aevgarik/paperclip
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: adapter model discovery, reasoning effort, and improved codex formatting

Browse Source 
Add dynamic OpenAI model list fetching for codex adapter with caching,
async listModels interface, reasoning effort support for both claude and
codex adapters, optional timeouts (default to unlimited), wakeCommentId
context propagation, and richer codex stdout event parsing/formatting.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Forgotten
2026-02-20 10:32:07 -06:00
parent fdd2ea6157
commit 2c3c2cf724
19 changed files with 890 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
server/src/adapters/process/execute.ts
View File

@@ -22,7 +22,7 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
if (typeof v === "string") env[k] = v;
}
const timeoutSec = asNumber(config.timeoutSec, 900);
const timeoutSec = asNumber(config.timeoutSec, 0);
const graceSec = asNumber(config.graceSec, 15);
if (onMeta) {