In-app agent chat: your own coding agents over ACP, plus OpenAI-compatible endpoints (#1102)

* Agent chat prototype: drive an ACP agent the user already has from a side panel

A desktop-only chat panel (off by default) that starts a coding agent over the
Agent Client Protocol and gives it SolidCraft's MCP server, bridged to the open
window through the token-protected control channel with the default folder
limits. It finds installed agents (Claude Code and Codex adapters, Gemini CLI,
Copilot, Qwen, OpenCode, goose) with version and login state, streams text,
tool calls and plans, shows the agent's permission requests, and when an agent
isn't signed in shows its own login methods without handling any credential.

Design notes and findings: docs/design/in-app-agent-chat.md.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* docs: say only what the end-to-end run showed

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Agent chat: gate, one undo per message, docking, process groups, discovery polish

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Agent chat: Settings → AI, several agents with a switcher, OpenAI-compatible endpoints, permission modes, toolbar button

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Agent chat: translations, tool cards, Add agent dialog fixes, test agent saves on its own

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Agent chat: third-party licences for the keychain crates; clippy

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Agent chat: badge text from the theme tokens

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Agent chat: Auto-allow model edits is the default permission mode

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
bherbruckandClaude Opus 5.5 authored and GitHub committed 2026-10-15 14:22:38 -04:00
1 parent 02fe495d38
commit 2d069ca186
36 files changed
+8078 -303

No files matched your search

+7
View File
@@ -222,6 +222,13 @@ retain their saved two-finger scroll preference; camera motion is available thro
Crash Reports…) with a reviewed issue draft; agents read them through
`diagnostics.crash_reports`, the MCP `crash_reports` tool or the CLI. Nothing is sent
anywhere. See [crash reports](docs/crash-reports.md).
- Agent chat (off by default, desktop): a side panel that drives a coding agent the user
already has (Claude Code through its ACP adapter, Codex, Gemini CLI, OpenCode, …) over the
Agent Client Protocol, under the user's own login; SolidCraft stores no keys. The agent works
through SolidCraft's MCP tools on a gated endpoint of its own: file actions wait for Allow or
Deny, crash reports are off limits, 24 changes per message, one undo step per message, and
the agent's whole process group ends with the panel or the app. Docks left or right,
minimises to a strip. See [agent chat](docs/agent-chat.md).
- Command scripts from designs (#886): `timeline.export_script` (CLI `solidcraft-cli script`)
writes a design's history as a script that `eval` and `run` replay into the same design —
user parameters, units, sheet metal and plastic rules and materials as their own commands,