only when effective Cursor `settingSources` load overlapping `user` / `project` rule layers. Uses exact `contextFiles` block removal exclusively via the `before_agent_start` hook, honors `-nc` and `PI_CURSOR_SETTING_SOURCES=none`, restores full pi context when switching to non-Cursor models, and supports `PI_CURSOR_PRESERVE_PI_AGENTS_MD=1` opt-out.
+- Fix collapsed read replay labels when Cursor reports only a local file preview.
+- Surface scrubbed Cursor SDK failure and abort reasons in pi instead of generic provider errors, and bound `ConnectError` / `ETIMEDOUT` failures at Cursor SDK async boundaries.
+- Harden replay fallbacks and debug discarded SDK tool calls without leaking raw call IDs or secret-bearing payloads.
+- Document #40 tool-call-as-plain-text triage and the repro template for distinguishing model narration from real pi replay failures.
+- Label Cursor web search and web fetch activity clearly in TUI/replay output without mislabeling SDK `semSearch`.
+- Surface direct local Cursor transcript `WebSearch` calls that the SDK stream omits.
+- Prevent Esc/user aborts during active local Cursor SDK runs from crashing pi with uncaught `ConnectError: [canceled] This operation was aborted` errors.
+- Prevent deferred lifecycle timers from leaking `Cursor …` progress into terminal error/final partials after `run.wait()` resolves or rejects.
+- Preserve abort-time incomplete-tool visibility for live runs, including when earlier replay or bridge events are still queued, without replaying or synthesizing earlier tool work.
+- Treat missing pi session snapshots in Cursor SDK debug artifacts as optional skipped debug data instead of false `pi_session_snapshot` errors, and let `debug-provider-events` backfill the snapshot after pi exits when the session file appears later.
+
+## 0.1.18 - 2026-05-23
+
+### Added
+
+- Add `scripts/isolated-cursor-smoke.sh` and `npm run smoke:isolated` for packed `/tmp` install smoke with seeded `auth.json`, plan-strip shim, and JSONL replay-error scans.
+- Add `scripts/fixtures/plan-strip-shim/` to simulate plan-mode execute stripping active tools to `read`, `bash`, `edit`, and `write`.
+- Extend `scripts/validate-smoke-jsonl.mjs` with `--replay-errors` and `--replay-errors-only` to fail on persisted `Tool grep/cursor/find/ls not found` entries.
+- Add [Cursor testing lessons](docs/cursor-testing-lessons.md) documenting auth.json seeding, isolated harness layout, JSONL replay scans, and the plan-mode replay regression chain.
+- Add regression coverage in `test/cursor-native-replay-stress.test.ts`, `test/cursor-native-replay-trace.test.ts`, `test/cursor-native-replay-routing.test.ts`, and expanded live-run / extension lifecycle tests.
+
+### Changed
+
+- Centralize native replay routing in `src/cursor-native-replay-routing.ts` (`resolveNativeReplayDisposition`, shared context-tool partitioning) for turn coordinator and live-run drain.
+- Unify 240-character display truncation in `src/cursor-display-text.ts` and share `getActiveContextToolNames()` via `src/cursor-context-tools.ts`.
+- Unify inactive native replay trace formatting through `src/cursor-native-replay-trace.ts` (`title: summary`) for both live-run drain and turn-coordinator paths.
+- On non-Cursor model switch, strip all registered native replay wrappers except core pi tools (`read`, `bash`, `edit`, `write`), not only `cursor`.
+- Document `auth.json` as the primary live-smoke auth source in the live smoke checklist, README maintainer gate, and UX spec.
+
+### Fixed
+
+- Fix `Tool grep not found` and related native replay failures after plan-mode execute resets active tools by re-syncing registered Cursor replay wrappers on `before_agent_start` and `turn_start`.
+- Skip native replay `toolUse` when a replay tool is inactive in `context.tools`; emit scrubbed thinking trace instead of a broken pi tool call.
+- Partition live-run drain replay emission so inactive queued native tools fall back to trace output instead of invalid `toolUse` turns.
+
 ## 0.1.17 - 2026-05-23
 
 ### Added

package/README.md

@@ -232,7 +232,15 @@ PI_CURSOR_PI_TOOL_BRIDGE_DEBUG=1 pi --model cursor/composer-2.5
 
 ### Maintainer live smoke release gate
 
-For Cursor provider/runtime changes, follow the manual [Cursor live smoke checklist](docs/cursor-live-smoke-checklist.md) before release. Assume every runtime surface is in scope. The checklist uses real `pi -e . --cursor-no-fast --model cursor/composer-2.5` runs with temporary session dirs and requires the visible TUI/output, scrubbed diagnostics, and persisted JSONL to agree. Do not mark a release ready with optional, deferred, mostly-passing, or unobserved smoke checks outstanding.
+For Cursor provider/runtime changes, follow the manual [Cursor live smoke checklist](docs/cursor-live-smoke-checklist.md) before release. See [Cursor testing lessons](docs/cursor-testing-lessons.md) for auth.json seeding, isolated `/tmp` harness layout, JSONL replay-error scans, and other regression traps. Assume every runtime surface is in scope. The checklist uses real `pi -e . --cursor-no-fast --model cursor/composer-2.5` runs with temporary session dirs and requires the visible TUI/output, scrubbed diagnostics, and persisted JSONL to agree. Do not mark a release ready with optional, deferred, mostly-passing, or unobserved smoke checks outstanding.
+
+### Maintainer Cursor SDK event capture
+
+Use `npm run debug:sdk-events` to capture timestamped `run.stream()`, `onDelta`, and `onStep` timelines for one direct `@cursor/sdk` run.
+
+Use `npm run debug:provider-events` to capture the same `onDelta`/`onStep` payloads **through pi's Cursor provider** (session agent reuse, bridge, native replay, send planning). Artifacts default under gitignored `.debug/cursor-sdk-events/`. Interactive multi-turn pi sessions group turns under `.debug/cursor-sdk-events/sessions/<session-slug>/turn-NNN-.../` with a `session.json` index. You can also opt in during any pi run with `PI_CURSOR_SDK_EVENT_DEBUG=1`; capture is file-only by default so the pi TUI stays normal.
+
+See [Cursor testing lessons](docs/cursor-testing-lessons.md#cursor-sdk-event-capture-probe) for usage, artifact layout, and safety notes.
 
