main
3
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
  adminandClaude Opus 5.5
|
0dd671ea26 |
Count each connected agent once in the editor badge (#429)
The Agent badge showed 2 or 3 while one Claude Code session was connected. The relay log against the open TCP connections in the container showed two causes. - A client may drop its event stream while the relay still asks the API about its token. The close was over before the relay listened for it, so the stream stayed in the list and counted for good. The relay now listens before the token check and keeps no stream that is already gone. It listens on the response, not the request. - Claude Code opens three sessions whenever it connects and keeps a stream on one of them. It never ends the others with a DELETE. Any session counted for two minutes after its last request, so the badge stood at 3 after each start. Now a session counts while its stream is open or it called a tool in the last two minutes. - The relay logs session start, stream open and close and each change of the count, with session ids cut to 8 characters. One case is left: after a relay restart Claude Code sometimes repeats its first call on a spare session. The badge then shows 2 for two minutes and drops to 1 on its own. Tests: - relay.test.ts: 27/27, three new. A dropped stream counts out, a stream dropped during the token check never counts, and spare sessions without a tool call do not count. - Counter-checks: without the early close listener the drop test turns red, with the old count two tests turn red. - Live: the badge showed 2 with one open SSE connection before. After the fix it shows "Agent · 1" and stays there after a normal call. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
adminandClaude Opus 5.5
|
25af064249 |
Let an AI agent read and edit the open project through MCP (#429)
Stage 2 of #429. Until now an agent could only look at the editor. Now it reads the project and changes it through the same commands the user's own edits run, so every change shows up live and one Ctrl+Z takes back a whole agent call. - Read tools: list_assets, get_asset, get_graph and catalog. The catalog lists the commands with their arguments, the nodes of a graph from the same palette the user sees, asset types and variable kinds. - run_commands runs its steps as one undo step named "Agent: ...". A failing step rolls back the steps before it. The answer names the step and the reason the editor gave. - A step can name what it made ("as") and later steps use "$name". Each step is built after the one before has run, so one call can make a behavior and fill it. - 23 commands cover assets, variables, scene objects and graphs. Textures, fonts, sounds and videos need a file and are left out. - open, select, play and undo/redo drive the editor. - Deleting asks the user with the same text as their own delete. The tab sends "wait", and the relay then gives the call 2 minutes instead of 30 seconds. - tools.json is the only source of the argument schemas. argCheck checks every call against them before anything runs. - An open menu now names its first entries in get_view, instead of an empty title. - The new host functions live in editorToolHost.ts, so Editor.ts does not grow further. Found while testing: e2e 71 hung for 30 s in Page.navigate after a failure. The beforeunload guard of an unsaved project held the page and hid the real error. The module now reports the error first and waits for the save before it navigates. Tests: - Gate on melektaus-atx: CHECK EXIT 0, 317 files, 4903 tests. - agent-edit 14/14, agent-view 10/10, relay 24/24. - e2e 71 16/16 on atx and against the live site. One call builds a sprite with an arrow-key behavior, play moves it from x 0 to -125, and one undo restores the assets exactly. - Counter-checks turned red: no rollback, a partial undo, no delete question, a relay that ignores "wait". Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
adminandClaude Opus 5.5
|
48ec722660 |
Let an AI agent see the open editor through MCP (#429)
Claude Code should be able to work inside the user's open editor tab. This first stage connects the two and lets the agent look: what the user sees and a picture of it. Changing the project comes in stage 2. - An agent token per account opens only /mcp, no API route. The dialog "Agent tokens..." in the account menu creates it once, shows the ready "claude mcp add" line and revokes it. The server keeps only its sha256 (api/lib/AgentTokens.php). - Wrong tokens count into the sign-in brake from #427. Changing the password, renaming or deleting an account ends its tokens. - The relay (tools/mcp/) is a small Node service without packages, WebSocket server included. It runs in the container feuerwerk-mcp because PHP-FPM cannot hold connections. Whether a token or a tab ticket is valid is still decided by the PHP API, through two routes that answer only with the relay key. - The tab joins over WebSocket on the same origin with the normal session, an Origin check and a one-time ticket. It connects only after "Agent" is switched on in the account menu. One tab per account is active, a new one takes over. Guests get nothing. - Tools: get_view (project, tab, document, selection with names, camera, play state, open dialog) and screenshot. The resource feuerwerk://view can be subscribed. Claude Code does not act on that reliably, so a changed view is also noted on the next answer. - A badge next to the account menu shows the connected agents. It counts only agents with an open stream or a request in the last two minutes. - CI starts the relay in front of php -S (tools/ci/serve.sh), and e2e 71 runs the whole path in the browser. Found on the live test: the badge showed four agents because old sessions of revoked tokens were still counted. Tests: - Gate on atx: 316 files, 4888 tests - relay protocol test with fake API and fake tabs: 23/23 - get_view, tools, socketUrl: 16/16 - PHP agents 29, rights 103 checks - e2e 71 on atx 10/10, against the live site 10/10, no CSP violation - real Claude Code against the live site: get_view answered - ZAP against /mcp: nothing at High or Medium - every new check fails when the guard it covers is taken out (6) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> |