DRAFT: Upgrade to Python 3.13 with libtmux race condition fix #1978

neubig · 2026-02-09T21:04:46Z

Summary

This PR upgrades the project to Python 3.13 and pins libtmux to neubig/libtmux@fix/new-session-race-condition which contains the fix for the race condition reported in libtmux#624.

Context

See upstream PR: tmux-python/libtmux#625

The issue was that new_session() in libtmux would:

Run tmux new-session -P -F#{session_id} to create session
Immediately run tmux list-sessions to fetch full session data

This created a race condition in Python 3.13 environments (especially with PyInstaller + Docker) where list-sessions might not see the newly created session yet, causing TmuxObjectDoesNotExist errors.

The fix expands the -F format string to include all Session fields and parses the output directly, eliminating the separate list-sessions query entirely.

Changes

Update target-version from py312 to py313 in root pyproject.toml (ruff)
Update pythonVersion from 3.12 to 3.13 in root pyproject.toml (pyright)
Update Python version in server.yml build matrix from 3.12 to 3.13
Update Python version in pypi-release.yml from 3.12 to 3.13
Update Python version in pr-review action from 3.12 to 3.13
Pin libtmux to neubig's branch: libtmux @ git+https://github.com/neubig/libtmux.git@fix/new-session-race-condition

Testing

This PR needs integration tests to verify the libtmux fix works correctly in our CI environment. The integration-test label should trigger those tests.

Note

This is a draft PR to test the libtmux fix. Once the upstream PR is merged and released to PyPI, we should update the dependency to the released version.

Related issues:

@neubig can click here to continue refining the PR

Agent Server images for this PR

• GHCR package: https://github.com/OpenHands/agent-sdk/pkgs/container/agent-server

Variants & Base Images

Variant	Architectures	Base Image	Docs / Tags
java	amd64, arm64	`eclipse-temurin:17-jdk`	Link
python	amd64, arm64	`nikolaik/python-nodejs:python3.13-nodejs22`	Link
golang	amd64, arm64	`golang:1.21-bookworm`	Link

Pull (multi-arch manifest)

# Each variant is a multi-arch manifest supporting both amd64 and arm64
docker pull ghcr.io/openhands/agent-server:bcad0e2-python

Run

docker run -it --rm \
  -p 8000:8000 \
  --name agent-server-bcad0e2-python \
  ghcr.io/openhands/agent-server:bcad0e2-python

All tags pushed for this build

ghcr.io/openhands/agent-server:bcad0e2-golang-amd64
ghcr.io/openhands/agent-server:bcad0e2-golang_tag_1.21-bookworm-amd64
ghcr.io/openhands/agent-server:bcad0e2-golang-arm64
ghcr.io/openhands/agent-server:bcad0e2-golang_tag_1.21-bookworm-arm64
ghcr.io/openhands/agent-server:bcad0e2-java-amd64
ghcr.io/openhands/agent-server:bcad0e2-eclipse-temurin_tag_17-jdk-amd64
ghcr.io/openhands/agent-server:bcad0e2-java-arm64
ghcr.io/openhands/agent-server:bcad0e2-eclipse-temurin_tag_17-jdk-arm64
ghcr.io/openhands/agent-server:bcad0e2-python-amd64
ghcr.io/openhands/agent-server:bcad0e2-nikolaik_s_python-nodejs_tag_python3.13-nodejs22-amd64
ghcr.io/openhands/agent-server:bcad0e2-python-arm64
ghcr.io/openhands/agent-server:bcad0e2-nikolaik_s_python-nodejs_tag_python3.13-nodejs22-arm64
ghcr.io/openhands/agent-server:bcad0e2-golang
ghcr.io/openhands/agent-server:bcad0e2-java
ghcr.io/openhands/agent-server:bcad0e2-python