 ## Fallback models
 
@@ -249,6 +257,7 @@ Actual Cursor runs still need a key from `/login`, `CURSOR_API_KEY`, or `--api-k
 - **Cursor native tool replay is display-only.** Replay renders recorded Cursor SDK activity and never re-runs Cursor-side commands, reapplies Cursor edits, calls MCP servers, or mutates pi state. Workflow tools such as Cursor `SwitchMode` and Cursor todo state are not pi workflow controls. See [Cursor native tool replay](docs/cursor-native-tool-replay.md) for supported replay cards, ordering, conflict handling, and opt-out flags.
 - **Cursor run state can span tool-use turns.** Within a pi session, the extension reuses one Cursor SDK agent across compatible follow-up turns and sends incremental prompts when context still matches. It recreates the agent when context diverges, after compaction or `/tree` navigation, on API key changes, after send errors, or on session shutdown. For bridged pi tools, the matching pi `toolResult` resolves into the same live Cursor SDK run without creating a new `Agent`, unless the run was disposed, aborted, or cancelled. Replay can also split one live Cursor SDK run across pi `toolUse` turns for display.
 - **Cursor setting sources default to all.** The extension passes `local.settingSources: ["all"]` by default so configured Cursor MCP servers, plugin tools, project/user settings, and related Cursor-native capabilities are available like they are in Cursor. To narrow loading, set a comma-separated list such as `PI_CURSOR_SETTING_SOURCES=project,user,plugins`. To disable ambient setting sources, set `PI_CURSOR_SETTING_SOURCES=none`. Direct Cursor SDK bootstrap logs (settings, skills, hook-load compatibility warnings, and similar) are suppressed so they do not pollute the TUI.
+- **AGENTS.md / CLAUDE.md are not duplicated on Cursor models when Cursor loads the same rules.** Pi discovers global and project context files (`AGENTS.md`, `CLAUDE.md`, and case variants) unless you start with `-nc`. On `cursor/*` models the extension removes only `<project_instructions>` blocks that overlap Cursor `settingSources` via the `before_agent_start` hook: `user` for `~/.pi/agent/AGENTS.md`, `project` for repo/parent `AGENTS.md` and `CLAUDE.md` (verified Cursor behavior: local agents load project `AGENTS.md` and `CLAUDE.md` alongside Cursor rules). `~/.pi/agent/CLAUDE.md` is not stripped (Cursor user rules use `~/.claude/CLAUDE.md`, not pi's agent dir). With `PI_CURSOR_SETTING_SOURCES=none` or `plugins`-only, pi context is left intact. Set `PI_CURSOR_PRESERVE_PI_AGENTS_MD=1` to keep duplicate injection.
 - **Max Mode is not a manual pi variant.** Cursor's SDK may enable Max Mode automatically for models that require it. This extension only advertises exact context-window variants that the SDK catalog exposes and otherwise uses conservative SDK-derived default/non-Max context windows.
 - **Output token limits are conservative.** Cursor SDK model metadata does not currently expose output token limits directly.
 - **Token usage is approximate in pi.** Cursor SDK usage events include cumulative internal agent/tool/cache work, so raw Cursor SDK counters are not copied into pi usage. The extension reports approximate pi session activity in `input`/`output`, including split-run tool calls and consumed tool results, while `totalTokens` tracks the replayable Cursor prompt/context estimate used for context display and compaction.
@@ -259,6 +268,12 @@ Actual Cursor runs still need a key from `/login`, `CURSOR_API_KEY`, or `--api-k
 
 You may be seeing fallback startup models or a missing/invalid key. In interactive pi, run `/login`, choose `Use an API key`, choose `Cursor`, paste the key, then run `/cursor-refresh-models`.
 
+When a Cursor run fails after auth is configured, pi now surfaces scrubbed provider detail instead of only `Cursor SDK run failed`. Generic SDK failures include safe run metadata such as model id, a short run id prefix, and duration when available. Check the red toast or assistant error message for that detail before retrying.
+
+Aborted runs now include a likely cause when determinable, for example `Cancelled: prompt interrupted.` for user cancel or `Cancelled: Cursor SDK run was cancelled.` for SDK-side cancellation.
+
+Network timeouts from the Cursor SDK connect layer (for example `ConnectError: read ETIMEDOUT`) surface as a scrubbed retry hint instead of crashing pi. Check your connection and retry; persistent timeouts may indicate a transient Cursor service or network issue.
+
 You can also restart pi with a key in the same shell or launcher that starts pi:
 
 ```bash
@@ -302,6 +317,16 @@ Cursor setting sources are loaded with `PI_CURSOR_SETTING_SOURCES=all` by defaul
 
 Cursor SDK local agents load MCP servers from Cursor setting sources and inline SDK config. This extension enables all Cursor setting sources by default, so a missing web search tool usually means it is not configured in Cursor or the run was started with a narrowing/disable override such as `PI_CURSOR_SETTING_SOURCES=none`.
 
+### I do not see Cursor web search or web fetch in pi's tool UI
+
+pi shows **Cursor web search** / **Cursor web fetch** activity cards only when the installed `@cursor/sdk` reports completed replayable tool data. Supported sources are SDK `mcp` completions whose `toolName` is `WebSearch` / `web_search` / `WebFetch` / similar, host tool names that normalize to those labels, and local Cursor transcript `webSearchToolCall` / `webFetchToolCall` records available through `Agent.messages.list()` after the run. This is separate from SDK `semSearch`, which is semantic **codebase** search.
+
+Known SDK boundary: some local Cursor web search activity is not emitted through live `onDelta`, `onStep`, or `run.stream()` tool events. When that happens, pi can only reconstruct a card from the local agent transcript after `run.wait()` finishes, so the **Cursor web search** card may appear after assistant text rather than as a live in-progress card. Buffering all assistant text until `run.wait()` would make the ordering prettier but would break normal streaming, so pi does not do that.
+
+Many runs never expose web activity as replayable SDK tool completions or local transcript web tool records. The model may still answer from internal Cursor web tooling or only mention search in assistant text/thinking. In that case pi cannot render a tool card because there is no completed SDK tool-call payload to replay. Capture a run with `npm run debug:provider-events` when investigating; if `on-delta.jsonl`, `on-step.jsonl`, `stream-events.jsonl`, `coordinator-events.jsonl`, and `display-decisions.jsonl` have no completed or transcript web tool data, the limitation is on the Cursor SDK surface, not pi replay registration.
+
+**Web fetch:** `pi-cursor-sdk` can display `webFetchToolCall` transcript records and web-fetch-shaped MCP/host completions when Cursor reports them. It cannot make Cursor expose or execute a `WebFetch` tool. If Cursor's current local SDK tool set does not include WebFetch, pi cannot fetch a URL through Cursor web fetch; use an allowed browser/shell/MCP tool instead.
+
 ### Cursor does not call my pi extension tool
 
 The local pi bridge only exposes tools that are active in the current pi session and present in pi's tool registry at Cursor run start. By default, it does not expose overlapping pi tool names that Cursor already has native equivalents for (`read`, `bash`, `write`, `edit`, `grep`, `find`, and `ls`). Opt in if you intentionally want Cursor to see both the Cursor-native tool and an overlapping built-in pi tool:
@@ -325,6 +350,18 @@ PI_CURSOR_MCP_TOOL_TIMEOUT_SECONDS=7200 pi --model cursor/composer-2.5
 PI_CURSOR_MCP_TOOL_TIMEOUT_MS=7200000 pi --model cursor/composer-2.5
 ```
 
