(MOT-4497) feat(fp,web,workflow,sandbox-code-runner,scrapling): opt-in guidance injection via configuration entries, hot-applied - #822
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
Warning Review limit reached
Next review available in: 9 minutes Limit details: You’ve used all 1 included review currently available under your plan. You've used all free OSS reviews for now. Wait for the free limit to reset to keep reviewing this public repository. 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: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: ⛔ Files ignored due to path filters (6)
📒 Files selected for processing (58)
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 |
Contributor
skill-check — worker0 verified, 61 skipped (no docs/).
Four for four. Nicely done. |
andersonleal
force-pushed
the
fix/token-usage-non-harness
branch
from
August 17, 2026 19:25
c7eade6 to
c7d3569
Compare
andersonleal
force-pushed
the
fix/token-usage-non-harness
branch
from
August 17, 2026 19:30
c7d3569 to
8d58c8b
Compare
…injection via configuration entries, hot-applied Move each worker's system-prompt usage guidance behind an inject_guidance knob (ON by default) in its builtin-configuration entry: flipping it binds or unbinds the pre-generate hook live, no restart, shrinking agent prompts when the guidance is not wanted. The non-harness half of the token-usage work. The config plumbing all five share lives in the new crates/config-client (iii-sdk range dep, the console-ui precedent): retry ladder with a NOT_FOUND fast-path, seed-only-when-nothing-stored (configuration::register REPLACES the stored value whenever initial_value is supplied, so the pre-check is load-bearing), case-SENSITIVE NOT_FOUND so an absent config plane never reads as "nothing stored yet", serialized reloads with the fetch inside the lock, and a post-bind boot refresh closing the fetch->bind gap; scrapling mirrors the same semantics in Python. All five treat the config path as best-effort at boot — warn and run on defaults rather than taking the worker's real surface off the bus (docs/sops/configuration.md now documents the cosmetic-knob exception). Also in this change: - sandbox-code-runner seeds on-config-change + ui-content into the claims registry (seeded_ids, the code-runner pattern), closing a boot window where a guest register_function could claim a late-registered worker id and abort the process via the SDK's duplicate-id panic. - sandbox-code-runner's dead custom console form is removed (it predated the entry and would have hidden the knob behind stale timeout fields); the console's schema-generated form renders the entry, and the README documents it. - fp ships no injected UI for its one boolean; the fp/ui package, build.rs, and src/ui.rs are gone and the schema form serves the knob. - llm-router resolves composite "provider::model" ids (the console display form) at the choke points: catalog queries retry an exact miss via the split pair with supports delegating to get, and chat/route/count_tokens split known-provider composites before dispatch — metadata and routing can never disagree about the same id. Rebased over the provider-lifecycle hardening (#812): availability checks run against the split pair. - workflow's stamp-reply and inject-guidance hook responses are typed structs (the interface publish gate refuses AnyValue response schemas); inject-guidance also adopts fp's rule of preserving the harness prompt on an empty/drifted base instead of replacing it with guidance alone, and stamp-reply's no-op answers an explicit continue (parsed identically to the old null). - provider-llamacpp, github-copilot, kimi, and openrouter tag their router-ready handlers internal, keeping the default engine::functions::list free of provider plumbing; the four providers' lockfiles are regenerated so the per-worker --locked gates resolve. - rust-security-audit audits every changed lockfile with a full fetch: the old --no-fetch on later iterations made each lockfile after the first fail its yanked lookups against a half-warmed index; the workflow-convention test pinning the old flag is updated, and the audit's first real catch on these lockfiles — quinn-proto RUSTSEC-2026-0185 in the kimi and web locks — is patched by a lock-only bump. - '!<worker>::on-config-change' denies for all five workers (web and workflow were missing theirs too) and configuration dependencies in the fp / sandbox-code-runner / workflow / scrapling manifests.
andersonleal
force-pushed
the
fix/token-usage-non-harness
branch
from
August 18, 2026 17:31
8d58c8b to
d2c1973
Compare
andersonleal
changed the title
…kit lockfile with post-release provider versions
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
1 participant
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.
Non-harness half of the token-usage work: each worker's system-prompt usage guidance moves behind an
inject_guidanceknob (ON by default) in its builtin-configurationentry. Flipping it in the console (schema form) or viaconfiguration::setbinds/unbinds the worker'spre-generatehook live — no restart — cutting the injected guidance out of every generation when it isn't wanted.What's here
crates/config-client— shared plumbing for the knob workers (fp, web, workflow, sandbox-code-runner; scrapling mirrors it in Python): retry ladder with aNOT_FOUNDfast-path, seed-only-when-nothing-stored (configuration::registerREPLACES the stored value wheneverinitial_valueis supplied, so the pre-check is load-bearing), case-SENSITIVENOT_FOUNDso an absent config plane never reads as "nothing stored yet", serialized reloads (fetch inside the lock), and a post-bind boot refresh closing the fetch→bind gap.seeded_ids()reserveson-config-change+ui-contentin the claims registry before any guest-facing surface is live, closing a boot window where a guestregister_functioncould claim a late-registered worker id and abort the process via the SDK's duplicate-id panic. The dead custom config form (pre-dating the entry, showing stale timeout fields) is removed so the console's schema form renders the knob; README documents the entry.provider::modelids (the console display form) resolve consistently everywhere — catalog queries retry an exact miss via the split pair (supportsdelegates toget, so they can never disagree), andchat/route/count_tokenssplit known-provider composites before dispatch. Metadata and routing can no longer disagree about the same id.internal, keeping the defaultengine::functions::listfree of provider plumbing.!<worker>::on-config-changedenies for all five workers (web and workflow were missing theirs too);configurationdependency declared in the fp / sandbox-code-runner / workflow / scrapling manifests.Verification
Per-worker
cargo fmt+clippy --all-features --all-targetsclean and tests green: fp 58, sandbox-code-runner 175 (+ 275 ui vitest, cleantsc), web 102, workflow 137, llm-router 158 (incl. engine-backed integration), the three tagged providers, and the new crate. Scrapling: ruff clean, configuration/guidance suites pass (the rest of its suite needs the real scrapling/browser deps and is unchanged here). Rebased onto main over #812's provider-lifecycle hardening — the merged routing keeps both the availability semantics and the composite resolution, re-verified post-merge.