chore(main): release 0.5.0 (#96)

🤖 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).

docs(mcp/skills): add validation steps to hillclimb skill

feat(evaluate): populate gcp_project_id in llmrater config (#90)

Extracts the GCP project ID from tools.yaml parameters to correctly
populate the gcp_project_id field in the generated LLM rater
configuration for Evalbench.

feat(mcp): update evalbench version to 1.4.0 (#83)

chore(mcp): bump evalbench version to 1.3.1 (#79)

feat(mcp): adopt ADC support for Cloud SQL and AlloyDB (#78)

chore(main): release 0.4.3 (#53)

🤖 I have created a release *beep* *boop*
---


##
[0.4.3](v0.4.2...v0.4.3)
(2026-04-02)


### Features

* add Spanner and CloudSQL support to value search generation
([#50](#50))
([5a56582](5a56582))
* **value-search:** extend support to Spanner, MySQL, and Postgres
([5a56582](5a56582))


### Bug Fixes

* **build:** disable strip and upx to resolve windows pyinstaller crash
([#52](#52))
([e07c52b](e07c52b))

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).

Co-authored-by: release-please[bot] <55107282+release-please[bot]@users.noreply.github.com>

feat: add Spanner and CloudSQL support to value search generation (#50)

feat(value-search): extend support to Spanner, MySQL, and Postgres

This PR expands the value search generation feature to support
additional database engines.

Changes included:
* Added support for Google SQL (Spanner)
* Added support for Cloud SQL (MySQL and PostgreSQL)
* Updated the prompt workflow to dynamically infer the database engine 
* Added engine-specific parameters and SQL match templates

Previously, this feature was only supported for AlloyDB.

Merge remote-tracking branch 'upstream' into feature/value-index-quer…

…ies-v2-patch

fix(build): disable strip and upx to resolve windows pyinstaller crash (

#52)