[codex] add Langfuse tracing and chat debug correlation
#535Comparing
pickle-receipt
(147d22a
) withmain
(3272781
)+80%
- Improvement
- 1
- Untouched
- 38
- Skipped
- 5
Different runtime environments detected
Some benchmarks with significant performance changes were compared across different runtime environments, which may affect the accuracy of the results. Learn more about regression causes.Benchmarks
44 total
env_substitution
crates/benchmarks/benches/boot.rs+80%
18.2 µs10.1 µs
context_window_lookup[gpt-4o]
crates/benchmarks/benches/boot.rs+5%
2.5 µs2.4 µs
context_window_lookup[o3]
crates/benchmarks/benches/boot.rs+4%
2.4 µs2.3 µs
context_window_lookup[gpt-5]
crates/benchmarks/benches/boot.rs+4%
2.5 µs2.4 µs
context_window_lookup[mistral-large-latest]
crates/benchmarks/benches/boot.rs+3%
2.6 µs2.6 µs
context_window_lookup[claude-sonnet-4-5-20250929]
crates/benchmarks/benches/boot.rs+3%
2.6 µs2.6 µs
context_window_lookup[kimi-k2.5]
crates/benchmarks/benches/boot.rs+2%
2.6 µs2.5 µs
context_window_lookup[gemini-2.0-flash]
crates/benchmarks/benches/boot.rs+2%
2.6 µs2.6 µs
context_window_lookup[unknown-model-xyz]
crates/benchmarks/benches/boot.rs+2%
2.7 µs2.7 µs
context_window_lookup[codestral-latest]
crates/benchmarks/benches/boot.rs+1%
2.5 µs2.5 µs
values_to_chat_messages[50]
crates/benchmarks/benches/boot.rs+1%
62.2 µs61.8 µs
values_to_chat_messages[500]
crates/benchmarks/benches/boot.rs0%
504.3 µs502.9 µs
values_to_chat_messages[2000]
crates/benchmarks/benches/boot.rs0%
2 ms2 ms
vision_support_lookup[gpt-4o]
crates/benchmarks/benches/boot.rs0%
2.4 µs2.4 µs
vision_support_lookup[gpt-5]
crates/benchmarks/benches/boot.rs0%
2.4 µs2.4 µs
sanitize_tool_result[100000]
crates/benchmarks/benches/boot.rs0%
1.5 ms1.5 ms
sanitize_tool_result[1000000]
crates/benchmarks/benches/boot.rs0%
15.1 ms15.1 ms
session_key_to_filename[user@host:session:42]
crates/benchmarks/benches/boot.rs0%
1.5 µs1.5 µs
sanitize_tool_result[10000]
crates/benchmarks/benches/boot.rs0%
159.1 µs159.1 µs
tool_result_to_content_vision[1000000]
crates/benchmarks/benches/boot.rs0%
22.3 ms22.3 ms
tool_result_to_content_vision[100000]
crates/benchmarks/benches/boot.rs0%
2.3 ms2.3 ms
tool_result_to_content_vision[10000]
crates/benchmarks/benches/boot.rs0%
240.9 µs241 µs
vision_support_lookup[o3]
crates/benchmarks/benches/boot.rs0%
2.4 µs2.4 µs
config_default_construction
crates/benchmarks/benches/boot.rs0%
32.4 µs32.6 µs
config_load_toml
crates/benchmarks/benches/boot.rs-1%
1.7 ms1.7 ms
Commits
Click on a commit to change the comparison rangeBase
main
3272781
+79.59%
feat(observability): add langfuse tracing
147d22a
16 hours ago
by penso