mirror of
https://github.com/Twigpine/zero.git
synced 2026-11-08 01:09:46 -10:00
Compare commits
11
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
7c55a09c07 | ||
|
|
d99f92b81a | ||
|
|
5aa54fe1d2 | ||
|
|
f912f80d00 | ||
|
|
9c4e3693e7 | ||
|
|
63962081cf | ||
|
|
2e10a4b60b | ||
|
|
4247a07aba | ||
|
|
b837448dd4 | ||
|
|
a0b036a3c7 | ||
|
|
164150633a |
No files matched your search
@@ -1 +1 @@
|
||||
{".":"0.11.0"}
|
||||
{".":"0.12.0"}
|
||||
@@ -6,6 +6,30 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
|
||||
aims to follow [Semantic Versioning](https://semver.org/spec/v2.0.0.html) once the first release is
|
||||
tagged. Until then, source builds report the version `dev`.
|
||||
|
||||
## [0.12.0](https://github.com/Twigpine/zero/compare/v0.11.0...v0.12.0) (2026-11-02)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* **providers:** add MiniMax-M3.1-Flash to catalog ([#1180](https://github.com/Twigpine/zero/issues/1180)) ([d99f92b](https://github.com/Twigpine/zero/commit/d99f92b81a671f186cede81614c89b8e8a7f9451))
|
||||
* **sandbox:** support self-exec pattern to eliminate separate helper binary ([#946](https://github.com/Twigpine/zero/issues/946)) ([8c4e759](https://github.com/Twigpine/zero/commit/8c4e7597989ef9b3ca67b7703dfd15d92372aed2))
|
||||
* **skills:** install a skill's bundled files and point the skill tool at them ([#1167](https://github.com/Twigpine/zero/issues/1167)) ([1641506](https://github.com/Twigpine/zero/commit/164150633a8b2e6ae864ae02fd7105b201eeb68e))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* **agent:** mark headless guardrail stops incomplete ([#1182](https://github.com/Twigpine/zero/issues/1182)) ([5aa54fe](https://github.com/Twigpine/zero/commit/5aa54fe1d2b419c9bbef73605a77919c9007cf7b))
|
||||
* bump Go to 1.26.10 for GO-2026-6809 ([#1168](https://github.com/Twigpine/zero/issues/1168)) ([6393a90](https://github.com/Twigpine/zero/commit/6393a90ed618a3536e09c02852f4ec829b97545b))
|
||||
* **chatgpt:** refresh subscription defaults and compatibility version ([#1179](https://github.com/Twigpine/zero/issues/1179)) ([f912f80](https://github.com/Twigpine/zero/commit/f912f80d002602e11ba0ef8548ecee58442874aa))
|
||||
* **deps:** refresh the lockfile to hono 4.13.13 ([#1171](https://github.com/Twigpine/zero/issues/1171)) ([de1443b](https://github.com/Twigpine/zero/commit/de1443b2edb44fd3747cc77200d54dc8cffcd0a7))
|
||||
* **oauth:** reuse the crash-safe secret store and sync encrypted publications ([#1165](https://github.com/Twigpine/zero/issues/1165)) ([84c1b15](https://github.com/Twigpine/zero/commit/84c1b1554076679a342e9cac61f8f8cdbaf3a429))
|
||||
* **redaction:** redact credentials whose trigger a greedy span swallowed ([#1158](https://github.com/Twigpine/zero/issues/1158)) ([a97db88](https://github.com/Twigpine/zero/commit/a97db8832fdba077f2d31bdf03ecef8d7c774fe1))
|
||||
* **sessions:** capture freeform apply_patch checkpoints ([#1183](https://github.com/Twigpine/zero/issues/1183)) ([6396208](https://github.com/Twigpine/zero/commit/63962081cf130c2171407936ce3beb7021d238b8))
|
||||
* **sessions:** preserve image attachment summaries on resume ([#1152](https://github.com/Twigpine/zero/issues/1152)) ([1e84849](https://github.com/Twigpine/zero/commit/1e848492e5c1919d187fb5e1eb5e7ef9bc6140dc)), closes [#1135](https://github.com/Twigpine/zero/issues/1135)
|
||||
* **tools:** grep stops where a file's line breaks stop ([#1160](https://github.com/Twigpine/zero/issues/1160)) ([aa9ba84](https://github.com/Twigpine/zero/commit/aa9ba8412eb8917daa2ca5cb3fdbd0a39276fa88))
