Skip to content

fix: allow configuring Ollama context size via OLLAMA_NUM_CTX env var #1088

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
octo-patch wants to merge 1 commit into
base: master
Choose a base branch
from
+9 −2
Open

fix: allow configuring Ollama context size via OLLAMA_NUM_CTX env var #1088

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 9 additions & 2 deletions src/lib/models/providers/ollama/ollamaLLM.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,11 @@ type OllamaConfig = {
options?: GenerateOptions;
};

const DEFAULT_OLLAMA_NUM_CTX = 32000;
const numCtx = process.env.OLLAMA_NUM_CTX
? parseInt(process.env.OLLAMA_NUM_CTX, 10)
Copy link
Copy Markdown
Contributor

@cubic-dev-ai cubic-dev-ai bot Apr 2, 2026 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2: OLLAMA_NUM_CTX parsing lacks validation; non-numeric truthy values produce NaN, which is then sent as num_ctx for all Ollama calls.

Prompt for AI agents 
Check if this issue is valid — if so, understand the root cause and fix it. At src/lib/models/providers/ollama/ollamaLLM.ts, line 24:

<comment>`OLLAMA_NUM_CTX` parsing lacks validation; non-numeric truthy values produce `NaN`, which is then sent as `num_ctx` for all Ollama calls.</comment>

<file context>
@@ -19,6 +19,11 @@ type OllamaConfig = {
 
+const DEFAULT_OLLAMA_NUM_CTX = 32000;
+const numCtx = process.env.OLLAMA_NUM_CTX
+  ? parseInt(process.env.OLLAMA_NUM_CTX, 10)
+  : DEFAULT_OLLAMA_NUM_CTX;
+
</file context>
Fix with Cubic

: DEFAULT_OLLAMA_NUM_CTX;

const reasoningModels = [
'gpt-oss',
'deepseek-r1',
Expand Down Expand Up @@ -94,7 +99,7 @@ class OllamaLLM extends BaseLLM<OllamaConfig> {
temperature:
input.options?.temperature ?? this.config.options?.temperature ?? 0.7,
num_predict: input.options?.maxTokens ?? this.config.options?.maxTokens,
num_ctx: 32000,
num_ctx: numCtx,
frequency_penalty:
input.options?.frequencyPenalty ??
this.config.options?.frequencyPenalty,
Expand Down Expand Up @@ -148,7 +153,7 @@ class OllamaLLM extends BaseLLM<OllamaConfig> {
top_p: input.options?.topP ?? this.config.options?.topP,
temperature:
input.options?.temperature ?? this.config.options?.temperature ?? 0.7,
num_ctx: 32000,
num_ctx: numCtx,
num_predict: input.options?.maxTokens ?? this.config.options?.maxTokens,
frequency_penalty:
input.options?.frequencyPenalty ??
Expand Down Expand Up @@ -195,6 +200,7 @@ class OllamaLLM extends BaseLLM<OllamaConfig> {
top_p: input.options?.topP ?? this.config.options?.topP,
temperature:
input.options?.temperature ?? this.config.options?.temperature ?? 0.7,
num_ctx: numCtx,
num_predict: input.options?.maxTokens ?? this.config.options?.maxTokens,
frequency_penalty:
input.options?.frequencyPenalty ??
Expand Down Expand Up @@ -235,6 +241,7 @@ class OllamaLLM extends BaseLLM<OllamaConfig> {
top_p: input.options?.topP ?? this.config.options?.topP,
temperature:
input.options?.temperature ?? this.config.options?.temperature ?? 0.7,
num_ctx: numCtx,
num_predict: input.options?.maxTokens ?? this.config.options?.maxTokens,
frequency_penalty:
input.options?.frequencyPenalty ??
Expand Down