Test windows run examples workflow #1309

ryanhoangt · 2025-12-03T16:29:25Z

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:python3.12-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:641e720-python

Run

docker run -it --rm \
  -p 8000:8000 \
  --name agent-server-641e720-python \
  ghcr.io/openhands/agent-server:641e720-python

All tags pushed for this build

ghcr.io/openhands/agent-server:641e720-golang-amd64
ghcr.io/openhands/agent-server:641e720-golang_tag_1.21-bookworm-amd64
ghcr.io/openhands/agent-server:641e720-golang-arm64
ghcr.io/openhands/agent-server:641e720-golang_tag_1.21-bookworm-arm64
ghcr.io/openhands/agent-server:641e720-java-amd64
ghcr.io/openhands/agent-server:641e720-eclipse-temurin_tag_17-jdk-amd64
ghcr.io/openhands/agent-server:641e720-java-arm64
ghcr.io/openhands/agent-server:641e720-eclipse-temurin_tag_17-jdk-arm64
ghcr.io/openhands/agent-server:641e720-python-amd64
ghcr.io/openhands/agent-server:641e720-nikolaik_s_python-nodejs_tag_python3.12-nodejs22-amd64
ghcr.io/openhands/agent-server:641e720-python-arm64
ghcr.io/openhands/agent-server:641e720-nikolaik_s_python-nodejs_tag_python3.12-nodejs22-arm64
ghcr.io/openhands/agent-server:641e720-golang
ghcr.io/openhands/agent-server:641e720-java
ghcr.io/openhands/agent-server:641e720-python

About Multi-Architecture Support

Each variant tag (e.g., 641e720-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., 641e720-python-amd64) are also available if needed

Enhanced _check_chromium_available to check common Windows installation paths for Chrome and Edge executables. Also added support for Playwright cache detection on Windows using LOCALAPPDATA.

Removed redundant os.name check and always define Windows Chromium and Edge paths. Simplified Playwright cache candidate logic by unconditionally including the Windows path.

Simplifies and generalizes the construction of Windows browser executable paths by iterating over environment variables and browser definitions. This reduces code duplication and improves maintainability.

Cleaned up unnecessary trailing whitespace in the _check_chromium_available function for improved code style.

Remove incorrect skip logic that prevented checking %LOCALAPPDATA% for Microsoft Edge installations. While Edge is typically installed system-wide, it can also be installed per-user in enterprise environments at %LOCALAPPDATA%\Microsoft\Edge\Application\msedge.exe. This fix ensures the browser detection can find Edge in both installation scenarios.

Renamed the 'browsers' variable to 'windows_browsers' for clarity and updated its usage in the Chromium availability check function.

Introduces WindowsBrowserToolExecutor in a new impl_windows.py for improved Chromium detection on Windows. Updates BrowserToolSet to use the Windows-specific executor when running on Windows, and refactors impl.py to remove Windows-specific code paths.

Co-authored-by: Copilot <[email protected]>

Moved Chromium detection functions into BrowserToolExecutor as instance methods and provided a Windows-specific override in WindowsBrowserToolExecutor. This improves platform extensibility and removes reliance on module-level function overrides.

Updated tests to instantiate BrowserToolExecutor and WindowsBrowserToolExecutor for Chromium detection methods, replacing direct function calls. This aligns tests with the refactored implementation and improves test accuracy for platform-specific logic.

Updated test cases in browser cleanup and initialization tests to use patch.object on BrowserToolExecutor for _ensure_chromium_available, instead of patching the function by import path. This improves test robustness and clarity by directly targeting the class method.