|
||||
* **workspaceindex:** import gitsafe under the Twigpine module path ([#1153](https://github.com/Twigpine/zero/issues/1153)) ([ef4da13](https://github.com/Twigpine/zero/commit/ef4da1323f1097863ae278224b5f304c2fff909a))
|
||||
* **workspaceindex:** run Scan's git calls through gitsafe ([#1149](https://github.com/Twigpine/zero/issues/1149)) ([2ffe183](https://github.com/Twigpine/zero/commit/2ffe1831b0950b1463ec46d487d03a5fcb679cc6))
|
||||
|
||||
## [0.11.0](https://github.com/Twigpine/zero/compare/v0.10.0...v0.11.0) (2026-10-15)
|
||||
|
||||
|
||||
|
||||
@@ -15,6 +15,7 @@
|
||||
<img alt="Go 1.26.10+" src="https://img.shields.io/badge/Go-1.26.10+-00ADD8?logo=go&logoColor=white">
|
||||
<img alt="25+ providers" src="https://img.shields.io/badge/providers-25+-34E2EA">
|
||||
<a href="https://discord.gg/CaQDS6wdFn"><img alt="Discord" src="https://img.shields.io/badge/Discord-join-5865F2?logo=discord&logoColor=white"></a>
|
||||
<a href="https://vercel.com/open-source-program"><img alt="Vercel OSS Program" src="https://vercel.com/oss/program-badge-2026.svg"></a>
|
||||
<br>
|
||||
<strong>English</strong> | <a href="README_ZH.md">中文</a>
|
||||
</p>
|
||||
@@ -87,9 +88,18 @@ zero exec --output-format stream-json < turns.jsonl
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td align="center" width="150" height="80">
|
||||
<a href="https://vercel.com/">
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="docs/assets/vercel-logo-dark.svg">
|
||||
<img src="docs/assets/vercel-logo.svg" alt="Vercel logo" width="120">
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center"><a href="https://www.gmicloud.ai/"><strong>GMI Cloud</strong></a></td>
|
||||
<td align="center"><a href="https://vercel.com/"><strong>Vercel</strong></a></td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
|
||||
@@ -15,6 +15,7 @@
|
||||
<img alt="Go 1.26.10+" src="https://img.shields.io/badge/Go-1.26.10+-00ADD8?logo=go&logoColor=white">
|
||||
<img alt="25+ providers" src="https://img.shields.io/badge/providers-25+-34E2EA">
|
||||
<a href="https://discord.gg/CaQDS6wdFn"><img alt="Discord" src="https://img.shields.io/badge/Discord-join-5865F2?logo=discord&logoColor=white"></a>
|
||||
<a href="https://vercel.com/open-source-program"><img alt="Vercel OSS Program" src="https://vercel.com/oss/program-badge-2026.svg"></a>
|
||||
<br>
|
||||
<a href="README.md">English</a> | <strong>中文</strong>
|
||||
</p>
|
||||
@@ -85,9 +86,18 @@ zero exec --output-format stream-json < turns.jsonl
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
<td align="center" width="150" height="80">
|
||||
<a href="https://vercel.com/">
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="docs/assets/vercel-logo-dark.svg">
|
||||
<img src="docs/assets/vercel-logo.svg" alt="Vercel logo" width="120">
|
||||
</picture>
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center"><a href="https://www.gmicloud.ai/"><strong>GMI Cloud</strong></a></td>
|
||||
<td align="center"><a href="https://vercel.com/"><strong>Vercel</strong></a></td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
|
||||
@@ -110,6 +110,8 @@ Discovery roots (earlier wins on name collisions):
|
||||
|
||||
A missing directory is fine — Zero just omits it. Management commands (`zero skill add` / `zero skill remove`) always write to the primary Zero dir only; `list` / `info` search primary + `~/.agents/skills`. `skill info` reports lock source/hash when present and whether the on-disk `SKILL.md` has drifted from the recorded hash.