+### Tool calls appear as a plain text list instead of pi tool cards
+
+This usually needs session JSONL to classify. Common cases:
+
+- **Model text echo:** Assistant `text` blocks contain lines like `Tool call`, `Cursor activity`, or `call cursor-replay-…` without matching `toolCall` blocks — the Cursor model narrated pi prompt transcript format instead of invoking SDK tools. See [Tool calls listed as plain text (#40 triage)](docs/cursor-testing-lessons.md#tool-calls-listed-as-plain-text-40-triage).
+- **Stale replay routing / plan-strip:** Error `toolResult` or error assistant messages contain `Tool grep/cursor/find/ls not found`, or provider debug shows `inactive_trace` after plan-mode execute stripped active tools — tracked in **#52** (distinct from model text echo and #55).
+- **Replay vs execution:** `cursor-replay-*` IDs and neutral **Cursor MCP** activity cards are display-only recorded Cursor results; they do not re-run browser/MCP work. See [Cursor native tool replay](docs/cursor-native-tool-replay.md).
+- **Run failure / discarded tools:** A red toast with scrubbed detail may indicate an SDK failure (#55). Started-but-never-completed Cursor tools now surface neutral **Cursor … did not complete** activity cards with a bounded reason; maintainer debug for the same gap remains in **#52** (`PI_CURSOR_SDK_EVENT_DEBUG=1`).
+- **Hard network crash:** pi exited with uncaught `ConnectError` / `ETIMEDOUT` — **#43**, not #40 text echo.
+
+Capture `pi --version`, extension version, model, flags, the exact prompt, and a redacted session dir before filing bugs.
+
 ### Cursor native tool cards conflict with another extension
 
 Cursor native replay is a UI enhancement for interactive TTY sessions. See [Cursor native tool replay](docs/cursor-native-tool-replay.md) for conflict behavior and opt-out flags.

package/docs/cursor-live-smoke-checklist.md

@@ -2,7 +2,7 @@
 
 ## Purpose
 
-Use this manual checklist before releasing Cursor provider/runtime changes. Unit tests and mocks are necessary, but they are not enough for this extension. Always assume every runtime surface is in scope. A release is not ready until every live check below has been observed with `cursor/composer-2.5` through the local working tree.
+Use this manual checklist before releasing Cursor provider/runtime changes. Unit tests and mocks are necessary, but they are not enough for this extension. See [Cursor testing lessons](./cursor-testing-lessons.md) for auth/isolated-harness pitfalls and the plan-mode replay regression that motivated recent hardening. Always assume every runtime surface is in scope. A release is not ready until every live check below has been observed with `cursor/composer-2.5` through the local working tree.
 
 ## Release rule
 
@@ -22,19 +22,38 @@ mkdir -p "$SMOKE_DIR"
 pi -e . --list-models cursor
 ```
 
+Live pi runs resolve provider auth from **`~/.pi/agent/auth.json`**, not only shell env. Isolated smoke copies that file into a clean temporary `HOME`. Ensure `auth.json` includes a `cursor` provider entry, or export `CURSOR_API_KEY` as a fallback.
+
 The repo also ships partial automation for the prerequisite/basic/default-settings/non-interactive math/TUI output polling/steering/diagnostic/JSONL subset:
 