Refactored browser path search to short-circuit on first found executable for efficiency and clarified environment variable handling. Updated test to use a more accurate mock for os.environ.get.

github-actions · 2025-12-03T16:33:14Z

🔄 Running Examples with `litellm_proxy/claude-sonnet-4-5-20250929`

Generated: 2025-12-03 16:46:20 UTC

Example	Status	Duration	Cost
01_standalone_sdk/02_custom_tools.py	✅ PASS	48.6s	$0.07
01_standalone_sdk/03_activate_skill.py	✅ PASS	36.2s	$0.03
01_standalone_sdk/05_use_llm_registry.py	✅ PASS	20.0s	$0.01
01_standalone_sdk/07_mcp_integration.py	✅ PASS	1m 25s	$0.10
01_standalone_sdk/09_pause_example.py	✅ PASS	24.8s	$0.03
01_standalone_sdk/10_persistence.py	✅ PASS	55.9s	$0.07
01_standalone_sdk/11_async.py	✅ PASS	1m 19s	$0.09
01_standalone_sdk/12_custom_secrets.py	✅ PASS	25.6s	$0.02
01_standalone_sdk/13_get_llm_metrics.py	✅ PASS	44.6s	$0.04
01_standalone_sdk/14_context_condenser.py	✅ PASS	2m 31s	$0.45
01_standalone_sdk/17_image_input.py	✅ PASS	28.1s	$0.03
01_standalone_sdk/18_send_message_while_processing.py	✅ PASS	39.9s	$0.03
01_standalone_sdk/19_llm_routing.py	✅ PASS	24.5s	$0.05
01_standalone_sdk/20_stuck_detector.py	✅ PASS	34.6s	$0.03
01_standalone_sdk/21_generate_extraneous_conversation_costs.py	✅ PASS	18.3s	$0.01
01_standalone_sdk/22_anthropic_thinking.py	✅ PASS	29.7s	$0.03
01_standalone_sdk/23_responses_reasoning.py	✅ PASS	37.4s	$0.01
01_standalone_sdk/24_planning_agent_workflow.py	✅ PASS	9m 5s	$0.97
01_standalone_sdk/25_agent_delegation.py	✅ PASS	3m 22s	$0.40
01_standalone_sdk/26_custom_visualizer.py	✅ PASS	37.6s	$0.06
01_standalone_sdk/28_ask_agent_example.py	✅ PASS	1m 4s	$0.08
01_standalone_sdk/29_llm_streaming.py	✅ PASS	1m 14s	$0.06
01_standalone_sdk/30_tom_agent.py	❌ FAIL Missing EXAMPLE_COST marker in stdout	42.8s	--
02_remote_agent_server/01_convo_with_local_agent_server.py	✅ PASS	2m 0s	$0.16
02_remote_agent_server/02_convo_with_docker_sandboxed_server.py	✅ PASS	3m 24s	$0.10
02_remote_agent_server/03_browser_use_with_docker_sandboxed_server.py	✅ PASS	2m 1s	$0.22
02_remote_agent_server/04_convo_with_api_sandboxed_server.py	✅ PASS	3m 42s	$0.15

❌ Some tests failed

Total: 27 | Passed: 26 | Failed: 1 | Total Cost: $3.28

Failed examples:

examples/01_standalone_sdk/30_tom_agent.py: Missing EXAMPLE_COST marker in stdout

View full workflow run

github-actions · 2025-12-03T16:36:07Z

Coverage Report •

File	Stmts	Miss	Cover	Missing
openhands-tools/openhands/tools/browser_use
definition.py	118	17	85%	43–46, 62, 65–66, 69–71, 82–83, 85–86, 88, 567, 571
impl.py	184	123	33%	25, 34, 36–38, 40–41, 48–50, 52–56, 61, 98, 107–110, 113, 118–121, 123, 132–135, 148, 178–179, 190–191, 206, 212, 226–227, 229–238, 241–250, 252–253, 259, 264–267, 275, 277–278, 283–284, 288–289, 294–295, 299–300, 304–305, 309, 311–312, 314–317, 320–321, 327, 329, 331, 340–341, 345–346, 350–351, 356–357, 363–367, 371–376, 380–383, 385–387, 390, 394–397
TOTAL	12869	6058	52%

