diff options
Diffstat (limited to 'internal/sandbox/guard.go')
| -rw-r--r-- | internal/sandbox/guard.go | 79 |
1 files changed, 79 insertions, 0 deletions
diff --git a/internal/sandbox/guard.go b/internal/sandbox/guard.go new file mode 100644 index 0000000..03cb964 --- /dev/null +++ b/internal/sandbox/guard.go @@ -0,0 +1,79 @@ +package sandbox + +import ( + "context" + "fmt" +) + +// Hook is a pre-tool-use guardrail check. Implementations inspect a +// proposed run_bash command or write_file path and return a non-nil error +// to reject it; the error's message becomes the human-readable reason +// surfaced back to the model. Hooks are stateless checks — Guarded is +// responsible for turning a rejection into a RejectionError so the +// agentloop can feed it back to the model as ordinary (non-fatal) tool +// content instead of aborting the whole execution. +type Hook interface { + CheckBash(ctx context.Context, command string) error + CheckWrite(ctx context.Context, path string) error +} + +// RejectionError is returned by Guarded.RunBash/WriteFile when a Hook +// rejects the call. internal/agentloop/tools.go specifically recognizes +// this type (via errors.As) and, instead of aborting the run the way an +// ordinary Sandbox error does, feeds Reason back to the model as normal +// tool-result content — a rejected command becomes something the model can +// read and self-correct around, not a crashed execution. +type RejectionError struct { + // Op is the tool that was rejected: "run_bash" or "write_file". + Op string + // Reason is the Hook's error message explaining the rejection. + Reason string +} + +func (e *RejectionError) Error() string { + return fmt.Sprintf("%s rejected by guardrail: %s", e.Op, e.Reason) +} + +// Guarded wraps a Sandbox with a set of Hooks that run before RunBash/ +// WriteFile delegate to the wrapped Sandbox. All other Sandbox methods +// (ReadFile, Glob, GitClone, GitPush, WorkDir, Cleanup) pass straight +// through unchanged — guardrails only gate the two tools capable of taking +// destructive or exfiltrating action (shell execution and file writes). +type Guarded struct { + Sandbox + Hooks []Hook +} + +var _ Sandbox = (*Guarded)(nil) + +// RunBash runs every Hook.CheckBash before delegating to the wrapped +// Sandbox. On rejection it returns a *RejectionError instead of calling the +// wrapped Sandbox at all — the command never executes. +func (g *Guarded) RunBash(ctx context.Context, command string) (stdout, stderr string, exitCode int, err error) { + for _, h := range g.Hooks { + if rejectErr := h.CheckBash(ctx, command); rejectErr != nil { + return "", "", 0, &RejectionError{Op: "run_bash", Reason: rejectErr.Error()} + } + } + return g.Sandbox.RunBash(ctx, command) +} + +// WriteFile runs every Hook.CheckWrite before delegating to the wrapped +// Sandbox. On rejection it returns a *RejectionError instead of calling the +// wrapped Sandbox at all — the file is never written. +func (g *Guarded) WriteFile(ctx context.Context, path, content string) error { + for _, h := range g.Hooks { + if rejectErr := h.CheckWrite(ctx, path); rejectErr != nil { + return &RejectionError{Op: "write_file", Reason: rejectErr.Error()} + } + } + return g.Sandbox.WriteFile(ctx, path, content) +} + +// DefaultHooks returns the standard guardrail hook set applied uniformly to +// every NativeRunner sandbox (Host or Docker) regardless of provider — see +// internal/executor/nativerunner.go. There is no per-role configurability +// yet; that lands with the role/config model in a later phase. +func DefaultHooks() []Hook { + return []Hook{&DenylistBashHook{}, &ProtectedPathHook{}} +} |
