Skip to content

use a non-reasoning model for session recaps #284

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

Merged
kevinjosethomas merged 2 commits into from
Jun 30, 2026
Merged

use a non-reasoning model for session recaps #284

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f9ba328
use qwen3-30b instruct for session recaps
kevinjosethomas Jun 30, 2026
fa986ab
drop explanatory comment on recap model
kevinjosethomas Jun 30, 2026
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
1 change: 1 addition & 0 deletions packages/ai/scripts/generate-models.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -146,6 +146,7 @@ const PRIME_INFERENCE_MODEL_METADATA: Record<string, PrimeInferenceModelMetadata
"openai/gpt-5.5": { contextWindow: 1050000, maxTokens: 128000, vision: true },
"prime-intellect/intellect-3": { contextWindow: 131072, maxTokens: 131072 },
"qwen/qwen3-235b-a22b-thinking-2507": { contextWindow: 262144, maxTokens: 4096 },
"qwen/qwen3-30b-a3b-instruct-2507": { contextWindow: 262144, maxTokens: 65536 },
"qwen/qwen3-coder-next": { contextWindow: 262144, maxTokens: 65536 },
"qwen/qwen3-max": { contextWindow: 262144, maxTokens: 65536 },
"qwen/qwen3-vl-235b-a22b-thinking": { contextWindow: 262144, maxTokens: 32768, vision: true },
Expand Down
18 changes: 18 additions & 0 deletions packages/ai/src/models.generated.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13169,6 +13169,24 @@ export const MODELS = {
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"qwen/qwen3-30b-a3b-instruct-2507": {
id: "qwen/qwen3-30b-a3b-instruct-2507",
name: "QWEN3 30B A3B Instruct 2507",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
reasoning: false,
input: ["text"],
cost: {
input: 0.2,
output: 0.8,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"qwen/qwen3-coder-next": {
id: "qwen/qwen3-coder-next",
name: "QWEN3 Coder Next",
Expand Down
3 changes: 1 addition & 2 deletions packages/coding-agent/src/modes/daemon/daemon-session-summarizer.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,9 +9,8 @@ const SWEEP_INTERVAL_MS = 25_000;
// Collapse a tool-use loop's rapid turn_end bursts into one summarization.
const SETTLE_DEBOUNCE_MS = 2_000;

// Small self-hosted open-weight model, off the proxied frontier models.
const SUMMARY_MODEL_PROVIDER = "prime-inference";
const SUMMARY_MODEL_ID = "nvidia/nemotron-3-nano-30b-a3b";
const SUMMARY_MODEL_ID = "qwen/qwen3-30b-a3b-instruct-2507";

const SUMMARY_CONTEXT_MESSAGES = 8;
const SUMMARY_MAX_CHARS_PER_MESSAGE = 600;
Expand Down
Loading