ci: retrigger after LLM_BASE_URL secret fix

fix: redesign repairJSON to handle all reviewer-reported edge cases
Rewrites the JSON repair algorithm to address two correctness bugs identified in code review: 1. Interior quoted word before comma: "say "yes", and go" was misidentified as structural close because "," followed the quote. 2. JSON-shaped content in strings: {"key": "val"} inside a string value was being parsed as actual JSON structure. The new approach: - Distinguishes keys from values (only values need repair) - Uses first-valid-candidate scan with deep lookahead - Verifies that after a candidate close, the continuation is not just a structural char but a complete valid JSON pattern - Validates keyword tokens (true/false/null) fully, not just first char - Checks container closes recursively for valid continuation Adds comprehensive tests for all reported edge cases plus a complex combined scenario with nested JSON-like content, quoted words before commas, and multiple failure modes in one string.
2026-05-04 23:15:08 -07:00 · 2026-05-04 21:27:39 -07:00 · 2026-05-03 09:47:22 -07:00
1 changed files with 2 additions and 24 deletions
@@ -28,33 +28,12 @@ jobs:
        include:
          - name: sonnet
            token_secret: SONNET_REVIEW_TOKEN
-            provider: anthropic
+            model: gpt-5
            llm_path: /anthropic/v1
            model: claude-sonnet-4-6
          - name: gpt
            token_secret: GPT_REVIEW_TOKEN
            provider: openai
            llm_path: /openai/v1
            model: gpt-5
          - name: gpt41
            token_secret: GPT_REVIEW_TOKEN
            provider: openai
            llm_path: /openai/v1
            model: gpt-4.1
          - name: gpt5-mini
            token_secret: GPT_REVIEW_TOKEN
            provider: openai
            llm_path: /openai/v1
            model: gpt-5-mini
          - name: gpt41-mini
            token_secret: GPT_REVIEW_TOKEN
            provider: openai
            llm_path: /openai/v1
            model: gpt-4.1-mini
          - name: security
            token_secret: SECURITY_REVIEW_TOKEN
            provider: openai
            llm_path: /openai/v1
            model: gpt-5
            system_prompt_file: SECURITY_REVIEW.md
    steps:
@@ -70,10 +49,9 @@ jobs:
          PR_NUMBER: ${{ github.event.pull_request.number }}
          REVIEWER_TOKEN: ${{ secrets[matrix.token_secret] }}
          REVIEWER_NAME: ${{ matrix.name }}
-          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}${{ matrix.llm_path }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
          LLM_MODEL: ${{ matrix.model }}
          LLM_PROVIDER: ${{ matrix.provider }}
          CONVENTIONS_FILE: "CONVENTIONS.md"
          PATTERNS_REPO: "rodin/go-patterns"
          PATTERNS_FILES: "README.md,patterns/"
Author	SHA1	Message	Date
Rodin	489457c184	ci: retrigger after LLM_BASE_URL secret fix CI / test (pull_request) Successful in 13s Details CI / review (gpt-4.1, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 20s Details CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m27s Details CI / review (gpt-5, security, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 1m52s Details	2026-05-04 23:15:08 -07:00
Rodin	25d1a670bf	fix: redesign repairJSON to handle all reviewer-reported edge cases CI / test (pull_request) Successful in 11s Details CI / review (gpt-4.1, gpt, GPT_REVIEW_TOKEN) (pull_request) Failing after 10s Details CI / review (gpt-5, security, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Failing after 10s Details CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Failing after 11s Details Rewrites the JSON repair algorithm to address two correctness bugs identified in code review: 1. Interior quoted word before comma: "say "yes", and go" was misidentified as structural close because "," followed the quote. 2. JSON-shaped content in strings: {"key": "val"} inside a string value was being parsed as actual JSON structure. The new approach: - Distinguishes keys from values (only values need repair) - Uses first-valid-candidate scan with deep lookahead - Verifies that after a candidate close, the continuation is not just a structural char but a complete valid JSON pattern - Validates keyword tokens (true/false/null) fully, not just first char - Checks container closes recursively for valid continuation Adds comprehensive tests for all reported edge cases plus a complex combined scenario with nested JSON-like content, quoted words before commas, and multiple failure modes in one string.	2026-05-04 21:27:39 -07:00
Rodin	80a9a7675b	fix: repair unescaped quotes in LLM JSON responses CI / test (pull_request) Successful in 13s Details CI / review (gpt-5, security, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Failing after 13s Details CI / review (gpt-4.1, gpt, GPT_REVIEW_TOKEN) (pull_request) Failing after 13s Details CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Failing after 12s Details LLMs (especially Sonnet) sometimes emit JSON with unescaped double quotes inside string values, e.g. (e.g. "28") instead of properly escaping them. This caused parse failures in CI. Add a repairJSON fallback that uses a character-by-character scanner to identify interior quotes (those not followed by structural JSON characters) and escape them before retrying the parse. Fixes sonnet-review failures on gargoyle PR #551.	2026-05-03 09:47:22 -07:00