mirror of
https://github.com/Ark0N/Codeman.git
synced 2026-11-17 03:39:33 +01:00
fix(custom-model): pi is told the endpoint's context window
A pi session on a custom endpoint got a model list entry with only the model id. pi then takes the model for a 128,000-token one (its footer reads "/128k") and asks for 16,384 reply tokens, so on a 65,536 or 32,768 window it never compacts before the server's real window is full. The entry now carries `contextWindow` (the full window) and `maxTokens` (a quarter of it, 8,192 at most) whenever the endpoint's context length is known: the same two figures the DeepSeek Harness patch already carries, now from one helper. An unknown length writes neither, as before. Measured on pi 1.5.2: with both fields `pi --list-models` shows the window, and the request carries `max_tokens: 8192`. Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
This commit is contained in:
1 parent
7bdef0d86a
commit
a5a1b6f9a2
2 files changed
+43
-17
No files matched your search
@@ -194,6 +194,21 @@ function opencodeModelLimit(contextLength: number | undefined): { context: numbe
|
||||
return { context: total, output };
|
||||
}
|
||||
|
||||
/**
|
||||
* The two fields pi's model list and the dsh provider patch (which is built on pi's model
|
||||
* layer) take for a model's window: `contextWindow`, the FULL window, and `maxTokens`, the
|
||||
* reply's share of it (a quarter, capped at 8192 on a large window). Empty for an unknown or
|
||||
* non-finite size: the CLI then keeps its own default, and no limit is invented here.
|
||||
*/
|
||||
function modelWindowFields(contextLength: number | undefined): { contextWindow?: number; maxTokens?: number } {
|
||||
if (contextLength === undefined || !Number.isFinite(contextLength) || contextLength <= 0) return {};
|
||||
return {
|
||||
contextWindow: Math.trunc(contextLength),
|
||||
// A quarter of the window keeps the reply inside the prompt's share; 8192 caps it on a large window.
|
||||
maxTokens: Math.max(1, Math.min(8192, Math.floor(contextLength / 4))),
|
||||
};
|
||||
}
|
||||
|
||||
function renderConfigContent(
|
||||
template: 'opencode-json',
|
||||
endpoint: CustomModelEndpoint,
|
||||
@@ -260,19 +275,7 @@ function renderConfigFile(
|
||||
apiKeyEnv: CUSTOM_MODEL_API_KEY_ENV_VAR,
|
||||
api: 'openai-completions',
|
||||
baseURL: baseUrl,
|
||||
models: [
|
||||
{
|
||||
id: modelId,
|
||||
name: modelId,
|
||||
...(contextLength !== undefined && Number.isFinite(contextLength) && contextLength > 0
|
||||
? {
|
||||
contextWindow: Math.trunc(contextLength),
|
||||
// A quarter of the window keeps the reply inside the prompt's share; 8192 caps it on a large window.
|
||||
maxTokens: Math.max(1, Math.min(8192, Math.floor(contextLength / 4))),
|
||||
}
|
||||
: {}),
|
||||
},
|
||||
],
|
||||
models: [{ id: modelId, name: modelId, ...modelWindowFields(contextLength) }],
|
||||
},
|
||||
},
|
||||
},
|
||||
@@ -327,6 +330,11 @@ function renderConfigFile(
|
||||
// true` is required too: pi does not automatically send `Authorization: Bearer
|
||||
// <apiKey>` just because `apiKey` is set (per the same doc) — without it, a real
|
||||
// (non-llama.cpp) endpoint that actually checks the key would reject every request.
|
||||
// The model entry carries the endpoint's context window when it is known. Without it pi
|
||||
// takes an unknown model for a 128,000-token one (its footer reads `/128k`) and asks for
|
||||
// 16,384 reply tokens, so on a 65,536 or 32,768 window it never compacts before the
|
||||
// server's real window is full. Measured on pi 1.5.2: with both fields `pi --list-models`
|
||||
// shows the window and the request carries `max_tokens: 8192`.
|
||||
return {
|
||||
content: JSON.stringify(
|
||||
{
|
||||
@@ -336,7 +344,7 @@ function renderConfigFile(
|
||||
apiKey,
|
||||
api: 'openai-completions',
|
||||
authHeader: true,
|
||||
models: [{ id: modelId }],
|
||||
models: [{ id: modelId, ...modelWindowFields(contextLength) }],
|
||||
},
|
||||
},
|
||||
},
|
||||
|
||||
Reference in new issue
Block a user