This release adds 1 notable feature for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+5 more
Summary
AI summaryFixes LLM error handling by selecting the model based on code type.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Low |
Ingest cipx.session.harness into cipx_trace_identities backend processing Ingest cipx.session.harness into cipx_trace_identities backend processing Source: llm_adapter@2026-07-14 Confidence: high |
— |
| Bugfix | Medium |
Mark GPT-5.6 models as reasoning models Mark GPT-5.6 models as reasoning models Source: llm_adapter@2026-07-14 Confidence: high |
— |
| Bugfix | Medium |
Pick LLM error model based on code type to avoid doomed OpenRouter parse Pick LLM error model based on code type to avoid doomed OpenRouter parse Source: llm_adapter@2026-07-14 Confidence: high |
— |
| Bugfix | Medium |
Union getProjectIds result stream instead of single() Union getProjectIds result stream instead of single() Source: llm_adapter@2026-07-14 Confidence: high |
— |
Full changelog
What's Changed
- [NA] [FE] fix: mark GPT-5.6 models as reasoning models by @AndreiCautisanu in https://github.com/comet-ml/opik/pull/7451
- [OPIK-7322] fix: pick LLM error model by code type to avoid doomed OpenRouter parse by @thiagohora in https://github.com/comet-ml/opik/pull/7457
- [OPIK-7321] fix: union getProjectIds result stream instead of single() by @thiagohora in https://github.com/comet-ml/opik/pull/7454
- [OPIK-7298] [BE] feat: ingest cipx.session.harness into cipx_trace_identities by @andriidudar in https://github.com/comet-ml/opik/pull/7448
Full Changelog: https://github.com/comet-ml/opik/compare/2.1.25...2.1.26
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About opik
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Related context
Related tools
Beta — feedback welcome: [email protected]