@emmaneugene/pi-cursor-sdk 0.3.7 → 0.4.1

package/dist/index.js

@@ -15,6 +15,7 @@ import { registerCursorAgentsContextDedup } from "./cursor-agents-context-regist
 import { registerCursorOverflowNormalization } from "./cursor-provider-overflow.js";
 import { registerCursorSdkSessionProcessErrorGuard } from "./cursor-sdk-process-error-guard.js";
 import { prepareCursorSessionForCompaction } from "./cursor-session-compaction-prep.js";
+import { claimCursorExtensionFactory, registerCursorExtensionFactoryRelease, releaseCursorExtensionFactory, } from "./cursor-extension-factory-guard.js";
 function createCursorProviderConfig(models) {
     return {
         name: "Cursor",
@@ -29,54 +30,69 @@ function registerCursorProvider(pi, models) {
     pi.registerProvider("cursor", createCursorProviderConfig(models));
 }
 export default async function (pi) {
-    // Session cwd must register before other session_start listeners that depend on it.
-    registerCursorSessionScope(pi);
-    registerCursorSessionAgentLineage(pi);
-    registerCursorSessionAgentLifecycle(pi);
-    registerCursorSessionAgentResume(pi);
-    pi.on("session_before_compact", async () => {
-        await prepareCursorSessionForCompaction();
-    });
-    registerCursorRuntimeControls(pi);
-    registerCursorNativeToolDisplay(pi);
-    registerCursorQuestionTool(pi);
-    registerCursorSkillTool(pi);
-    registerCursorPiToolBridge(pi);
-    registerCursorAgentsContextDedup(pi);
-    registerCursorOverflowNormalization(pi);
-    let fallbackIssue;
-    const models = await discoverModels({
-        onFallback: (issue) => {
-            fallbackIssue = issue;
-        },
-    });
-    if (fallbackIssue) {
-        registerCursorFallbackIssueWarning(pi, fallbackIssue);
+    const factoryClaim = claimCursorExtensionFactory();
+    if (factoryClaim.kind === "nested")
+        return;
+    try {
+        // Discover first. A discovery failure must not leave process-global
+        // registrars from a discarded extension load.
+        let fallbackIssue;
+        const models = await discoverModels({
+            onFallback: (issue) => {
+                fallbackIssue = issue;
+            },
+        });
+        // Session cwd must register before other session_start listeners that depend on it.
+        registerCursorSessionScope(pi);
+        registerCursorSessionAgentLineage(pi);
+        registerCursorSessionAgentLifecycle(pi);
+        registerCursorSessionAgentResume(pi);
+        pi.on("session_before_compact", async () => {
+            await prepareCursorSessionForCompaction();
+        });
+        registerCursorRuntimeControls(pi);
+        registerCursorNativeToolDisplay(pi);
+        registerCursorQuestionTool(pi);
+        registerCursorSkillTool(pi);
+        registerCursorPiToolBridge(pi);
+        registerCursorAgentsContextDedup(pi);
+        registerCursorOverflowNormalization(pi);
+        if (fallbackIssue) {
+            registerCursorFallbackIssueWarning(pi, fallbackIssue);
+        }
+        pi.registerCommand("cursor-refresh-models", {
+            description: "Refresh the live Cursor model catalog without restarting pi",
+            handler: async (_args, ctx) => {
+                let refreshFallbackIssue;
+                const apiKey = resolveCursorApiKey(await ctx.modelRegistry.getApiKeyForProvider("cursor"));
+                const refreshedModels = await discoverModels({
+                    apiKey,
+                    forceRefresh: true,
+                    onFallback: (issue) => {
+                        refreshFallbackIssue = issue;
+                    },
+                });
+                registerCursorProvider(pi, refreshedModels);
+                if (!ctx.hasUI)
+                    return;
+                if (refreshFallbackIssue) {
+                    ctx.ui.notify(`Cursor model catalog refresh did not use a live catalog: ${refreshFallbackIssue.message}`, "warning");
+                }
+                else {
+                    ctx.ui.notify(`Cursor model catalog refreshed with ${refreshedModels.length} model${refreshedModels.length === 1 ? "" : "s"}.`, "info");
+                }
+            },
+        });
+        registerCursorProvider(pi, models);
+        // Keep the process error guard near the end so earlier Cursor cleanup
+        // remains protected during session shutdown.
+        registerCursorSdkSessionProcessErrorGuard(pi);
+        // Register last so ownership remains protected until all other Cursor
+        // session_shutdown handlers finish.
+        registerCursorExtensionFactoryRelease(pi, factoryClaim);
+    }
+    catch (error) {
+        releaseCursorExtensionFactory(factoryClaim.token);
+        throw error;
     }
-    pi.registerCommand("cursor-refresh-models", {
-        description: "Refresh the live Cursor model catalog without restarting pi",
-        handler: async (_args, ctx) => {
-            let refreshFallbackIssue;
-            const apiKey = resolveCursorApiKey(await ctx.modelRegistry.getApiKeyForProvider("cursor"));
-            const refreshedModels = await discoverModels({
-                apiKey,
-                forceRefresh: true,
-                onFallback: (issue) => {
-                    refreshFallbackIssue = issue;
-                },
-            });
-            registerCursorProvider(pi, refreshedModels);
-            if (!ctx.hasUI)
-                return;
-            if (refreshFallbackIssue) {
-                ctx.ui.notify(`Cursor model catalog refresh did not use a live catalog: ${refreshFallbackIssue.message}`, "warning");
-            }
-            else {
-                ctx.ui.notify(`Cursor model catalog refreshed with ${refreshedModels.length} model${refreshedModels.length === 1 ? "" : "s"}.`, "info");
-            }
-        },
-    });
-    registerCursorProvider(pi, models);
-    // Register last so session_shutdown cleanup remains protected until other Cursor handlers finish.
-    registerCursorSdkSessionProcessErrorGuard(pi);
 }

package/docs/cursor-dogfood-checklist.md

@@ -1,6 +1,6 @@
 # Cursor dogfood checklist
 
-Short maintainer checklist for **minimal-surface** validation after prompt, bridge, replay, or manifest changes. This is the fast path from pi-cursor-composer dogfood sessions—not a substitute for the required [platform smoke gate](./platform-smoke.md).
+Short maintainer checklist for **minimal-surface** validation after prompt, bridge, replay, or manifest changes. This is the fast path from pi-cursor-composer dogfood sessions. It complements the current fork release evidence bar; the cross-platform matrix in [platform smoke](./platform-smoke.md) is deferred under issue #2.
 
 ## Minimal environment
 
@@ -55,11 +55,11 @@ After a Cursor **edit** tool call, confirm the activity card:
 - `details.diffString` present on the replay record
 - Collapsed diff preview with colored add/remove lines in the TUI
 
-Canonical visual evidence: `npm run smoke:visual` (see [Cursor native tool visual audit](./cursor-native-tool-visual-audit.md)).
+Canonical visual evidence: `npm run smoke:visual -- --label release-check --prompt 'Read ./package.json and reply with its package name.'` (see [Cursor native tool visual audit](./cursor-native-tool-visual-audit.md)).
 
