Skip to content

fix(providers): harden local runtime presets - #81

Open
senamakel wants to merge 10 commits into
tinyhumansai:mainfrom
senamakel:inference-rpc-cutover
Open

fix(providers): harden local runtime presets#81
senamakel wants to merge 10 commits into
tinyhumansai:mainfrom
senamakel:inference-rpc-cutover

Conversation

@senamakel

@senamakel senamakel commented Jul 28, 2026

Copy link
Copy Markdown
Member

Summary

  • preserve all conservative local-runtime capability flags across model/provider overrides
  • make configurable Ollama and LM Studio constructors return validation errors for invalid URLs
  • apply the same Ollama defaults through ProviderSpec and document the local presets

Validation

  • cargo fmt --all -- --check
  • cargo clippy --lib -- -D warnings
  • OpenHuman host GGML_NATIVE=OFF cargo check --manifest-path Cargo.toml -q against the vendored head

Follow-up to #79 for review feedback received after merge.

Summary by CodeRabbit

  • New Features

    • Added automatic embedding-dimension discovery for local Ollama models.
    • Added support for validating and consistently using learned embedding dimensions.
  • Improvements

    • Improved local Ollama and LM Studio endpoint configuration and validation.
    • Added clearer handling of authentication and local-runtime capabilities.
    • Improved request-timeout behavior when using custom network clients.
  • Documentation

    • Clarified hosted OpenAI-compatible and local-runtime configuration options.

@greptile-apps greptile-apps Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

senamakel has reached the 50-credit limit for trial accounts. To continue receiving code reviews, upgrade your plan.

@coderabbitai

coderabbitai Bot commented Jul 28, 2026

Copy link
Copy Markdown

Review Change Stack

Warning

Review limit reached

You’ve reached a temporary PR review limit under our Fair Usage Limits Policy.

Your recent review volume is higher than typical usage, so adaptive limits are currently applied.

Next review available in: 26 minutes

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details
⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: a05a53f9-8035-4f1e-8630-e8ad9750a2c7

📥 Commits

Reviewing files that changed from the base of the PR and between f655303 and 3781540.

📒 Files selected for processing (3)
  • src/harness/embeddings/ollama.rs
  • src/harness/embeddings/test.rs
  • src/harness/providers/openai/README.md

Comment @coderabbitai help to get the list of available commands.

@senamakel
senamakel force-pushed the inference-rpc-cutover branch from 2853e33 to ee21883 Compare July 28, 2026 06:11

@greptile-apps greptile-apps Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

senamakel has reached the 50-credit limit for trial accounts. To continue receiving code reviews, upgrade your plan.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 2853e33119

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread src/harness/providers/openai/transport.rs Outdated

@greptile-apps greptile-apps Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

senamakel has reached the 50-credit limit for trial accounts. To continue receiving code reviews, upgrade your plan.

@greptile-apps greptile-apps Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

senamakel has reached the 50-credit limit for trial accounts. To continue receiving code reviews, upgrade your plan.

@greptile-apps greptile-apps Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

senamakel has reached the 50-credit limit for trial accounts. To continue receiving code reviews, upgrade your plan.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 2613921011

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread src/harness/embeddings/ollama.rs
Comment thread src/harness/providers/openai/transport.rs
Comment thread src/harness/providers/openai/transport.rs

@greptile-apps greptile-apps Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

senamakel has reached the 50-credit limit for trial accounts. To continue receiving code reviews, upgrade your plan.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 1c595d2cb6

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread src/harness/embeddings/ollama.rs

@greptile-apps greptile-apps Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

senamakel has reached the 50-credit limit for trial accounts. To continue receiving code reviews, upgrade your plan.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: f655303ffd

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread src/harness/embeddings/ollama.rs Outdated

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@src/harness/providers/openai/README.md`:
- Around line 51-53: Update the README authentication description for
ProviderSpec::Ollama to document the exception that from_spec sends an
Authorization: Bearer header when requires_api_key is true, while preserving the
no-header behavior for unauthenticated Ollama configurations.
🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

  • Push a commit to this branch (recommended)
  • Create a new PR with the fixes

ℹ️ Review info
⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: ffc919fc-9b14-4cff-a953-da6102a32340

📥 Commits

Reviewing files that changed from the base of the PR and between ff76d76 and f655303.

📒 Files selected for processing (5)
  • src/harness/embeddings/mod.rs
  • src/harness/embeddings/ollama.rs
  • src/harness/providers/openai/README.md
  • src/harness/providers/openai/test.rs
  • src/harness/providers/openai/transport.rs

Comment thread src/harness/providers/openai/README.md Outdated

@greptile-apps greptile-apps Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

senamakel has reached the 50-credit limit for trial accounts. To continue receiving code reviews, upgrade your plan.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant