docs: add DaoXE OpenAI-compatible gateway integration - #2436
Closed
seven7763 wants to merge 3 commits into
Closed
Conversation
Signed-off-by: seven7763 <seven7763@users.noreply.github.com>
Signed-off-by: seven7763 <seven7763@users.noreply.github.com>
Contributor
Author
|
Friendly ping in case this fell off the radar — small docs-only addition showing how to point the OpenAI client at an OpenAI-compatible gateway via |
jxnl
added a commit
that referenced
this pull request
Aug 3, 2026
## Summary - accumulate declared, nested, and unknown numeric OpenAI/Anthropic usage fields across retries while preserving non-numeric metadata - add corrective feedback when a Responses API retry receives no tool call - preserve raw iterable type hints through sync and async v2 parallel-tool wrappers - strengthen API-key-free coverage for current and future SDK usage counters ## Consolidated and superseded items - closes #2493 - consolidates contributor work from #2498, #2500, and #2501 with original commit authorship preserved - supersedes #2497 because it drops unknown `model_extra` counters - supersedes #2499 because its hand-maintained provider field lists would drift as SDKs evolve ## Validation - focused changed-surface suite: `110 passed` - broad offline v2/coverage suite: `2368 passed, 91 skipped, 73 deselected` - Ruff check and format check: passed - scoped `ty check`: passed - `uv lock --check`: passed - pre-commit hooks and `git diff --check`: passed The 73 deselected tests require live provider credentials. An unfiltered local run confirmed its 22 failures were provider network connections in the restricted environment; GitHub provider jobs remain the authoritative validation for those paths. ## Intentionally skipped - provider additions or expansions: #2436, #2435, #2423, #2409, #2384, #2322, #2306, #2298, #2283, #2168, #2086; issues #2408, #2383, #2365, #2260, #2084, #2076 - broad architecture, product, security, or streaming decisions: #2394, #2392, #2357, #2356, #2355, #2351, #2321, #2307, #2287, #2263; issues #2479, #2403, #2393, #2391, #2316, #2272, #2056 - dependency batch: #2433 - nontrivial examples and editorial/resource additions: #2468, #2405, #2401, #2354, #2346, #2311, #2305; issue #2404 These remain open because they need dedicated product, architecture, provider, security, dependency, or editorial review and are not required for the `1.15.5` patch release. <!-- CURSOR_SUMMARY --> --- > [!NOTE] > **Medium Risk** > Changes retry usage totals and reask message content on failure paths; scope is limited and heavily covered by tests, with no auth or data-store changes. > > **Overview** > Bundles three v2 retry and wrapper fixes for a patch release. > > **Retry usage accounting** replaces hand-maintained token field sums with generic `_accumulate_models` on Pydantic usage objects. Numeric fields (including nested models and `model_extra` counters) add across retries; booleans and other non-numeric metadata are not treated as billable. OpenAI and Anthropic paths share this logic. > > **OpenAI Responses reask** appends a user correction when `RESPONSES_TOOLS` validation fails but the output has no tool calls (e.g. reasoning-only), so retries include feedback instead of repeating the same request. > > **Parallel tools** in `patch_v2` skips `prepare_response_model` and does not replace `response_model` with the handler’s prepared wrapper for parallel modes, keeping raw `Iterable[...]` hints so schemas and parsed results include every member type. > > <sup>Reviewed by [Cursor Bugbot](https://cursor.com/bugbot) for commit bbddca1. Configure [here](https://www.cursor.com/dashboard/bugbot).</sup> <!-- /CURSOR_SUMMARY -->
jxnl
added a commit
that referenced
this pull request
Aug 3, 2026
## Summary - update the wheel/sdist repository metadata from the former `instructor-ai` organization to `567-labs/instructor` - make release preparation reject stale repository metadata before artifacts are built or published - include the compact OpenAI-compatible multi-model gateway `base_url` example from #2504 while preserving contributor authorship - document the package metadata correction in the `1.15.5` notes The package metadata defect was found by inspecting the exact wheel produced by the non-publishing readiness run after #2503 merged. ## Included / superseded - includes #2504 as the canonical compact docs update - supersedes the broader DaoXE-specific docs PR #2436 with the generic eight-line example Both source commits remain separately attributed on this branch. ## Validation - release validator tests: 6 passed - Ruff check and format: passed - scoped test type check: passed - release metadata validation for `1.15.5`: passed - `uv lock --check`: passed - pre-commit hooks: passed - wheel and sdist build: passed - Twine metadata checks: passed - built wheel reports `Project-URL: repository, https://github.com/567-labs/instructor` - DaoXE `api.daoxe.com/v1/models` and `daoxe.com/v1/models` endpoints both return the expected authenticated API response - `git diff --check`: passed ## Skipped - no runtime/provider implementation changes - no dependency changes - no tag, release, PyPI publication, or social post <!-- CURSOR_SUMMARY --> --- > [!NOTE] > **Low Risk** > Metadata, release script, docs, and tests only—no library runtime or dependency changes. > > **Overview** > Updates **published package metadata** so `project.urls.repository` points at `567-labs/instructor` instead of the old `instructor-ai` org, and records that fix in the **1.15.5** changelog. > > **Release preparation** now reads that URL from `pyproject.toml` and fails fast with a repository URL mismatch if it still points at the wrong GitHub org, with a test covering the stale-URL case. > > **Docs** add a short `from_provider` example for OpenAI-compatible gateways using `base_url` and a gateway API key (DaoXE as the sample endpoint). > > <sup>Reviewed by [Cursor Bugbot](https://cursor.com/bugbot) for commit 5ff8c87. Configure [here](https://www.cursor.com/dashboard/bugbot).</sup> <!-- /CURSOR_SUMMARY -->
Collaborator
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
2 participants
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
docs/integrations/daoxe.mdfor using Instructor with DaoXE via OpenAI-compatible Chat Completions (https://daoxe.com/v1).Account-scoped model IDs only; multi-protocol context; no static public price table.
I maintain DaoXE. Examples: https://github.com/seven7763/DaoXE-AI