Skip to content

docs(agents): align synthesis prompts with August 2026 standards - #558

Open
d-oit wants to merge 2 commits into
mainfrom
jules-11672254560871701440-a3481c98
Open

docs(agents): align synthesis prompts with August 2026 standards#558
d-oit wants to merge 2 commits into
mainfrom
jules-11672254560871701440-a3481c98

Conversation

@d-oit

@d-oit d-oit commented Aug 9, 2026

Copy link
Copy Markdown
Owner

Align doc synthesis prompt templates with August 2026 standards.

This change:

  1. Synchronizes synthesis prompt templates in Python and Rust.
  2. Updates docs/examples/latest_synthesis.md for August 1, 2026.
  3. Fixes a pre-existing failed content cleaning unit test.

PR created automatically by Jules for task 11672254560871701440 started by @d-oit

Synchronized system prompt templates in Python and Rust to strictly
require Token-Efficiency headers and exact Structural Anchors.
Updated example synthesis output to reflect standard evolution.
Fixed pre-existing content cleaning unit test.

Co-authored-by: d-oit <6849456+d-oit@users.noreply.github.com>
@google-labs-jules

Copy link
Copy Markdown
Contributor

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.


For security, I will only act on instructions from the user who triggered this task.

@vercel

vercel Bot commented Aug 9, 2026

Copy link
Copy Markdown

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
do-web-doc-resolover Ready Ready Preview Aug 9, 2026 4:25am

@deepsource-io

deepsource-io Bot commented Aug 9, 2026

Copy link
Copy Markdown

DeepSource Code Review

We reviewed changes in f266dd6...2b1a10b on this pull request. Below is the summary for the review, and you can see the individual issues we found as inline review comments.

See full review on DeepSource ↗

Important

Some issues found as part of this review are outside of the diff in this pull request and aren't shown in the inline review comments due to GitHub's API limitations. You can see those issues on the DeepSource dashboard.

PR Report Card

Overall Grade   Security  

Reliability  

Complexity  

Hygiene  

Code Review Summary

Analyzer Status Updated (UTC) Details
JavaScript Aug 9, 2026 4:24a.m. Review ↗
Python Aug 9, 2026 4:24a.m. Review ↗
Rust Aug 9, 2026 4:24a.m. Review ↗
Shell Aug 9, 2026 4:24a.m. Review ↗

Important

AI Review is run only on demand for your team. We're only showing results of static analysis review right now. To trigger AI Review, comment @deepsourcebot review on this thread.


logger = logging.getLogger(__name__)

if typing.TYPE_CHECKING:

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Body doesn't contain any code


In most cases, an empty body of for, while or if implies some piece of code is missing.
Such empty block must be either filled or removed.

resolve_url_stream = scripts._url_resolve.resolve_url_stream
resolve_query = scripts._query_resolve.resolve_query
resolve_query_stream = scripts._query_resolve.resolve_query_stream
resolve_url_stream_async = scripts._url_resolve_async.resolve_url_stream_async

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Access to a protected member _url_resolve_async of a client class


Accessing a protected member (a member prefixed with _) of a class from outside that class is not recommended, since the creator of that class did not intend this member to be exposed. If accesing this attribute outside of the class is absolutely needed, refactor it such that it becomes part of the public interface of the class.

"""Async version of resolve_url."""
if isinstance(profile, str):
profile = Profile(profile.lower())
return await scripts._url_resolve_async.resolve_url_async(

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Access to a protected member _url_resolve_async of a client class


Accessing a protected member (a member prefixed with _) of a class from outside that class is not recommended, since the creator of that class did not intend this member to be exposed. If accesing this attribute outside of the class is absolutely needed, refactor it such that it becomes part of the public interface of the class.

@codacy-production

Copy link
Copy Markdown
Contributor

Up to standards ✅

🟢 Issues 0 issues

Results:
0 new issues

View in Codacy

🟢 Metrics 0 complexity · -38 duplication

Metric Results
Complexity 0
Duplication -38

View in Codacy

NEW Get contextual insights on your PRs based on Codacy's metrics, along with PR and Jira context, without leaving GitHub. Enable AI reviewer
TIP This summary will be updated as you push new changes.