github-actions · 2025-12-03T16:43:26Z

🔄 Running Examples with `litellm_proxy/claude-sonnet-4-5-20250929`

Generated: 2025-12-03 16:55:10 UTC

Example	Status	Duration	Cost
01_standalone_sdk/02_custom_tools.py	✅ PASS	44.8s	$0.07
01_standalone_sdk/03_activate_skill.py	✅ PASS	30.5s	$0.04
01_standalone_sdk/05_use_llm_registry.py	✅ PASS	19.1s	$0.02
01_standalone_sdk/07_mcp_integration.py	✅ PASS	1m 12s	$0.08
01_standalone_sdk/09_pause_example.py	✅ PASS	27.6s	$0.03
01_standalone_sdk/10_persistence.py	✅ PASS	59.9s	$0.07
01_standalone_sdk/11_async.py	✅ PASS	1m 10s	$0.08
01_standalone_sdk/12_custom_secrets.py	✅ PASS	22.2s	$0.03
01_standalone_sdk/13_get_llm_metrics.py	✅ PASS	46.7s	$0.04
01_standalone_sdk/14_context_condenser.py	✅ PASS	4m 5s	$0.75
01_standalone_sdk/17_image_input.py	✅ PASS	33.4s	$0.05
01_standalone_sdk/18_send_message_while_processing.py	✅ PASS	30.2s	$0.03
01_standalone_sdk/19_llm_routing.py	✅ PASS	24.5s	$0.05
01_standalone_sdk/20_stuck_detector.py	✅ PASS	26.8s	$0.02
01_standalone_sdk/21_generate_extraneous_conversation_costs.py	✅ PASS	18.0s	$0.01
01_standalone_sdk/22_anthropic_thinking.py	✅ PASS	29.1s	$0.03
01_standalone_sdk/23_responses_reasoning.py	✅ PASS	36.5s	$0.01
01_standalone_sdk/24_planning_agent_workflow.py	✅ PASS	6m 8s	$0.60
01_standalone_sdk/25_agent_delegation.py	✅ PASS	3m 12s	$0.49
01_standalone_sdk/26_custom_visualizer.py	✅ PASS	45.9s	$0.07
01_standalone_sdk/28_ask_agent_example.py	✅ PASS	49.3s	$0.08
01_standalone_sdk/29_llm_streaming.py	✅ PASS	1m 14s	$0.08
01_standalone_sdk/30_tom_agent.py	❌ FAIL Missing EXAMPLE_COST marker in stdout	51.2s	--
02_remote_agent_server/01_convo_with_local_agent_server.py	✅ PASS	1m 50s	$0.16
02_remote_agent_server/02_convo_with_docker_sandboxed_server.py	✅ PASS	2m 28s	$0.11
02_remote_agent_server/03_browser_use_with_docker_sandboxed_server.py	✅ PASS	3m 5s	$0.16
02_remote_agent_server/04_convo_with_api_sandboxed_server.py	✅ PASS	2m 22s	$0.11

❌ Some tests failed

Total: 27 | Passed: 26 | Failed: 1 | Total Cost: $3.29

Failed examples:

examples/01_standalone_sdk/30_tom_agent.py: Missing EXAMPLE_COST marker in stdout

