github/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-10 02:02:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(ollama): unify context window handling across discovery, merge, and OpenAI-compat transport (#29205)

Browse Source 
* fix(ollama): inject num_ctx for OpenAI-compatible transport

* fix(ollama): discover per-model context and preserve higher limits

* fix(agents): prefer matching provider model for fallback limits

* fix(types): require numeric token limits in provider model merge

* fix(types): accept unknown payload in ollama num_ctx wrapper

* fix(types): simplify ollama settled-result extraction

* config(models): add provider flag for Ollama OpenAI num_ctx injection

* config(schema): allow provider num_ctx injection flag

* config(labels): label provider num_ctx injection flag

* config(help): document provider num_ctx injection flag

* agents(ollama): gate OpenAI num_ctx injection with provider config

* tests(ollama): cover provider num_ctx injection flag behavior

* docs(config): list provider num_ctx injection option

* docs(ollama): document OpenAI num_ctx injection toggle

* docs(config): clarify merge token-limit precedence

* config(help): note merge uses higher model token limits

* fix(ollama): cap /api/show discovery concurrency

* fix(ollama): restrict num_ctx injection to OpenAI compat

* tests(ollama): cover ipv6 and compat num_ctx gating

* fix(ollama): detect remote compat endpoints for ollama-labeled providers

* fix(ollama): cap per-model /api/show lookups to bound discovery load
This commit is contained in:
Vincent Koc
2026-02-27 17:20:47 -08:00
committed by GitHub
parent 70a4f25ab1
commit f16ecd1dac
14 changed files with 582 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
src/agents/models-config.ts
View File

@@ -15,6 +15,12 @@ type ModelsConfig = NonNullable<OpenClawConfig["models"]>;
const DEFAULT_MODE: NonNullable<ModelsConfig["mode"]> = "merge";
function resolvePreferredTokenLimit(explicitValue: number, implicitValue: number): number {
// Keep catalog refresh behavior for stale low values while preserving
// intentional larger user overrides (for example Ollama >128k contexts).
return explicitValue > implicitValue ? explicitValue : implicitValue;
}
function mergeProviderModels(implicit: ProviderConfig, explicit: ProviderConfig): ProviderConfig {
const implicitModels = Array.isArray(implicit.models) ? implicit.models : [];
const explicitModels = Array.isArray(explicit.models) ? explicit.models : [];
@@ -55,8 +61,11 @@ function mergeProviderModels(implicit: ProviderConfig, explicit: ProviderConfig)
...explicitModel,
input: implicitModel.input,
reasoning: "reasoning" in explicitModel ? explicitModel.reasoning : implicitModel.reasoning,
contextWindow: implicitModel.contextWindow,
maxTokens: implicitModel.maxTokens,
contextWindow: resolvePreferredTokenLimit(
explicitModel.contextWindow,
implicitModel.contextWindow,
),
maxTokens: resolvePreferredTokenLimit(explicitModel.maxTokens, implicitModel.maxTokens),
};
});