Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions .changeset/tall-trams-turn.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
---
"braintrust": patch
---

fix(eve): Avoid reporting unresolved dynamic model fallbacks as model metadata
2 changes: 1 addition & 1 deletion e2e/config/pr-comment-scenarios.json
Original file line number Diff line number Diff line change
Expand Up @@ -228,7 +228,7 @@
"scenarioDirName": "eve-instrumentation",
"label": "Eve Instrumentation",
"metadataScenario": "eve-instrumentation",
"variants": [{ "variantKey": "eve-v0-20-0", "label": "v0.20.0" }]
"variants": [{ "variantKey": "eve-v0-22-1", "label": "v0.22.1" }]
},
{
"scenarioDirName": "github-copilot-instrumentation",
Expand Down

Large diffs are not rendered by default.

Original file line number Diff line number Diff line change
Expand Up @@ -48,16 +48,14 @@
],
"metadata": {
"eve.session_id": "<eve.session_id:1>",
"model": "gpt-5.4-mini",
"provider": "openai",
"scenario": "eve-instrumentation",
"testRunId": "<run:1>"
},
"metrics": {
"completion_tokens": 67,
"prompt_cached_tokens": 0,
"prompt_tokens": 6744,
"tokens": 6811
"prompt_tokens": 2308,
"tokens": 2375
}
},
{
Expand Down Expand Up @@ -111,7 +109,7 @@
},
"metrics": {
"completion_tokens": 26,
"prompt_cached_tokens": 5504,
"prompt_cached_tokens": 0,
"prompt_tokens": 6554,
"tokens": 6580
}
Expand Down Expand Up @@ -230,7 +228,7 @@
},
"metrics": {
"completion_tokens": 48,
"prompt_cached_tokens": 12032,
"prompt_cached_tokens": 6528,
"prompt_tokens": 13178,
"tokens": 13226
}
Expand Down Expand Up @@ -360,16 +358,14 @@
],
"metadata": {
"eve.session_id": "<eve.session_id:1>",
"model": "gpt-5.4-mini",
"provider": "openai",
"scenario": "eve-instrumentation",
"testRunId": "<run:1>"
},
"metrics": {
"completion_tokens": 66,
"prompt_cached_tokens": 6528,
"prompt_tokens": 6894,
"tokens": 6960
"prompt_cached_tokens": 2048,
"prompt_tokens": 2458,
"tokens": 2524
}
}
],
Expand All @@ -382,16 +378,14 @@
"output": "Final answer from read: Researcher result: Eve instrumentation — https://eve.dev/docs/guides/instrumentation; read title: Eve instrumentation; URL: https://eve.dev/docs/guides/instrumentation; excerpt: Eve hooks expose runtime stream events that Braintrust maps into a nested turn trace.",
"metadata": {
"eve.session_id": "<eve.session_id:1>",
"model": "gpt-5.4-mini",
"provider": "openai",
"scenario": "eve-instrumentation",
"testRunId": "<run:1>"
},
"metrics": {
"completion_tokens": 133,
"prompt_cached_tokens": 6528,
"prompt_tokens": 13638,
"tokens": 13771
"prompt_cached_tokens": 2048,
"prompt_tokens": 4766,
"tokens": 4899
}
},
{
Expand Down Expand Up @@ -530,16 +524,14 @@
],
"metadata": {
"eve.session_id": "<eve.session_id:1>",
"model": "gpt-5.4-mini",
"provider": "openai",
"scenario": "eve-instrumentation",
"testRunId": "<run:1>"
},
"metrics": {
"completion_tokens": 68,
"prompt_cached_tokens": 6528,
"prompt_tokens": 6977,
"tokens": 7045
"prompt_cached_tokens": 2048,
"prompt_tokens": 2541,
"tokens": 2609
}
},
{
Expand Down Expand Up @@ -593,7 +585,7 @@
},
"metrics": {
"completion_tokens": 27,
"prompt_cached_tokens": 6528,
"prompt_cached_tokens": 0,
"prompt_tokens": 6555,
"tokens": 6582
}
