mirror of
https://github.com/CopilotKit/CopilotKit.git
synced 2026-09-14 16:26:20 +08:00
Ran Shem Tov
620cf00974
Strands mints UUID tool_call_ids for tool results (confirmed via the aimock journal), so the langgraph-python toolCallId-keyed follow-up fixtures never matched and the agent re-emitted the tool, looping (text-unstable) across frontend-tools, gen-ui-agent, gen-ui-open, gen-ui-open-advanced, gen-ui-headless-complete, reasoning-chain and the weather pills. Re-key the affected multi-leg fixtures to the id- and thread-history-invariant sequenceIndex pattern (as built-in-agent does), for both integrations. Also: - Add write_document poem/email/quantum fixtures for shared-state-streaming (was a stale single fixture that 404d). - Strip content from reasoning-chain tool legs (content+toolCalls in one fixture is undefined behavior); reasoning rides toolCalls alone. - Narrow the over-broad d4 summarize catch-all to "Summarize the sales pipeline" so it stops shadowing gen-ui-agent competitor pill; matches langgraph-python. - Commit the real multimodal sample.png/sample.pdf (were git-LFS pointers the harness could not resolve).
39 lines
1.8 KiB
JSON
39 lines
1.8 KiB
JSON
{
|
|
"_meta": {
|
|
"description": "D6 fixtures for strands / tool-rendering-default-catchall",
|
|
"sourceFile": "d5-tool-rendering-default-catchall.ts",
|
|
"created": "2026-05-22",
|
|
"updated": "2026-06-15",
|
|
"note": "Reordered toolCallId-keyed narration BEFORE the tool-emit fixture (first-match-wins) and dropped hasToolResult:false on the tool-emit fixture for consistency with the canonical pattern. Single-prompt demo so hasToolResult:false would still work in isolation, but the canonical shape is more robust to thread-state changes."
|
|
},
|
|
"fixtures": [
|
|
{
|
|
"_comment": "tool-rendering-default-catchall — 'forecast for Tokyo' 1st leg: emit get_weather. sequenceIndex:0 gates it to the first match — with stopStreamingAfterResult removed the agent takes a 2nd turn, and Strands' UUID tool ids defeat the old toolCallId follow-up; sequenceIndex is id-invariant so the bare narration below catches the 2nd leg. The built-in default catchall renderer fires for unhandled tools ([data-testid='copilot-tool-render'][data-tool-name='get_weather']).",
|
|
"match": {
|
|
"userMessage": "forecast for Tokyo",
|
|
"sequenceIndex": 0,
|
|
"context": "strands"
|
|
},
|
|
"response": {
|
|
"toolCalls": [
|
|
{
|
|
"id": "call_d6_default_catchall_weather_001",
|
|
"name": "get_weather",
|
|
"arguments": "{\"location\":\"Tokyo\"}"
|
|
}
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"_comment": "tool-rendering-default-catchall — 'forecast for Tokyo' 2nd leg: narration after get_weather (sequenceIndex:0 exhausted).",
|
|
"match": {
|
|
"userMessage": "forecast for Tokyo",
|
|
"context": "strands"
|
|
},
|
|
"response": {
|
|
"content": "Tokyo is 22°C and partly cloudy with light easterly winds."
|
|
}
|
|
}
|
|
]
|
|
}
|