airkjw/claude-mem
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

MAESTRO: Close PR #786 - GLM provider has process.env concurrency bug and YAGNI preset

Browse Source 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Alex Newman
2026-02-06 03:28:29 -05:00
parent 10675f7125
commit 936080d710
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Auto Run Docs/PR-Triage/PR-Triage-12.md
+1 -1
View File
@@ -8,7 +8,7 @@ Multiple community members want to add provider support. Evaluate whether the pr
- [x] Evaluate PR #808 (`feat: Add AnthropicAPIAgent for direct API observation processing` by @MrSaneApps, 4 files). **CLOSED.** Memory concerns (the core motivation) were already addressed by merged PR #806. Having two Anthropic providers (SDK + direct API) creates user confusion and maintenance burden. Claude SDK via CLI auth remains the recommended path. Closed with detailed explanation thanking the contributor.
- [ ] Evaluate PR #786 (`feat: add GLM provider and custom Anthropic-compatible API support` by @Zorglub4242, 13 files). Adds GLM (Chinese AI) and generic Anthropic-compatible API support. Decision: Is custom API support in scope? If yes, review and merge. If not: close with thanks.
- [x] Evaluate PR #786 (`feat: add GLM provider and custom Anthropic-compatible API support` by @Zorglub4242, 13 files). **CLOSED.** Three issues: (1) `process.env` mutation is a concurrency bug — env vars leak between sessions since the worker handles multiple sessions on one process. (2) GLM preset is YAGNI — a generic custom provider option would cover GLM users without a dedicated preset. (3) Custom Anthropic-compatible API support is a good concept but needs subprocess-scoped env vars, not global mutation. Invited contributor to re-submit a focused custom-provider-only PR.
- [ ] Evaluate PR #644 (`feat: Add OpenAI provider support` by @niteeshm, 10 files). OpenAI as an alternative provider. Decision: How many providers should the project support? Currently: Claude SDK, Gemini, OpenRouter. Adding OpenAI directly may duplicate OpenRouter (which already supports OpenAI models). If OpenRouter covers this: `gh pr close 644 --comment "OpenAI models are accessible via the OpenRouter provider. We'd prefer to keep the provider count manageable. Thank you!"`