 ## Related docs
 
 - [Cursor tool surfaces in pi](./cursor-tool-surfaces.md) — three namespaces and discoverability
-- [Platform smoke gate](./platform-smoke.md) — required cross-platform release gate
-- [Cursor live smoke checklist](./cursor-live-smoke-checklist.md) — inner-loop/manual debug checks
+- [Deferred platform smoke matrix](./platform-smoke.md) — future cross-platform release gate tracked in issue #2
+- [Cursor live smoke checklist](./cursor-live-smoke-checklist.md) — live release evidence and focused checks
 - [Cursor testing lessons](./cursor-testing-lessons.md) — auth, JSONL scans, plan-mode traps

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

@@ -1,20 +1,20 @@
 # Cursor Live Smoke Checklist
 
-> **Platform Smoke:** The required local cross-platform release gate is `npm run smoke:platform:all`; it runs doctor first. Cloud-runtime changes also require `npm run smoke:cloud`. See [docs/platform-smoke.md](./platform-smoke.md) for the full contract. The manual checks below remain useful inner-loop/debug tools but are not the required release gate.
+> **Release evidence:** This checklist is part of the current fork release evidence bar. The Crabbox-backed cross-platform matrix is deferred under [issue #2](https://github.com/emmaneugene/pi-cursor-sdk/issues/2). See [docs/platform-smoke.md](./platform-smoke.md) for the retained future matrix.
 
 ## Purpose
 
-Use this manual checklist during development and debugging of 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. For release readiness, run the local platform gate in [docs/platform-smoke.md](./platform-smoke.md), plus `npm run smoke:cloud` for cloud-runtime changes; this checklist is inner-loop evidence only.
+Use this checklist for live provider/runtime evidence. 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. For release readiness, run the current fork evidence bar: a live print-mode Cursor run and `npm run smoke:visual`.
 
 ## Inner-loop rule
 
-- Build first: `npm run build` after any `src/` edit — the pi manifest loads compiled `dist/`, so unbuilt runs validate stale code. (the cloud/steering/local-resume/provider-debug launchers rebuild automatically even when run directly with `node scripts/...`; `smoke:live`/`smoke:visual`/`smoke:isolated` build via their npm scripts; direct `pi -e .` invocations do not build.)
+- Build first: `npm run build` after any `src/` edit — the pi manifest loads compiled `dist/`, so unbuilt runs validate stale code. (the steering/local-resume/provider-debug launchers rebuild automatically even when run directly with `node scripts/...`; `smoke:live`/`smoke:visual`/`smoke:isolated` build via their npm scripts; direct `pi -e .` invocations do not build.)
 - Run from a clean working tree except for the intended branch diff.
-- Use the local extension under test: `pi --approve -e . --cursor-no-fast --model cursor/grok-4.6`.
+- Use the local extension under test: `pi -ne --approve -e . --cursor-no-fast --model cursor/grok-4.6`. `-ne` keeps a host `pi install` of this package from colliding with `-e .`.
 - Use a temporary `--session-dir` for every run.
 - Do not paste or commit Cursor API keys, raw session contents with secrets, endpoint URLs, or local private paths.
-- If an inner-loop check fails, stop and fix or use [docs/platform-smoke.md](./platform-smoke.md) as the release-blocking source of truth. Do not treat this checklist as a narrower replacement for the platform gate.
-- Do not narrow the smoke scope to the apparent code diff. Treat provider reality, TUI behavior, bridge behavior, replay behavior, diagnostics safety, abort/cancel cleanup, usage accounting, packaging, and cleanup as in scope for every Cursor provider/runtime release.
+- If a live check fails, stop and fix it. Do not treat the deferred platform matrix as a current release blocker.
+- Match focused live checks to the changed surface. Provider reality, TUI behavior, bridge behavior, replay behavior, diagnostics safety, abort/cancel cleanup, usage accounting, packaging, and cleanup each need targeted evidence when the change touches them.
 - A check is passed only when the visible TUI/output, stderr diagnostics, and persisted JSONL agree with the expected behavior.
 
 ## Prerequisites
@@ -24,7 +24,7 @@ export SMOKE_DIR="/tmp/pi-cursor-sdk-live-smoke-$(date +%Y%m%dT%H%M%S)"
 mkdir -p "$SMOKE_DIR"
 pi --version
 npm ls @cursor/sdk @earendil-works/pi-coding-agent @earendil-works/pi-ai @earendil-works/pi-tui
-pi --approve -e . --list-models cursor
+pi -ne --approve -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.
@@ -64,12 +64,12 @@ node scripts/validate-smoke-jsonl.mjs --replay-errors-only "$SMOKE_DIR/session-s
 
 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).
 
-`npm run smoke:live` 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 the canonical rendered-PNG visual review in section 4. Run the relevant helper `--self-test` (`smoke:live`, `smoke:visual`, `smoke:steering`, or `smoke:isolated`) when changing sealed PATH or env wrappers. Release readiness requires the platform smoke gate. Run focused manual checks below when debugging detailed visual TUI behavior, bridge, standalone native replay, abort/cancel, packaging, cleanup, or any touched runtime surface before rerunning the platform gate.
+`npm run smoke:live` polls the section 3 TUI for answer/footer evidence and then cleans up the tmux session. It does not replace the canonical rendered-PNG visual review in section 4. Run the relevant helper `--self-test` (`smoke:live`, `smoke:visual`, `smoke:steering`, or `smoke:isolated`) when changing sealed PATH or env wrappers. Release readiness requires both a live print-mode run and the visual smoke evidence. Run focused manual checks below when debugging detailed visual TUI behavior, bridge, standalone native replay, abort/cancel, packaging, cleanup, or any touched runtime surface.
 
 Pass criteria:
 
 - `pi --version` reports Pi 0.84.0 for this cutover baseline.
-- `npm ls` shows `@cursor/sdk@1.0.27` and local `@earendil-works/*@0.84.0` packages.
+- `npm ls` shows `@cursor/sdk@1.0.30` and local `@earendil-works/*@0.84.0` packages.
 - `cursor/grok-4.6` appears in the model list.
 - No Cursor key or auth token is printed.
 - If neither `~/.pi/agent/auth.json` cursor auth nor `CURSOR_API_KEY` is available, stop and report the live smoke as blocked.
@@ -78,7 +78,7 @@ Pass criteria:
 
 ```bash
 PI_CURSOR_SETTING_SOURCES=none \
-pi --approve -e . --cursor-no-fast --model cursor/grok-4.6 \
+pi -ne --approve -e . --cursor-no-fast --model cursor/grok-4.6 \
   --session-dir "$SMOKE_DIR/basic" \
   --no-tools \
   -p 'Live smoke. Reply exactly: PI_CURSOR_SMOKE_OK' \
@@ -96,7 +96,7 @@ Pass criteria:
 ## 2. Default setting-source startup noise check
 
