sscoble/pi-mono
1
0
Fork 0
mirror of https://github.com/badlogic/pi-mono.git synced 2026-11-05 23:37:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

fix(coding-agent): use llama context for output limit (#7034)

Browse source 
Fixes #6994.
This commit is contained in:
Christian Klotz 2026-07-24 00:06:03 +03:00 • committed by GitHub
parent 241431c69b
commit 6abb4b0640
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 4 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

4
packages/coding-agent/src/extensions/llama/provider.ts
View file

@ -12,8 +12,6 @@ import { LlamaClient, type LlamaModelInfo, llamaInferenceUrl, normalizeLlamaServ
export const LLAMA_PROVIDER_ID = "llama.cpp";
export const DEFAULT_LLAMA_SERVER_URL = "http://127.0.0.1:8080";
const DEFAULT_MAX_TOKENS = 16384;
function credentialServerUrl(credential: ApiKeyCredential | undefined): string | undefined {
const value = credential?.env?.LLAMA_BASE_URL;
return typeof value === "string" && value.trim() ? normalizeLlamaServerUrl(value) : undefined;
@ -40,7 +38,7 @@ function toPiModel(model: LlamaModelInfo, serverUrl: string): Model<"openai-comp
input: model.architecture?.input_modalities?.includes("image") ? ["text", "image"] : ["text"],
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
contextWindow,
maxTokens: Math.min(DEFAULT_MAX_TOKENS, contextWindow),
maxTokens: contextWindow,
compat: {
supportsStore: false,
supportsDeveloperRole: false,

6
packages/coding-agent/test/llama-extension.test.ts
View file

@ -67,7 +67,7 @@ describe("llama.cpp extension", () => {
id: "loaded",
status: { value: "loaded", args: ["llama-server", "--n-gpu-layers", "999"] },
architecture: { input_modalities: ["text", "image"] },
meta: { n_ctx: 16384, n_ctx_train: 131072 },
meta: { n_ctx: 65536, n_ctx_train: 131072 },
},
{ id: "unloaded", status: { value: "unloaded" } },
{ id: "loading", status: { value: "loading" } },
@ -79,8 +79,8 @@ describe("llama.cpp extension", () => {
expect.objectContaining({
id: "loaded",
baseUrl: "http://localhost:8080/v1",
contextWindow: 16384,
maxTokens: 16384,
contextWindow: 65536,
maxTokens: 65536,
input: ["text", "image"],
}),
]);