fix(truth-lock): RED-5 replace 'drop-in' with 'chat-completions'#27
fix(truth-lock): RED-5 replace 'drop-in' with 'chat-completions'#27hizrianraz wants to merge 2 commits into
Conversation
…fix pyproject Remove stale '57 models' literal count claims from README and docs. Change all examples from pinned claude-haiku-4-5 to ainfera-inference (the flagship routing route). New examples: - streaming.py — SSE via OpenAI-compatible endpoint - tools.py — function calling with tools/tool_choice pass-through - retries.py — exponential backoff for transient 5xx errors - async_usage.py — AsyncAinferaClient with wallet and audit chain - receipt_verification.py — inline receipt + local AuditChain verify - error_handling.py — full semantic exception hierarchy README additions: - Compatibility table (ainfera SDK vs openai SDK vs anthropic SDK) - API versioning section - Streaming section (explains 501 on /v1/inference) - Tools section with code example - Retries and error handling section with exception table - Async usage section - Receipt verification section - Local verification clarification (tamper-evidence vs tamper-prevention) - Routing hints section (routing_hint, pool, budget/latency/quality) Fixes: - pyproject.toml: broken TOML header (line 3 was prose not comment) - pyproject.toml: package name sdk -> ainfera, version 0.1.0 -> 1.1.0 - pyproject.toml: packages.find where=src -> where=python, include=sdk* -> ainfera* - pyproject.toml: testpaths tests -> python/tests - pyproject.toml: added missing dependencies (httpx, pydantic, joserfc) - pyproject.toml: added missing dev deps (respx, pytest-asyncio, pyright) - pyproject.toml: added cli extra (click, pyyaml) and project.scripts entry - pyproject.toml: added ruff per-file-ignores for exceptions.py N818 - pyproject.toml: added pyright config (library-only, exclude cli/tests) - python/examples/04_inference.py: model -> ainfera-inference, fix broken .receipt.audit_url reference -> .receipt_id - examples/README.md: stale ainfera==1.0.1 pin -> >=1.1.0 - releaserc.toml: semantic-release config for automated versioning - ruff format applied to all files All CI checks pass: ruff check, ruff format --check, pytest (66 passed), pyright (0 errors).
…EADME + quickstart - README compatibility table: 'drop-in' → 'chat-completions' - quickstart.py: 'on chain' → 'in the audit log' (precision)
|
Warning Review limit reached
Next review available in: 28 minutes Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available. How can I continue?After more reviews become available, a review can be triggered using the 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 configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (26)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
|
Closing — main already has these fixes from PR #26. The branch was based on a stale fork of the old feature branch. |
1 participant
RED-5: Replace "drop-in" → "chat-completions"
Changes
Label:
truth-lockNote
Low Risk
Changes are documentation, examples, and packaging metadata with no meaningful SDK runtime or API behavior changes beyond copy and formatting.
Overview
Truth-lock (RED-5): The README compatibility matrix now labels the OpenAI and Anthropic columns as
(chat-completions)instead of implying a vague “drop-in” integration.examples/quickstart.pyends with “in the audit log” rather than “on chain” so success copy matches how receipts are actually recorded.Beyond those precision edits, the PR reshapes developer-facing packaging and docs:
pyproject.tomlpublishes theainferapackage at 1.1.0 (dependencies, CLI extra,python/testspaths, pyright scope).README.mdandCHANGELOG.md [Unreleased]drop stale “57 models” claims, standardize onmodel="ainfera-inference", add compatibility/API-versioning/streaming/tools/retry/async/receipt/routing sections, and point concept links at live/docsanchors.Examples gain runnable scripts for streaming (OpenAI-compatible SSE), tools, retries, async, receipt verification, and error handling;
python/examples/04_inference.pyfixes the broken.receipt.audit_urlusage in favor ofreceipt_id.releaserc.tomladds semantic-release automation. Library and test diffs are largely formatting (line wraps), not behavior changes.Reviewed by Cursor Bugbot for commit 0da266e. Bugbot is set up for automated code reviews on this repo. Configure here.