 ```bash
 npm run smoke:live
 ```
 
+For native replay regression checks (packed install, plan-strip resync, JSONL replay-error scan), use the isolated helper:
+
+```bash
+npm run smoke:isolated
+# unit tests + pack only (no live Cursor):
+SKIP_LIVE=1 npm run smoke:isolated
+```
+
+Scan persisted sessions for native replay tool failures:
+
+```bash
+node scripts/validate-smoke-jsonl.mjs --replay-errors "$SMOKE_DIR"
+node scripts/validate-smoke-jsonl.mjs --replay-errors-only "$SMOKE_DIR/session-subdir"
+```
+
+The replay scan flags only error `toolResult` / error assistant messages with `Tool grep/cursor/find/ls not found`, not successful reads of docs that mention those strings. See [Cursor testing lessons](./cursor-testing-lessons.md#what-counts-as-a-replay-failure).
+
 The script is a helper only; it polls the section 3 TUI for answer/footer evidence and then cleans up the tmux session, but it does not replace manual visual review of the full TUI checklist. Release readiness still requires the manual checks below for detailed TUI behavior, bridge, standalone native replay, abort/cancel, packaging, cleanup, and any touched runtime surface not covered by the helper.
 
 Pass criteria:
 
 - `cursor/composer-2.5` appears in the model list.
 - No Cursor key or auth token is printed.
-- If `CURSOR_API_KEY` is unavailable and `/login` is not configured, stop and report the live smoke as blocked.
+- If neither `~/.pi/agent/auth.json` cursor auth nor `CURSOR_API_KEY` is available, stop and report the live smoke as blocked.
 
 ## 1. Basic provider reality check
 
@@ -261,6 +280,7 @@ Everything in this section is in scope for Cursor provider/runtime releases. The
 - Native replay cards beyond read, especially shell/edit/write cards, when those renderers change.
 - Bridge question UI when `cursor_ask_question` changes.
 - MCP timeout override behavior when timeout code changes.
+- SDK `semSearch` / `recordScreen` activity replay when those formatters change. There is no reliable local prompt that forces Cursor to call these built-in SDK tools on demand; regression is covered by `test/cursor-tool-transcript.test.ts`. Opportunistically confirm neutral `Cursor semantic search` / `Cursor screen recording` cards if a live run surfaces them.
 - Ambient Cursor setting-source behavior when startup filtering or local Cursor settings handling changes.
 - Model discovery aliases/context variants when model-discovery code or Cursor SDK versions change.
 

package/docs/cursor-model-ux-spec.md

@@ -17,6 +17,7 @@ Current implementation notes:
 - `@cursor/sdk` is a package dependency of this extension; users should not need a global SDK install.
 - Cursor auth uses pi-native API-key resolution for provider `cursor`: CLI `--api-key`, stored `~/.pi/agent/auth.json` API key from `/login`, then `CURSOR_API_KEY`. The extension config file stores only non-secret Cursor-only state such as fast defaults.
 - Local agents pass `settingSources: ["all"]` by default so Cursor MCP servers, plugin tools, project/user settings, and related Cursor-native capabilities are available. Users can narrow loading with a comma-separated list such as `PI_CURSOR_SETTING_SOURCES=project,user,plugins`, or disable ambient setting sources with `PI_CURSOR_SETTING_SOURCES=none`. The provider suppresses direct Cursor SDK bootstrap stdout/stderr/console noise (including late first-send workspace loading such as hook compatibility warnings) so it does not pollute pi's TUI.
+- On `cursor/*` models, pi-cursor-sdk removes only pi-generated `<project_instructions>` blocks that overlap the effective Cursor `settingSources`: `user` for `~/.pi/agent/AGENTS.md`; `project` for discovered repo/parent `AGENTS.md` and `CLAUDE.md` (verified Cursor behavior: local agents load project `AGENTS.md` and `CLAUDE.md`). `~/.pi/agent/CLAUDE.md` is not removed (Cursor user layer uses `~/.claude/CLAUDE.md`). Blocks are removed by exact pi serialization match from structured `contextFiles` via the `before_agent_start` hook, not in `buildCursorPrompt` sanitization. Suppression is skipped with `-nc`, `PI_CURSOR_SETTING_SOURCES=none`, narrowed sources such as `plugins` that omit the matching layer, or `PI_CURSOR_PRESERVE_PI_AGENTS_MD=1`. Switching away from a Cursor model restores pi's full context block on the next user message.
 - Cursor SDK models are treated as thinking-capable even when pi reports `thinking=no`; that pi column only means the SDK did not expose a pi-controllable thinking parameter for that model.
 - Cursor-side thinking remains visible through pi's native thinking rendering when the Cursor SDK emits thinking or summary deltas.
 - Local Cursor agents get two tool surfaces. First, Cursor keeps the Cursor SDK local-agent tool surface plus configured Cursor settings, plugins, and Cursor MCP servers. Second, pi-cursor-sdk exposes active pi tools through a default-on, tokenized loopback MCP bridge when bridgeable tools exist.
@@ -27,16 +28,16 @@ Current implementation notes:
 - Cursor SDK MCP tool calls use a guarded timeout override because installed `@cursor/sdk` 1.0.13 has a 60-second MCP request default with no public per-server timeout option. The extension extends that Cursor SDK MCP `callTool` timeout path to 3600 seconds by default. Users can override it with `PI_CURSOR_MCP_TOOL_TIMEOUT_MS` or `PI_CURSOR_MCP_TOOL_TIMEOUT_SECONDS`.
 - Bridge diagnostics are opt-in only: `PI_CURSOR_PI_TOOL_BRIDGE_DEBUG=1` writes typed, allowlisted, scrubbed single-line JSONL records to `process.stderr` with prefix `[pi-cursor-sdk:bridge]`. Diagnostics are scrubbed operational logs, not anonymous telemetry. They intentionally include tool names, safe correlation IDs, run lifecycle, exposed pi↔MCP name pairs, queued requests, result resolution, rejection, cancellation, and pending counts. Correlation IDs are generated independently from the tokenized endpoint path, and Cursor MCP call IDs are hashed before serialization. Diagnostics must not include endpoint paths/URLs/path components/tokens, API keys, bearer tokens, cookies, session credentials, raw args/results, stdout/stderr payloads, file contents, Cursor settings output, or local private session paths in tracked docs, and they must not call pi UI status, notification, or footer APIs. If tool names themselves are unacceptable for a release target, bridge debug diagnostics are not safe for shared logs under the current contract.
 - This repo does not provide a generic desktop-automation, browser-driver, or CDP recipe. Provider docs should describe pi-cursor-sdk's Cursor provider/bridge contract only.
-- Cursor internal tool activity is recorded from SDK events and scrubbed. In interactive TTY sessions, supported completed `read`, `bash`, `grep`, `find`, `ls`, `edit`, `write`, diagnostics, delete, todo/plan, task, image generation, and MCP activity is replayed through pi's native tool-call rendering path with recorded Cursor results, so the TUI can show native-looking cards without rerunning Cursor's reads/shell commands/file edits. Cursor `glob` activity is replayed through native `find` cards. Cursor write activity is replayed through native-looking `write` cards, and Cursor StrReplace/edit activity uses native-looking `edit` only when recorded arguments truthfully satisfy pi's `edit` schema; path-only Cursor edit and notebook edit replay falls back to neutral Cursor activity before pi validation. Diagnostics, delete, todos/plans, task, image, and MCP activity use neutral Cursor activity cards with pi's default success/error shell. Neutral Cursor activity calls include `activityTitle` and, when available, `activitySummary` so partial/collapsed cards preserve identity such as `Cursor plan`, `Cursor todos`, `Cursor MCP`, or `Cursor edit`. When the Cursor SDK emits a running `task` tool