Add a clause to the preformatted deny-simplify note so Claude proceeds
silently with the simpler version instead of narrating the change.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A fourth button on the permission card that denies the action with a
preformatted note: it's too complex for the permission system, retry in a
simpler/more granular form, and explicitly do NOT add a memory or change
permission settings (so Claude reformulates instead of fiddling with the
permission surface). A typed note is appended rather than discarded.
Addressable by number key (4 with remember, else 3); tooltip explains it.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The prompt card's number-key shortcuts matched only digit1..digit9
(the number row); numpad 1-9 fell through to ignored. Add a
parallel _numpadKeys list and check it in _onKey so the keypad
maps to the same 1-9 selection for Allow/Deny and question
options. numpadEnter was already handled. The hasPrimaryFocus
guard still lets digits type into a focused note field.
Adds four widget tests (numpad Allow/Deny, question option,
focused-note swallow). Closes T-310 (under UI epic T-276).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
In a ToolPromptCard, number keys pick the matching button/option (labels are
prefixed 1./2./3.…) and Enter confirms the primary action — matching the Claude
CLI. Permission: 1=Allow, 2=Allow&remember (when offered) else Deny, 3=Deny.
AskUserQuestion: 1..N select/toggle the current question's options + Other.
The card autofocuses and the key handler self-guards on hasPrimaryFocus, so once
the user clicks into a note field the digits type normally and never fire a
button. Shared the permission/option actions between the buttons and the keys.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The team cockpit / chat / config-tab work landed under-tested and pulled
total line coverage to 94.32%. Add tests for the team chat sidebar + pane
(@-completion, overlay, interrupt, message rows), the config loaders, the
stream-json MCP/streaming/rate-limit paths, and the conversation/prompt
card variants — restoring the total to 95.06%.
Co-Authored-By: Claude <noreply@anthropic.com>
The conversation pane now exploits the structured stream instead of
dumping tool input as JSON. ConversationController indexes tool_use by id
so a tool_result pairs back to its call and renders the Edit/Write diff or
is_error failure in place; per-tool bodies (Bash command+output, Read/Grep
file/query) reuse the shared renderers factored out of the permission
card. SessionStatus gains cost + contextWindow + rate-limit, read straight
off the init/result/rate_limit_event events, so the in-pane status line
reflects live state without the config probe.
Partial-message streaming is wired behind --include-partial-messages but
its event shape is unverified against the live binary and degrades to a
no-op if it differs — see T-184.
T-168.
Co-Authored-By: Claude <noreply@anthropic.com>
Claude often sends the file path itself as the tool description for
Write/Edit. The card body already renders that path, so printing the
description line above it showed the same path twice. Suppress the
description when it just repeats file_path.
Co-Authored-By: Claude <noreply@anthropic.com>
Bash, Write, and Edit/MultiEdit each get a tool-appropriate body in
the permission card instead of the indented-JSON dump: Bash renders
the command as a shell code block with a background/timeout footer,
Write shows path + content syntax-highlighted from the extension, and
Edit shows path + before/after blocks. Unknown tools keep the JSON
fallback.
Co-Authored-By: Claude <noreply@anthropic.com>
Two spot-check fixes (T-178, T-179), both grounded in a boundary test of
the stream-json wire (findings folded into the spike doc):
- Harness-injected user messages (skill loads, slash-command expansions,
system reminders) carry isSynthetic on the wire (isMeta in the
transcript). They were rendering as blue "you" cards though the user
never typed them; now UserMessage.injected flags them and the view
shows a muted, collapsed "context" card instead.
- Permission prompts now show the command/input being permitted (a
capped, scrollable code block) so you can see what you approve. Instead
of fully hiding a prompted tool-use, once resolved it collapses to a
one-line summary with a green (approved) or red (denied) border; the
session tracks per-tool_use_id outcome and the view colours it. The
result is kept.
Corrects an earlier wrong assumption: the Skill tool is auto-allowed
(no permission prompt); the inject only appears once the Skill tool is
actually invoked, which is why deny-captures missed it.
T-178, T-179, D-78.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Builds on the in-composer prompt surface (D-78):
- Permission prompts (T-175): Allow / Allow-and-don't-ask-again / Deny.
"Don't ask again" appears only when the request carries a
permission_suggestion and echoes it back as updatedPermissions. An
optional note rides Deny as the message, or Allow as a follow-up user
message (the protocol has no allow-with-message).
- AskUserQuestion picker (T-176): a single question renders bare; 2-4
questions step one at a time (nav shows "N · Header", ✓ when answered)
then a review/confirm screen. Each question offers an "Other" free-text
choice and a per-choice note; multi-select joins labels. A "chat
instead" escape denies the prompt so the user can type freely. On
submit the answer is echoed into the log, since the card is ephemeral.
- Collapsed tool cards (T-177): multi-line tool_use / tool_result start
collapsed behind a one-line summary; one-line output renders inline.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Replaces the Claude pane's tmux-TUI + transcript-tail backend with
Claude Code's stream-json control protocol (D-77/D-78). A
StreamJsonSession owns the `claude` process: its event stream feeds the
existing ConversationController, and permission / AskUserQuestion
prompts arrive as can_use_tool control_requests. Those surface as a
ToolPrompt in the composer zone — the pane swaps the text input for an
Allow/Deny card or an option picker while a prompt is open, so
interaction stays out of the conversation stream and the prompt buttons
don't fight the message-card hover chrome. The decision is written back
as a control_response (allow echoes updatedInput; AskUserQuestion
answers go in updatedInput.answers). Unsupported control subtypes are
answered with an error so a turn never hangs.
Session continuity is --resume (existing transcript) vs --session-id
(new); /clear and /resume respawn the process. The transcript reader
still backs the sidebar/status/team surfaces. T-165, T-166.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
jpmschweitzerandClaude Opus 4.8