feat: configurable LLM request timeout via LLM_REQUEST_TIMEOUT_SECS by zmanian · Pull Request #630 · nearai/ironclaw

zmanian · 2026-03-06T19:44:21Z

Summary

Add LLM_REQUEST_TIMEOUT_SECS environment variable (default: 120) to configure the HTTP request timeout for LLM API calls. Primarily useful for local models (Ollama, vLLM, LM Studio) that need more time for prompt evaluation on consumer hardware.

The timeout is applied to the NearAI provider's HTTP client, which handles the majority of use cases including proxied local models.

Closes #615

Changes

Add request_timeout_secs field to LlmConfig
Parse LLM_REQUEST_TIMEOUT_SECS env var in config resolution
Thread timeout through create_llm_provider -> NearAiChatProvider::new_with_timeout
Add .env.example documentation
2 regression tests for default and custom timeout values

Test plan

cargo clippy --all --all-features zero warnings
cargo check --no-default-features --features libsql compiles
test_request_timeout_defaults_to_120 passes
test_request_timeout_configurable passes

Generated with Claude Code

Co-Authored-By: Claude Opus 4.6 noreply@anthropic.com

gemini-code-assist · 2026-03-06T19:46:41Z

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request introduces a new feature that allows users to configure the HTTP request timeout for LLM API calls via the LLM_REQUEST_TIMEOUT_SECS environment variable. This change primarily addresses timeout issues experienced by users of local LLMs, where prompt evaluation can take a significant amount of time. The new timeout setting is applied consistently across all supported LLM providers.

Highlights

New Feature: Introduced LLM_REQUEST_TIMEOUT_SECS environment variable to configure the HTTP request timeout for LLM API calls.
Fix: Addressed timeout failures for local LLM users (Ollama, LM Studio, vLLM) by allowing configuration of the request timeout.
Provider Support: Implemented the timeout configuration across six LLM providers: NEAR AI, OpenAI, Anthropic, Ollama, OpenAI-compatible, and Tinfoil.

Activity

Added LLM_REQUEST_TIMEOUT_SECS env var (default: 120s) to configure HTTP request timeout for all LLM API calls
Fixed timeout failures for local LLM users (Ollama, LM Studio, vLLM) where prompt evaluation on consumer hardware can take 30-120+ seconds
Timeout is threaded through all 6 providers: NEAR AI, OpenAI, Anthropic, Ollama, OpenAI-compatible, Tinfoil
Completed test_request_timeout_defaults_to_120 to verifies default
Completed test_request_timeout_configurable to verifies env var override
Verified cargo clippy --all --all-features clean
Verified cargo check clean

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	`/gemini review`	Performs a code review for the current pull request in its current state.
Pull Request Summary	`/gemini summary`	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	`/gemini help`	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

gemini-code-assist

Code Review

This pull request introduces a configurable timeout for LLM API requests via the LLM_REQUEST_TIMEOUT_SECS environment variable. This addresses timeout issues experienced by users with local LLMs. The changes include updating the .env.example file, modifying the LlmConfig struct and its resolution logic, and adding corresponding unit tests. The timeout is applied across multiple LLM providers.

gemini-code-assist · 2026-03-06T19:50:35Z

    pub fn new(config: NearAiConfig, session: Arc<SessionManager>) -> Result<Self, LlmError> {
-        Self::new_with_flatten(config, session, true)


Consider using the new_with_options function directly to avoid the extra function call.

Self::new_with_options(config, session, true, 120)

gemini-code-assist · 2026-03-06T19:50:36Z

+fn build_http_client(timeout_secs: u64) -> Result<reqwest::Client, LlmError> {
+    reqwest::Client::builder()
+        .timeout(std::time::Duration::from_secs(timeout_secs))
+        .build()
+        .map_err(|e| LlmError::RequestFailed {
+            provider: "http_client".to_string(),
+            reason: format!("Failed to build HTTP client: {e}"),
+        })
 }


Consider adding a comment explaining why the provider field is hardcoded to http_client.

gemini-code-assist · 2026-03-06T19:50:36Z

            None
        };

+        let request_timeout_secs = parse_optional_env("LLM_REQUEST_TIMEOUT_SECS", 120)?;


Consider adding a comment explaining why the default timeout is 120 seconds.