View full workflow run

github-actions · 2025-12-03T17:14:48Z

🔄 Running Examples with `litellm_proxy/claude-sonnet-4-5-20250929`

Generated: 2025-12-03 17:26:32 UTC

Example	Status	Duration	Cost
01_standalone_sdk/02_custom_tools.py	✅ PASS	47.2s	$0.08
01_standalone_sdk/03_activate_skill.py	✅ PASS	29.2s	$0.04
01_standalone_sdk/05_use_llm_registry.py	✅ PASS	18.0s	$0.02
01_standalone_sdk/07_mcp_integration.py	✅ PASS	1m 43s	$0.12
01_standalone_sdk/09_pause_example.py	✅ PASS	26.8s	$0.03
01_standalone_sdk/10_persistence.py	✅ PASS	58.3s	$0.07
01_standalone_sdk/11_async.py	✅ PASS	1m 6s	$0.10
01_standalone_sdk/12_custom_secrets.py	✅ PASS	23.4s	$0.04
01_standalone_sdk/13_get_llm_metrics.py	✅ PASS	43.6s	$0.04
01_standalone_sdk/14_context_condenser.py	✅ PASS	5m 36s	$0.95
01_standalone_sdk/17_image_input.py	✅ PASS	28.3s	$0.05
01_standalone_sdk/18_send_message_while_processing.py	✅ PASS	25.6s	$0.02
01_standalone_sdk/19_llm_routing.py	✅ PASS	21.8s	$0.04
01_standalone_sdk/20_stuck_detector.py	✅ PASS	29.4s	$0.02
01_standalone_sdk/21_generate_extraneous_conversation_costs.py	✅ PASS	17.4s	$0.01
01_standalone_sdk/22_anthropic_thinking.py	✅ PASS	26.5s	$0.03
01_standalone_sdk/23_responses_reasoning.py	✅ PASS	1m 18s	$0.02
01_standalone_sdk/24_planning_agent_workflow.py	✅ PASS	6m 15s	$0.61
01_standalone_sdk/25_agent_delegation.py	✅ PASS	3m 15s	$0.51
01_standalone_sdk/26_custom_visualizer.py	✅ PASS	34.2s	$0.06
01_standalone_sdk/28_ask_agent_example.py	✅ PASS	53.2s	$0.08
01_standalone_sdk/29_llm_streaming.py	✅ PASS	1m 5s	$0.07
01_standalone_sdk/30_tom_agent.py	✅ PASS	38.5s	$0.04
02_remote_agent_server/01_convo_with_local_agent_server.py	✅ PASS	1m 50s	$0.17
02_remote_agent_server/02_convo_with_docker_sandboxed_server.py	✅ PASS	2m 52s	$0.11
02_remote_agent_server/03_browser_use_with_docker_sandboxed_server.py	✅ PASS	2m 58s	$0.17
02_remote_agent_server/04_convo_with_api_sandboxed_server.py	✅ PASS	2m 4s	$0.12

✅ All tests passed!

Total: 27 | Passed: 27 | Failed: 0 | Total Cost: $3.61

View full workflow run

BrowserToolExecutor now checks common Linux and macOS installation paths for Chromium and Chrome if not found in PATH. Corresponding tests were added to verify detection via these standard paths.

Renamed the example script for consistency or to reflect updated numbering in the standalone SDK examples directory.

Adds a print statement to display the accumulated cost from the LLM metrics at the end of the Tom agent consultation example.

Changed references from 30_windows.py to 31_windows.py in the exemption list and workflow configuration to reflect the new filename.

openhands-ai · 2025-12-04T12:50:30Z

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

GitHub Actions are failing:
- Run Examples Scripts

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

@OpenHands please fix the failing actions on PR #1309 at branch `smj-chromium`

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

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

github-actions · 2025-12-04T12:55:28Z

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

Generated: 2025-12-04 13:03:09 UTC

Example	Status	Duration	Cost
01_standalone_sdk/02_custom_tools.py	✅ PASS	30.7s	$0.03
01_standalone_sdk/03_activate_skill.py	✅ PASS	19.4s	$0.02
01_standalone_sdk/05_use_llm_registry.py	✅ PASS	16.3s	$0.01
01_standalone_sdk/07_mcp_integration.py	✅ PASS	1m 6s	$0.04
01_standalone_sdk/09_pause_example.py	✅ PASS	21.1s	$0.01
01_standalone_sdk/10_persistence.py	✅ PASS	43.8s	$0.02
01_standalone_sdk/11_async.py	✅ PASS	44.4s	$0.03
01_standalone_sdk/12_custom_secrets.py	✅ PASS	15.3s	$0.01
01_standalone_sdk/13_get_llm_metrics.py	✅ PASS	38.4s	$0.01
01_standalone_sdk/14_context_condenser.py	✅ PASS	2m 31s	$0.27
01_standalone_sdk/17_image_input.py	✅ PASS	18.4s	$0.02
01_standalone_sdk/18_send_message_while_processing.py	✅ PASS	25.2s	$0.01
01_standalone_sdk/19_llm_routing.py	✅ PASS	17.8s	$0.02
01_standalone_sdk/20_stuck_detector.py	✅ PASS	30.0s	$0.02
01_standalone_sdk/21_generate_extraneous_conversation_costs.py	✅ PASS	10.2s	$0.00
01_standalone_sdk/22_anthropic_thinking.py	✅ PASS	14.9s	$0.01
01_standalone_sdk/23_responses_reasoning.py	✅ PASS	41.4s	$0.01
01_standalone_sdk/24_planning_agent_workflow.py	✅ PASS	4m 11s	$0.27
01_standalone_sdk/25_agent_delegation.py	✅ PASS	2m 12s	$0.16
01_standalone_sdk/26_custom_visualizer.py	✅ PASS	21.9s	$0.02
01_standalone_sdk/28_ask_agent_example.py	✅ PASS	36.9s	$0.02
01_standalone_sdk/29_llm_streaming.py	✅ PASS	38.3s	$0.02
01_standalone_sdk/30_tom_agent.py	✅ PASS	25.1s	$0.01
01_standalone_sdk/31_windows.py	✅ PASS	1m 1s	$0.05
02_remote_agent_server/01_convo_with_local_agent_server.py	✅ PASS	1m 2s	$0.03
02_remote_agent_server/02_convo_with_docker_sandboxed_server.py	✅ PASS	2m 4s	$0.08
02_remote_agent_server/03_browser_use_with_docker_sandboxed_server.py	✅ PASS	53.7s	$0.05
02_remote_agent_server/04_convo_with_api_sandboxed_server.py	✅ PASS	1m 33s	$0.03

✅ All tests passed!

Total: 28 | Passed: 28 | Failed: 0 | Total Cost: $1.28

View full workflow run

SmartManoj and others added 26 commits November 4, 2025 14:55

Add Windows browser path checks to Chromium detection

c2b68cd

Enhanced _check_chromium_available to check common Windows installation paths for Chrome and Edge executables. Also added support for Playwright cache detection on Windows using LOCALAPPDATA.

Merge branch 'main' into chromium

7adba85

format

87938d3

Refactor Windows Chromium path checks in impl.py

87718f5

Removed redundant os.name check and always define Windows Chromium and Edge paths. Simplified Playwright cache candidate logic by unconditionally including the Windows path.

Merge branch 'main' into chromium

2dd4ab7

Merge branch 'main' into chromium

3614642

Merge branch 'main' into chromium

2e0060a

Refactor Windows browser path detection logic

aa05bf0

Simplifies and generalizes the construction of Windows browser executable paths by iterating over environment variables and browser definitions. This reduces code duplication and improves maintainability.

Remove trailing whitespace in impl.py

3830639

Cleaned up unnecessary trailing whitespace in the _check_chromium_available function for improved code style.

Rename browsers list to windows_browsers

cb7086e

Renamed the 'browsers' variable to 'windows_browsers' for clarity and updated its usage in the Chromium availability check function.

Merge branch 'main' into chromium

c6c1ef8

Merge branch 'main' into chromium

b58f093

lint

3972616

Merge branch 'main' into chromium

feb388b

Apply suggestions from code review

881b20c

Co-authored-by: Copilot <[email protected]>

Apply suggestions from code review

c041799

Improve Windows Chrome detection logic

b9d8b5b

Refactored browser path search to short-circuit on first found executable for efficiency and clarified environment variable handling. Updated test to use a more accurate mock for os.environ.get.

add new example to run on windows only

e952337

skip wait on fork PR

93ac594

exclude 30_windows.py example from doc check

fc2c451

set visualizer to none

3b95b45

ryanhoangt added the test-examples Run all applicable "examples/" files. Expensive operation. label Dec 3, 2025

update model name & base url

54d93bc

ryanhoangt force-pushed the smj-chromium branch from 0f6c32a to 54d93bc Compare December 3, 2025 16:39

ryanhoangt added test-examples Run all applicable "examples/" files. Expensive operation. and removed test-examples Run all applicable "examples/" files. Expensive operation. labels Dec 3, 2025

SmartManoj and others added 6 commits December 4, 2025 05:20

Add standard browser installation path detection

1e3173e

BrowserToolExecutor now checks common Linux and macOS installation paths for Chromium and Chrome if not found in PATH. Corresponding tests were added to verify detection via these standard paths.