 ```bash
-pi --approve -e . --cursor-no-fast --model cursor/grok-4.6 \
+pi -ne --approve -e . --cursor-no-fast --model cursor/grok-4.6 \
   --session-dir "$SMOKE_DIR/default-settings" \
   --no-tools \
   -p 'Default settings smoke. Include PRODUCT=42 in the final answer.' \
@@ -118,14 +118,14 @@ Run a real interactive session under tmux:
 ```bash
 SESSION="pi-cursor-sdk-smoke-$(date +%s)"
 tmux new-session -d -s "$SESSION" -x 120 -y 40 -- zsh -lc \
-  "cd '$PWD' && PI_CURSOR_SETTING_SOURCES=none pi --approve -e . --cursor-no-fast --model cursor/grok-4.6 --session-dir '$SMOKE_DIR/tui' --session-id cursor-sdk-1016-tui --no-tools 'TUI smoke. Compute 19 + 23. Reply only with SUM=<number>.'"
+  "cd '$PWD' && PI_CURSOR_SETTING_SOURCES=none pi -ne --approve -e . --cursor-no-fast --model cursor/grok-4.6 --session-dir '$SMOKE_DIR/tui' --session-id cursor-sdk-1016-tui --no-tools 'TUI smoke. Compute 19 + 23. Reply only with SUM=<number>.'"
 ```
 
 Observe with `tmux capture-pane -pt "$SESSION"` or attach manually.
 
 Pass criteria:
 
-- Footer shows `(cursor) composer-2-5`. With `--cursor-no-fast`, Cursor fast mode is off and the Cursor extension status should show `cursor:local · fast:off`; ignore unrelated status text from other extensions.
+- Footer shows `(cursor) grok-4.6`. With `--cursor-no-fast`, Cursor fast mode is off and the Cursor extension status should show `cursor · fast:off`; ignore unrelated status text from other extensions.
 - The run uses Pi 0.84.0 `--session-id` successfully.
 - Assistant answer appears correctly.
 - `/session` shows one user and one assistant message for the simple run.
@@ -134,7 +134,7 @@ Pass criteria:
 
 ## 4. Focused visual card/color rendering check
 
-This is the canonical inner-loop visual debug path for Cursor provider/runtime changes. It requires offscreen TUI visual inspection, not only JSONL or code review. Use Pi 0.84.0, `@cursor/sdk@1.0.27`, a fresh temporary session dir, Cursor SDK `plan` mode, native replay enabled, and the checked-in visual runner. The runner resolves `pi` by directly walking the parent `PATH`, uses `process.execPath` for Node, and prepends that Node directory for both prereq checks and tmux launches so `#!/usr/bin/env node` shims use the validated Node. The default matrix is native replay only: native replay registration is forced on, settings sources are `none`, the pi bridge is off, overlapping built-in pi tools are not exposed, and inherited Cursor SDK event-debug artifact env is cleared. With `--event-debug`, debug capture writes to a deterministic directory under `VISUAL_DIR`.
+This is the canonical visual evidence path for Cursor provider/runtime changes. It requires offscreen TUI visual inspection, not only JSONL or code review. Use Pi 0.84.0, `@cursor/sdk@1.0.30`, a fresh temporary session dir, Cursor SDK `plan` mode, native replay enabled, and the checked-in visual runner. The runner resolves `pi` by directly walking the parent `PATH`, uses `process.execPath` for Node, and prepends that Node directory for both prereq checks and tmux launches so `#!/usr/bin/env node` shims use the validated Node. The default matrix is native replay only: native replay registration is forced on, settings sources are `none`, the pi bridge is off, overlapping built-in pi tools are not exposed, and inherited Cursor SDK event-debug artifact env is cleared. With `--event-debug`, debug capture writes to a deterministic directory under `VISUAL_DIR`.
 
 ```bash
 VISUAL_DIR="$(mktemp -d /tmp/pi-cursor-sdk-1016-visual.XXXXXX)"
@@ -183,7 +183,7 @@ npm run smoke:visual -- "${VISUAL_ARGS[@]}" \
   --prompt 'Stay in Cursor plan mode. If Cursor exposes plan, todo, task, or mode activity for this request, use that capability to outline a tiny unit test without editing files. Otherwise answer with a concise numbered plan. Do not use shell or file mutation tools.'
 ```
 
-By default, `npm run smoke:visual` writes `.ansi`, `.txt`, `.html`, `.png`, and `.jsonl.path` artifacts. If Playwright Chromium is unavailable in an agent-harness run, rerun with `--no-screenshot`, open the generated `.html` with `agent_browser`, save a PNG screenshot, and record that PNG path beside the runner artifacts. To visually audit bridge behavior or ambient Cursor settings, opt in with `--bridge`, `--bridge --expose-builtin-tools`, or `--setting-sources <value>` and label that evidence separately; do not count those opt-in runs as default native replay matrix proof.
+By default, `npm run smoke:visual` writes `.ansi`, `.txt`, `.html`, `.png`, and `.jsonl.path` artifacts. The runner uses Playwright's Chromium or a system Chrome installation. If neither is available in an agent-harness run, rerun with `--no-screenshot`, open the generated `.html` with `agent_browser`, save a PNG screenshot, and record that PNG path beside the runner artifacts. To visually audit bridge behavior or ambient Cursor settings, opt in with `--bridge`, `--bridge --expose-builtin-tools`, or `--setting-sources <value>` and label that evidence separately; do not count those opt-in runs as default native replay matrix proof.
 
 Expected proof for each category is defined in [Cursor Native Tool Visual Audit Workflow](./cursor-native-tool-visual-audit.md). Do not mark a category passed because the prompt was sent. A category passes only when the PNG shows the expected card and the JSONL shows the expected completed `toolCall` / `toolResult` pair with the expected `isError` state.
 
@@ -191,7 +191,7 @@ Pass criteria:
 
