feat(mcp): add autoctx-hillclimb workflow skill and tools#59
Merged
wangauone merged 6 commits intofeat/hill-climbingfrom Apr 2, 2026
Merged
feat(mcp): add autoctx-hillclimb workflow skill and tools#59wangauone merged 6 commits intofeat/hill-climbingfrom
wangauone merged 6 commits intofeat/hill-climbingfrom
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces a hill-climbing refinement workflow for ContextSets, including a new configuration file, a detailed workflow guide in SKILL.md, and a mutate_context_set tool in mcp/main.py. The feedback focuses on improving the robustness of the new tool by ensuring the documentation provides a complete schema example for template additions and adding a type check to verify that the input mutations JSON is a list before processing.
helloeve
reviewed
Apr 1, 2026
Base automatically changed from
feat/autoctx-evaluate-workflow
to
feat/hill-climbing
April 1, 2026 20:07
wangauone
force-pushed
the
feat/autoctx-hillclimb-workflow
branch
from
df07fbf to
d1e51af
Compare
wangauone
force-pushed
the
feat/autoctx-hillclimb-workflow
branch
from
7b0d976 to
fdd2735
Compare
wangauone
force-pushed
the
feat/autoctx-hillclimb-workflow
branch
from
fdd2735 to
2dcd77e
Compare
helloeve
approved these changes
Apr 2, 2026
wangauone
added a commit
that referenced
this pull request
Apr 21, 2026
🤖 I have created a release *beep* *boop* --- ## [0.5.0](v0.4.3...v0.5.0) (2026-04-21) ### Features * **autoctx:** introduce automated context generation ([#95](#95)) ([57f8aa7](57f8aa7)) * **bootstrap:** enrich workflow with user-provided docs and code ([#70](#70)) ([04c8455](04c8455)) * **bootstrap:** enrich workflow with user-provided docs and code ([#72](#72)) ([bd04743](bd04743)) * **evaluate:** add custom runner configs to lower evalbench parallelism ([#65](#65)) ([f0758fa](f0758fa)) * **evaluate:** populate gcp_project_id in llmrater config ([#90](#90)) ([016af70](016af70)) * **evaluate:** simplify golden dataset format and write configs dire… ([#68](#68)) ([a76b4bb](a76b4bb)) * **evaluate:** support llm rater configuration in evalbench generator ([#64](#64)) ([d181b82](d181b82)) * **evaluate:** unify failure reporting and add execution errors ([#80](#80)) ([c11ff47](c11ff47)) * **evaluate:** use gemini-2.5-pro for evaluation rater ([#67](#67)) ([5c8f92d](5c8f92d)) * **facet:** enforce qualified table names in prompts ([#85](#85)) ([b37480f](b37480f)) * **hillclimb:** support eval result reading tool ([#69](#69)) ([bb5a249](bb5a249)) * **mcp:** add autoctx-hillclimb workflow skill and tools ([#59](#59)) ([2236964](2236964)) * **mcp:** adopt ADC support for Cloud SQL and AlloyDB ([#78](#78)) ([f4091fa](f4091fa)) * **mcp:** centralize Gemini model configuration ([#73](#73)) ([97c5c25](97c5c25)) * **mcp:** migrate autoctx infrastructure to autoctx/ folder ([#92](#92)) ([0b4f52d](0b4f52d)) * **mcp:** switch default model to gemini-2.5-flash ([#93](#93)) ([60800e5](60800e5)) * **mcp:** update evalbench version to 1.4.0 ([#83](#83)) ([0b4ffb3](0b4ffb3)) * **skills:** update bootstrap skill to include upload URL ([#77](#77)) ([fd65bff](fd65bff)) ### Miscellaneous Chores * force release version 0.5.0 ([da04e7c](da04e7c)) * force release version 0.5.0 ([#97](#97)) ([82364d6](82364d6)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please).
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.
This PR introduces the autoctx-hillclimb workflow, enabling systematic, iterative refinement of context sets based on evaluation metrics. It adds a guided skill document, a CLI trigger, and a structured mutation tool to automate workspace validation, gap analysis, and context mutations.
Key Changes:
SKILL.md):[EntityError],[GoldenDataError]) and report format for capturing fails for all failed queries.mutate_context_set): Exposed a specialized MCP tool to programmatically update context JSON files without manual JSON editing (prevents JSON schema corruption).hillclimb.toml): Added definitions to trigger the workflow viagemini run hillclimb.