Skip to content

feat: Use new eve instrumentation hooks #2373

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Luca Forstner (lforst) merged 2 commits into from
Aug 18, 2026
Merged

feat: Use new eve instrumentation hooks #2373

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f747ce7
feat: Use new eve instrumentation hooks
lforst Aug 18, 2026
06dab19
Update PR #2373
lforst Aug 18, 2026
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/eve-instrumentation-hooks.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
---
"braintrust": minor
---

feat: Use new eve instrumentation hooks
1 change: 1 addition & 0 deletions e2e/config/pr-comment-scenarios.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -632,6 +632,7 @@
"metadataScenario": "eve-instrumentation",
"variants": [
{ "variantKey": "eve-v0", "label": "v0 pinned" },
{ "variantKey": "eve-v0-provider", "label": "v0 provider minimum" },
{ "variantKey": "eve-v0-latest", "label": "v0 latest" }
]
},
Expand Down
1,242 changes: 1,242 additions & 0 deletions ...ve-v0.cassette.blobs/11348723a450e1213a1ca7c27418718de9989615ec2b9975a932a37c2f37e780.bin
View file
Open in desktop

Large diffs are not rendered by default.

738 changes: 365 additions & 373 deletions ...eedac127cccd155bc523b865f44812dd777c5.bin → ...4f6e6dbc606c50747cb974720fb6edafab95d.bin
View file
Open in desktop

Large diffs are not rendered by default.

792 changes: 378 additions & 414 deletions ...fd2c806667788b33dd474af7d2ea5d15936c7.bin → ...83cfec5d42aba70cd8553e7b95df64e4d63c7.bin
View file
Open in desktop

Large diffs are not rendered by default.

786 changes: 380 additions & 406 deletions ...2e1b642b39cd2d68a68cb58a4f84a2bb0ecb9.bin → ...3f31554e4834bd4a699fe3ac8767bb746caa3.bin
View file
Open in desktop

Large diffs are not rendered by default.

766 changes: 0 additions & 766 deletions ...ve-v0.cassette.blobs/6c5b3c53f51cad1dca528d20af687f68eaf25bece4d46bd0b827937a60a980fd.bin
View file
Open in desktop

This file was deleted.

390 changes: 390 additions & 0 deletions ...ve-v0.cassette.blobs/7fc825ec2cf23db586316b01277ebe52383e87873cd4b36863788ef8532cc5ce.bin
View file
Open in desktop

Large diffs are not rendered by default.

1,226 changes: 1,226 additions & 0 deletions ...ve-v0.cassette.blobs/a410f2937610c4823cd83f63b994f62f3f137c0cc3ff2bb4379a33067b812658.bin
View file
Open in desktop

Large diffs are not rendered by default.

410 changes: 0 additions & 410 deletions ...ve-v0.cassette.blobs/ab78b58d485ed97fe33bc4687899ca9f74eb334607b4130aa931ffc17fdaece2.bin
View file
Open in desktop

This file was deleted.

664 changes: 0 additions & 664 deletions ...ve-v0.cassette.blobs/af1f8d2692b69628be68360634bca1745a21beb28725c82ab2641c019ce12a56.bin
View file
Open in desktop

This file was deleted.

454 changes: 454 additions & 0 deletions ...ve-v0.cassette.blobs/e2a193c2ec0953ce81416f327bf603edbe5418721cbcc23910cb4b4d0793ac78.bin
View file
Open in desktop

Large diffs are not rendered by default.

472 changes: 0 additions & 472 deletions ...ve-v0.cassette.blobs/f0e6f00e794ed5a3fb8f7852859834c64caf2e3628413c096ba164c8d91b988f.bin
View file
Open in desktop

This file was deleted.

519 changes: 282 additions & 237 deletions e2e/scenarios/eve-instrumentation/__cassettes__/eve-v0.cassette.json
View file
Open in desktop

Large diffs are not rendered by default.