 - PNG screenshots exist for every claimed card category, not only text/JSONL logs.
 - JSONL paths exist for every claimed card category.
-- Required cutover categories have matching PNG + JSONL proof from the default native replay matrix: read, grep/search, find/glob, list, shell success, write, edit/diff, and true read failure.
+- Required categories have matching PNG + JSONL proof from the default native replay matrix: read, grep/search, find/glob, shell success, write, edit/diff, and true read failure. The list category remains optional because Cursor does not reliably route it through native `ls`.
 - Native-looking read/search/find/list/shell/write/edit cards use intended pi card styling.
 - Shell success is not red/error-styled; stdout is readable.
 - Edit/diff previews show red/green added/removed colors and readable paths.
@@ -205,7 +205,7 @@ Pass criteria:
 
 ```bash
 PI_CURSOR_SETTING_SOURCES=none \
-pi --approve -e . --cursor-no-fast --cursor-mode plan --model cursor/grok-4.6 \
+pi -ne --approve -e . --cursor-no-fast --cursor-mode plan --model cursor/grok-4.6 \
   --session-dir "$SMOKE_DIR/cursor-mode-plan" \
   --session-id cursor-sdk-1016-plan \
   --no-tools \
@@ -227,7 +227,7 @@ Pass criteria:
 PI_CURSOR_SETTING_SOURCES=none \
 PI_CURSOR_EXPOSE_BUILTIN_TOOLS=1 \
 PI_CURSOR_PI_TOOL_BRIDGE_DEBUG=1 \
-pi --approve -e . --cursor-no-fast --model cursor/grok-4.6 \
+pi -ne --approve -e . --cursor-no-fast --model cursor/grok-4.6 \
   --session-dir "$SMOKE_DIR/bridge" \
   -p 'Bridge smoke. Do exactly two tool calls before answering: first call pi__read on ./package.json; second call pi__read on ./definitely-missing-pi-cursor-sdk-smoke-file.txt. Then answer: OK_NAME=<package name>; MISSING_RESULT=<error or success>. Do not use shell.' \
   > "$SMOKE_DIR/bridge.stdout.txt" \
@@ -236,7 +236,7 @@ pi --approve -e . --cursor-no-fast --model cursor/grok-4.6 \
 
 Pass criteria:
 
-- stdout includes `OK_NAME=pi-cursor-sdk`.
+- stdout includes `OK_NAME=@emmaneugene/pi-cursor-sdk`.
 - Diagnostics include `run_created`, `tools_exposed`, two `request_queued`, two `request_resolved`, and `run_disposed`.
 - The missing-file request has `isError: true`.
 - Persisted JSONL contains real pi tool calls named `read`, matching `toolResult` messages, and final assistant output.
@@ -248,7 +248,7 @@ Pass criteria:
 PI_CURSOR_SETTING_SOURCES=none \
 PI_CURSOR_PI_TOOL_BRIDGE=0 \
 PI_CURSOR_NATIVE_TOOL_DISPLAY=1 \
-pi --approve -e . --cursor-no-fast --model cursor/grok-4.6 \
+pi -ne --approve -e . --cursor-no-fast --model cursor/grok-4.6 \
   --session-dir "$SMOKE_DIR/native-replay" \
   -p 'Native replay smoke. Use your Cursor file-reading capability to read ./README.md, then answer README_SEEN=yes if it contains pi-cursor-sdk.' \
   > "$SMOKE_DIR/native-replay.stdout.txt" \
@@ -314,7 +314,7 @@ Pass criteria:
 
 ## 9. Long-running bridge and abort/cancel
 
-Use this focused check when debugging abort cleanup. The platform smoke gate is the release-blocking source of truth for every Cursor provider/runtime release.
+Use this focused check when debugging abort cleanup. The current fork release evidence bar is documented at the top of this checklist; the platform matrix is deferred under issue #2.
 
 Use a harmless long-running command and interrupt it after the bridge request is queued:
 
@@ -322,7 +322,7 @@ Use a harmless long-running command and interrupt it after the bridge request is
 PI_CURSOR_SETTING_SOURCES=none \
 PI_CURSOR_EXPOSE_BUILTIN_TOOLS=1 \
 PI_CURSOR_PI_TOOL_BRIDGE_DEBUG=1 \
-pi --approve -e . --cursor-no-fast --model cursor/grok-4.6 \
+pi -ne --approve -e . --cursor-no-fast --model cursor/grok-4.6 \
   --session-dir "$SMOKE_DIR/abort" \
   -p 'Abort smoke. Call pi__bash with command: sleep 30 && echo SHOULD_NOT_PRINT. Do not answer until the tool completes.'
 ```
@@ -383,7 +383,7 @@ Pass criteria:
 
 ## Coverage gaps this checklist makes explicit
 
-Everything in this section is in scope when using this checklist for Cursor provider/runtime debugging. Release readiness still comes from the platform smoke gate:
+Everything in this section is in scope when using this checklist for Cursor provider/runtime debugging. The current fork release evidence bar is the full unit/typecheck suite, package dry run, a live print-mode run, and visual smoke. Add focused checks below when a change touches one of these surfaces:
 
 - Long-running bridged tool abort/cancel cleanup.
 - Native replay cards beyond read, especially shell/edit/write cards, when those renderers change.
@@ -393,4 +393,4 @@ Everything in this section is in scope when using this checklist for Cursor prov
 - 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.
 
-If any surface has no adequate platform or focused live check, add that coverage before release instead of assuming mocks cover reality.
+If any changed surface has no adequate focused live check, add that coverage before release instead of assuming mocks cover reality.