Expand Down Expand Up @@ -712,7 +704,7 @@
},
"metrics": {
"completion_tokens": 49,
"prompt_cached_tokens": 13056,
"prompt_cached_tokens": 6528,
"prompt_tokens": 13182,
"tokens": 13231
}
Expand Down Expand Up @@ -930,16 +922,14 @@
],
"metadata": {
"eve.session_id": "<eve.session_id:1>",
"model": "gpt-5.4-mini",
"provider": "openai",
"scenario": "eve-instrumentation",
"testRunId": "<run:1>"
},
"metrics": {
"completion_tokens": 66,
"prompt_cached_tokens": 0,
"prompt_tokens": 7128,
"tokens": 7194
"prompt_cached_tokens": 2048,
"prompt_tokens": 2692,
"tokens": 2758
}
}
],
Expand All @@ -952,16 +942,14 @@
"output": "Final answer from read: Researcher result: Eve instrumentation — https://eve.dev/docs/guides/instrumentation; read title: Eve instrumentation; URL: https://eve.dev/docs/guides/instrumentation; excerpt: Eve hooks expose runtime stream events that Braintrust maps into a nested turn trace.",
"metadata": {
"eve.session_id": "<eve.session_id:1>",
"model": "gpt-5.4-mini",
"provider": "openai",
"scenario": "eve-instrumentation",
"testRunId": "<run:1>"
},
"metrics": {
"completion_tokens": 134,
"prompt_cached_tokens": 6528,
"prompt_tokens": 14105,
"tokens": 14239
"prompt_cached_tokens": 4096,
"prompt_tokens": 5233,
"tokens": 5367
}
}
]
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -9,16 +9,14 @@ span_tree:
│ output: "Final answer from read: Researcher result: Eve instrumentation — https://eve.dev/docs/guides/instrumentation; read title: Eve instrumentation; URL: https://eve.dev/docs/guides/instrumentation; excerpt: Eve hooks expose runtime stream events that Braintrust maps into a nested turn trace."
│ metadata: {
│ "eve.session_id": "<eve.session_id:1>",
│ "model": "gpt-5.4-mini",
│ "provider": "openai",
│ "scenario": "eve-instrumentation",
│ "testRunId": "<run:1>"
│ }
│ metrics: {
│ "completion_tokens": 133,
│ "prompt_cached_tokens": 6528,
│ "prompt_tokens": 13638,
│ "tokens": 13771
│ "prompt_cached_tokens": 2048,
│ "prompt_tokens": 4766,
│ "tokens": 4899
│ }
│ ├── eve.step [llm]
│ │ input: [
Expand Down Expand Up @@ -61,16 +59,14 @@ span_tree:
│ │ ]
│ │ metadata: {
│ │ "eve.session_id": "<eve.session_id:1>",
│ │ "model": "gpt-5.4-mini",
│ │ "provider": "openai",
│ │ "scenario": "eve-instrumentation",
│ │ "testRunId": "<run:1>"
│ │ }
│ │ metrics: {
│ │ "completion_tokens": 67,
│ │ "prompt_cached_tokens": 0,
│ │ "prompt_tokens": 6744,
│ │ "tokens": 6811
│ │ "prompt_tokens": 2308,
│ │ "tokens": 2375
│ │ }
│ ├── researcher [tool]
│ │ input: {
Expand Down Expand Up @@ -99,7 +95,7 @@ span_tree:
│ │ }
│ │ metrics: {
│ │ "completion_tokens": 48,
│ │ "prompt_cached_tokens": 12032,
│ │ "prompt_cached_tokens": 6528,
│ │ "prompt_tokens": 13178,
│ │ "tokens": 13226
│ │ }
Expand Down Expand Up @@ -143,7 +139,7 @@ span_tree:
│ │ │ }
│ │ │ metrics: {
│ │ │ "completion_tokens": 26,
│ │ │ "prompt_cached_tokens": 5504,
│ │ │ "prompt_cached_tokens": 0,
│ │ │ "prompt_tokens": 6554,
│ │ │ "tokens": 6580
│ │ │ }
Expand Down Expand Up @@ -343,16 +339,14 @@ span_tree:
│ ]
│ metadata: {
│ "eve.session_id": "<eve.session_id:1>",
│ "model": "gpt-5.4-mini",
│ "provider": "openai",
│ "scenario": "eve-instrumentation",
│ "testRunId": "<run:1>"
│ }
│ metrics: {
│ "completion_tokens": 66,