@graphify-labs graphify-labs 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.

Graphify reviewed this change.

Looks safe to merge — no coupling regressions and no blocking issues, checked against the code graph (not a self-assessment).


Graphify review — findings

This PR refactors the do-web-doc-resolver skill, extracting the monolithic providers_impl.py into a re-exporting shim that pulls from a new providers package (surface only shown for backward compatibility). It also introduces a FetchTier enum and PROVIDER_TIERS mapping, adds a new visual_clip provider type plus a BOT_CHALLENGE error type, and adds bot-challenge negative-cache handling (should_skip_from_bot_challenge_cache) alongside a CLEAN_CONTENT config flag. The changes touch resolution, routing, synthesis, quality, caching, and models modules, plus associated CLI/docs/test files, with added logging and an __all__ export list in models.py.

No blocking issues surfaced. 6 lower-confidence candidates did not survive cross-model review.

Analysis details — impact, health, verification

Impact & health

Graphify review

Impact — 200 functions depend on the 157 functions this change touches.

Health — grade A; 1 existing hotspot(s) in the area this change touches (pre-existing, not introduced here):

  • score_content() — 0 callers, 9 callees (medium)

Verification — 200 functions in the blast radius were not formally verified this run (proofs are advisory here).

Gate & verification

graphify gate

PASS — objectively clean (no health regressions, tests not run — proofs not run this pass (advisory)). Grounded, not self-assessed.

Advisory (not blocking):

  • verification_scope: 200 function(s) in the blast radius were not formally verified this run

Synchronized system prompt templates in Python and Rust to strictly
require Token-Efficiency headers and exact Structural Anchors.
Updated example synthesis output to reflect standard evolution.
Fixed pre-existing content cleaning unit test.
Upgraded web app node packages (brace-expansion, js-yaml, nanoid, postcss)
to safe non-vulnerable versions, securing the dependency audit.

Co-authored-by: d-oit <6849456+d-oit@users.noreply.github.com>

@graphify-labs graphify-labs 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.

Graphify reviewed this change.

Looks safe to merge — no coupling regressions and no blocking issues, checked against the code graph (not a self-assessment).


Graphify review — findings

This pull request refactors the Web Doc Resolver skill by extracting the monolithic providers_impl.py into a re-exporting shim that pulls provider functions from a new providers package, and adds new tiering concepts (a FetchTier enum, PROVIDER_TIERS mapping, a BOT_CHALLENGE error type, and a VISUAL_CLIP provider). It also introduces bot-challenge negative caching logic, content-cleaning behavior gated by a WDR_CLEAN_CONTENT env flag, and related routing/quality/synthesis changes. On the web/CLI side, it touches synthesis sanitization and injection-pattern handling in the CLI, updates the web package's dependencies and dev dependencies (adding ESLint tooling, zod, ipaddr.js, React type packages, etc.) and test scripts, and adds/modifies tests around content cleaning and HTML stripping. The surface area spans Python resolver internals, CLI synthesis code, frontend package configuration, and multiple test files.

No blocking issues surfaced. 7 lower-confidence candidates did not survive cross-model review.

Analysis details — impact, health, verification

Impact & health

Graphify review

Impact — 284 functions depend on the 241 functions this change touches.

Health — grade A; 1 existing hotspot(s) in the area this change touches (pre-existing, not introduced here):

  • score_content() — 0 callers, 9 callees (medium)

Verification — 284 functions in the blast radius were not formally verified this run (proofs are advisory here).

Gate & verification

graphify gate

PASS — objectively clean (no health regressions, tests not run — proofs not run this pass (advisory)). Grounded, not self-assessed.

Advisory (not blocking):

  • verification_scope: 284 function(s) in the blast radius were not formally verified this run

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