74 changes: 14 additions & 60 deletions e2e/scenarios/eve-instrumentation/__snapshots__/eve-v0-latest.span-tree.json
View file
Open in desktop

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

74 changes: 14 additions & 60 deletions e2e/scenarios/eve-instrumentation/__snapshots__/eve-v0-latest.span-tree.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,24 +1,10 @@
span_tree:
├── eve.turn [task]
│ input: [
│ {
│ "content": "Run the Braintrust Eve instrumentation e2e scenario",
│ "role": "user"
│ }
│ ]
│ output: "Final answer from read: Researcher result: [Eve instrumentation](https://eve.dev/docs/guides/instrumentation). 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>",
│ "scenario": "eve-instrumentation",
│ "testRunId": "<run:1>"
│ }
│ metrics: {
│ "completion_tokens": 853,
│ "prompt_cache_creation_tokens": 0,
│ "prompt_cached_tokens": 0,
│ "prompt_tokens": 7934,
│ "tokens": 8787
│ }
│ ├── eve.step [llm]
│ │ input: [
│ │ {
Expand Down Expand Up @@ -65,6 +51,8 @@ span_tree:
│ │ ]
│ │ metadata: {
│ │ "eve.session_id": "<eve.session_id:1>",
│ │ "model": "qwen/qwen3-30b-a3b",
│ │ "provider": "openrouter",
│ │ "scenario": "eve-instrumentation",
│ │ "testRunId": "<run:1>"
│ │ }
Expand All @@ -81,32 +69,17 @@ span_tree:
│ │ }
│ │ output: "Researcher result: [Eve instrumentation](https://eve.dev/docs/guides/instrumentation)"
│ │ metadata: {
│ │ "eve.action_kind": "subagent-call",
│ │ "eve.session_id": "<eve.session_id:1>",
│ │ "scenario": "eve-instrumentation",
│ │ "testRunId": "<run:1>"
│ │ }
│ │ └── eve.turn [task]
│ │ input: [
│ │ {
│ │ "content": "You are the subagent \"researcher\".\nDescription: Research the Eve instrumentation documentation before the parent reads it.\n\nThe caller delegated the following task to you. Complete it and return the final result directly.\n\nCaller message:\nRun the Braintrust Eve instrumentation e2e scenario",
│ │ "role": "user"
│ │ }
│ │ ]
│ │ output: "Researcher result: [Eve instrumentation](https://eve.dev/docs/guides/instrumentation)"
│ │ metadata: {
│ │ "eve.session_id": "<eve.session_id:1>",
│ │ "model": "qwen/qwen3-30b-a3b",
│ │ "provider": "openrouter",
│ │ "scenario": "eve-instrumentation",
│ │ "testRunId": "<run:1>"
│ │ }
│ │ metrics: {
│ │ "completion_tokens": 388,
│ │ "prompt_cache_creation_tokens": 0,
│ │ "prompt_cached_tokens": 0,
│ │ "prompt_tokens": 6326,
│ │ "tokens": 6714
│ │ }
│ │ ├── eve.step [llm]
│ │ │ input: [
│ │ │ {
Expand Down Expand Up @@ -167,6 +140,7 @@ span_tree:
│ │ │ "url": "https://eve.dev/docs/guides/instrumentation"
│ │ │ }
│ │ │ metadata: {
│ │ │ "eve.action_kind": "tool-call",
│ │ │ "eve.session_id": "<eve.session_id:1>",
│ │ │ "scenario": "eve-instrumentation",
│ │ │ "testRunId": "<run:1>"
Expand Down Expand Up @@ -257,6 +231,7 @@ span_tree:
│ │ "url": "https://eve.dev/docs/guides/instrumentation"
│ │ }
│ │ metadata: {
│ │ "eve.action_kind": "tool-call",
│ │ "eve.session_id": "<eve.session_id:1>",
│ │ "scenario": "eve-instrumentation",
│ │ "testRunId": "<run:1>"