call with a description, the provider surfaces one low-noise in-progress line such as `Cursor task: Explore AI/automation projects` from SDK args only; it does not emit generic heartbeat text or per-tool start cards for ordinary `read`, `bash`, or `grep` activity. Replay-only tools display recorded Cursor results, normalize workspace-local paths/diff headers for display, use pi diff colors for edit previews and path-inferred syntax highlighting for write previews, and fail closed if called without a recorded result. Native replay wrappers are registered only for tool names not already owned by another extension; conflicting tools use the bounded scrubbed transcript fallback. Cursor workflow tools such as `SwitchMode` and Cursor todo state are not pi workflow controls; reported todo/plan events are displayed as Cursor activity only. Plan/todo replay cards can be followed by Cursor's final plan text, selected from `run.wait().result` when Cursor provides one and trimmed against already-emitted text. Started Cursor SDK tool calls that never receive a completion event are discarded without synthetic replay errors; explicit failures remain visible when Cursor reports them through completed tool calls or step results. `PI_CURSOR_NATIVE_TOOL_DISPLAY=0` disables native replay, and `PI_CURSOR_REGISTER_NATIVE_TOOLS=0` is a registration-only opt-out that keeps the transcript fallback without shadowing pi tool names. When bridge or native replay cards are emitted, the provider mirrors Codex's turn shape as Cursor SDK activity arrives: assistant `toolUse`, pi `toolResult`s, live post-tool Cursor thinking/text, any later tool batches as further `toolUse` turns, then Cursor's final assistant answer. For shell replay, completed `stdout` / `stderr` are primary; unambiguous `shell-output-delta` data is used only as display-only fallback for empty successful shell completions, and overlapping shell calls drop ambiguous deltas instead of guessing. Non-interactive runs keep bounded scrubbed transcript output instead, preserving `pi -p` assistant text output. Cursor text deltas stream live when no live-run turn split is active.
+- Cursor internal tool activity is recorded from SDK events and scrubbed. Maintainer reference for all 16 `@cursor/sdk@^1.0.13` `ToolType` values, runtime alias normalization, and intentional mapping/fallback rules: [Cursor native tool replay — SDK ToolType replay matrix](./cursor-native-tool-replay.md#sdk-tooltype-replay-matrix) (official SDK docs: https://cursor.com/docs/sdk/typescript). In interactive TTY sessions, supported completed `read`, `bash`, `grep`, `find`, `ls`, `edit`, `write`, diagnostics, delete, todo/plan, task, image generation, MCP, semantic search, and screen recording activity is replayed through pi's native tool-call rendering path with recorded Cursor results, so the TUI can show native-looking cards without rerunning Cursor's reads/shell commands/file edits. Cursor `glob` activity is replayed through native `find` cards. Cursor write activity is replayed through native-looking `write` cards, and Cursor StrReplace/edit activity uses native-looking `edit` only when recorded arguments truthfully satisfy pi's `edit` schema; path-only Cursor edit and notebook edit replay falls back to neutral Cursor activity before pi validation. Diagnostics, delete, todos/plans, task, image, and MCP activity use neutral Cursor activity cards with pi's default success/error shell. Neutral Cursor activity calls include `activityTitle` and, when available, `activitySummary` so partial/collapsed cards preserve identity such as `Cursor plan`, `Cursor todos`, `Cursor MCP`, or `Cursor edit`. For long-running or externally meaningful Cursor tools (`task`, `shell`, `mcp`, `generateImage`, `recordScreen`, `semSearch`, web search/fetch, plan/todo), the provider may surface one low-noise deferred in-progress thinking line such as `Cursor MCP: external_search` from bounded, scrubbed SDK args; fast local tools (`read`, `grep`, `glob`, and similar) skip lifecycle lines when completion follows immediately, and pi bridge MCP calls are excluded because pi already shows real pi tool execution ([lifecycle visibility](./cursor-native-tool-replay.md#low-noise-tool-lifecycle-visibility)). Replay-only tools display recorded Cursor results, normalize workspace-local paths/diff headers for display, use pi diff colors for edit previews and path-inferred syntax highlighting for write previews, and fail closed if called without a recorded result. Native replay wrappers are registered only for tool names not already owned by another extension; conflicting tools use the bounded scrubbed transcript fallback. Cursor workflow tools such as `SwitchMode` and Cursor todo state are not pi workflow controls; reported todo/plan events are displayed as Cursor activity only. Plan/todo replay cards can be followed by Cursor's final plan text, selected from `run.wait().result` when Cursor provides one and trimmed against already-emitted text. Started Cursor SDK tool calls that never receive a completion event are surfaced with bounded user-visible labels/traces (neutral activity cards when native replay routing allows, otherwise the same inactive or transcript trace fallbacks used for completed replay) instead of being silently discarded; explicit failures remain visible when Cursor reports them through completed tool calls or step results. Pi bridge MCP starts remain excluded from duplicate incomplete Cursor cards because pi already shows real pi tool execution. `PI_CURSOR_NATIVE_TOOL_DISPLAY=0` disables native replay, and `PI_CURSOR_REGISTER_NATIVE_TOOLS=0` is a registration-only opt-out that keeps the transcript fallback without shadowing pi tool names. When bridge or native replay cards are emitted, the provider mirrors Codex's turn shape as Cursor SDK activity arrives: assistant `toolUse`, pi `toolResult`s, live post-tool Cursor thinking/text, any later tool batches as further `toolUse` turns, then Cursor's final assistant answer. For shell replay, completed `stdout` / `stderr` are primary; unambiguous `shell-output-delta` data is used only as display-only fallback for empty successful shell completions, and overlapping shell calls drop ambiguous deltas instead of guessing. Non-interactive runs keep bounded scrubbed transcript output instead, preserving `pi -p` assistant text output. Cursor text deltas stream live when no live-run turn split is active.
 - Synthetic replay names are internal compatibility details. New model-facing prompt text and user-visible cards use native tool names when renderer-compatible, or neutral Cursor activity labels when not. Legacy sessions containing old internal replay names are sanitized before prompt/display. Bridge MCP names such as `pi__sem_reindex` are MCP-only; pi session output uses real pi tool names.
 - Cursor SDK usage events report cumulative internal agent/tool/cache work, not the replayable pi prompt context. The extension does not copy raw Cursor SDK usage into pi usage or compaction. For Cursor assistant messages, `usage.input`/`usage.output` are approximate pi session activity components: initial Cursor prompt input is counted once, consumed split-run tool results are counted as deduped input on the following assistant turn, and assistant output includes visible text/thinking/tool-call content. `usage.totalTokens` is the replayable Cursor prompt/context estimate derived from the same `buildCursorPrompt()` path used for `Agent.send`; it may differ from `input + output` and is the context-safe value for display/compaction. `src/cursor-usage-accounting.ts` owns this usage policy, and `src/cursor-live-run-accounting.ts` owns prompt-once and consumed-tool-result accounting so provider usage and bridge result resolution share the same matched tool-result boundary.