About Multi-Architecture Support

Each variant tag (e.g., bcad0e2-python) is a multi-arch manifest supporting both amd64 and arm64
Docker automatically pulls the correct architecture for your platform
Individual architecture tags (e.g., bcad0e2-python-amd64) are also available if needed

- Update target-version and pythonVersion to 3.13 in root pyproject.toml - Update Python version in server.yml build matrix to 3.13 - Update Python version in pypi-release.yml to 3.13 - Update Python version in pr-review action to 3.13 - Pin libtmux to neubig/libtmux#fix/new-session-race-condition branch which fixes the race condition in new_session() that causes TmuxObjectDoesNotExist errors in Python 3.13 environments The libtmux fix avoids the race condition by eliminating the separate list-sessions query after session creation, instead parsing the session data directly from the -P output of new-session. Fixes the Python 3.13 + PyInstaller + Docker compatibility issue reported in libtmux#624. Co-authored-by: openhands <openhands@all-hands.dev>

github-actions · 2026-02-09T21:04:55Z

Hi! I started running the integration tests on your PR. You will receive a comment with the results shortly.

github-actions · 2026-02-09T21:09:08Z

🧪 Integration Tests Results

Overall Success Rate: 100.0%
Total Cost: $0.90
Models Tested: 4
Timestamp: 2026-02-09 21:08:59 UTC

📁 Detailed Logs & Artifacts

Click the links below to access detailed agent/LLM logs showing the complete reasoning process for each model. On the GitHub Actions page, scroll down to the 'Artifacts' section to download the logs.

litellm_proxy_deepseek_deepseek_reasoner: 📥 View & Download Logs
litellm_proxy_moonshot_kimi_k2_thinking: 📥 View & Download Logs
litellm_proxy_gemini_3_pro_preview: 📥 View & Download Logs
litellm_proxy_claude_sonnet_4_5_20250929: 📥 View & Download Logs

📊 Summary

Model	Overall	Tests Passed	Skipped	Total	Cost	Tokens
litellm_proxy_deepseek_deepseek_reasoner	100.0%	7/7	1	8	$0.03	586,389
litellm_proxy_moonshot_kimi_k2_thinking	100.0%	7/7	1	8	$0.15	225,951
litellm_proxy_gemini_3_pro_preview	100.0%	8/8	0	8	$0.31	230,266
litellm_proxy_claude_sonnet_4_5_20250929	100.0%	8/8	0	8	$0.41	236,012

📋 Detailed Results

litellm_proxy_deepseek_deepseek_reasoner

Success Rate: 100.0% (7/7)
Total Cost: $0.03
Token Usage: prompt: 571,330, completion: 15,059, cache_read: 529,280, reasoning: 6,086
Run Suffix: litellm_proxy_deepseek_deepseek_reasoner_122e797_deepseek_v3_2_reasoner_run_N8_20260209_210520
Skipped Tests: 1

Skipped Tests:

t08_image_file_viewing: This test requires a vision-capable LLM model. Please use a model that supports image input.

litellm_proxy_moonshot_kimi_k2_thinking

Success Rate: 100.0% (7/7)
Total Cost: $0.15
Token Usage: prompt: 220,509, completion: 5,442, cache_read: 172,544
Run Suffix: litellm_proxy_moonshot_kimi_k2_thinking_122e797_kimi_k2_thinking_run_N8_20260209_210544
Skipped Tests: 1

Skipped Tests:

t08_image_file_viewing: This test requires a vision-capable LLM model. Please use a model that supports image input.