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

@@ -16,10 +16,8 @@ Current implementation notes:
 - Installed `@cursor/sdk` user messages accept images, and Cursor models are treated as image-capable; registered input metadata is `text` plus `image`.
 - Image payload forwarding sends images only from the latest user message. If the latest user turn is plain text after an earlier image turn, the transcript keeps an `[image omitted from transcript]` placeholder but no image bytes are sent to Cursor. The prompt explicitly tells Cursor that prior image bytes are unavailable and to ask the user to reattach or describe a prior image when needed. Carrying images forward across turns remains a future product decision because it affects token cost, privacy, stale visual context, and expected multimodal follow-up behavior.
 - Exact `@cursor/sdk@1.0.30` is a package dependency of this extension; users should not need a global SDK install. Pi 0.84.0 is the minimum supported and current validation baseline, while optional published Pi core peer dependencies use `"*"` ranges per current Pi package guidance.
-- After each finished SDK run, the provider calls `agent.getUsage()` (no `runId` on local agents; `runId` only for cloud `run-*` IDs) and maps billed spend into pi `usage` spend fields. Occupancy `totalTokens` uses only in-window local turn-ended occupancy below the latest compaction `tokensBefore`; billed rows never become occupancy, so footer/auto-compact stay aligned with the post-compact Cursor prompt.
-- Startup discovery does not duplicate Pi CLI parsing: it uses stored `~/.pi/agent/auth.json` API-key auth from `/login`, then `CURSOR_API_KEY`, otherwise it registers the bundled fallback catalog. Provider turns keep Pi's resolved `options.apiKey`. `/cursor-refresh-models` and `/cursor-cloud` mutations resolve provider `cursor` through the command context's Pi ModelRegistry, then normalize placeholders through `CURSOR_API_KEY`. The extension config file stores only non-secret Cursor-only state such as fast defaults and the user-level local HTTP transport preference.
-- Cursor Cloud repository overrides accept only HTTPS repository URLs without userinfo, query parameters, or fragments. Invalid values fail during preflight before `Agent.create()`, messages never echo the supplied URL, and shared provider/maintainer scrubbing removes URL/SCP-style userinfo defensively.
-- Cursor Cloud requires a persisted pi session. Immediately after remote `Agent.create()` returns, before debug work or abort checks, the provider appends a branch-local pi lifecycle entry, fsyncs the existing Pi session JSONL anchor through a read-write descriptor, and then fsyncs a newline-framed sidecar keyed by the stable pi session ID (POSIX mode `0600`; Windows inherits the user session directory ACL) in the session directory. Journal creation is exclusive, and existing append/read opens reject symlinks and require matching regular-file descriptor/path identity before using the descriptor. Existing session files use the exact lifecycle entry ID as anchor; fileless first turns use an orphan marker that a same-session-ID restart durably claims onto exactly one matching or replacement branch, surviving the timestamped path change and later JSONL creation without granting sibling access; returned run IDs are fsynced before abort/wait handling, readers skip malformed/truncated lines independently, and branch-only history events are reduced after deduplicated sidecar history, and tombstones are tracked before records exist. A durable sidecar result remains authoritative if its optional Pi mirror append fails; if the sidecar result itself fails, the prior durable intent remains pending and blocks retry rather than claiming success. `--no-session` and durable-ledger failures fail closed before send, while post-send ledger failure requests bounded cancellation. `/cursor-cloud` always validates the embedded session ID, accepts only null anchors while truly fileless, and reconciles each orphan to one branch before listing or mutation. Successive record events merge run/branch metadata monotonically even when mirrored sources arrive out of order. Archive/delete require resolved Cursor auth, fsync a durable intent before the SDK call, and fsync a durable success result afterward; unresolved intent blocks repeat mutation and requires dashboard inspection.
+- After each finished SDK run, the provider calls `agent.getUsage()` and maps billed spend into pi `usage` spend fields. Occupancy `totalTokens` uses only in-window local turn-ended occupancy below the latest compaction `tokensBefore`; billed rows never become occupancy, so footer/auto-compact stay aligned with the post-compact Cursor prompt.
+- Startup discovery does not duplicate Pi CLI parsing: it uses stored `~/.pi/agent/auth.json` API-key auth from `/login`, then `CURSOR_API_KEY`, otherwise it registers the bundled fallback catalog. Provider turns keep Pi's resolved `options.apiKey`. `/cursor-refresh-models` resolves provider `cursor` through the command context's Pi ModelRegistry, then normalizes placeholders through `CURSOR_API_KEY`. The extension config file stores only non-secret Cursor-only state such as fast defaults and the user-level local HTTP transport preference.
 - 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`. `/cursor-refresh-config` calls the current pooled SDK agent's `agent.reload()` to refresh filesystem Cursor config without recreating the agent. 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.
@@ -27,24 +25,24 @@ Current implementation notes:
 - 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.
 - `buildCursorPiToolBridgeSnapshot()` is the runtime capability source for pi bridge tools. It snapshots `pi.getActiveTools()` and `pi.getAllTools()`, carries pi 0.77+ per-tool `promptGuidelines` into bridge MCP descriptions, filters internal replay names, hides overlapping built-in pi tools (`read`, `bash`, `write`, `edit`, `grep`, `find`, `ls`) unless `PI_CURSOR_EXPOSE_BUILTIN_TOOLS=1`, and creates collision-safe MCP names such as `pi__sem_reindex`. Cursor discovers the current run's exposed bridge tools through MCP `listTools`. Bootstrap prompts include a compact callable-surface manifest from `buildCursorToolManifestText()` by default (`PI_CURSOR_TOOL_MANIFEST=1`); disable with `PI_CURSOR_TOOL_MANIFEST=0`. There is no per-turn visible tool list, status manifest, or footer manifest. User-facing summary: [Cursor tool surfaces in pi](./cursor-tool-surfaces.md).
 - Prompt text is the primary provider/bridge contract. Bootstrap prompts carry a short boundary block plus the callable-surface manifest by default (`PI_CURSOR_TOOL_MANIFEST=1`). MCP `listTools` descriptions use a one-line pointer to the bootstrap prompt instead of repeating the full contract (`buildCursorPiBridgeMcpToolDescription()`). Cursor must call the exposed `pi__*` MCP name, not the real pi tool name shown in pi history or transcripts. When exposed, `pi__mcp` takes preference over Cursor-configured MCP for MCP work and `pi__subagent` takes preference over Cursor-native subagents for delegation; the Cursor-native surfaces remain fallbacks when the matching pi bridge tool is absent or unavailable. Pi emits and executes the real pi tool name. Maintainer debug: `/cursor-tools` prints bridge/manifest enablement, effective `PI_CURSOR_SETTING_SOURCES`, and the current callable-surface snapshot.
-- The provider also registers `cursor_ask_question` for Cursor models when the bridge and default-on `PI_CURSOR_ASK_QUESTION` control are enabled. While the tool awaits pi UI input it emits package event `pi-cursor-sdk:ask-question:blocked` with `{ active: true }` and clears `{ active: false }` in `finally`; the tool runs with `executionMode: "sequential"` so parallel sibling calls cannot overlap dialogs. Cursor sees it as `pi__cursor_ask_question`, and pi executes it through the normal tool path so interactive users can choose options from pi UI. `PI_CURSOR_ASK_QUESTION=0` removes only this tool while preserving the rest of the bridge. In non-UI modes it reports that UI is unavailable so Cursor can state a default assumption instead. When pi has visible Agent Skills loaded, the provider rewrites the skill catalog for Cursor and registers `cursor_activate_skill` as `pi__cursor_activate_skill`; pi executes it through the normal tool path so Cursor can load the full `SKILL.md` and skill resource list for the current pi-loaded skill source of truth. `PI_CURSOR_PI_TOOL_BRIDGE=0` disables the local bridge, including question and skill activation bridging. Cloud Cursor agents remain out of scope for the bridge.
+- The provider also registers `cursor_ask_question` for Cursor models when the bridge and default-on `PI_CURSOR_ASK_QUESTION` control are enabled. While the tool awaits pi UI input it emits package event `pi-cursor-sdk:ask-question:blocked` with `{ active: true }` and clears `{ active: false }` in `finally`; the tool runs with `executionMode: "sequential"` so parallel sibling calls cannot overlap dialogs. Cursor sees it as `pi__cursor_ask_question`, and pi executes it through the normal tool path so interactive users can choose options from pi UI. `PI_CURSOR_ASK_QUESTION=0` removes only this tool while preserving the rest of the bridge. In non-UI modes it reports that UI is unavailable so Cursor can state a default assumption instead. When pi has visible Agent Skills loaded, the provider rewrites the skill catalog for Cursor and registers `cursor_activate_skill` as `pi__cursor_activate_skill`; pi executes it through the normal tool path so Cursor can load the full `SKILL.md` and skill resource list for the current pi-loaded skill source of truth. `PI_CURSOR_PI_TOOL_BRIDGE=0` disables the local bridge, including question and skill activation bridging.
