diff options
| author | Adam Malczewski <[email protected]> | 2026-06-02 15:30:42 +0900 |
|---|---|---|
| committer | Adam Malczewski <[email protected]> | 2026-06-02 15:30:42 +0900 |
| commit | 9c89ec9db22d0a7226c36b62640addc00918029b (patch) | |
| tree | 35ae0c91b27ec7e6aeea7800f8987fe1db268950 /packages/api/src | |
| parent | c0c08720cceb75b5e635e71190ae1f956f535133 (diff) | |
| download | dispatch-9c89ec9db22d0a7226c36b62640addc00918029b.tar.gz dispatch-9c89ec9db22d0a7226c36b62640addc00918029b.zip | |
fix(tabs): advertise send_to_tab/read_tab in the agent system prompt
Granted tab-messaging tools were registered in the API tool payload but
buildSystemPrompt built its 'You have access to the following tools' list
by filtering toolNames through TOOL_DESCRIPTIONS, which had no entries for
send_to_tab/read_tab. The model was therefore told it lacked those tools
and refused to use them even when explicitly granted.
Add the two missing TOOL_DESCRIPTIONS entries so the capability list
matches the granted toolset. Add regression tests that capture the
constructed Agent's systemPrompt and assert the tab-messaging tools are
listed when granted (and omitted when not), locking the prompt list to
the schema list so they can't drift again.
Diffstat (limited to 'packages/api/src')
| -rw-r--r-- | packages/api/src/agent-manager.ts | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/packages/api/src/agent-manager.ts b/packages/api/src/agent-manager.ts index 85dd160..36a26f8 100644 --- a/packages/api/src/agent-manager.ts +++ b/packages/api/src/agent-manager.ts @@ -83,6 +83,10 @@ const TOOL_DESCRIPTIONS: Record<string, string> = { web_search: "Search the web and optionally scrape full page content from results.", youtube_transcribe: "Fetch the transcript/subtitles for a YouTube video. Set background=true to start in the background and get a job_id for later retrieval.", + send_to_tab: + "Send a message to another tab (agent) by its short ID, as shown in the tab bar. Fire-and-forget: it queues/wakes the target and returns immediately without waiting for a reply. Use read_tab later to read the target's response.", + read_tab: + "Read another tab (agent)'s most recent completed response by its short ID. Returns a non-blocking snapshot; if the target is still running you get its previous completed turn. Use after send_to_tab to collect a reply.", }; /** |