litellm_proxy_gemini_3_pro_preview

Success Rate: 100.0% (8/8)
Total Cost: $0.31
Token Usage: prompt: 223,711, completion: 6,555, cache_read: 120,260, reasoning: 4,076
Run Suffix: litellm_proxy_gemini_3_pro_preview_122e797_gemini_3_pro_run_N8_20260209_210520

litellm_proxy_claude_sonnet_4_5_20250929

Success Rate: 100.0% (8/8)
Total Cost: $0.41
Token Usage: prompt: 229,436, completion: 6,576, cache_read: 158,218, cache_write: 70,849, reasoning: 1,996
Run Suffix: litellm_proxy_claude_sonnet_4_5_20250929_122e797_claude_sonnet_4_5_20250929_run_N8_20260209_210519

github-actions · 2026-02-09T21:11:55Z

Coverage Report •

File	Stmts	Miss	Cover	Missing
TOTAL	18219	4880	73%

report-only-changed-files is enabled. No files were changed during this commit :)

github-actions · 2026-02-09T21:37:21Z

🔄 Running Examples with `openhands/claude-haiku-4-5-20251001`

Generated: 2026-02-09 21:45:19 UTC

Example	Status	Duration	Cost
01_standalone_sdk/02_custom_tools.py	✅ PASS	28.7s	$0.03
01_standalone_sdk/03_activate_skill.py	✅ PASS	21.6s	$0.03
01_standalone_sdk/05_use_llm_registry.py	✅ PASS	11.9s	$0.01
01_standalone_sdk/07_mcp_integration.py	✅ PASS	48.3s	$0.04
01_standalone_sdk/09_pause_example.py	✅ PASS	19.9s	$0.02
01_standalone_sdk/10_persistence.py	✅ PASS	27.5s	$0.02
01_standalone_sdk/11_async.py	✅ PASS	34.3s	$0.03
01_standalone_sdk/12_custom_secrets.py	✅ PASS	16.5s	$0.02
01_standalone_sdk/13_get_llm_metrics.py	✅ PASS	21.5s	$0.01
01_standalone_sdk/14_context_condenser.py	✅ PASS	4m 25s	$0.53
01_standalone_sdk/17_image_input.py	✅ PASS	18.7s	$0.02
01_standalone_sdk/18_send_message_while_processing.py	✅ PASS	27.9s	$0.02
01_standalone_sdk/19_llm_routing.py	✅ PASS	15.8s	$0.02
01_standalone_sdk/20_stuck_detector.py	✅ PASS	22.3s	$0.02
01_standalone_sdk/21_generate_extraneous_conversation_costs.py	✅ PASS	9.7s	$0.00
01_standalone_sdk/22_anthropic_thinking.py	✅ PASS	22.2s	$0.02
01_standalone_sdk/23_responses_reasoning.py	✅ PASS	1m 27s	$0.01
01_standalone_sdk/24_planning_agent_workflow.py	✅ PASS	5m 5s	$0.41
01_standalone_sdk/25_agent_delegation.py	✅ PASS	2m 16s	$0.18
01_standalone_sdk/26_custom_visualizer.py	✅ PASS	20.6s	$0.02
01_standalone_sdk/28_ask_agent_example.py	✅ PASS	38.4s	$0.03
01_standalone_sdk/29_llm_streaming.py	✅ PASS	36.6s	$0.03
01_standalone_sdk/30_tom_agent.py	✅ PASS	11.2s	$0.01
01_standalone_sdk/31_iterative_refinement.py	✅ PASS	3m 7s	$0.21
01_standalone_sdk/32_configurable_security_policy.py	✅ PASS	19.7s	$0.02
01_standalone_sdk/34_critic_example.py	❌ FAIL Exit code 1	3.8s	--
01_standalone_sdk/36_event_json_to_openai_messages.py	✅ PASS	9.8s	$0.00
01_standalone_sdk/37_llm_profile_store.py	✅ PASS	4.0s	$0.00
02_remote_agent_server/01_convo_with_local_agent_server.py	✅ PASS	58.3s	$0.04
02_remote_agent_server/02_convo_with_docker_sandboxed_server.py	❌ FAIL Exit code 1	1m 4s	--
02_remote_agent_server/03_browser_use_with_docker_sandboxed_server.py	❌ FAIL Exit code 1	16.8s	--
02_remote_agent_server/04_convo_with_api_sandboxed_server.py	❌ FAIL Exit code 1	1m 1s	--
02_remote_agent_server/07_convo_with_cloud_workspace.py	✅ PASS	31.8s	$0.02
02_remote_agent_server/08_convo_with_apptainer_sandboxed_server.py	❌ FAIL Exit code 1	4.1s	--
04_llm_specific_tools/01_gpt5_apply_patch_preset.py	✅ PASS	18.7s	$0.02
04_llm_specific_tools/02_gemini_file_tools.py	✅ PASS	44.4s	$0.08
05_skills_and_plugins/01_loading_agentskills/main.py	✅ PASS	12.5s	$0.01
05_skills_and_plugins/02_loading_plugins/main.py	✅ PASS	7.8s	$0.01