…615) Add LLM_REQUEST_TIMEOUT_SECS env var (default: 120) to configure the HTTP request timeout for LLM API calls. Primarily useful for local models (Ollama, vLLM, LM Studio) that need more time for prompt evaluation on consumer hardware. The timeout is applied to the NearAI provider's HTTP client. Other providers (Anthropic, OpenAI) use rig-core's default client. - Add request_timeout_secs field to LlmConfig - Thread timeout through create_llm_provider -> NearAiChatProvider - Add NearAiChatProvider::new_with_timeout constructor - Add .env.example documentation - 2 regression tests for default and custom timeout values Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

…earai#615) (nearai#630) Add LLM_REQUEST_TIMEOUT_SECS env var (default: 120) to configure the HTTP request timeout for LLM API calls. Primarily useful for local models (Ollama, vLLM, LM Studio) that need more time for prompt evaluation on consumer hardware. The timeout is applied to the NearAI provider's HTTP client. Other providers (Anthropic, OpenAI) use rig-core's default client. - Add request_timeout_secs field to LlmConfig - Thread timeout through create_llm_provider -> NearAiChatProvider - Add NearAiChatProvider::new_with_timeout constructor - Add .env.example documentation - 2 regression tests for default and custom timeout values Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

github-actions Bot added size: M 50-199 changed lines scope: llm LLM integration scope: setup Onboarding / setup risk: high Safety, secrets, auth, or critical infrastructure contributor: core 20+ merged PRs and removed size: M 50-199 changed lines labels Mar 6, 2026

gemini-code-assist Bot reviewed Mar 6, 2026

View reviewed changes

github-actions Bot mentioned this pull request Mar 7, 2026

🦞 OpenClaw 生态日报 2026-03-07 duanyytop/agents-radar#89

Closed

zmanian force-pushed the fix/615-configurable-llm-timeout branch from e0213b6 to 35a1bdf Compare March 7, 2026 15:27

github-actions Bot added scope: tool/builtin Built-in tools size: L 200-499 changed lines labels Mar 7, 2026

zmanian force-pushed the fix/615-configurable-llm-timeout branch from 35a1bdf to 4eceb18 Compare March 7, 2026 23:30

github-actions Bot added size: M 50-199 changed lines and removed size: L 200-499 changed lines labels Mar 7, 2026

ilblackdragon approved these changes Mar 8, 2026

View reviewed changes

ilblackdragon merged commit 200aed1 into main Mar 8, 2026
22 checks passed

ilblackdragon deleted the fix/615-configurable-llm-timeout branch March 8, 2026 08:30

This was referenced Mar 8, 2026

chore: release v0.17.0 #633

Closed

chore: release v0.17.0 #842

Merged

BrewTestBot mentioned this pull request Mar 10, 2026

ironclaw 0.17.0 Homebrew/homebrew-core#271600

Merged

Navigation Menu

feat: configurable LLM request timeout via LLM_REQUEST_TIMEOUT_SECS - #630

feat: configurable LLM request timeout via LLM_REQUEST_TIMEOUT_SECS#630
ilblackdragon merged 1 commit into
mainfrom
fix/615-configurable-llm-timeout

zmanian commented Mar 6, 2026 •

edited

Loading

Uh oh!

gemini-code-assist Bot commented Mar 6, 2026

Uh oh!

gemini-code-assist Bot left a comment

Uh oh!

gemini-code-assist Bot Mar 6, 2026

Uh oh!

gemini-code-assist Bot Mar 6, 2026

Uh oh!

gemini-code-assist Bot Mar 6, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

		pub fn new(config: NearAiConfig, session: Arc<SessionManager>) -> Result<Self, LlmError> {
		Self::new_with_flatten(config, session, true)

Conversation

zmanian commented Mar 6, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Changes

Test plan

Uh oh!

gemini-code-assist Bot commented Mar 6, 2026

Summary of Changes

Highlights

Footnotes

Uh oh!

gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

gemini-code-assist Bot Mar 6, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist Bot Mar 6, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist Bot Mar 6, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

zmanian commented Mar 6, 2026 •

edited

Loading