mirror of
https://github.com/Twigpine/zero.git
synced 2026-11-12 16:23:18 -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]>
148 lines
4.4 KiB
Go
148 lines
4.4 KiB
Go
package tools
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"strings"
|
|
"sync"
|
|
)
|
|
|
|
type PlanItem struct {
|
|
ID string
|
|
Content string
|
|
Status string
|
|
Notes string
|
|
}
|
|
|
|
type updatePlanTool struct {
|
|
baseTool
|
|
// mu guards currentPlan: Run() writes it on the agent goroutine while
|
|
// CurrentPlan()/ClearPlan() are called from the TUI goroutine (e.g. /plan).
|
|
mu sync.Mutex
|
|
currentPlan []PlanItem
|
|
}
|
|
|
|
func NewUpdatePlanTool() *updatePlanTool {
|
|
return &updatePlanTool{
|
|
baseTool: baseTool{
|
|
name: "update_plan",
|
|
description: "Create or update the in-memory plan for the current task. " +
|
|
"Pass the full ordered list of steps each call; it replaces the previous plan. " +
|
|
"Each item needs a `content` string; `status` defaults to \"pending\" and `id` is " +
|
|
"auto-numbered, so you only need to supply `content` (and `status` as the task progresses).",
|
|
parameters: Schema{
|
|
Type: "object",
|
|
Properties: map[string]PropertySchema{
|
|
// The item structure (content/status/id) is described textually
|
|
// above. A structured nested-object Items schema is deferred until
|
|
// the agent's PropertySchema serializer (propertyToRuntimeMap)
|
|
// passes nested Properties/Required through to providers; until then
|
|
// a nested schema here would be silently dropped, so keep it flat.
|
|
"plan": {
|
|
Type: "array",
|
|
Description: "Ordered list of plan items, replacing any previous plan. Each item is an object with a required `content` string, an optional `status` (pending|in_progress|completed|failed, defaults to pending), optional `notes`, and an optional `id` (auto-numbered from position when omitted).",
|
|
},
|
|
},
|
|
Required: []string{"plan"},
|
|
AdditionalProperties: false,
|
|
},
|
|
safety: readOnlySafety("Updates in-memory planning state only."),
|
|
},
|
|
}
|
|
}
|
|
|
|
func (tool *updatePlanTool) Run(_ context.Context, args map[string]any) Result {
|
|
plan, err := parsePlanItems(args["plan"])
|
|
if err != nil {
|
|
return errorResult("Error: Invalid arguments for update_plan: " + err.Error())
|
|
}
|
|
tool.mu.Lock()
|
|
tool.currentPlan = plan
|
|
tool.mu.Unlock()
|
|
return okResult(formatPlan(plan))
|
|
}
|
|
|
|
func (tool *updatePlanTool) CurrentPlan() []PlanItem {
|
|
tool.mu.Lock()
|
|
defer tool.mu.Unlock()
|
|
return append([]PlanItem{}, tool.currentPlan...)
|
|
}
|
|
|
|
func (tool *updatePlanTool) ClearPlan() {
|
|
tool.mu.Lock()
|
|
tool.currentPlan = nil
|
|
tool.mu.Unlock()
|
|
}
|
|
|
|
func parsePlanItems(value any) ([]PlanItem, error) {
|
|
items, ok := value.([]any)
|
|
if !ok {
|
|
return nil, fmt.Errorf("plan must be an array")
|
|
}
|
|
|
|
plan := make([]PlanItem, 0, len(items))
|
|
for index, item := range items {
|
|
object, ok := item.(map[string]any)
|
|
if !ok {
|
|
return nil, fmt.Errorf("plan item %d must be an object", index+1)
|
|
}
|
|
|
|
content, err := stringArg(object, "content", "", true)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("plan item %d %s", index+1, err.Error())
|
|
}
|
|
// id is optional: weaker models can't reliably mint stable ids, and the
|
|
// plan is displayed by 1-based position anyway. Auto-number when omitted.
|
|
id, err := stringArgWithEmpty(object, "id", fmt.Sprintf("%d", index+1), false, true)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("plan item %d %s", index+1, err.Error())
|
|
}
|
|
if id == "" {
|
|
id = fmt.Sprintf("%d", index+1)
|
|
}
|
|
// status is optional and defaults to pending.
|
|
status, err := stringArgWithEmpty(object, "status", "pending", false, true)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("plan item %d %s", index+1, err.Error())
|
|
}
|
|
if status == "" {
|
|
status = "pending"
|
|
}
|
|
if !isPlanStatus(status) {
|
|
return nil, fmt.Errorf("plan item %d status must be pending, in_progress, completed, or failed", index+1)
|
|
}
|
|
notes, err := stringArgWithEmpty(object, "notes", "", false, true)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("plan item %d %s", index+1, err.Error())
|
|
}
|
|
|
|
plan = append(plan, PlanItem{
|
|
ID: id,
|
|
Content: content,
|
|
Status: status,
|
|
Notes: notes,
|
|
})
|
|
}
|
|
return plan, nil
|
|
}
|
|
|
|
func isPlanStatus(status string) bool {
|
|
return status == "pending" || status == "in_progress" || status == "completed" || status == "failed"
|
|
}
|
|
|
|
func formatPlan(plan []PlanItem) string {
|
|
if len(plan) == 0 {
|
|
return "Plan is currently empty."
|
|
}
|
|
|
|
lines := make([]string, 0, len(plan))
|
|
for index, item := range plan {
|
|
line := fmt.Sprintf("%d. [%s] %s", index+1, item.Status, item.Content)
|
|
if item.Notes != "" {
|
|
line += "\n Notes: " + item.Notes
|
|
}
|
|
lines = append(lines, line)
|
|
}
|
|
return "Current Plan:\n" + strings.Join(lines, "\n")
|
|
}
|