 - The bridge queues MCP calls, emits provider `toolcall_*` events, waits for matching pi `toolResult` messages by `toolCallId`, resolves the result back into the same live Cursor SDK run without creating a new `Agent`, and never calls tool `execute()` handlers directly. The same-run resume invariant holds unless the run was disposed, aborted, or cancelled.
 - Cursor SDK MCP tool calls use a guarded timeout override because installed `@cursor/sdk` 1.0.30 still has a 60-second MCP request default with no public per-server timeout option. The extension extends the verified Cursor SDK MCP `callTool` timeout path to 3600 seconds by default and shortens the verified first-send MCP initialize/listTools timeout paths to 10 seconds by default so unavailable configured MCP servers do not block the first reply for a full minute; unknown MCP protocol timeout stacks keep the SDK default. Users can override tool-call timeouts with `PI_CURSOR_MCP_TOOL_TIMEOUT_MS` or `PI_CURSOR_MCP_TOOL_TIMEOUT_SECONDS`, and initialize/listTools timeouts with `PI_CURSOR_MCP_CONNECT_TIMEOUT_MS` or `PI_CURSOR_MCP_CONNECT_TIMEOUT_SECONDS`. Bridged `CallTool` waits also have a local fail-closed deadline that defaults to and cannot exceed the effective MCP tool timeout; `PI_CURSOR_PI_BRIDGE_CALL_TIMEOUT_MS` can lower it, expiry or MCP cancellation aborts active pi execution when available, and expired bridge events are dropped before pi tool emission.
-- Cursor SDK local safety controls are off by default. `--cursor-auto-review` / `PI_CURSOR_AUTO_REVIEW` and `--cursor-sandbox` / `PI_CURSOR_SANDBOX` pass only explicit enabled values into `Agent.create({ local })`; user or trusted project config can set `local.autoReview` and `local.sandboxOptions.enabled`; project config is active only when Pi's project-trust flow reached the extension and approved the project or the run used explicit `--approve`, and project saves require the same immutable trust provenance rather than creating Pi trust resources automatically. Pi 0.84.0 loads `pi install -l` project-local extensions after the trust event, so those installs require `--approve` on every run that reads or writes `.pi/cursor-sdk.json`. Explicit runtime, fast-default, and HTTP transport saves preserve unrecognized config fields, reject malformed or non-object JSON without rewriting it, and use one lock-protected read-modify-write path; fast saves mutate only the selected model key. Because Pi can mutate its in-memory session branch before a journal append throws, a completed global save is authoritative and the command reports the partial journal failure instead of attempting an ambiguous rollback; the new global value stays authoritative over stale branch entries until a later successful save or session restart.
-- Local HTTP/1.1/SSE compatibility is strictly opt-in through `PI_CURSOR_HTTP_1_1`, `/cursor-http on|off|toggle`, or user `cursor-sdk.json` `local.useHttp1ForAgent`. Precedence is session, environment, user, then the built-in unset default; project config is excluded. Unset makes no `Cursor.configure()` call. Explicit values configure the installed SDK before local `Agent.create()`, extension-owned explicit state is cleared with the SDK's documented `null` reset when returning to unset and during session shutdown before module reload, and default/HTTP2/HTTP1 choices split pooled local agents. Pi's supported CLI/TUI/print/RPC lifecycle has one active session runtime per process; concurrent independent `AgentSession` embedding in one process is outside this transport toggle's contract because the installed SDK setting and executor cache are module-global. The footer adds `http1` only for enabled local runtime; cloud creation and status remain untouched.
+- Cursor SDK local safety controls are off by default. `--cursor-auto-review` / `PI_CURSOR_AUTO_REVIEW` and `--cursor-sandbox` / `PI_CURSOR_SANDBOX` pass only explicit enabled values into `Agent.create({ local })`; user or trusted project config can set `local.autoReview` and `local.sandboxOptions.enabled`; project config is active only when Pi's project-trust flow reached the extension and approved the project or the run used explicit `--approve`, and project saves require the same immutable trust provenance rather than creating Pi trust resources automatically. Pi 0.84.0 loads `pi install -l` project-local extensions after the trust event, so those installs require `--approve` on every run that reads or writes `.pi/cursor-sdk.json`. Fast-default and HTTP transport saves preserve unrecognized config fields, reject malformed or non-object JSON without rewriting it, and use one lock-protected read-modify-write path; fast saves mutate only the selected model key. Because Pi can mutate its in-memory session branch before a journal append throws, a completed global save is authoritative and the command reports the partial journal failure instead of attempting an ambiguous rollback; the new global value stays authoritative over stale branch entries until a later successful save or session restart.
+- Local HTTP/1.1/SSE compatibility is strictly opt-in through `PI_CURSOR_HTTP_1_1`, `/cursor-http on|off|toggle`, or user `cursor-sdk.json` `local.useHttp1ForAgent`. Precedence is session, environment, user, then the built-in unset default; project config is excluded. Unset makes no `Cursor.configure()` call. Explicit values configure the installed SDK before local `Agent.create()`, extension-owned explicit state is cleared with the SDK's documented `null` reset when returning to unset and during session shutdown before module reload, and default/HTTP2/HTTP1 choices split pooled local agents. Pi's supported CLI/TUI/print/RPC lifecycle has one active session runtime per process; concurrent independent `AgentSession` embedding in one process is outside this transport toggle's contract because the installed SDK setting and executor cache are module-global. The extension factory is also process-global: the first load owns the bridge, session scope, and pooled SDK agent. A nested child `createAgentSession` load is ignored until that owner session shuts down, so a live parent `pi__subagent` MCP run is not disposed as an extension reload. The footer adds `http1` only when HTTP/1.1 transport is enabled.
 - 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. Maintainer reference for `@cursor/sdk@1.0.30` `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 TUI sessions and structured JSON/RPC modes, 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 users and JSON/RPC consumers can see native-looking cards/events 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/subagent, image, and MCP activity use neutral Cursor activity cards with pi's default success/error shell. Cursor SDK `task` activity is labeled **Cursor subagent** by default because it represents Cursor-spawned child-agent work; the card summary includes description plus subagent kind/model/short ID when Cursor reports them, and `PI_CURSOR_TASK_PRESENTATION=task` restores the older **Cursor task** wording for comparison. This is visibility over Cursor SDK task events, not a native pi subagent session: pi shows start/final output plus any `conversationSteps` tool-call summaries Cursor returns, but cannot show a live nested read/shell/MCP trail when the SDK only returns final subagent text. Neutral Cursor activity calls include `activityTitle` and, when available, `activitySummary` so partial/collapsed cards preserve identity such as `Cursor plan`, `Cursor todos`, `Cursor subagent`, `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 mode/task/todo/plan activity 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 when the run failed, was aborted, or produced no assistant text; after a successful text-producing run, missing-completion starts remain maintainer-debug-only for all tools: installed `@cursor/sdk` 1.0.30 emits `tool-call-started` with no completion delta, step, or conversation entry when a permission policy or hook denies a call, and offers no way to distinguish such denials from lost completions, so suppression is the deliberate choice over false error cards. 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 also shown as bounded live progress while one shell call is active and used as display-only fallback for empty successful shell completions, while overlapping shell calls drop ambiguous deltas instead of guessing. Print mode keeps 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 native replay uses one neutral replay tool name, `cursor`, plus native-compatible card names when renderer-compatible (`read`, `bash`, `grep`, `find`, `ls`, `edit`, `write`). Neutral replay identity lives in `activityTitle`, `activitySummary`, and typed replay details, not in extra registered tool names. Bridge MCP names such as `pi__sem_reindex` are MCP-only; pi session output uses real pi tool names.