-- Audit observation, 2026-05-19, superseded by the 2026-05-21 replay pass: a missing-file read with Composer 2.5 emitted `tool-call-started` for Cursor `read`, then streamed final text `Error: File not found`, but did not emit `tool-call-completed` or an `onStep` `toolCall` error result. Leftover started calls are now discarded at run completion instead of becoming synthetic replay errors. Cursor-reported completed/step errors remain visible.
+- Audit observation, 2026-05-19, superseded by the 2026-05-21 replay pass and #68 incomplete visibility: a missing-file read with Composer 2.5 emitted `tool-call-started` for Cursor `read`, then streamed final text `Error: File not found`, but did not emit `tool-call-completed` or an `onStep` `toolCall` error result. Leftover started calls are now surfaced at run completion through the same native replay routing as completed tools (activity cards when allowed, otherwise inactive/transcript traces) instead of becoming synthetic replay errors or bogus `cursor` toolUse events. Cursor-reported completed/step errors remain visible.
 - Maintainer visual verification for replay-card changes should follow [Cursor Native Tool Visual Audit Workflow](./cursor-native-tool-visual-audit.md): offscreen PTY-driven pi run, xterm.js/Playwright screenshot rendering, and JSONL inspection before accepting commits or PRs.
-- Cursor provider/runtime releases should follow [Cursor Live Smoke Checklist](./cursor-live-smoke-checklist.md) with real `pi -e . --cursor-no-fast --model cursor/composer-2.5` invocations, manual observation, temporary session dirs, diagnostics scans, and persisted JSONL inspection. Assume every runtime surface is in scope. A release is not ready when any live check is optional, deferred, mostly passing, or unobserved.
+- Cursor provider/runtime releases should follow [Cursor Live Smoke Checklist](./cursor-live-smoke-checklist.md) with real `pi -e . --cursor-no-fast --model cursor/composer-2.5` invocations, manual observation, temporary session dirs, diagnostics scans, and persisted JSONL inspection. See [Cursor testing lessons](./cursor-testing-lessons.md) for auth.json seeding, isolated smoke harnesses, and replay JSONL scans. Assume every runtime surface is in scope. A release is not ready when any live check is optional, deferred, mostly passing, or unobserved.
 - For models without a catalog `context` parameter, context windows are not hardcoded. The extension ships a bundled SDK-derived default/non-Max cache generated from `createAgentPlatform().checkpointStore.loadLatest(agentId).tokenDetails.maxTokens`. Successful runs can update a local override cache, but model discovery does not probe models at startup.
 - Max Mode context windows are distinct from default/non-Max context windows. `@cursor/sdk` 1.0.13 documentation says the SDK may enable Max Mode automatically when a selected model requires it, but the public local-agent `ModelSelection` path still does not expose a manual Max Mode selector. Do not advertise Max Mode context windows unless the SDK catalog exposes an exact parameter/variant or the SDK public API adds a Max Mode selector that the extension actually sends.
 - `@cursor/sdk` 1.0.13 adds latest-style `ModelListItem.aliases`. The extension registers only unambiguous aliases as pi model IDs (with the same context suffixes when applicable) and sends the alias back in `ModelSelection.id`, while sharing Cursor-only state such as fast defaults with the underlying catalog `id`. Aliases shared by multiple base models, such as generic family aliases, are skipped because the pi row metadata would otherwise imply one base model while Cursor may resolve the alias to another.
-- Session-scoped Cursor SDK agent pooling reuses one live `@cursor/sdk` agent across compatible follow-up turns within the same pi session scope. `computeCursorContextFingerprint()` and `shouldBootstrapCursorSend()` decide whether the next turn sends a full bootstrap prompt or an incremental follow-up. The pool recreates the agent when context diverges, when branch or compaction summaries appear after `/tree` navigation or compaction, when the API key identity changes, after send errors, on `session_shutdown`, and when `session_before_tree` / `session_tree` invalidate the active branch. Incremental sends omit the full Cursor SDK tool boundary block because the session agent retains prior bootstrap context.
+- Session-scoped Cursor SDK agent pooling reuses one live `@cursor/sdk` agent across compatible follow-up turns within the same pi session scope. `planCursorSessionSend()` in `src/cursor-session-send-policy.ts` decides whether the next turn sends a full bootstrap prompt or an incremental follow-up, whether the SDK agent must be recreated, and why. `computeCursorContextFingerprint()` and `shouldBootstrapCursorContext()` remain the context-only bootstrap signal. The pool recreates the agent when context diverges, when branch or compaction summaries appear after `/tree` navigation or compaction, after 20 completed incremental sends, when the API key identity changes, after send errors, on `session_shutdown`, and when `session_before_tree` / `session_tree` invalidate the active branch. Incremental sends omit the full Cursor SDK tool boundary block because the session agent retains prior bootstrap context, but every send ends with a short tool tail guard placed after the latest user request.
 - Pi steering/follow-up delivery can arrive while a split live Cursor SDK run is still active. The provider resolves pending live runs by scanning trailing `toolResult` messages while skipping trailing `user` messages, tracks the active live run per session scope, and resumes the in-flight run instead of calling `Agent.send()` again. When the context ends with steering user text after tool results, the provider releases the prior live run and chains an incremental `Agent.send()` for the latest user message in the same provider turn; if the prior run emits more text or tool requests after steering arrives, that stale activity is cancelled instead of surfacing another old-run tool turn and losing the new user input. A pre-send guard waits for or resumes any still-active scoped live run before starting a fresh send so `@cursor/sdk` `AgentBusyError` (`already has active run`) does not surface to pi users.
 
 ## Goal

package/docs/cursor-native-tool-replay.md

@@ -50,10 +50,80 @@ When Cursor reports completed tool activity, the extension can display recorded
 - tasks
 - image generation
 - MCP activity
+- semantic codebase search (`semSearch`)
+- screen recording (`recordScreen`)
+- web search and web fetch activity (when reported as replayable SDK `mcp` or host tool completions; not SDK `semSearch`)
 
 Cursor `glob` activity is displayed through native `find` cards.
 
-Edit and write activity replays through pi-facing `edit` and `write` cards only when replay arguments truthfully satisfy the matching pi schema, but still uses recorded Cursor results only. The adapter passes through truthful Cursor paths, content when Cursor reported it, and recorded diff/details; it does not pretend Cursor's editing schema is pi's schema and it fails closed if a recorded replay result is missing. Cursor `StrReplace` with recorded replacement text displays as native-looking `edit`; path-only Cursor `edit` and notebook edit activity fall back to neutral Cursor activity so pi does not reject the replay before recorded-result handling. Cursor `write` displays as native-looking `write`. Diagnostics, delete, todos/plans, task, image, and MCP activity use neutral Cursor activity cards with pi's default success/error tool shell. Neutral Cursor activity cards carry display metadata such as `activityTitle` and `activitySummary`, so partial/collapsed cards can say `Cursor plan`, `Cursor todos`, `Cursor MCP`, or `Cursor edit` instead of only `Cursor activity`. These replay tools only display recorded Cursor results; they never mutate files or execute tool work directly. Replay paths are normalized to workspace-relative paths when possible. Collapsed replay cards include bounded previews for diffs and text details so small edits, todos, task output, and MCP results are visible without expanding; edit previews omit raw unified diff headers and show compact numbered changed/context lines using pi's native diff added/removed/context colors, and write previews use syntax highlighting when pi can infer a language from the path. Image generation replay cards show the saved image path in the collapsed summary and render the image inline when pi terminal image display is enabled and the generated file is still readable.
