docs: clarify "primary docker image" error is an LLM backend failure#325
Open
mason5052 wants to merge 2 commits into
Open
docs: clarify "primary docker image" error is an LLM backend failure#325mason5052 wants to merge 2 commits into
mason5052 wants to merge 2 commits into
Conversation
…xcontrol#309) Add a troubleshooting subsection to the Docker Image Configuration section explaining that "failed to select primary docker image via llm call" (older versions: "failed to get primary docker image") is raised when PentAGI's first LLM call fails during image selection, not when Docker or the registry is unhealthy. Points users to PentAGI and LLM backend logs, provider URL/key/model verification, and tool-call parser configuration for custom/OpenAI-compatible/vLLM/sglang backends.
Contributor
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
Adds targeted documentation to help users distinguish LLM-backend failures from Docker/registry issues when flow creation fails during primary image selection.
Changes:
- Documented what the
"failed to select primary docker image via llm call"error usually indicates. - Added diagnostic steps focusing on PentAGI and LLM backend configuration/logs.
- Clarified common misdirection from older PentAGI error wording.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Address review feedback on PR vxcontrol#325: capitalize SGLang to match the project's name and clarify that tool calling and function calling refer to the same capability. Refs vxcontrol#309
7 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Add a troubleshooting subsection to the README "Docker Image Configuration" section clarifying that the
failed to select primary docker image via llm callerror (older versions:failed to get primary docker image) is an LLM backend failure during image selection, not a Docker or registry problem.Refs #309
Problem
On a fresh install, creating a flow can fail immediately with:
The phrase "primary docker image" leads users to debug Docker, the image registry, or pull access even though Docker is healthy. As the maintainer noted on #309 (and on the related #312 and #203), the real cause is the configured LLM backend: PentAGI makes its first LLM call to choose the primary image when a flow starts, so a backend failure (502/404, unreachable endpoint, wrong model, or a missing/mismatched tool-call parser on custom/sglang-style backends) surfaces at this step.
The error string itself was already made more precise in #312 / #320 (
failed to get primary docker image->failed to select primary docker image via llm call). This PR closes the remaining documentation gap so users can act on that clarified message.Solution
Add a short
#### Troubleshootingsubsection under "Docker Image Configuration" that:docker logs pentagi, check the LLM backend logs, verify the provider URL/key/model, and confirm tool-call / function-calling parser support for custom, OpenAI-compatible, vLLM, or sglang backends.Documentation only. No runtime, schema, config, or behavior changes.
User Impact
Users who hit this error can immediately look in the right place (the LLM backend) instead of debugging Docker, reducing time-to-resolution for a recurring fresh-install confusion reported across #309, #312, and #203.
Test Plan
git diff --checkreports no whitespace errors.README.mdis modified (15 insertions).#custom-llm-provider-configurationresolves to the existing "Custom LLM Provider Configuration" heading.