Rename 30_windows.py to 31_windows.py

352a97b

Renamed the example script for consistency or to reflect updated numbering in the standalone SDK examples directory.

Report LLM cost in Tom agent example

dc29b77

Adds a print statement to display the accumulated cost from the LLM metrics at the end of the Tom agent consultation example.

Merge branch 'main' into chromium

bc2c12e

Update Windows example filename references

696241f

Changed references from 30_windows.py to 31_windows.py in the exemption list and workflow configuration to reflect the new filename.

fix encoding error for windows example

d8a11d7

ryanhoangt force-pushed the smj-chromium branch from 802a1b5 to d8a11d7 Compare December 4, 2025 12:43

ryanhoangt added test-examples Run all applicable "examples/" files. Expensive operation. and removed test-examples Run all applicable "examples/" files. Expensive operation. labels Dec 4, 2025

fix hidden dir

6ba981c

ryanhoangt added test-examples Run all applicable "examples/" files. Expensive operation. and removed test-examples Run all applicable "examples/" files. Expensive operation. labels Dec 4, 2025

ryanhoangt mentioned this pull request Dec 4, 2025

Add Windows browser path checks to Chromium detection #1014

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Test windows run examples workflow #1309

Test windows run examples workflow #1309

Uh oh!

ryanhoangt commented Dec 3, 2025 •

edited by github-actions bot

Loading

Uh oh!

github-actions bot commented Dec 3, 2025 •

edited

Loading

Uh oh!

github-actions bot commented Dec 3, 2025 •

edited

Loading

Uh oh!

github-actions bot commented Dec 3, 2025 •

edited

Loading

Uh oh!

github-actions bot commented Dec 3, 2025 •

edited

Loading

Uh oh!

openhands-ai bot commented Dec 4, 2025

Uh oh!

github-actions bot commented Dec 4, 2025 •

edited

Loading

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Test windows run examples workflow #1309

Are you sure you want to change the base?

Test windows run examples workflow #1309

Uh oh!

Conversation

ryanhoangt commented Dec 3, 2025 • edited by github-actions bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions bot commented Dec 3, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔄 Running Examples with litellm_proxy/claude-sonnet-4-5-20250929

❌ Some tests failed

Uh oh!

github-actions bot commented Dec 3, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions bot commented Dec 3, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔄 Running Examples with litellm_proxy/claude-sonnet-4-5-20250929

❌ Some tests failed

Uh oh!

github-actions bot commented Dec 3, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔄 Running Examples with litellm_proxy/claude-sonnet-4-5-20250929

✅ All tests passed!

Uh oh!

openhands-ai bot commented Dec 4, 2025

Uh oh!

github-actions bot commented Dec 4, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

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

✅ All tests passed!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

ryanhoangt commented Dec 3, 2025 •

edited by github-actions bot

Loading

github-actions bot commented Dec 3, 2025 •

edited

Loading

🔄 Running Examples with `litellm_proxy/claude-sonnet-4-5-20250929`

github-actions bot commented Dec 3, 2025 •

edited

Loading

github-actions bot commented Dec 3, 2025 •

edited

Loading

🔄 Running Examples with `litellm_proxy/claude-sonnet-4-5-20250929`

github-actions bot commented Dec 3, 2025 •

edited

Loading

🔄 Running Examples with `litellm_proxy/claude-sonnet-4-5-20250929`

github-actions bot commented Dec 4, 2025 •

edited

Loading

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