❌ Some tests failed

Total: 38 | Passed: 33 | Failed: 5 | Total Cost: $1.94

Failed examples:

examples/01_standalone_sdk/34_critic_example.py: Exit code 1
examples/02_remote_agent_server/02_convo_with_docker_sandboxed_server.py: Exit code 1
examples/02_remote_agent_server/03_browser_use_with_docker_sandboxed_server.py: Exit code 1
examples/02_remote_agent_server/04_convo_with_api_sandboxed_server.py: Exit code 1
examples/02_remote_agent_server/08_convo_with_apptainer_sandboxed_server.py: Exit code 1

View full workflow run

…HUB_SHA GitHub Actions sets GITHUB_SHA to the merge commit by default, which differs from the PR head commit. Use a custom variable AGENT_SERVER_SHA to explicitly pass the PR head SHA to example scripts for Docker image selection. Co-authored-by: openhands <openhands@all-hands.dev>

github-actions · 2026-02-10T09:23:56Z

🔄 Running Examples with `openhands/claude-haiku-4-5-20251001`

Generated: 2026-02-10 09:37:15 UTC

Example	Status	Duration	Cost
01_standalone_sdk/02_custom_tools.py	✅ PASS	25.3s	$0.03
01_standalone_sdk/03_activate_skill.py	✅ PASS	17.9s	$0.03
01_standalone_sdk/05_use_llm_registry.py	✅ PASS	11.1s	$0.01
01_standalone_sdk/07_mcp_integration.py	✅ PASS	41.2s	$0.04
01_standalone_sdk/09_pause_example.py	✅ PASS	13.5s	$0.01
01_standalone_sdk/10_persistence.py	✅ PASS	27.9s	$0.02
01_standalone_sdk/11_async.py	✅ PASS	28.7s	$0.03
01_standalone_sdk/12_custom_secrets.py	✅ PASS	11.2s	$0.01
01_standalone_sdk/13_get_llm_metrics.py	✅ PASS	20.8s	$0.01
01_standalone_sdk/14_context_condenser.py	✅ PASS	4m 22s	$0.54
01_standalone_sdk/17_image_input.py	✅ PASS	17.2s	$0.02
01_standalone_sdk/18_send_message_while_processing.py	✅ PASS	25.1s	$0.01
01_standalone_sdk/19_llm_routing.py	✅ PASS	13.2s	$0.02
01_standalone_sdk/20_stuck_detector.py	✅ PASS	19.5s	$0.02
01_standalone_sdk/21_generate_extraneous_conversation_costs.py	✅ PASS	14.8s	$0.00
01_standalone_sdk/22_anthropic_thinking.py	✅ PASS	18.1s	$0.01
01_standalone_sdk/23_responses_reasoning.py	✅ PASS	1m 10s	$0.01
01_standalone_sdk/24_planning_agent_workflow.py	✅ PASS	2m 54s	$0.22
01_standalone_sdk/25_agent_delegation.py	✅ PASS	2m 4s	$0.17
01_standalone_sdk/26_custom_visualizer.py	✅ PASS	18.6s	$0.02
01_standalone_sdk/28_ask_agent_example.py	✅ PASS	28.3s	$0.02
01_standalone_sdk/29_llm_streaming.py	✅ PASS	38.6s	$0.03
01_standalone_sdk/30_tom_agent.py	✅ PASS	12.2s	$0.01
01_standalone_sdk/31_iterative_refinement.py	❌ FAIL Timed out after 600 seconds	10m 0s	--
01_standalone_sdk/32_configurable_security_policy.py	✅ PASS	23.7s	$0.02
01_standalone_sdk/34_critic_example.py	❌ FAIL Exit code 1	3.9s	--
01_standalone_sdk/36_event_json_to_openai_messages.py	✅ PASS	21.3s	$0.01
01_standalone_sdk/37_llm_profile_store.py	✅ PASS	4.1s	$0.00
02_remote_agent_server/01_convo_with_local_agent_server.py	✅ PASS	1m 5s	$0.04
02_remote_agent_server/02_convo_with_docker_sandboxed_server.py	❌ FAIL Exit code 1	4.7s	--
02_remote_agent_server/03_browser_use_with_docker_sandboxed_server.py	❌ FAIL Exit code 1	5.7s	--
02_remote_agent_server/04_convo_with_api_sandboxed_server.py	❌ FAIL Exit code 1	5m 11s	--
02_remote_agent_server/07_convo_with_cloud_workspace.py	✅ PASS	28.3s	$0.03
02_remote_agent_server/08_convo_with_apptainer_sandboxed_server.py	❌ FAIL Exit code 1	4.7s	--
04_llm_specific_tools/01_gpt5_apply_patch_preset.py	✅ PASS	31.8s	$0.04
04_llm_specific_tools/02_gemini_file_tools.py	✅ PASS	1m 10s	$0.05
05_skills_and_plugins/01_loading_agentskills/main.py	✅ PASS	10.5s	$0.01
05_skills_and_plugins/02_loading_plugins/main.py	✅ PASS	7.5s	$0.01