+For the full `@cursor/sdk@^1.0.13` `ToolType` set, disposition matrix, and runtime alias normalization, see [SDK ToolType replay matrix](#sdk-tooltype-replay-matrix) below. Official SDK reference: https://cursor.com/docs/sdk/typescript
+
+Edit and write activity replays through pi-facing `edit` and `write` cards only when replay arguments truthfully satisfy the matching pi schema, but still uses recorded Cursor results only. The adapter passes through truthful Cursor paths, content when Cursor reported it, and recorded diff/details; it does not pretend Cursor's editing schema is pi's schema and it fails closed if a recorded replay result is missing. Cursor `StrReplace` with recorded replacement text displays as native-looking `edit`; path-only Cursor `edit` and notebook edit activity fall back to neutral Cursor activity so pi does not reject the replay before recorded-result handling. Cursor `write` displays as native-looking `write`. Diagnostics, delete, todos/plans, task, image, MCP, semantic search, screen recording, and web search/fetch activity use neutral Cursor activity cards with pi's default success/error tool shell. MCP completions whose `toolName` is `WebSearch` / `web_search` / `WebFetch` / similar are labeled **Cursor web search** or **Cursor web fetch** instead of generic **Cursor MCP**. Neutral Cursor activity cards carry display metadata such as `activityTitle` and `activitySummary`, so partial/collapsed cards can say `Cursor plan`, `Cursor todos`, `Cursor MCP`, `Cursor semantic search`, `Cursor screen recording`, `Cursor web search`, `Cursor web fetch`, or `Cursor edit` instead of only `Cursor activity`. These replay tools only display recorded Cursor results; they never mutate files or execute tool work directly. Replay paths are normalized to workspace-relative paths when possible. Collapsed replay cards include bounded previews for diffs and text details so small edits, todos, task output, and MCP results are visible without expanding; edit previews omit raw unified diff headers and show compact numbered changed/context lines using pi's native diff added/removed/context colors, and write previews use syntax highlighting when pi can infer a language from the path. Image generation replay cards show the saved image path in the collapsed summary and render the image inline when pi terminal image display is enabled and the generated file is still readable.
+
+## SDK ToolType replay matrix
+
+Source of truth for SDK tool names: `@cursor/sdk@^1.0.13` conversation `ToolType` values and https://cursor.com/docs/sdk/typescript
+
+Implementation owners: `src/cursor-transcript-tool-specs.ts` (`TOOL_DISPLAY_SPECS`), `src/cursor-native-tool-display-replay.ts`, and `src/cursor-transcript-utils.ts` (`normalizeToolName()`).
+
+This matrix covers **Cursor native tool replay only**. It does not describe the [live pi MCP bridge](#live-bridge-vs-replay) or Cursor-native host tools, settings, plugins, and configured MCP servers from the Cursor SDK local-agent path.
+
+| SDK `ToolType` | pi disposition | pi card / tool name | Notes |
+| --- | --- | --- | --- |
+| `read` | native replay | `read` | Recorded Cursor read results |
+| `shell` | native replay | `bash` | SDK `shell` maps to pi `bash` cards |
+| `grep` | native replay | `grep` | |
+| `glob` | native replay | `find` | Intentional mapping; not a missing `glob` replay bug |
+| `ls` | native replay | `ls` | |
+| `edit` | native replay or neutral activity | `edit` or `cursor` | Native `edit` only when recorded args satisfy pi's `edit` schema; path-only or notebook edits fall back to neutral **Cursor edit** activity |
+| `write` | native replay or neutral activity | `write` or `cursor` | Native `write` only when recorded content/path args satisfy pi's `write` schema; otherwise neutral **Cursor write** activity |
+| `delete` | neutral activity | `cursor` | Collapsed label **Cursor delete** |
+| `readLints` | neutral activity | `cursor` | Collapsed label **Cursor diagnostics** |
+| `updateTodos` | neutral activity | `cursor` | Collapsed label **Cursor todos**; display-only, does not drive pi todos |
+| `createPlan` | neutral activity | `cursor` | Collapsed label **Cursor plan**; display-only, does not drive pi plan mode |
+| `task` | neutral activity | `cursor` | Collapsed label **Cursor task** |
+| `generateImage` | neutral activity | `cursor` | Collapsed label **Cursor image generation** |
+| `mcp` | neutral activity | `cursor` | Collapsed label **Cursor MCP** for non-web MCP completions; web search/fetch MCP `toolName` values reclassify to the rows below |
+| `semSearch` | neutral activity | `cursor` | Collapsed label **Cursor semantic search**; semantic codebase search, not web search |
+| `recordScreen` | neutral activity | `cursor` | Collapsed label **Cursor screen recording** |
+| *(host/MCP alias)* `WebSearch` / `web_search` / similar | neutral activity | `cursor` | Collapsed label **Cursor web search**; display-only Cursor web access reported by the SDK, not an executable pi web tool |
+| *(host/MCP alias)* `WebFetch` / `web_fetch` / similar | neutral activity | `cursor` | Collapsed label **Cursor web fetch**; display-only Cursor web access reported by the SDK, not an executable pi web tool |
+| _(no spec; future/unknown SDK name)_ | neutral activity | `cursor` | Collapsed label **Cursor** plus SDK tool name via `buildGenericPiToolDisplay()`; bounded fallback transcript only |
+
+**Unknown/future fallback path:** SDK tool names with no `TOOL_DISPLAY_SPECS` entry (future or unknown types) use `buildGenericPiToolDisplay()` in `src/cursor-transcript-tool-specs.ts` with bounded `formatFallback()` content from `src/cursor-transcript-tool-formatters.ts`. When native replay is enabled, those completions queue through neutral pi tool name `cursor` (not native pi `read`/`bash`/… cards). Collapsed labels read like **Cursor futureSemSearchWidget** (title `Cursor` plus the SDK tool name) with optional bounded `activitySummary` from scrubbed args/result lines. Errors keep `details.summary` undefined so unbounded raw errors do not leak into replay cards (#52). Known explicit specs still win over this path; pi and bridge tool names are never shadowed.
+
+Neutral activity rows use pi tool name `cursor` with `activityTitle` / `activitySummary` metadata. Legacy internal replay label keys such as `cursor_sem_search` are compatibility details; user-visible collapsed cards use labels like **Cursor semantic search**.
+
+## Runtime alias normalization
+
+Before lookup in `TOOL_DISPLAY_SPECS`, completed SDK tool names pass through `normalizeToolName()` in `src/cursor-transcript-utils.ts`. Documented aliases:
+
+| Runtime alias | Canonical SDK name |
+| --- | --- |
+| `read_file` | `read` |
+| `list_dir` | `ls` |
+| `run_terminal_cmd`, `terminal`, `bash`, `shell` | `shell` |
+| `grep_search`, `search` | `grep` |
+| `file_search` | `glob` |
+| `write_file`, `writefile` | `write` |
