Skip to content

feat(hunt): add trace-aware hunting (grounding, propagation, get_trace enrichment) #222

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
jithin23-kv wants to merge 4 commits into
base: master
Choose a base branch
from
Open

feat(hunt): add trace-aware hunting (grounding, propagation, get_trace enrichment) #222

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
9b3ee9e
feat(hunt): add trace-aware hunting (grounding, propagation, get_trac…
jithin23-kv Jul 28, 2026
6be453c
fix(hunt): address coderabbit review findings on trace-aware hunting
jithin23-kv Jul 28, 2026
9e57e99
fix(hunt): warn on unrecognized telemetry fields instead of ignoring …
jithin23-kv Jul 28, 2026
935705c
fix(hunt): use own-property key checks, report explicitly-null telemetry
jithin23-kv Jul 28, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions AGENTS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ Opfor is an open-source red-teaming toolkit for AI agents and MCP servers. It ge
opfor/
├── core/ # @keyvaluesystems/agent-opfor-core — shared engine (npm workspace, compiled to core/dist/)
│ └── src/
│ ├── autonomous/ # Autonomous red-teaming orchestration (orchestrator, prompts, tools, state, report, knowledge)
│ ├── autonomous/ # Autonomous red-teaming orchestration (orchestrator, prompts, tools, state, report, knowledge). Optional trace-aware testing lives in lib/telemetry.ts (grounding + per-thread trace-id propagation + finding/get_trace enrichment), reusing core/src/telemetry/
│ ├── catalog/ # discoverEvaluators.ts, loadCatalog.ts — YAML evaluator/suite discovery
│ ├── config/ # types.ts, schema.ts (Zod), evaluatorsLayout.ts, skillsLayout.ts, resolveTelemetryEnv.ts, loadPrompt.ts
│ ├── execute/ # Run orchestration: runAll.ts (thin orchestrator) → evaluatorLoop.ts → attackRunner.ts (Template Method) + agentAttackDriver.ts/mcpAttackDriver.ts; plus aggregate.ts, baselineScanner.ts, runListener.ts, runAllBrowser.ts, types.ts
Expand Down Expand Up @@ -212,7 +212,7 @@ npm test # vitest in core/
| `runners/cli/src/index.ts` | CLI entrypoint — registers `setup`, `run`, and `hunt` |
| `runners/cli/src/commands/setup.ts` | Interactive wizard; emits `.opfor/configs/opfor-config-<ts>-<id>.json`; supports `--agent/--mcp/--empty` |
| `runners/cli/src/commands/run.ts` | `opfor run` — reads `--config` (or runs the setup wizard inline when omitted), calls `runAll`, then `writeReport`. Overrides: `--effort`/`--turns`/`--output`/`--env`; `--events <path>` streams NDJSON lifecycle events. |
| `runners/cli/src/commands/hunt.ts` | `opfor hunt` — autonomous red-teaming; agentic commander/operator/scout architecture; `--ui` flag for browser setup UI |
| `runners/cli/src/commands/hunt.ts` | `opfor hunt` — autonomous red-teaming; agentic commander/operator/scout architecture; `--ui` flag for browser setup UI; optional trace-aware testing via `--telemetry-config` (or a `telemetry` block in `--target-config`) |
| `runners/cli/src/lib/artifacts.ts` | `.opfor/configs/` + `.opfor/reports/` path helpers (`newConfigPath()`, `ensureOpforDirs()`) |
| `runners/mcp/src/index.ts` | MCP server: registers `opfor_list_evaluators`, `opfor_setup`, `opfor_run` tools |
| `runners/extension/service_worker.js` | Extension entry point — message routing; imports from focused ES modules |
Expand Down
17 changes: 17 additions & 0 deletions core/src/autonomous/lib/models.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
// Model-alias resolution shared across the autonomous runner (self_check verifier,
// trace-curation model, …). Maps short aliases to full Anthropic ids, honoring the
// ANTHROPIC_DEFAULT_*_MODEL gateway overrides.

/** Resolve a model alias to a full Anthropic API model id, respecting gateway env-var overrides. */
export function resolveModelId(model: string): string {
switch (model) {
case "opus":
return process.env.ANTHROPIC_DEFAULT_OPUS_MODEL ?? "claude-opus-4-8";
case "sonnet":
return process.env.ANTHROPIC_DEFAULT_SONNET_MODEL ?? "claude-sonnet-4-6";
case "haiku":
return process.env.ANTHROPIC_DEFAULT_HAIKU_MODEL ?? "claude-haiku-4-5-20251001";
default:
return model; // assume a full id was provided
}
}
Loading
Loading