❌ Some tests failed

Total: 38 | Passed: 32 | Failed: 6 | Total Cost: $1.52

Failed examples:

examples/01_standalone_sdk/31_iterative_refinement.py: Timed out after 600 seconds
examples/01_standalone_sdk/34_critic_example.py: Exit code 1
examples/02_remote_agent_server/02_convo_with_docker_sandboxed_server.py: Exit code 1
examples/02_remote_agent_server/03_browser_use_with_docker_sandboxed_server.py: Exit code 1
examples/02_remote_agent_server/04_convo_with_api_sandboxed_server.py: Exit code 1
examples/02_remote_agent_server/08_convo_with_apptainer_sandboxed_server.py: Exit code 1

View full workflow run

- Regenerate uv.lock with pinned libtmux git dependency - Simplify Generator[T, None, None] to Generator[T] in test files Co-authored-by: openhands <openhands@all-hands.dev>

github-actions · 2026-02-10T09:44:52Z

🔄 Running Examples with `openhands/claude-haiku-4-5-20251001`

Generated: 2026-02-10 09:54:23 UTC

Example	Status	Duration	Cost
01_standalone_sdk/02_custom_tools.py	✅ PASS	25.7s	$0.03
01_standalone_sdk/03_activate_skill.py	✅ PASS	20.0s	$0.03
01_standalone_sdk/05_use_llm_registry.py	✅ PASS	14.0s	$0.01
01_standalone_sdk/07_mcp_integration.py	✅ PASS	30.2s	$0.02
01_standalone_sdk/09_pause_example.py	✅ PASS	18.5s	$0.01
01_standalone_sdk/10_persistence.py	✅ PASS	35.4s	$0.03
01_standalone_sdk/11_async.py	✅ PASS	31.4s	$0.03
01_standalone_sdk/12_custom_secrets.py	✅ PASS	20.0s	$0.02
01_standalone_sdk/13_get_llm_metrics.py	✅ PASS	21.1s	$0.02
01_standalone_sdk/14_context_condenser.py	✅ PASS	6m 29s	$0.84
01_standalone_sdk/17_image_input.py	✅ PASS	16.4s	$0.02
01_standalone_sdk/18_send_message_while_processing.py	✅ PASS	23.3s	$0.01
01_standalone_sdk/19_llm_routing.py	✅ PASS	15.6s	$0.02
01_standalone_sdk/20_stuck_detector.py	✅ PASS	15.8s	$0.02
01_standalone_sdk/21_generate_extraneous_conversation_costs.py	✅ PASS	11.4s	$0.00
01_standalone_sdk/22_anthropic_thinking.py	✅ PASS	16.7s	$0.01
01_standalone_sdk/23_responses_reasoning.py	✅ PASS	57.8s	$0.01
01_standalone_sdk/24_planning_agent_workflow.py	✅ PASS	51.3s	$0.05
