lingyuzeng/collective-memory-repo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update opencode default provider to infini kimi-k2.5

Browse Source
This commit is contained in:
hotwa
2026-03-18 15:43:07 +08:00
parent 4e1d0707ba
commit 537ee62363
3 changed files with 21 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
agents/openclaw-main/warp-acp-ops.md
View File

@@ -63,8 +63,11 @@ Each wrapper should:
Current `opencode` default-model routing baseline:
- `mac-5`
- default model: `opencode/minimax-m2.5-free`
- rationale: the minimax free cloud route already passed direct + ACP minimal validation and avoids the timeout-prone local `oMLX` ACP path
- provider label: `infini`
- base URL: `https://cloud.infini-ai.com/maas/coding/v1`
- model id: `kimi-k2.5`
- default model: `infini/kimi-k2.5`
- rationale: removed the temporary `ckimi / kimi-for-coding` route because `Kimi For Coding` is currently limited to coding-agent products and is not a reliable `opencode` default path
- `mac-6`
- provider label: `vllm`
- base URL: `http://100.64.0.5:8000/v1`

13
daily/2026-03-18.md
View File

@@ -28,6 +28,19 @@
- `mac-6` ACP 最小测试结果：`MAC6_VLLM_ACP_OK`
- `mac-7` ACP 最小测试结果：`MAC7_VLLM_ACP_OK`
## opencode provider/default 切换（mac-5）
- hotwa 要求撤掉 `opencode` 上一会话里为 `Kimi For Coding` 临时接入的 `ckimi` provider
- 原因：`Kimi For Coding` 当前仅面向 Coding Agents（如 Kimi CLI / Claude Code / Roo Code / Kilo Code 等），不支持当前这条 `opencode` 使用路径
- 已将 `~/.config/opencode/opencode.json` 改为：
- 删除 `ckimi` provider
- 新默认 provider：`infini`
- 新默认模型：`infini/kimi-k2.5`
- `baseURL`：`https://cloud.infini-ai.com/maas/coding/v1`
- `apiKey`：`{env:WARP_INFINI_API_KEY}`
- 已用 `opencode models infini` 最小校验，返回：`infini/kimi-k2.5`
- 结论：`mac-5` 的当前 `opencode` 默认模型基线，已从 `opencode/minimax-m2.5-free` 调整为 `infini/kimi-k2.5`
## 备注
- 这次更新针对的是 `opencode` 默认模型策略，不等于废弃原有 subagent / worker 的本地模型拓扑说明

6
shared/long-term/projects/warp-acp-integration.md
View File

@@ -93,19 +93,19 @@ The cluster no longer uses a single "default to each machine's own local model"
Current node-specific default policy:
- `mac-5`: default `opencode` model is `opencode/minimax-m2.5-free`
- `mac-5`: default `opencode` model is `infini/kimi-k2.5` via `https://cloud.infini-ai.com/maas/coding/v1`
- `mac-6`: default `opencode` model is `vllm/Qwen3.5-27B` via `http://100.64.0.5:8000/v1`
- `mac-7`: default `opencode` model is `vllm/Qwen3.5-27B` via `http://100.64.0.5:8000/v1`
Operational meaning:
- `mac-5` prefers the already-validated free cloud minimax route for daily ACP stability.
- `mac-5` prefers the Infini coding endpoint with `kimi-k2.5`; the earlier `ckimi / kimi-for-coding` stopgap was removed because `Kimi For Coding` is currently targeted at coding-agent products rather than this `opencode` path.
- `mac-6` and `mac-7` prefer the shared local vLLM endpoint instead of their previous per-node local `oMLX` default for `opencode` ACP.
- This rule is specific to current `opencode` defaults; it does not invalidate separate worker/subagent topology docs.
Observed validation status:
- `mac-5`: direct `opencode` and ACP minimal tests succeeded with `opencode/minimax-m2.5-free`
- `mac-5`: direct `opencode` config validation succeeded with `infini/kimi-k2.5` (`opencode models infini` returned `infini/kimi-k2.5`)
- `mac-6`: ACP minimal test succeeded with `vllm/Qwen3.5-27B`
- `mac-7`: ACP minimal test succeeded with `vllm/Qwen3.5-27B`