- rpc.go: handle the new "inspector/fixRequested" SPA notification by
  logging "there is an error and user want AI to fix (source=...): ..."
  to the inspector logger. The standalone host has no Copilot UI, so
  this turns the SPA's Fix buttons into a usable signal during preview.
- Re-embed the rebuilt SPA bundle (azd flavor) carrying the matching
  frontend changes: Fix buttons now route through this notification,
  and Events/Tools/Output empty states say "Run the agent" instead of
  "Run the workflow" under VITE_HOST=azd.

handleFixRequested now writes the "user wants AI to fix" line directly
to os.Stderr in addition to the regular logger. The root command
redirects log.Default() to io.Discard (no --debug) or a daily file
(with --debug), so the existing s.logger.Printf was invisible at the
terminal. Other inspector logs stay on the existing path — only this
specific user-facing signal is teed to stderr.

- rpc.go handleFixRequested: prefix output with "[inspector]
  [fix-with-ai] ", drop the "(source=...)" tag, and indent
  continuation lines so multi-line summaries align under the prefix.
  Empty summaries fall back to "(no error details provided)".
- Re-embed the rebuilt SPA bundle (azd flavor) carrying the matching
  generateFixPrompt change: the "Fix this failed workflow step:
  <executorId>." prefix line is gone, leaving only the fields that
  actually carry data (Failed step / Error Code / Error Message /
  Traceback).

…Default)

Drop the URL-based "/responses" gate in proxyInvoke and the hardcoded
logRaw=false in proxyFetchSSE. Both now log unconditionally through
s.logger; --debug controls visibility through the existing
log.Default() routing (file with --debug, io.Discard without).

- proxyInvoke: always log POST body and response (full body for
  /responses, byte count for others to keep diagnostics readable).
- proxyInvoke streaming: pass logRaw=true so SSE chunks are logged for
  every streaming response, not just /responses.
- proxyFetchSSE: pass logRaw=true so SPA-driven SSE channels (e.g.
  /agentdev/v1/diagnostics that powers the Events tab) are also
  captured. Previously these were silently dropped even with --debug.

proxyInvoke now logs the full buffered response body for every URL,
not just /responses. Symmetry with the streaming SSE path which
already logs every chunk regardless of endpoint. --debug still
controls visibility through log.Default().

Add an SSESink callback on inspector.Config so the CLI receives the
proxied SSE bytes; when the inspector webview chats, the terminal now
echoes user input and streams the agent response (or error) using
the same printAgentResponse formatter as `azd ai agent invoke --local`.

Adapter layer (injectSSEEvents in invoke_inspector.go) synthesises
event: lines from the local agentserver's typed data: chunks so the
existing readSSEStream parser can be reused unchanged.

Also collapse the fix-with-ai stderr line to a single line.

…-pr-review

Resolves the per-agent session_id and conversation.id via the existing
resolveStoredID helper and pipes them through inspector.Config and the
navigateToStep boot payload so the SPA continues whatever conversation
the CLI was using instead of minting a fresh UUID per browser mount.

Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>

Replace the proxyInvoke pump's split close paths (deferred resp.Body.Close
plus a goroutine close-on-cancel) with a single cancel()-driven close, so
Body is closed exactly once whether the stream ends normally or the
session is torn down mid-read. Add a test that asserts upstream sees its
request context cancelled within ~2s of the inspector WebSocket closing.

Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>