Merge remote-tracking branch 'origin/master' into simpl-e-acp-trim

packages/ui/acp/src/index.ts

@@ -196,8 +196,8 @@ interface SessionRecord {
  * Drive the in-flight prompt's settle from the harness event stream. The bridge
  * settles off the durable log: the `turn/end` session event on the
  * `session/event` feed for the prompt's own turn, with the agent
- * erroring/settling to idle as a fallback (AGENTS.md "honor cross-seam contracts
- * on BOTH sides") for the case where a throwing peer `session/event` listener
+ * erroring/settling to idle as a fallback (docs/defensive-patterns.md "honor
+ * cross-seam contracts on BOTH sides") for the case where a throwing peer `session/event` listener
  * starved the bridge's listener before it saw the boundary. The first of these
  * to fire settles the prompt; `settle` is then cleared so the others are no-ops
  * (settle-exactly-once).
@@ -271,7 +271,7 @@ export function apply(ctx: Context, config: AcpConfig): void {
     // sessionUpdate returns a promise; a closed connection rejects it. The
     // update is best-effort UI feed, never load-bearing for correctness, so a
     // throwing/rejecting send must not break the turn (the chunk is emitted
-    // inside the model step — see AGENTS.md "contain callback exceptions").
+    // inside the model step — see docs/defensive-patterns.md "contain callback exceptions").
     /* v8 ignore next 3 -- the rejection only fires on a stdout/connection write
        failure (closed pipe), which the in-memory test transport never induces;
        the swallow is a defensive best-effort guard like the loop's emit traps */
@@ -628,7 +628,7 @@ export function apply(ctx: Context, config: AcpConfig): void {
   conn = new AgentSideConnection(makeAgent, stream)
 
   /**
-   * Tear ALL live sessions down to quiescence (AGENTS.md "dispose must reach
+   * Tear ALL live sessions down to quiescence (docs/defensive-patterns.md "dispose must reach
    * quiescence"): for each session settle any pending prompt `cancelled`, then
    * run that session's {@link AgentHandle} `dispose()` — which stops the loop
    * (sets `disposed`, aborts the in-flight step), AWAITS the loop's exit (the
@@ -881,7 +881,7 @@ export class ToolPresenter {
    * @param onError invoked when a tool's `presentCall`/`presentResult` THROWS;
    *   the presenter swallows the error and falls back to the generic
    *   presentation so a buggy display callback can never fail a live turn or a
-   *   `session/load` replay (AGENTS.md "contain callback exceptions at the
+   *   `session/load` replay (docs/defensive-patterns.md "contain callback exceptions at the
    *   boundary"). Defaults to a no-op for callers that don't supply a logger.
    */
   constructor(

packages/ui/acp/tests/bridge.spec.ts

@@ -20,7 +20,7 @@ describe('acp bridge', () => {
   })
 
   afterEach(async () => {
-    // e2e/integration tests own their resources (AGENTS.md): dispose even on
+    // e2e/integration tests own their resources (docs/testing.md): dispose even on
     // failure so a flaky run never leaks a context or persistence dir.
     if (harness) await harness.dispose()
     harness = undefined

packages/ui/acp/tests/harness.ts

@@ -158,7 +158,7 @@ export async function makeBridgeHarness(options: {
    * Plug the REAL `dsh-bash-local` executor + `dsh-tool-bash` tools (instead of
    * a test's own inline tool). Lets a test drive the actual `bash` tool — its
    * real `presentCall`/`presentResult` — through the bridge, so tool-call UI
-   * tests verify the SHIPPING tool, not a stand-in (AGENTS.md "prefer the real
+   * tests verify the SHIPPING tool, not a stand-in (docs/testing.md "prefer the real
    * implementation over a mock in tests").
    */
   withBash?: boolean

packages/ui/acp/tests/load.spec.ts

@@ -62,7 +62,7 @@ describe('acp bridge — session/load replay', () => {
     // bridge. The replayed tool_call/tool_call_update must carry the tool's OWN
     // presentation — identical to how it streamed live — via a throwaway
     // presenter that pairs call→result as the log replays in order. Uses the
-    // shipping tool (withBash), not a stand-in (AGENTS.md "prefer the real
+    // shipping tool (withBash), not a stand-in (docs/testing.md "prefer the real
     // implementation over a mock in tests").
     live = await makeBridgeHarness({
       storageDir,

packages/ui/acp/tests/stream-update.spec.ts

@@ -289,7 +289,7 @@ describe('ToolPresenter (tool-owned presentation via the tool registry)', () =>
 
   it('a THROWING presentCall/presentResult is contained: generic fallback + onError, never propagates', () => {
     // A buggy tool whose display callbacks throw must NOT fail a live turn or a
-    // session/load replay (AGENTS.md "contain callback exceptions at the
+    // session/load replay (docs/defensive-patterns.md "contain callback exceptions at the
     // boundary"). The presenter swallows the throw, reports via onError, and
     // falls back to the generic presentation.
     const boom: ToolDefinition = {
@@ -381,7 +381,7 @@ describe('ToolPresenter (tool-owned presentation via the tool registry)', () =>
   it('forwards fs-tool render intents onto the wire (REAL read → generic locations, edit → diff content)', async () => {
     // Use the SHIPPING fs tools (not a stand-in), booted through their real
     // plugins, so the wire tool_call carries the actual presentCall output —
-    // read's follow-along `locations` and edit's `diff` content block. (AGENTS.md
+    // read's follow-along `locations` and edit's `diff` content block. (docs/testing.md
     // "prefer the real implementation over a mock".)
     const ctx = new Context()
     await ctx.plugin(SystemPrompt)

packages/ui/acp/tests/turns.spec.ts

@@ -82,7 +82,7 @@ describe('acp bridge — turn outcomes', () => {
   it('the REAL bash tool drives the tool-call UI end-to-end: command title + description block + console output', async () => {
     // Use the SHIPPING tool (dsh-tool-bash + dsh-bash-local), not an inline
     // stand-in, so this verifies the actual presentCall/presentResult the editor
-    // sees (AGENTS.md "prefer the real implementation over a mock in tests").
+    // sees (docs/testing.md "prefer the real implementation over a mock").
     // The mock MODEL still scripts the tool call (no real LLM needed), but the
     // tool and executor are real: a real `echo` runs and its real output flows
     // back through the bridge.