01_standalone_sdk/25_agent_delegation.py	✅ PASS	1m 44s	$0.19
01_standalone_sdk/26_custom_visualizer.py	✅ PASS	22.6s	$0.03
01_standalone_sdk/28_ask_agent_example.py	✅ PASS	35.2s	$0.03
01_standalone_sdk/29_llm_streaming.py	✅ PASS	44.6s	$0.04
01_standalone_sdk/30_tom_agent.py	✅ PASS	10.6s	$0.01
01_standalone_sdk/31_iterative_refinement.py	✅ PASS	3m 7s	$0.22
01_standalone_sdk/32_configurable_security_policy.py	✅ PASS	16.6s	$0.02
01_standalone_sdk/34_critic_example.py	❌ FAIL Exit code 1	3.8s	--
01_standalone_sdk/36_event_json_to_openai_messages.py	✅ PASS	13.1s	$0.00
01_standalone_sdk/37_llm_profile_store.py	✅ PASS	4.1s	$0.00
02_remote_agent_server/01_convo_with_local_agent_server.py	✅ PASS	59.4s	$0.04
02_remote_agent_server/02_convo_with_docker_sandboxed_server.py	❌ FAIL Exit code 1	4.8s	--
02_remote_agent_server/03_browser_use_with_docker_sandboxed_server.py	❌ FAIL Exit code 1	4.9s	--
02_remote_agent_server/04_convo_with_api_sandboxed_server.py	❌ FAIL Exit code 1	5m 11s	--
02_remote_agent_server/07_convo_with_cloud_workspace.py	✅ PASS	28.6s	$0.02
02_remote_agent_server/08_convo_with_apptainer_sandboxed_server.py	❌ FAIL Exit code 1	5.6s	--
04_llm_specific_tools/01_gpt5_apply_patch_preset.py	✅ PASS	20.8s	$0.03
04_llm_specific_tools/02_gemini_file_tools.py	✅ PASS	57.7s	$0.07
05_skills_and_plugins/01_loading_agentskills/main.py	✅ PASS	14.0s	$0.02
05_skills_and_plugins/02_loading_plugins/main.py	✅ PASS	7.6s	$0.01

❌ Some tests failed

Total: 38 | Passed: 33 | Failed: 5 | Total Cost: $1.90

Failed examples:

examples/01_standalone_sdk/34_critic_example.py: Exit code 1
examples/02_remote_agent_server/02_convo_with_docker_sandboxed_server.py: Exit code 1
examples/02_remote_agent_server/03_browser_use_with_docker_sandboxed_server.py: Exit code 1
examples/02_remote_agent_server/04_convo_with_api_sandboxed_server.py: Exit code 1
examples/02_remote_agent_server/08_convo_with_apptainer_sandboxed_server.py: Exit code 1

View full workflow run

openhands-ai · 2026-02-10T09:54:44Z

Looks like there are a few issues preventing this PR from being merged!

