mirror of
https://github.com/Twigpine/zero.git
synced 2026-11-12 08:41:32 -10:00
* Tools: arg-tolerance, ask_user, secret scrubbing, structured results, hardening First module of the tools->agent->tui chain that leads to the TUI shell (off main). Scope: internal/tools (+ a 1-line specialist vocabulary update). 3-way merged onto main's specialist drift (RunOptions tool-context fields, Safety.AdvertiseInAuto, optionsAwareTool dispatch, PropertySchema, base structured Result) and grafted the runtime-core additions: - Shared arg-tolerance layer (argtolerance.go: alias-aware/type-strict arg resolution + slice coercion) adopted across all tools so weak models' non-canonical arg shapes are accepted; bool/int coercion in args.go. - ask_user tool (interactive clarifying questions) wired into CoreReadOnlyTools; nested PropertySchema (Properties/Required) for its object questions + update_plan. - Secret scrubbing at the registry boundary (scrubResultSecrets via internal/redaction) applied to every tool-execution path, incl. the optionsAwareTool dispatch; structured Result (Display/Redacted/ChangedFiles). - mutation_targets (paths a mutating tool will write, for session checkpointing) + hardened grep (symlink confinement), apply_patch, bash, edit/write. EXCLUDED per the module split: the blueprint task tool (subagents — another dev's area; the merged specialist Task is separate) and the skill tool (ships with the later skills module); plus their subagent-only registry helpers (Without/isolateForChild). ask_user is now a core tool, so internal/specialist knownToolNames adds "ask_user" to keep the TestKnownToolNamesMatchCoreRegistry cross-package invariant. No new deps; build/vet/-race/windows/full-suite green. Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]> * Address #119 review (CodeRabbit): scrub Display, validate apply_patch mutation paths, narrow test skips - registry.go: scrubResultSecrets now redacts Result.Display.Summary too (not just Output), so a caller preferring Display can't bypass the boundary redaction. - mutation_targets.go: apply_patch targets now run through validatePatchPaths(applyRoot, ...) before being returned, so a traversal patch (../x) can't yield an out-of-workspace checkpoint target. Regression case added to TestMutationTargetsRejectsEscapingPaths. - argtolerance_test/write_tools_test: the apply_patch tests no longer Skipf on ANY non-OK result (which masked real diff/apply regressions); they skip ONLY when the git binary is unavailable (gitApplyUnavailable helper checks exec's 'executable file not found') and otherwise Fatalf. build/vet/-race/full-suite + GOOS=windows build green. Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]> * Address #119 re-review (CodeRabbit): best-effort multiSelect + Display.Summary scrub coverage - ask_user: an uncoercible multiSelect no longer fails the whole call — it's a UI hint, so it defaults to false (best-effort, mirroring the lenient options path). Test: TestParseAskUserQuestionsLenientOptions extended. - registry_test: TestRunWithOptionsScrubsSecretsForAllCallers now also leaks a secret via Result.Display.Summary and asserts it is redacted, locking in the boundary scrub for the structured-result path (secretTool gained a display field). build/vet/-race/full-suite + GOOS=windows build green. Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]> * Address #119 review (@Vasanthdev2004): scrub ALL registry return paths + harden intArg [blocker] RunWithOptions now scrubs every return path, not just tool-execution: a named return + a single 'defer scrubResultSecrets(result)' covers the unknown-tool, sandbox-deny, sandbox-approval-required, permission-required and permission-denied early returns too. Previously a sandbox denial that echoed a secret-bearing path/arg returned it raw with Redacted=false. Regression: TestRunWithOptionsScrubsSecretsOnDenialPaths (permission-denied reason carrying a token -> scrubbed + Redacted). [non-blocking] intArg fails closed on NaN/Inf/out-of-range floats (and their string forms) via a floatToInt helper, before any implementation-defined cast. Tests added for NaN/Inf/NaN-string/non-integral. build/vet/-race/full-suite + GOOS=windows build green. Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]> * Address #119 review (CodeRabbit grep TOCTOU + anandh8x dependency blockers) - grep: close the confinement TOCTOU — confineGrepFile now returns the symlink-RESOLVED path and collectGrepMatches reads THAT (not the raw candidate), so a symlink swapped in between check and read can't escape the workspace. - ask_user: removed from CoreReadOnlyTools. It needs the agent loop's interactive intercept (OnAskUser), which is in the (unmerged) agent module; without it the tool only returns the non-interactive fallback. The tool still ships (NewAskUserTool); the agent module registers it in core + wires the intercept together. Reverted the specialist knownToolNames 'ask_user' entry + the ask_user-in-core test accordingly. - update_plan: reverted the plan schema to a flat array (item structure documented in the description). The structured nested-object Items schema depends on the agent's PropertySchema serializer (propertyToRuntimeMap) passing nested Properties/Required through to providers, which is in the agent module; a nested schema here would be silently dropped. PropertySchema.Properties/Required fields are kept (used by ask_user.go's own schema + the later MCP module). build/vet/-race/full-suite + GOOS=windows build green; no new deps. Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]> * Harden #119 from adversarial self-review: sandbox alias-gate, Meta scrub, intArg 2^63 A multi-dimension adversarial review of the tools diff surfaced 3 real issues beyond the reviewer rounds: - [major/security] write_file/edit_file path aliases file_path/filename/filepath bypassed the sandbox workspace+symlink gate: sandbox.requestPaths only inspected path/cwd/file/dir, so an aliased target skipped enforcement (same class as audit H4). Aligned requestPaths with the tools' path-alias lists (internal/sandbox/risk.go). The tools' own resolveWorkspaceTargetPath still confined, but the sandbox LAYER/audit/symlink-check was silently skipped. Regression: TestRegistrySandboxGatesPathAliasKeys. - [minor] scrubResultSecrets skipped Result.Meta, which is forwarded to the transcript and carries model-controlled strings (glob pattern, bash cwd). Now scrubs Meta values too. Covered in TestRunWithOptionsScrubsSecretsForAllCallers. - [minor] floatToInt used f > float64(MaxInt); that constant rounds up to 2^63 so exactly 2^63 slipped to an out-of-range cast. Changed to >=. Test added for 2^63 float+string. build/vet/-race/full-suite + GOOS=windows build green; no new deps. Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]> --------- Co-authored-by: KRATOS <[email protected]> Co-authored-by: Claude Opus 4.8 (1M context) <[email protected]>
134 lines
3.4 KiB
Go
134 lines
3.4 KiB
Go
package tools
|
|
|
|
import (
|
|
"fmt"
|
|
"math"
|
|
"strconv"
|
|
"strings"
|
|
)
|
|
|
|
func stringArg(args map[string]any, key string, fallback string, required bool) (string, error) {
|
|
return stringArgWithEmpty(args, key, fallback, required, false)
|
|
}
|
|
|
|
func stringArgWithEmpty(args map[string]any, key string, fallback string, required bool, allowEmpty bool) (string, error) {
|
|
value, ok := args[key]
|
|
if !ok || value == nil {
|
|
if required {
|
|
return "", fmt.Errorf("%s is required", key)
|
|
}
|
|
return fallback, nil
|
|
}
|
|
|
|
text, ok := value.(string)
|
|
if !ok {
|
|
return "", fmt.Errorf("%s must be a string", key)
|
|
}
|
|
if !allowEmpty && text == "" {
|
|
return "", fmt.Errorf("%s must be a non-empty string", key)
|
|
}
|
|
return text, nil
|
|
}
|
|
|
|
// boolArg reads a boolean argument, tolerating the string/number forms models
|
|
// commonly emit ("true"/"false", "yes"/"no", "on"/"off", 1/0) since not every
|
|
// model sends a JSON boolean.
|
|
func boolArg(args map[string]any, key string, fallback bool) (bool, error) {
|
|
value, ok := args[key]
|
|
if !ok || value == nil {
|
|
return fallback, nil
|
|
}
|
|
|
|
switch typed := value.(type) {
|
|
case bool:
|
|
return typed, nil
|
|
case string:
|
|
switch strings.ToLower(strings.TrimSpace(typed)) {
|
|
case "true", "yes", "on", "1":
|
|
return true, nil
|
|
case "false", "no", "off", "0":
|
|
return false, nil
|
|
}
|
|
case float64:
|
|
if typed == 1 {
|
|
return true, nil
|
|
}
|
|
if typed == 0 {
|
|
return false, nil
|
|
}
|
|
case int:
|
|
if typed == 1 {
|
|
return true, nil
|
|
}
|
|
if typed == 0 {
|
|
return false, nil
|
|
}
|
|
}
|
|
return false, fmt.Errorf("%s must be a boolean", key)
|
|
}
|
|
|
|
// floatToInt converts a float to int only when it is finite, integral, and in
|
|
// range; NaN/Inf/non-integer/out-of-range return ok=false so callers fail closed
|
|
// before an implementation-defined cast.
|
|
func floatToInt(f float64) (int, bool) {
|
|
// Use >= against float64(math.MaxInt): that constant rounds UP to 2^63, so a
|
|
// strict > would let exactly 2^63 through to an out-of-range int(f) cast. The
|
|
// largest representable in-range float (2^63-1024) is still < it, so nothing
|
|
// valid is excluded. MinInt (-2^63) is exactly representable, so > is correct there.
|
|
if math.IsNaN(f) || math.IsInf(f, 0) || math.Trunc(f) != f || f >= float64(math.MaxInt) || f < float64(math.MinInt) {
|
|
return 0, false
|
|
}
|
|
return int(f), true
|
|
}
|
|
|
|
func intArg(args map[string]any, key string, fallback int, min int, max int) (int, error) {
|
|
value, ok := args[key]
|
|
if !ok || value == nil {
|
|
return fallback, nil
|
|
}
|
|
|
|
var number int
|
|
switch typed := value.(type) {
|
|
case int:
|
|
number = typed
|
|
case int32:
|
|
number = int(typed)
|
|
case int64:
|
|
number = int(typed)
|
|
case float64:
|
|
n, ok := floatToInt(typed)
|
|
if !ok {
|
|
return 0, fmt.Errorf("%s must be an integer", key)
|
|
}
|
|
number = n
|
|
case string:
|
|
// Some models send numbers as strings ("5"); accept whole numbers.
|
|
trimmed := strings.TrimSpace(typed)
|
|
if parsed, perr := strconv.Atoi(trimmed); perr == nil {
|
|
number = parsed
|
|
} else if f, ferr := strconv.ParseFloat(trimmed, 64); ferr == nil {
|
|
n, ok := floatToInt(f)
|
|
if !ok {
|
|
return 0, fmt.Errorf("%s must be an integer", key)
|
|
}
|
|
number = n
|
|
} else {
|
|
return 0, fmt.Errorf("%s must be an integer", key)
|
|
}
|
|
default:
|
|
return 0, fmt.Errorf("%s must be an integer", key)
|
|
}
|
|
|
|
if number < min {
|
|
return 0, fmt.Errorf("%s must be at least %d", key, min)
|
|
}
|
|
if max > 0 && number > max {
|
|
return 0, fmt.Errorf("%s must be at most %d", key, max)
|
|
}
|
|
return number, nil
|
|
}
|
|
|
|
func intPtr(value int) *int {
|
|
return &value
|
|
}
|