-- Local Cursor SDK usage events are used when the SDK reports them before the corresponding pi turn is emitted and the reported counts fit the selected pi model window. For each safe local SDK-attributed assistant turn, `usage.input`, `usage.output`, `usage.cacheRead`, and `usage.cacheWrite` come from the latest per-turn raw `turn-ended.usage` (not SDK `toTokenUsage`): observed local runtime keeps `inputTokens` as the full prompt with cache fields as a partition, even though published SDK `TokenUsage.totalTokens` sums all four fields. Pi maps that raw local shape to disjoint components (`input = inputTokens - cacheReadTokens - cacheWriteTokens`) and `usage.totalTokens = inputTokens + outputTokens` for occupancy/compaction only when that total is below the latest compaction `tokensBefore`; otherwise occupancy uses the post-compaction estimate floor. Cloud billed `getUsage()` rows map to spend fields only and never become occupancy. Approximate fallback never reports less occupancy than the last compatible same-model in-window assistant measurement in context. Cumulative `RunResult.usage` is never used for per-message occupancy. If the local SDK reports no usage in time, or reports full-agent-context-sized usage outside the selected model window, the provider falls back to local `input/output` activity estimates while setting `usage.totalTokens` to the current replayable context estimate so footer/compaction context does not collapse after split tool turns; after a split live-run turn times out waiting for SDK usage, later SDK usage for that live run is ignored rather than risk applying stale usage to the wrong pi turn. Cursor SDK cost is unavailable, so cost remains absent/zero. `src/cursor-usage-accounting.ts` owns this policy.
+- Local Cursor SDK usage events are used when the SDK reports them before the corresponding pi turn is emitted and the reported counts fit the selected pi model window. For each safe local SDK-attributed assistant turn, `usage.input`, `usage.output`, `usage.cacheRead`, and `usage.cacheWrite` come from the latest per-turn raw `turn-ended.usage` (not SDK `toTokenUsage`): observed local runtime keeps `inputTokens` as the full prompt with cache fields as a partition, even though published SDK `TokenUsage.totalTokens` sums all four fields. Pi maps that raw local shape to disjoint components (`input = inputTokens - cacheReadTokens - cacheWriteTokens`) and `usage.totalTokens = inputTokens + outputTokens` for occupancy/compaction only when that total is below the latest compaction `tokensBefore`; otherwise occupancy uses the post-compaction estimate floor. Approximate fallback never reports less occupancy than the last compatible same-model in-window assistant measurement in context. Cumulative `RunResult.usage` is never used for per-message occupancy. If the local SDK reports no usage in time, or reports full-agent-context-sized usage outside the selected model window, the provider falls back to local `input/output` activity estimates while setting `usage.totalTokens` to the current replayable context estimate so footer/compaction context does not collapse after split tool turns; after a split live-run turn times out waiting for SDK usage, later SDK usage for that live run is ignored rather than risk applying stale usage to the wrong pi turn. Cursor SDK cost is unavailable, so cost remains absent/zero. `src/cursor-usage-accounting.ts` owns this policy.
 - Audit observation, 2026-05-19, superseded by the 2026-05-21 replay pass and #68 incomplete visibility, then narrowed by the 2026-05-26 fast-local suppression: 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 from failed, aborted, or no-text runs are surfaced at run completion through the same native replay routing as completed tools (activity cards when allowed, otherwise inactive/transcript traces), while all missing-completion starts are debug-only after a successful text-producing run (widened 2026-09-04 after a `beforeShellExecution` deny-hook reproduction against `@cursor/sdk` 1.0.30 showed a denied shell call emits no completion delta, step, or conversation entry; the same suppression is applied to all tools as a product choice). 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 must pass the local [Platform Smoke Gate](./platform-smoke.md): `npm run smoke:platform:all`. Cloud-runtime changes must also pass `npm run smoke:cloud`. Use [Cursor Live Smoke Checklist](./cursor-live-smoke-checklist.md) only for focused inner-loop/debug runs with real `pi --approve -e . --cursor-no-fast --model cursor/grok-4.6` 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.
+- Current fork release evidence for Cursor provider/runtime changes is the full unit/typecheck suite, package dry run, a live print-mode Cursor run, and visual smoke. The Crabbox-backed platform matrix is deferred under [issue #2](https://github.com/emmaneugene/pi-cursor-sdk/issues/2). Use [Cursor Live Smoke Checklist](./cursor-live-smoke-checklist.md) for live verification with real `pi -ne --approve -e . --cursor-no-fast --model cursor/grok-4.6` invocations, 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.
 - 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` 1.0.30 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.
 - The installed `@cursor/sdk` exposes 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`. Cursor-only fast preferences are keyed by the selected SDK model ID/alias, with read fallback for older preferences keyed by 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.
 - Local restart resume treats user entries already present at `session_start` or selected by tree navigation as crash-ambiguous: an older SDK handle cannot span them because the prior process may already have submitted that prompt. A user entry appended after startup in the current process may span the last completed handle for the normal next send.
-- Persisted pi sessions use a session-scoped Cursor SDK SQLite store at `<getDefaultSdkStateRoot(cwd)>/pi-sessions/<session-hash>/`; create/resume, transcript reads, checkpoint lookup, and exact-ID cleanup all receive that same store. Fileless acquisitions use unique OS-temporary stores that are removed on graceful disposal; invalidation starts a fresh agent instead of reopening a disposed temporary store. Resume entries version the store identity. Legacy entries still resume against the SDK default workspace store, then move to the per-session store after fallback or agent replacement. Removing a persisted pi session does not automatically remove its store directory; only a verified session-derived `pi-sessions/<session-hash>` root may be removed after no pi process uses it. The shared SDK default workspace root recorded by legacy entries must never be removed as session cleanup. Cloud agents are unchanged.
+- Persisted pi sessions use a session-scoped Cursor SDK SQLite store at `<getDefaultSdkStateRoot(cwd)>/pi-sessions/<session-hash>/`; create/resume, transcript reads, checkpoint lookup, and exact-ID cleanup all receive that same store. Fileless acquisitions use unique OS-temporary stores that are removed on graceful disposal; invalidation starts a fresh agent instead of reopening a disposed temporary store. Resume entries version the store identity. Legacy entries still resume against the SDK default workspace store, then move to the per-session store after fallback or agent replacement. Removing a persisted pi session does not automatically remove its store directory; only a verified session-derived `pi-sessions/<session-hash>` root may be removed after no pi process uses it. The shared SDK default workspace root recorded by legacy entries must never be removed as session cleanup.
 - Session-scoped Cursor SDK agent pooling reuses one live `@cursor/sdk` agent across compatible follow-up turns within the same pi session scope. Independently, each distinct local agent whose `Agent.send()` is initiated is best-effort recorded once per native pi session as a non-resumable `cursor-sdk-agent-lineage` custom entry (including failed/cancelled sends and when local resume is disabled). Cloned/forked sessions record lineage under their own pi session ID; donor entries do not suppress the new session. `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, after five minutes without a successful send (`CURSOR_LOCAL_AGENT_IDLE_MS`; `Agent.create`, not `Agent.resume`), 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 (including an explicit shell `cd` hint). True incremental sends also omit invariant Pi system instructions; system-prompt changes are part of the context fingerprint and force a full context-divergence bootstrap that includes the updated system section.
 - 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. Pooled session agents mark busy as soon as live/direct `run.wait()` tracking starts (`trackRunCompletion` on the session lease), and `acquireSessionCursorAgent()` awaits that busy state before returning a lease so send planning, transcript offsets, and later `Agent.send()` do not race the prior turn's SDK run completion (for example pi auto-compaction summarization). `session_before_compact` calls `prepareCursorSessionForCompaction()` to release scoped live-run drain state and reset the pooled agent before summarization streams. Tracked completions and send commits are scoped to the pooled agent `instanceId` so disposal/replacement drops stale tracking and ignores late commits from disposed agents.
 
