Google ADK Python / AI Coding Tools

Google ADK Python LoadSkillResourceTool Infinite Retry Loop Consumes Call Budget

Fix Google ADK Python LoadSkillResourceTool retry loop consuming entire call budget on RESOURCE_NOT_FOUND Includes evidence for Google ADK Python troubleshooting demand.

Source-backed Last updated May 12, 2026 1 source Needs local verification

Category: AI Coding Tools
Error signature: RESOURCE_NOT_FOUND — LoadSkillResourceTool retries indefinitely until max_llm_calls (default 500) exhausted
Quick fix: Compare the failing environment with a known working setup, then change one configuration value at a time.
Updated: May 12, 2026
Verification status: Source-backed
Evidence: 1 public source URL

Before you change production

This page includes public source URLs in the imported troubleshooting record. Compare those references with your version and environment before applying changes.

Reproduce the smallest failing action and save non-secret logs before changing configuration.
Check versions for Google ADK Python, related SDKs, package managers, CI runners, and hosting providers.
Change one setting or dependency at a time, then rerun the same failing command or request.
Avoid destructive commands, credential rotation, billing changes, or security relaxations without a rollback plan.

What this error means

RESOURCE_NOT_FOUND — LoadSkillResourceTool retries indefinitely until max_llm_calls (default 500) exhausted is a Google ADK Python failure pattern reported for developers trying to fix google adk python loadskillresourcetool retry loop consuming entire call budget on resource_not_found. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

GitHub issue #5652 reports LoadSkillResourceTool returning RESOURCE_NOT_FOUND as structured soft-error, causing LLM to retry same path until RunConfig.max_llm_calls (default 500) is exhausted. Single hallucinated path silently consumes entire per-invocation call budget.

Common causes

When an LLM passes a hallucinated path to LoadSkillResourceTool in Google ADK Python, the tool returns RESOURCE_NOT_FOUND as a soft-error string. The LLM treats this as recoverable and retries indefinitely until max_llm_calls (default 500) is exhausted — silently consuming the entire call budget on a single failing tool.
GitHub issue #5652 reports LoadSkillResourceTool returning RESOURCE_NOT_FOUND as structured soft-error, causing LLM to retry same path until RunConfig.max_llm_calls (default 500) is exhausted. Single hallucinated path silently consumes entire per-invocation call budget.

Quick fixes

Confirm the exact error signature matches RESOURCE_NOT_FOUND — LoadSkillResourceTool retries indefinitely until max_llm_calls (default 500) exhausted.
Check the Google ADK Python account, local tool state, and provider configuration involved in the failing workflow.
Compare the failing environment with a known working setup, then change one configuration value at a time.

Platform/tool-specific checks

Verify the command, editor, extension, or API client that produced the error.
Compare local settings with CI, deployment, or editor-level settings when the error appears in only one environment.
Avoid deleting credentials, local model data, or project settings until the failing scope is clear.

Step-by-step troubleshooting

Capture the exact error message and the command, editor action, or request that triggered it.
Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
Review the source evidence below and compare it with your environment.
Apply one change at a time and rerun the smallest failing action.
Keep the working fix documented for the team or deployment environment.

How to prevent it

Keep provider/tool configuration documented.
Record non-secret diagnostics such as tool version, provider name, model name, and command path.
Add a lightweight check before CI or production workflows depend on the tool.

Diagnostic flow for this page

Match RESOURCE_NOT_FOUND — LoadSkillResourceTool retries indefinitely until max_llm_calls (default 500) exhausted exactly before applying the quick fix.
Compare the failing environment with Google ADK Python versions, account scope, provider settings, and deployment context.
Check the listed common causes in order, starting with the cause that best matches your logs.
Use the evidence status below to decide whether to confirm against public sources or official documentation.
Apply one reversible change, rerun the smallest failing action, and keep rollback notes.

FAQ

What does RESOURCE_NOT_FOUND — LoadSkillResourceTool retries indefinitely until max_llm_calls (default 500) exhausted mean in Google ADK Python?

RESOURCE_NOT_FOUND — LoadSkillResourceTool retries indefinitely until max_llm_calls (default 500) exhausted indicates the workflow described by "Google ADK Python LoadSkillResourceTool Infinite Retry Loop Consumes Call Budget" failed in a AI Coding Tools context. Start by confirming the exact signature and the component that emitted it.

What should I check first for RESOURCE_NOT_FOUND — LoadSkillResourceTool retries indefinitely until max_llm_calls (default 500) exhausted?

Check whether this cause matches your environment: When an LLM passes a hallucinated path to LoadSkillResourceTool in Google ADK Python, the tool returns RESOURCE_NOT_FOUND as a soft-error string. The LLM treats this as recoverable and retries indefinitely until max_llm_calls (default 500) is exhausted — silently consuming the entire call budget on a single failing tool.

Is the RESOURCE_NOT_FOUND — LoadSkillResourceTool retries indefinitely until max_llm_calls (default 500) exhausted guidance source-backed?

The "Google ADK Python LoadSkillResourceTool Infinite Retry Loop Consumes Call Budget" page is labeled source-backed. It has 1 public source URL from github.com, so use that evidence status when deciding how much additional verification you need.

When should I avoid the quick fix for RESOURCE_NOT_FOUND — LoadSkillResourceTool retries indefinitely until max_llm_calls (default 500) exhausted?

For "Google ADK Python LoadSkillResourceTool Infinite Retry Loop Consumes Call Budget", avoid applying "Compare the failing environment with a known working setup, then change one configuration value at a time." when the error text differs, the affected version or provider is different, or the change would touch credentials, billing, DNS, production deploy settings, or irreversible data.

What should I collect before debugging RESOURCE_NOT_FOUND — LoadSkillResourceTool retries indefinitely until max_llm_calls (default 500) exhausted?

For "Google ADK Python LoadSkillResourceTool Infinite Retry Loop Consumes Call Budget", collect the failing Google ADK Python command or request, non-secret configuration, versions, timestamps, request IDs when available, and the smallest reproduction that still triggers the signature.