│ "prompt_cached_tokens": 6528,
│ "prompt_tokens": 6894,
│ "tokens": 6960
│ "prompt_cached_tokens": 2048,
│ "prompt_tokens": 2458,
│ "tokens": 2524
│ }
└── eve.turn [task]
input: [
Expand All @@ -364,16 +358,14 @@ span_tree:
output: "Final answer from read: Researcher result: Eve instrumentation — https://eve.dev/docs/guides/instrumentation; read title: Eve instrumentation; URL: https://eve.dev/docs/guides/instrumentation; excerpt: Eve hooks expose runtime stream events that Braintrust maps into a nested turn trace."
metadata: {
"eve.session_id": "<eve.session_id:1>",
"model": "gpt-5.4-mini",
"provider": "openai",
"scenario": "eve-instrumentation",
"testRunId": "<run:1>"
}
metrics: {
"completion_tokens": 134,
"prompt_cached_tokens": 6528,
"prompt_tokens": 14105,
"tokens": 14239
"prompt_cached_tokens": 4096,
"prompt_tokens": 5233,
"tokens": 5367
}
├── eve.step [llm]
│ input: [
Expand Down Expand Up @@ -504,16 +496,14 @@ span_tree:
│ ]
│ metadata: {
│ "eve.session_id": "<eve.session_id:1>",
│ "model": "gpt-5.4-mini",
│ "provider": "openai",
│ "scenario": "eve-instrumentation",
│ "testRunId": "<run:1>"
│ }
│ metrics: {
│ "completion_tokens": 68,
│ "prompt_cached_tokens": 6528,
│ "prompt_tokens": 6977,
│ "tokens": 7045
│ "prompt_cached_tokens": 2048,
│ "prompt_tokens": 2541,
│ "tokens": 2609
│ }
├── researcher [tool]
│ input: {
Expand Down Expand Up @@ -542,7 +532,7 @@ span_tree:
│ }
│ metrics: {
│ "completion_tokens": 49,
│ "prompt_cached_tokens": 13056,
│ "prompt_cached_tokens": 6528,
│ "prompt_tokens": 13182,
│ "tokens": 13231
│ }
Expand Down Expand Up @@ -586,7 +576,7 @@ span_tree:
│ │ }
│ │ metrics: {
│ │ "completion_tokens": 27,
│ │ "prompt_cached_tokens": 6528,
│ │ "prompt_cached_tokens": 0,
│ │ "prompt_tokens": 6555,
│ │ "tokens": 6582
│ │ }
Expand Down Expand Up @@ -874,14 +864,12 @@ span_tree:
]
metadata: {
"eve.session_id": "<eve.session_id:1>",
"model": "gpt-5.4-mini",
"provider": "openai",
"scenario": "eve-instrumentation",
"testRunId": "<run:1>"
}
metrics: {
"completion_tokens": 66,
"prompt_cached_tokens": 0,
"prompt_tokens": 7128,
"tokens": 7194
"prompt_cached_tokens": 2048,
"prompt_tokens": 2692,
"tokens": 2758
}
11 changes: 9 additions & 2 deletions e2e/scenarios/eve-instrumentation/agent/agent.ts
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
import { defineAgent } from "eve";
import { defineAgent, defineDynamic } from "eve";
import { createOpenAI } from "@ai-sdk/openai";

const openai = createOpenAI({
Expand All @@ -7,7 +7,14 @@ const openai = createOpenAI({
: {}),
});

const dynamicModel = openai("gpt-5.4-mini");

export default defineAgent({
model: openai("gpt-5.4-mini"),
model: defineDynamic({
fallback: openai("gpt-5.4-mini"),
events: {
"step.started": () => dynamicModel,
},
}),
modelContextWindowTokens: 8_192,
});
2 changes: 1 addition & 1 deletion e2e/scenarios/eve-instrumentation/package.json
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
"type": "module",
"dependencies": {
"@ai-sdk/openai": "4.0.0-beta.44",
"eve": "0.20.0",
"eve": "0.22.1",
"zod": "4.3.6"
}
}
10 changes: 5 additions & 5 deletions e2e/scenarios/eve-instrumentation/pnpm-lock.yaml

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

Loading