Spaces:
Runtime error
Runtime error
Commit History
-
lint and use logger
Uanderson Silva01d948e -
update theagent to work with docker
Tales-Cunha2a70ee5
-
Merge branch 'dev' of github.com:uandersonricardo/projeto-talp1 into teste_agent
Tales-Cunhae682a3d -
refactor: remove old files
Tales-Cunha8bf5d01
-
docs: Add detailed ARCHITECTURE.md and clean up repository
Tales-Cunhaff2afe2
-
feat: refactor tester agent to PoCo LangGraph architecture and add synthetic benchmark
Tales-Cunha017c628
-
Fix: change the agent
Tales-Cunhaa23bb47
-
feat: update the agent structure
Tales-Cunha52550fd
-
docs: create tester architecture definition
Tales-Cunha- Created Definicao_Agente_Tester.md mapping the 4 phases of the Tester (Oracle, Analyze, Generate, Run) mimicking the Auditor's PDF structure. - Also includes the previous uncommitted production gap fixes (mapFinding context pass, customSandboxDir, reduced max iterations).4e2e30e
-
feat: smart patch, dep stubs, progress log, docker fix
Tales-CunhaBenchmark improvements (Run 3: 27.3% -> 54.5% reproducibility): - applyPatchSmart: fix critical patch application bug (specificity was 0%) Previously cp -rv copied wrong directory level, patch was never applied Now strips 1-3 path prefix levels to match files correctly - computePatchDiff: correct diff using same strip-depth matching logic - dependencyStubber.ts: pre-forge probe creates stubs for missing deps Targets 7 failing cases using lib/caviar or node_modules imports - projectContextExtractor.ts: BFS test file selection + remappings context - compileFailures counter + MINIMAL_INTERFACE escape at 3 failures - Patch diff shown in analyzeVulnerabilityNode for specific assertions - Improved prompts: reentrancy receive() pattern, unchecked return pattern - Error lines surfaced in fix prompt for faster compiler error resolution Docker / integration: - setup-sandbox.sh: source ~/.foundry/env for non-interactive shells Fixes case 046 (forge not in PATH in Docker) Fallback: chec…c01b9cd
-
feat: update the archtecture from the testet agent
Tales-CunhaI add new prompts and new structure. I also add the benchmark to evaluate the agent through time and change. I am using the same model7e26449
-
create new frontend interface
Uanderson Silvafc99222
-
unify logs under custom logger
Uanderson Silva48c7a9b
-
fix: sandbox script and prompts
Tales-Cunha7e6051f -
fix: use createllm
Tales-Cunha22ad395 -
fix: revert the changes from the auditor agent and update the poc agent
Tales-Cunhad26fc11
-
feat: integrate the agents
Tales-Cunha3f143e9 -
feat(tester): implement PoC generator with DeepSeek and Foundry loop
Tales-Cunha5710d63
-
docs: add readme and change the foundryRunner
Tales-Cunha2eb19c1 -
tests: add e2e test for the agent
Tales-Cunha0579f2b -
feat: Validated Implementation with Centrifuge Case
Tales-CunhaSYSTEM_PROMPT: Updated with expert guidelines (explainability, quality, iterative refinement)086d1ff
-
feat: Implementar `scaffoldGenerator` and Implementar `oracleNode`
Tales-Cunha6389903 -
feat: Criar nodes stub e grafo linear
Tales-Cunha69b971b
-
implement base agents
Uanderson Silvab6cd280