v0.11.0: Z.AI GLM Coding Plan as first-class provider#13
Merged
Conversation
May-2026 community-patterns research flagged Z.AI as the most-cited post-Anthropic-OAuth-ban migration target (Anthropic killed third-party OAuth Jan/Feb 2026; OpenCode removed code March 2026). v0.11.0 makes Z.AI a first-class provider across detector / configurator / picker / docs. Verified live against Z.AI docs (fetched 2026-05-18): - baseURL: https://api.z.ai/api/paas/v4 (OpenAI-compatible) - Default model: glm-4.6 (most-documented stable) - Pricing: Coding Plan $10/mo (or $30/quarter, $80/year — quarterly restructure May 2026; flat $18/mo SKU retired) export ZAI_API_KEY='...' npx opencode-sdlc-wizard pick # auto-detected npx opencode-sdlc-wizard pick --tier proprietary --provider zai npx opencode-sdlc-wizard pick --tier proprietary --provider glm # alias Implementation: - configure-backend.sh: PROVIDER_ALIASES (zai/z.ai/z_ai/glm -> zai), fragmentFor proprietary/zai case with @ai-sdk/openai-compatible adapter - detect-backends.sh: PR_ZAI_SET probe, JSON output entry, both privacy-first and free-tier cascades updated (Z.AI ranked above Anthropic/OpenAI in free-tier cascade because flat-fee beats per-token for heavy users) - pick-backend.sh: default_model_for proprietary/zai -> glm-4.6 - AGENTS.md: privacy-tier table updated Tests: T53-T55 in test-backend-picker (provider block, alias, detector), T12 sub-test in test-pick. 379 tests / 12 suites (was 375 / 12 in v0.10.6). Minor version bump (v0.10.x -> v0.11.0): new provider surface is user-visible (new env var, alias group, default-model entry, docs row). Purely additive — every v0.10.x flag and provider works unchanged.
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.
Most-cited post-Anthropic-OAuth-ban migration target per May-2026 research. Verified live against Z.AI docs (fetched 2026-05-18): baseURL
https://api.z.ai/api/paas/v4, default modelglm-4.6, OpenAI-compatible.Implementation
configure-backend.sh:PROVIDER_ALIASES(zai/z.ai/z_ai/glm → zai),proprietary/zaifragment with@ai-sdk/openai-compatibledetect-backends.sh:ZAI_API_KEYprobe, JSON entry, both cascades updated (free-tier cascade ranks Z.AI above Anthropic/OpenAI since flat-fee beats per-token for heavy users)pick-backend.sh: default modelglm-4.6AGENTS.md: privacy-tier tableTest plan
Why minor bump (v0.10.x → v0.11.0)
New provider surface is user-visible (env var, alias group, default-model entry, docs row). Purely additive — every v0.10.x flag works unchanged.