@@ -388,7 +386,7 @@ Rules:
 - Toggle unsuffixed models with `/cursor-fast`; do not persist a new default while a virtual fast alias is selected.
 - Store per-session and global per-base-model preferences for unsuffixed models.
 - When calling `Agent.create()` or `agent.send()`, include the selected `fast` value in Cursor model params.
-- Show fast-capable local models as `cursor:local · fast:on` or `cursor:local · fast:off` through `ctx.ui.setStatus()` while a Cursor model is active; cloud runtime shows `cursor:cloud · fast:n/a`.
+- Show fast-capable models as `cursor · fast:on` or `cursor · fast:off` through `ctx.ui.setStatus()` while a Cursor model is active.
 - Keep `--cursor-fast` and `--cursor-no-fast` as explicit process-level force flags.
 
 Reason:
@@ -399,9 +397,9 @@ Reason:
 Status examples:
 
 ```text
-cursor:local · fast:off
-cursor:local · fast:on
-cursor:local · fast:on · http1
+cursor · fast:off
+cursor · fast:on
+cursor · fast:on · http1
 ```
 
 ## Cursor SDK Mode Behavior
@@ -429,10 +427,9 @@ Rules:
 Status examples:
 
 ```text
-cursor:local · fast:n/a · plan
-cursor:local · fast:off · plan
-cursor:local · fast:on · plan
-cursor:cloud · fast:n/a · plan
+cursor · fast:n/a · plan
+cursor · fast:off · plan
+cursor · fast:on · plan
 ```
 
 ## Footer Behavior
@@ -441,7 +438,7 @@ Hard requirement:
 
 - Leave pi's default footer intact.
 - Do not use `ctx.ui.setFooter()` for the first pass.
-- Use `ctx.ui.setStatus()` only while a Cursor model is active, showing Cursor-only state that pi cannot show natively, such as `cursor:local`, `cursor:cloud`, local `fast:on|off|n/a`, enabled local `http1`, and non-default Cursor SDK `plan` mode.
+- Use `ctx.ui.setStatus()` only while a Cursor model is active, showing Cursor-only state that pi cannot show natively, such as `cursor`, `fast:on|off|n/a`, enabled `http1`, and non-default Cursor SDK `plan` mode.
 - Non-cursor models must have no Cursor status.
 
 Reason:
@@ -455,13 +452,13 @@ Expected native footer behavior:
 - provider/model is shown by pi from the selected `cursor` model,
 - thinking level is shown by pi when `reasoning` is true,
 - context usage is computed from `contextWindow`,
-- extension status adds only Cursor-only text such as `cursor:local · fast:n/a`, `cursor:local · fast:off`, `cursor:local · fast:on · http1`, `cursor:local · fast:on · plan`, or `cursor:cloud · fast:n/a`.
+- extension status adds only Cursor-only text such as `cursor · fast:n/a`, `cursor · fast:off`, `cursor · fast:on · http1`, or `cursor · fast:on · plan`.
 
 `ctx.ui.setStatus()` adds an extension status line in the default footer. It does not patch the built-in model segment. The native shape is closer to:
 
 ```text
 ...                                      (cursor) gpt-5.5@1m • medium
-cursor:local · fast:off · plan
+cursor · fast:off · plan
 ```
 
 not:
@@ -569,7 +566,7 @@ pi --model cursor/gpt-5.5@1m --cursor-fast -p "Say ok only"
 
 ## Discovered Model Capability Examples
 
-These examples document the capability shapes the extension handles, not an exhaustive live catalog. The exact Cursor catalog changes over time; use `pi --approve -e . --list-models cursor` or `Cursor.models.list()` for the current model surface. When the SDK reports aliases, only unambiguous aliases are registered; shared generic aliases are skipped.
+These examples document the capability shapes the extension handles, not an exhaustive live catalog. The exact Cursor catalog changes over time; use `pi -ne --approve -e . --list-models cursor` or `Cursor.models.list()` for the current model surface. When the SDK reports aliases, only unambiguous aliases are registered; shared generic aliases are skipped.
 
 | Example model shape | Cursor controls | Pi representation |
 |---|---|---|
@@ -594,14 +591,14 @@ Initial Cursor default for Composer 2.5:
 pi model: cursor/composer-2-5
 Cursor params: fast=true
 pi thinking: off
-Cursor status: cursor:local · fast:on
+Cursor status: cursor · fast:on
 ```
 
 Toggle fast:
 
 ```text
 Cursor params: fast=false
-Cursor status: cursor:local · fast:off
+Cursor status: cursor · fast:off
 ```
 
 `shift+tab`: no-op because the model is not reasoning-capable.
@@ -614,7 +611,7 @@ Initial Cursor default:
 pi model: cursor/gpt-5.5@1m
 Cursor params: context=1m; reasoning=medium; fast=false
 pi thinking: medium
-Cursor status: cursor:local · fast:off
+Cursor status: cursor · fast:off
 ```
 
 After selecting the 272k variant:
@@ -629,7 +626,7 @@ After fast toggle:
 
 ```text
 Cursor params: context=272k; reasoning=medium; fast=true
-Cursor status: cursor:local · fast:on
+Cursor status: cursor · fast:on
 ```
 
 After `shift+tab` to xhigh:
@@ -647,7 +644,7 @@ Initial Cursor default:
 pi model: cursor/gpt-5.3-codex
 Cursor params: reasoning=high; fast=true
 pi thinking: high
-Cursor status: cursor:local · fast:on
+Cursor status: cursor · fast:on
 ```
 
 After `shift+tab` to low:
@@ -742,9 +739,9 @@ Before calling done:
    - launch interactive with Cursor
    - verify default pi footer remains unchanged
    - verify Cursor status appears only for Cursor models
-   - verify Cursor fast-capable local models show `cursor:local · fast:on` or `cursor:local · fast:off`
-   - required `cursor-http1-live` platform lane proves an enabled local HTTP/1.1/SSE turn completes and shows `http1`; unit/default live lanes prove local-disabled and cloud statuses omit it
-   - verify Cursor `plan` status appears only in non-default mode and combines with status as `cursor:local · fast:n/a · plan`, `cursor:local · fast:on · plan`, `cursor:local · fast:off · plan`, or `cursor:cloud · fast:n/a · plan`
+   - verify Cursor fast-capable models show `cursor · fast:on` or `cursor · fast:off`
+   - when HTTP/1.1 transport code changes, a focused live check proves an enabled HTTP/1.1/SSE turn completes and shows `http1`; unit/default live lanes prove disabled statuses omit it
+   - verify Cursor `plan` status appears only in non-default mode and combines with status as `cursor · fast:n/a · plan`, `cursor · fast:on · plan`, or `cursor · fast:off · plan`
    - verify non-cursor footer/status unchanged
    - verify `shift+tab` uses pi native thinking
    - verify context changes through native model selection