ton/pi_harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add deferred tools support for kimi in openai-completions api

Browse Source
This commit is contained in:
David Brailovsky
2026-07-16 12:26:56 +00:00
parent 36db3fa385
commit f16b4e0cda
10 changed files with 223 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/coding-agent/docs/models.md
+1
View File
@@ -449,6 +449,7 @@ For providers with partial OpenAI compatibility, use the `compat` field.
| `sendSessionAffinityHeaders` | For `openai-completions`, send session-affinity headers from the session id when caching is enabled. Default: `false`. |
| `sessionAffinityFormat` | For `openai-completions` and `openai-responses`, the session-affinity header format: `openai` sends `session_id`/`x-client-request-id` (completions also `x-session-affinity`), `openai-nosession` omits the underscore-containing `session_id` header, `openrouter` sends `x-session-id`. Does not affect the `prompt_cache_key` body param. Default: auto-detected. |
| `supportsStrictMode` | Include the `strict` field in tool definitions |
| `deferredToolsMode` | Use provider-specific deferred tool serialization. Currently only `"kimi"` is supported for Kimi's OpenAI-compatible Chat Completions format. |
| `supportsLongCacheRetention` | Whether the provider accepts long cache retention when cache retention is `long`: `prompt_cache_retention: "24h"` for OpenAI prompt caching, or `cache_control.ttl: "1h"` when `cacheControlFormat` is `anthropic`. Default: `true`. |
| `openRouterRouting` | OpenRouter provider routing preferences. This object is sent as-is in the `provider` field of the [OpenRouter API request](https://openrouter.ai/docs/guides/routing/provider-selection). |
| `vercelGatewayRouting` | Vercel AI Gateway routing config for provider selection (`only`, `order`) |