b12df1a6366bc50a89395edd0a570ddf7793efcc
2
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 claw
|
cf453504cb |
feat: add native SAP AI Core support
CI / test (pull_request) Successful in 13s
CI / review (/anthropic/v1, claude-sonnet-4-6, sonnet, anthropic, SONNET_REVIEW_TOKEN) (pull_request) Failing after 12s
CI / review (/openai/v1, gpt-4.1, gpt41, openai, GPT_REVIEW_TOKEN) (pull_request) Failing after 12s
CI / review (/openai/v1, gpt-4.1-mini, gpt41-mini, openai, GPT_REVIEW_TOKEN) (pull_request) Failing after 14s
CI / review (/openai/v1, gpt-5-mini, gpt5-mini, openai, GPT_REVIEW_TOKEN) (pull_request) Failing after 11s
CI / review (/openai/v1, gpt-5, security, openai, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 1m12s
CI / review (/openai/v1, gpt-5, gpt, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m28s
Adds a new 'aicore' LLM provider that authenticates directly with SAP AI Core
using OAuth client credentials. This eliminates the need for an external proxy
(hai-aicore or hai) when running review-bot in SAP environments.
Key changes:
- New llm/aicore.go with AICoreClient for OAuth token management and
deployment discovery
- Thread-safe token caching with automatic refresh before expiry
- Automatic routing to /invoke (Anthropic) or /chat/completions (OpenAI)
based on model name
- New CLI flags: --aicore-client-id, --aicore-client-secret, --aicore-auth-url,
--aicore-api-url, --aicore-resource-group
- Updated action.yml with corresponding inputs
- Comprehensive test coverage for AI Core client
Example usage in CI:
llm-provider: aicore
llm-model: anthropic--claude-4.6-sonnet
aicore-client-id: ${{ secrets.AICORE_CLIENT_ID }}
aicore-client-secret: ${{ secrets.AICORE_CLIENT_SECRET }}
aicore-auth-url: ${{ secrets.AICORE_AUTH_URL }}
aicore-api-url: ${{ secrets.AICORE_API_URL }}
Closes #49
|
||
|
claw
|
db479d0ff4 |
fix: retry on transient LLM response body truncation
CI / test (pull_request) Successful in 15s
CI / review (/openai/v1, gpt-4.1, gpt41, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 25s
CI / review (/openai/v1, gpt-4.1-mini, gpt41-mini, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 29s
CI / review (/anthropic/v1, claude-sonnet-4-6, sonnet, anthropic, SONNET_REVIEW_TOKEN) (pull_request) Successful in 49s
CI / review (/openai/v1, gpt-5, security, openai, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 50s
CI / review (/openai/v1, gpt-5, gpt, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m15s
CI / review (/openai/v1, gpt-5-mini, gpt5-mini, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 52s
Addresses intermittent 'unexpected end of JSON input' failures where the LLM response body is truncated in transit between the proxy and client. Root cause: network-level truncation where io.ReadAll returns partial data (observed in 3/50 CI runs through HAI proxy). The response body reading was already using io.ReadAll correctly, but transient network issues between the proxy and client can still cause partial reads. Changes: - Add Content-Length validation in doRequest: detect when fewer bytes arrive than the server declared, triggering a retry - Add retry logic in Complete: retries once on retryable errors (body read failures, content-length mismatches) with a 500ms backoff - Add parse-level retry in main: if ParseResponse fails, re-requests from the LLM once before giving up (defensive, since retries always succeed per issue evidence) - Improve ParseResponse error diagnostics: log raw vs cleaned lengths and a preview of the cleaned content to aid future debugging Does NOT retry on API errors (4xx/5xx) or structural issues — only transient body read problems. Closes #47 |