NCBM/plyngent
1
0
Fork 0
mirror of https://github.com/NCBM/plyngent.git synced 2026-11-07 07:17:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs: describe the adaptive-thinking retry

Browse Source
This commit is contained in:
worldmozara
2026-10-16 22:12:09 +08:00
parent 9156df2b02
commit 06a5bafab7
3 changed files with 7 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -175,7 +175,7 @@ max_context_tokens = 200000
Per-provider **`timeout`** is passed to the HTTP session for chat/completions, Responses, and `GET /models`. A single number sets one timeout; `{ connect, read }` splits TCP/TLS setup vs idle wait between response bytes (SSE can run longer than `read` while chunks keep arriving). Tool/process timeouts (`run_argv`, PTY, policy confirm) are separate.
**Thinking strength** (`reasoning_effort`) can be set on `[agent]`, on a provider, or on a single model: the most specific layer wins, per field, so a model may override only the effort or only the budget. `""` sends nothing and lets the provider apply its own default. Each API surface maps the value onto its own wire field — chat completions send `reasoning_effort`, Responses send `reasoning.effort`, and Anthropic has no effort level at all, so it sends `thinking` with the token budget that level maps onto (`minimal` 1024 … `xhigh`/`max` 32768; `none` disables thinking). `max` is DeepSeek's own top level on chat completions and clamps to `xhigh` everywhere else. `thinking_budget_tokens` overrides that mapping; either way the request stays valid: the budget never drops below 1024, and when it would swallow the output limit `max_tokens` grows so the answer still has room. DeepSeek chat keeps `thinking.type = "enabled"` unless the effort is `none`.
**Thinking strength** (`reasoning_effort`) can be set on `[agent]`, on a provider, or on a single model: the most specific layer wins, per field, so a model may override only the effort or only the budget. `""` sends nothing and lets the provider apply its own default. Each API surface maps the value onto its own wire field — chat completions send `reasoning_effort`, Responses send `reasoning.effort`, and Anthropic has no effort level at all, so it sends `thinking` with the token budget that level maps onto (`minimal` 1024 … `xhigh`/`max` 32768; `none` disables thinking); a model that no longer takes a budget answers 400 and wants adaptive thinking instead (from Claude 4.7 on), so the request is retried once as `thinking.type = "adaptive"` with the level in `output_config.effort`, and that model is remembered for the session — `thinking_budget_tokens` has no adaptive equivalent and is then ignored. `max` is DeepSeek's own top level on chat completions and clamps to `xhigh` everywhere else. `thinking_budget_tokens` overrides that mapping; either way the request stays valid: the budget never drops below 1024, and when it would swallow the output limit `max_tokens` grows so the answer still has room. DeepSeek chat keeps `thinking.type = "enabled"` unless the effort is `none`.
```toml
[providers.deepseek]