GitHub Actions are failing:
- Run Examples Scripts
- Pre-commit checks

If you'd like me to help, just leave a comment, like

@OpenHands please fix the failing actions on PR #1978 at branch `upgrade-python313-with-libtmux-fix`

Feel free to include any additional details that might help me get this PR into a better state.

_{^{You can manage your notification settings}}

neubig added the integration-test Runs the integration tests and comments the results label Feb 9, 2026 — with OpenHands AI

neubig added the test-examples Run all applicable "examples/" files. Expensive operation. label Feb 9, 2026

neubig removed the test-examples Run all applicable "examples/" files. Expensive operation. label Feb 10, 2026

neubig added the test-examples Run all applicable "examples/" files. Expensive operation. label Feb 10, 2026 — with OpenHands AI

fix: update uv.lock and simplify Generator type hints for Python 3.13

cbb660f

- Regenerate uv.lock with pinned libtmux git dependency - Simplify Generator[T, None, None] to Generator[T] in test files Co-authored-by: openhands <openhands@all-hands.dev>

neubig removed the test-examples Run all applicable "examples/" files. Expensive operation. label Feb 10, 2026

neubig added the test-examples Run all applicable "examples/" files. Expensive operation. label Feb 10, 2026 — with OpenHands AI

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

DRAFT: Upgrade to Python 3.13 with libtmux race condition fix #1978

DRAFT: Upgrade to Python 3.13 with libtmux race condition fix #1978

Uh oh!

neubig commented Feb 9, 2026 •

edited by github-actions bot

Loading

Uh oh!

github-actions bot commented Feb 9, 2026

Uh oh!

github-actions bot commented Feb 9, 2026

Uh oh!

github-actions bot commented Feb 9, 2026 •

edited

Loading

Uh oh!

github-actions bot commented Feb 9, 2026 •

edited

Loading

Uh oh!

github-actions bot commented Feb 10, 2026 •

edited

Loading

Uh oh!

github-actions bot commented Feb 10, 2026 •

edited

Loading

Uh oh!

openhands-ai bot commented Feb 10, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

DRAFT: Upgrade to Python 3.13 with libtmux race condition fix #1978

Are you sure you want to change the base?

DRAFT: Upgrade to Python 3.13 with libtmux race condition fix #1978

Uh oh!

Conversation

neubig commented Feb 9, 2026 • edited by github-actions bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Context

Changes

Testing

Note

Uh oh!

github-actions bot commented Feb 9, 2026

Uh oh!

github-actions bot commented Feb 9, 2026

🧪 Integration Tests Results

📁 Detailed Logs & Artifacts

📊 Summary

📋 Detailed Results

litellm_proxy_deepseek_deepseek_reasoner

litellm_proxy_moonshot_kimi_k2_thinking

litellm_proxy_gemini_3_pro_preview

litellm_proxy_claude_sonnet_4_5_20250929

Uh oh!

github-actions bot commented Feb 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions bot commented Feb 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔄 Running Examples with openhands/claude-haiku-4-5-20251001

❌ Some tests failed

Uh oh!

github-actions bot commented Feb 10, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔄 Running Examples with openhands/claude-haiku-4-5-20251001

❌ Some tests failed

Uh oh!

github-actions bot commented Feb 10, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔄 Running Examples with openhands/claude-haiku-4-5-20251001

❌ Some tests failed

Uh oh!

openhands-ai bot commented Feb 10, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

neubig commented Feb 9, 2026 •

edited by github-actions bot

Loading

github-actions bot commented Feb 9, 2026 •

edited

Loading

github-actions bot commented Feb 9, 2026 •

edited

Loading

🔄 Running Examples with `openhands/claude-haiku-4-5-20251001`

github-actions bot commented Feb 10, 2026 •

edited

Loading

🔄 Running Examples with `openhands/claude-haiku-4-5-20251001`

github-actions bot commented Feb 10, 2026 •

edited

Loading

🔄 Running Examples with `openhands/claude-haiku-4-5-20251001`