feat: Add DashScope Coding Plan provider (alibaba_coding)#543
Open
cryptonahue wants to merge 6 commits intoRightNow-AI:mainfrom
Open
feat: Add DashScope Coding Plan provider (alibaba_coding)#543cryptonahue wants to merge 6 commits intoRightNow-AI:mainfrom
cryptonahue wants to merge 6 commits intoRightNow-AI:mainfrom
Conversation
Chromium refuses to launch without --no-sandbox when the process is running as UID 0. This causes the browser hand to fail immediately with 'Chromium exited before printing DevTools URL' on any server-based OpenFang installation that runs as root (the default install). Added is_running_as_root() which reads /proc/self/status on Linux to detect UID 0 without requiring a libc dependency, with a fallback to the HOME env var for other Unix systems. When root is detected, --no-sandbox is appended to the Chromium launch args automatically.
…en_coding_intl)
Adds native support for Alibaba Cloud's DashScope Coding Plan, which provides
access to Qwen, GLM, Kimi, and MiniMax models via a single DASHSCOPE_API_KEY.
Three new providers:
- qwen_intl: DashScope international standard endpoint
- qwen_coding: DashScope Coding Plan (China) endpoint
- qwen_coding_intl: DashScope Coding Plan (International) endpoint
Eight new model catalog entries under qwen_coding_intl:
- qwen3.5-plus (1M ctx, 65k output, vision+tools)
- qwen3-max-2026-01-23 (131k ctx, Frontier)
- qwen3-coder-plus (131k ctx, Smart)
- qwen3-coder-next (131k ctx, Frontier)
- qwen_coding_intl/glm-5 (Zhipu GLM-5 via coding plan)
- qwen_coding_intl/glm-4.7 (Zhipu GLM-4.7 via coding plan)
- qwen_coding_intl/kimi-k2.5 (Moonshot Kimi K2.5 via coding plan)
- qwen_coding_intl/MiniMax-M2.5 (MiniMax M2.5 via coding plan)
Multi-brand models use the "provider/model" prefix convention (same pattern as
OpenRouter). The existing strip_provider_prefix() in agent_loop strips the
prefix before the API call, so the API receives the bare model name ("glm-5",
"kimi-k2.5", etc.) as expected by the DashScope endpoint.
Native providers (zhipu, moonshot, minimax) are unchanged — users with
separate API keys for those providers are not affected.
Also adds wizard support for all three new providers and fixes
qwen3-235b-a22b max_output_tokens (8192 → 32768).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
… only Remove qwen_intl and qwen_coding (China/International variants) that added confusion without providing distinct model sets. Keep: - qwen: standard DashScope endpoint (existing 11 models) - qwen_coding_intl: DashScope Coding Plan, renamed to "DashScope Coding Plan" Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add special-case driver path for qwen_coding_intl that injects the required User-Agent: OpenClaw/1.0 header, eliminating the need for the proxy. Also fix base URL from /compatible-mode/v1 to /v1. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds native support for Alibaba Cloud's DashScope Coding Plan, which provides access to Qwen, GLM, Kimi, and MiniMax models via a single
ALIBABA_CODING_API_KEY.Key Discovery: The Alibaba Coding Plan API requires a specific
User-Agent: OpenClaw/1.0header to bypass the "Coding Agents only" restriction.Features
alibaba_coding(DashScope Coding Plan International endpoint)https://coding-intl.dashscope.aliyuncs.com/v1Bonus
--no-sandboxflag for Chromium when running as root (fixes browser hand on servers)Testing
✅ Live integration tested with qwen3.5-plus model