# Add agent-shell-quote-reply and DWIM context prefill for queue-compose

[timvisher-dd]

Summary

Two related compose-buffer enhancements:

• agent-shell-quote-reply (new) pops the queue-compose buffer
  prefilled with the agent's last prose reply, wrapped as a GFM
  block quote. Bound to q in the agent-shell-help-menu
  "Insert" group.
• agent-shell-queue-request, when called interactively without
  a prompt, now gathers any DWIM context available in the source
  buffer (active region, error at point, dired marked files) and
  prefills the compose buffer with it. Regions from buffers with
  no file association are wrapped as GFM block quotes; file-
  visiting and dired context keep their existing purpose-built
  decoration.

Why not just use shell-maker--command-and-response-at-point?

It returns the entire rendered turn span — shell-maker--extract- history' takes a buffer-substring' between
`' and the next prompt, so tool-call
drawers and thought blocks are included. For a quote-reply that's
not what you want.

agent-shell--last-agent-message-text' walks back from point-max' to the most recent fragment whose
agent-shell-ui-state' qualified-id ends in -agent_message_chunk' and pulls the raw body from
`agent-shell-ui--content-store'. Tool-call and thought fragments
are skipped by the suffix check.

`text-property-search-backward' gotcha

When its predicate rejects the nearest match, it returns nil
rather than continuing the walk. The first implementation used
the built-in predicate path and silently returned nil whenever a
tool-call fragment sat between point-max and the agent message.
The fix loops over property changes manually and applies the
suffix check each step — the regression test
(`agent-shell--last-agent-message-text-skips-tool-calls') fails
without the loop.

Test plan

• 13 new ERT tests in tests/agent-shell-tests.el:
  • `agent-shell--gfm-blockquote' (single-line, multiline,
    nested code fence, already-quoted input)
  • `agent-shell--last-agent-message-text' (returns body,
    skips tool calls, picks last of many, nil when empty)
  • `agent-shell-quote-reply' (error outside shell, error when
    no reply, pops compose with quoted reply)
  • agent-shell-queue-compose-pop' :initial-content' (insert
    into fresh buffer, append to existing draft with blank-line
    separator, no-op when omitted)
  • agent-shell--compose-initial-content' (quotes non-file region, delegates to --context' otherwise)
  • Updated agent-shell-queue-request-without-prompt-pops- compose' for the new &key' signature.
• Full bin/test: 259/260 passing, 1 pre-existing skip,
  all CI checks green.
• Live-validate: not yet run (1Password CLI not signed in
  when prepping the PR). Worth a manual run that produces a
  reply with tool calls in the same turn, then exercising
  `agent-shell-quote-reply' to confirm the quoted output
  contains only the prose.

Refs

• agent-shell-wafa