docs: replace deprecated validation_context with context parameter

[devin-ai-integration]

docs: replace deprecated validation_context with context parameter

Summary

Standardized all documentation to use the context= parameter instead of the deprecated validation_context= parameter across 9 documentation files. This includes updating code examples, comments, and prose references throughout the docs to reflect that validation_context has been deprecated in favor of the simpler context parameter name.

Files Updated:

• Core concept docs (hooks.md, patching.md)
• Example tutorials (exact_citations.md, bulk_classification.md, youtube_clips.md)
• Blog posts (validation-part1.md, version-1.md)
• Main documentation (llms.txt)
• Advanced techniques (universal_self_consistency.md)

Review & Testing Checklist for Human

• Test code examples work: Pick 2-3 examples from the updated files and verify they run successfully with context= parameter
• Verify API alignment: Confirm that context= is indeed the current/preferred parameter name in the actual instructor codebase
• Check completeness: Search docs for any remaining validation_context references that might have been missed

Notes

• All changes are documentation-only - no code logic was modified
• Lint checks couldn't be run locally due to environment setup (ruff not available), so CI will handle validation
• This addresses the user request from @jxnl to clean up docs and standardize on context= parameter usage
• Session: https://app.devin.ai/sessions/081e8685573f4c31ba3246a130e2112b
• Requested by: @jxnl

---

Important

Replaces deprecated validation_context with context in documentation across 9 files, updating examples and references.

• Documentation Update:
  • Replaces validation_context with context in 9 documentation files.
  • Updates include code examples, comments, and prose references.
• Files Affected:
  • Core concept docs: hooks.md, patching.md
  • Example tutorials: exact_citations.md, bulk_classification.md, youtube_clips.md
  • Blog posts: validation-part1.md, version-1.md
  • Main documentation: llms.txt
  • Advanced techniques: universal_self_consistency.md
• Misc:
  • All changes are documentation-only; no code logic was modified.

^{This description was created by for 18136bf. You can customize this summary. It will automatically update as commits are pushed.}

[devin-ai-integration]

🤖 Devin AI Engineer

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

• Address comments on this PR. Add '(aside)' to your comment to have me ignore it.
• Look at CI failures and help fix them

Note: I can only respond to comments from users who have write access to this repository.

⚙️ Control Options:

• Disable automatic comment and CI monitoring

[ellipsis-dev]

Caution

Changes requested ❌

Reviewed everything up to 18136bf in 2 minutes and 5 seconds. Click for details.

• Reviewed 183 lines of code in 9 files
• Skipped 0 files when reviewing.
• Skipped posting 10 draft comments. View those below.
• Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.

1. docs/blog/posts/validation-part1.md:410

• Draft comment:
  Good update – replaced validation_context with context in the explanation for how context is passed to validator functions. Changes are clear and consistent.
• Reason this comment was not posted:
  Comment did not seem useful. Confidence is useful = 0% <= threshold 85% This comment is purely informative and does not provide any actionable feedback or suggestions for improvement. It simply acknowledges a change that was made, which violates the rule against making purely informative comments.

2. docs/concepts/hooks.md:15

• Draft comment:
  The hook documentation now correctly mentions the context parameter. Looks clear and consistent.
• Reason this comment was not posted:
  Comment did not seem useful. Confidence is useful = 0% <= threshold 85% This comment is purely informative and does not provide any actionable feedback or suggestions. It simply states that the documentation looks clear and consistent, which is not necessary for the PR author to know.

3. docs/concepts/patching.md:13

• Draft comment:
  Replaced validation_context with context in the list of added parameters – this aligns documentation with current API usage.
• Reason this comment was not posted:
  Comment did not seem useful. Confidence is useful = 0% <= threshold 85% This comment is purely informative, explaining a change made to align documentation with current API usage. It doesn't provide a suggestion, ask for confirmation, or highlight a potential issue. According to the rules, purely informative comments should be removed.

4. docs/examples/bulk_classification.md:173

• Draft comment:
  Good change – all instances of validation_context replaced with context in async classification examples.
• Reason this comment was not posted:
  Comment did not seem useful. Confidence is useful = 0% <= threshold 85% This comment is purely informative, as it just acknowledges a change without providing any actionable feedback or suggestions. It does not align with the rules for useful comments.

5. docs/examples/exact_citations.md:113

• Draft comment:
  Updated the comment and parameter name to use context instead of validation_context. Documentation is now consistent.
• Reason this comment was not posted:
  Comment did not seem useful. Confidence is useful = 0% <= threshold 85% This comment is purely informative, stating that a comment and parameter name were updated for consistency. It doesn't provide any actionable feedback or suggestions for improvement.

6. docs/examples/youtube_clips.md:86

• Draft comment:
  Replaced usage of validation_context with context in the sample call. The change is clear and consistent with other examples.
• Reason this comment was not posted:
  Comment did not seem useful. Confidence is useful = 0% <= threshold 85% This comment is purely informative, stating what was changed without providing any actionable feedback or suggestions. It doesn't ask for confirmation or suggest improvements.

7. docs/llms.txt:885

• Draft comment:
  Updated text and code from using validation_context to context. This helps maintain consistency across documentation.
• Reason this comment was not posted:
  Comment did not seem useful. Confidence is useful = 0% <= threshold 85% This comment is purely informative and does not provide any actionable feedback or suggestions. It simply states what was changed and why, which is not necessary for a code review comment.

8. docs/prompting/ensembling/universal_self_consistency.md:91

• Draft comment:
  The self-consistency example now uses context (e.g., passing number_responses) correctly in the validation. Looks good overall.
• Reason this comment was not posted:
  Comment did not seem useful. Confidence is useful = 0% <= threshold 85% This comment is purely informative and does not provide any actionable feedback or suggestions for improvement. It simply states that the example now uses context correctly, which does not align with the rules provided.

9. docs/blog/posts/validation-part1.md:439

• Draft comment:
  Typographical suggestion: Consider hyphenating "self correct" to "self-correct" for clarity.
• Reason this comment was not posted:
  Comment was on unchanged code.

10. docs/blog/posts/version-1.md:22

• Draft comment:
  Typo: "isntructor" should be corrected to "instructor".
• Reason this comment was not posted:
  Comment was on unchanged code.

Workflow ID: wflow_jHc3stTrligXQfjD

^{You can customize by changing your verbosity settings, reacting with 👍 or 👎, replying to comments, or adding code review rules.}

[ellipsis-dev]

Updated text to refer to context instead of validation_context. Also note a minor typo: "isntructor" should be corrected to "instructor".

Suggested change

Over the past 10 months, we've build up instructor with the [principle](../../why.md) of 'easy to try, and easy to delete'. We accomplished this by patching the openai client with the `instructor` package and adding new arguments like `response_model`, `max_retries`, and `context`. As a result I truly believe isntructor is the [best way](./best_framework.md) to get structured data out of llm apis.

Over the past 10 months, we've build up instructor with the [principle](../../why.md) of 'easy to try, and easy to delete'. We accomplished this by patching the openai client with the `instructor` package and adding new arguments like `response_model`, `max_retries`, and `context`. As a result I truly believe instructor is the [best way](./best_framework.md) to get structured data out of llm apis.

[cloudflare-workers-and-pages]

Deploying with    Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status	Name	Latest Commit	Updated (UTC)
✅ Deployment successful! View logs	instructor	18136bf	Oct 01 2025, 01:48 PM