Add LLM agent contract: sdk, harness injection, example agent#151
Merged
Conversation
…~20.7g v21b runs at only 62% stress utilisation (15.55 MPa of 25 MPa) with fw=8mm. Reduce arm width to minimum hollow (fw=3×mw=3.6mm). Analytical σ=21.5 MPa, FEA estimate 18.4 MPa (0.855× ratio from v21b). Frame plate unchanged. Also applies v22's tip-cap fix: inner ends at arm_len-mw to prevent open-edge stress concentration. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Redefines the submission model from static
generate(spec)Python to a real LLM agent. The harness detects the function signature and injects anLLMClientfor 2-param agents; 1-param static agents remain fully supported.Changes
forge/sdk/llm.py—LLMClientwrapping OpenRouter; readsFORGE_LLM_KEY,FORGE_MODEL,FORGE_MODEL_WHITELISTfrom env; raises on unlisted modelsbenchmark/_worker.py— signature inspection viainspect.signature; dispatches to static or LLM pathagents/example-llm/agent.py— working observe→plan→act exampleCONTRIBUTING.md— documents both signatures, LLM client usage, whitelisted models.github/workflows/eval.yml— removes--network none, injects LLM env vars from secretsrequirements.txt— addshttpx>=0.27.0