Expand Down Expand Up @@ -347,6 +322,8 @@ span_tree:
│ ]
│ metadata: {
│ "eve.session_id": "<eve.session_id:1>",
│ "model": "qwen/qwen3-30b-a3b",
│ "provider": "openrouter",
│ "scenario": "eve-instrumentation",
│ "testRunId": "<run:1>"
│ }
Expand All @@ -358,25 +335,11 @@ span_tree:
│ "tokens": 4603
│ }
└── eve.turn [task]
input: [
{
"content": "Run the Braintrust Eve instrumentation e2e scenario again",
"role": "user"
}
]
output: "Final answer from read: Researcher result: [Eve instrumentation](https://eve.dev/docs/guides/instrumentation). 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>",
"scenario": "eve-instrumentation",
"testRunId": "<run:1>"
}
metrics: {
"completion_tokens": 568,
"prompt_cache_creation_tokens": 0,
"prompt_cached_tokens": 0,
"prompt_tokens": 8224,
"tokens": 8792
}
├── eve.step [llm]
│ input: [
│ {
Expand Down Expand Up @@ -498,6 +461,8 @@ span_tree:
│ ]
│ metadata: {
│ "eve.session_id": "<eve.session_id:1>",
│ "model": "qwen/qwen3-30b-a3b",
│ "provider": "openrouter",
│ "scenario": "eve-instrumentation",
│ "testRunId": "<run:1>"
│ }
Expand All @@ -514,32 +479,17 @@ span_tree:
│ }
│ output: "Researcher result: Eve instrumentation https://eve.dev/docs/guides/instrumentation"
│ metadata: {
│ "eve.action_kind": "subagent-call",
│ "eve.session_id": "<eve.session_id:1>",
│ "scenario": "eve-instrumentation",
│ "testRunId": "<run:1>"
│ }
│ └── eve.turn [task]
│ input: [
│ {
│ "content": "You are the subagent \"researcher\".\nDescription: Research the Eve instrumentation documentation before the parent reads it.\n\nThe caller delegated the following task to you. Complete it and return the final result directly.\n\nCaller message:\nRun the Braintrust Eve instrumentation e2e scenario again",
│ "role": "user"
│ }
│ ]
│ output: "Researcher result: Eve instrumentation https://eve.dev/docs/guides/instrumentation"
│ metadata: {
│ "eve.session_id": "<eve.session_id:1>",
│ "model": "qwen/qwen3-30b-a3b",
│ "provider": "openrouter",
│ "scenario": "eve-instrumentation",
│ "testRunId": "<run:1>"
│ }
│ metrics: {
│ "completion_tokens": 376,
│ "prompt_cache_creation_tokens": 0,
│ "prompt_cached_tokens": 0,
│ "prompt_tokens": 6314,
│ "tokens": 6690
│ }
│ ├── eve.step [llm]
│ │ input: [
│ │ {
Expand Down Expand Up @@ -600,6 +550,7 @@ span_tree:
│ │ "url": "https://eve.dev/docs/guides/instrumentation"
│ │ }
│ │ metadata: {
│ │ "eve.action_kind": "tool-call",
│ │ "eve.session_id": "<eve.session_id:1>",
│ │ "scenario": "eve-instrumentation",
│ │ "testRunId": "<run:1>"
Expand Down Expand Up @@ -690,6 +641,7 @@ span_tree:
│ "url": "https://eve.dev/docs/guides/instrumentation"
│ }
│ metadata: {
│ "eve.action_kind": "tool-call",
│ "eve.session_id": "<eve.session_id:1>",
│ "scenario": "eve-instrumentation",
│ "testRunId": "<run:1>"
Expand Down Expand Up @@ -855,6 +807,8 @@ span_tree:
]
metadata: {
"eve.session_id": "<eve.session_id:1>",
"model": "qwen/qwen3-30b-a3b",
"provider": "openrouter",
"scenario": "eve-instrumentation",
"testRunId": "<run:1>"
}
Expand Down
Loading
Loading