+| `strreplace`, `str_replace`, `str-replace`, `edit_file`, `editfile`, `edit_notebook`, `editnotebook`, `notebook_edit`, `notebookedit` | `edit` |
+| `websearch`, `web_search`, `web-search` | `webSearch` (via `resolveTranscriptToolName()`) |
+| `webfetch`, `web_fetch`, `web-fetch` | `webFetch` (via `resolveTranscriptToolName()`) |
+
+Unlisted aliases keep their original name and fall through to the spec lookup or fallback transcript path. SDK `mcp` completions whose nested `toolName` is `WebSearch` / `web_search` / `WebFetch` / `web_fetch` (or `tool_name`) also resolve to `webSearch` / `webFetch` before display lookup.
+
+## Intentional mappings and fallbacks
+
+These behaviors are by design. They are not pi replay execution bugs:
+
+- **`glob` → `find`:** Cursor glob completions render as native pi `find` cards.
+- **`shell` → `bash`:** Cursor shell completions render as native pi `bash` cards, including aliases normalized to `shell`.
+- **`edit` / `StrReplace` / notebook edits:** native pi `edit` cards only when recorded replay args truthfully satisfy pi's `edit` schema; otherwise neutral **Cursor edit** activity so pi validation does not reject the replay before recorded-result handling.
+- **`write`:** native pi `write` cards only when recorded content/path args satisfy pi's schema; otherwise neutral **Cursor write** activity.
+- **Plan/todo tools:** `createPlan` and `updateTodos` replay is display-only and does not drive pi plan mode or pi todo state (see [What replay does not do](#what-replay-does-not-do)).
+- **`semSearch`:** semantic codebase search activity, not web search.
+- **Web search/fetch:** visible **Cursor web search** / **Cursor web fetch** activity when the SDK reports completed replayable tool data (SDK `mcp` with web `toolName`, host aliases above, or local transcript `webSearchToolCall` / `webFetchToolCall` records). These cards are display-only; pi does not expose executable web search/fetch tools through replay.
+- **Unknown/future SDK tools:** neutral Cursor activity cards titled with the SDK tool name (for example **Cursor futureSemSearchWidget**) and bounded scrubbed args/result/error text until an explicit spec is added.
 
 ## What replay does not do
 
@@ -64,11 +134,35 @@ Native replay is display-only:
 - pi does not call Cursor-side MCP servers.
 - replay-only cards do not update pi state or generate images.
 - replay does not expose pi tool schemas to Cursor; the local pi MCP bridge is the separate path that exposes active pi tools.
+- replay does not add pi web search, web fetch, or browser tools; **Cursor web search** / **Cursor web fetch** cards only mirror SDK-reported Cursor web activity.
 - Cursor workflow tools such as `SwitchMode` and Cursor todo state are not pi workflow controls; reported todo/plan events are displayed as Cursor activity only. Plan/todo replay cards do not drive pi plan-mode state.
 
 If a Cursor read completion reports no content, the extension may include a bounded local file preview for safe in-workspace paths. That preview is labeled as a local preview captured at transcript time, not guaranteed Cursor-observed content.
 
-Other unsupported Cursor SDK tools may still be described through a bounded scrubbed activity transcript when the SDK reports completed tool-call data. Started Cursor SDK tool calls that never receive a completion event are discarded without a synthetic replay error; missing completion is not itself treated as a Cursor tool failure. Explicit failures remain visible when Cursor reports an error through a completed tool call or step result. Some Cursor-internal workflow actions may only appear in Cursor's own thinking stream or not be reported as replayable SDK tool completions.
+Other unsupported Cursor SDK tools may still be described through a bounded scrubbed activity transcript when the SDK reports completed tool-call data. Started Cursor SDK tool calls that never receive a completion event are surfaced as neutral **Cursor … did not complete** activity cards or equivalent low-noise thinking traces with a bounded reason such as `missing completion`, `aborted`, or `SDK run failed`. They are not replayed as successful results and raw args/results/errors are not dumped. Explicit failures remain visible when Cursor reports an error through a completed tool call or step result. Some Cursor-internal workflow actions (including web search/fetch that never surfaces as replayable SDK tool completions or local transcript web tool records) may only appear in Cursor's own thinking stream, assistant text, or not be reported as replayable SDK tool data at all.
+
+## SDK reporting limits
+
+These are integration boundaries, not pi replay bugs:
+
+- **Live web-search ordering:** local Cursor WebSearch can be absent from live `onDelta`, `onStep`, and `run.stream()` tool events. When the only evidence is a post-run local transcript `webSearchToolCall`, pi can display the **Cursor web search** card only after `run.wait()` finishes. The extension intentionally keeps assistant text streaming instead of buffering the whole answer just to reorder that card.
+- **WebFetch availability:** `pi-cursor-sdk` can display a Cursor web fetch only after the SDK reports a `webFetchToolCall`, web-fetch-shaped MCP completion, or web-fetch host alias. It cannot make the Cursor SDK expose or execute WebFetch in a run where Cursor's tool set does not include it.
+- **Future SDK tools:** Cursor's official SDK docs say tool names, args, and result payloads can change. Unknown completed tools therefore fall back to neutral Cursor activity cards with bounded, scrubbed text. The extension cannot render tools that the SDK never emits.
+- **Abort exceptions:** user aborts are guarded for the observed Cursor SDK ConnectRPC cancellation shape. A materially different future SDK process-level abort error must be added to the guard after it is observed; broad suppression would hide real crashes.
+
+Maintainer debug (`PI_CURSOR_SDK_EVENT_DEBUG=1`) still records the same discarded started-call events in `coordinator-events.jsonl` under phase `discarded-incomplete-started-tool-call` for investigation (**#52**). User-visible incomplete cards and debug artifacts are complementary: cards explain the gap in the TUI; debug files retain normalized tool names and scrubbed call-id hashes without changing default stderr behavior.
+
+## Low-noise tool lifecycle visibility
+
+Most Cursor tool visibility is completion-based: the completed replay card (or bounded transcript trace) is the source of truth for recorded results. For long-running or externally meaningful tools, the provider may also surface one low-noise in-progress line while Cursor is still waiting on the tool.
+
+Lifecycle rules:
+
+- Eligible tools include `task`, `shell`, `mcp`, `generateImage`, `recordScreen`, `semSearch`, web search/fetch activity, and plan/todo activity. Fast local tools such as `read`, `grep`, and `glob` do not get lifecycle lines in normal cases.
+- Lifecycle text is emitted as a single bounded, scrubbed thinking line such as `Cursor MCP: external_search` or `Cursor shell: shell`. Shell pending labels intentionally omit command text; the completed replay card remains the source of truth for recorded shell activity. Lifecycle lines are not separate permanent replay cards and do not rerun tools.
+- A short defer window coalesces fast start+complete pairs: if a tool completes before the defer elapses, only the completed replay card/trace is shown.
+- pi bridge MCP calls (`pi__*`) are excluded because pi already shows the real pi tool execution path.
+- Implementation: `src/cursor-tool-lifecycle.ts` (eligibility/labels) and `src/cursor-provider-turn-coordinator.ts` (defer, emit, bridge exclusion).
 
 ## Ordering and non-interactive output