|
||||
|
||||
For a skill installed since Zero started installing bundled files, `skill info` also reports drift in any file installed with it.
|
||||
|
||||
```text
|
||||
~/.local/share/zero/skills/ # primary (install/remove target)
|
||||
run-benchmarks/
|
||||
@@ -140,6 +142,15 @@ Only `name` and `description` are recognized in the frontmatter today. The `name
|
||||
|
||||
The `skill` tool lets the agent load any discovered skill by name (primary, agents, or plugin).
|
||||
|
||||
A skill can ship files beside its `SKILL.md`, in the [agentskills.io](https://agentskills.io/specification) layout: `scripts/`, `references/`, `assets/` or anything else the instructions refer to. `zero skill add` installs the whole skill directory, leaving out hidden entries such as `.git` and not following or copying symlinks (it lists any it skipped). A skill larger than 1,000 files or 32 MiB is refused. When the `skill` tool loads a skill that has such files, its output ends with the skill's directory and a list of the files, so instructions like "run `scripts/fill.py`" can be followed. Running a bundled script goes through the normal tool permissions; installing or loading a skill never runs anything.
|
||||
|
||||
```text
|
||||
pdf/
|
||||
SKILL.md
|
||||
scripts/fill.py
|
||||
references/form-fields.md
|
||||
```
|
||||
|
||||
## 4. Hooks
|
||||
|
||||
Hooks fire shell commands on lifecycle events. Configure them in JSON:
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
<svg xmlns="http://www.w3.org/2000/svg" width="261" height="52" fill="none" viewBox="0 0 261 52"><path fill="white" d="M59.8 52H0L29.9 0zm67.82-38.45q4.9 0 8.81 2.13a15.5 15.5 0 0 1 6.22 6.32q2.3 4.2 2.38 10.26v2.06h-26.35q.27 4.4 2.58 6.92 2.38 2.47 6.36 2.47a8.4 8.4 0 0 0 7.76-4.93l9.16.67q-1.68 4.98-6.29 7.99t-10.63 3q-5.53 0-9.64-2.27a16 16 0 0 1-6.43-6.46 20 20 0 0 1-2.31-9.72q0-5.52 2.3-9.72a16 16 0 0 1 6.44-6.46 20 20 0 0 1 9.64-2.26m62.55 0q4.47 0 8.18 1.66a15.3 15.3 0 0 1 6.15 4.6q2.38 3 2.87 7.05l-9.23.47a8 8 0 0 0-2.8-5 7.7 7.7 0 0 0-5.17-1.86q-4.33 0-6.7 3-2.4 3-2.39 8.52t2.38 8.52q2.37 3 6.71 3 3.15 0 5.39-1.87 2.24-1.92 2.72-5.46l9.3.4a14.7 14.7 0 0 1-2.87 7.33 16 16 0 0 1-6.15 4.86 21 21 0 0 1-8.39 1.66q-5.53 0-9.64-2.26a16 16 0 0 1-6.44-6.46 20 20 0 0 1-2.3-9.72q0-5.52 2.3-9.72a16 16 0 0 1 6.44-6.46 20 20 0 0 1 9.64-2.26m38.66 0q4.9 0 8.8 2.13a15.5 15.5 0 0 1 6.22 6.32q2.31 4.2 2.38 10.26v2.06h-26.35q.28 4.4 2.58 6.92 2.38 2.47 6.36 2.47a8.4 8.4 0 0 0 7.77-4.93l9.15.67q-1.68 5-6.29 7.99t-10.62 3q-5.53 0-9.65-2.27a16 16 0 0 1-6.43-6.46 20 20 0 0 1-2.31-9.72q0-5.52 2.3-9.72a16 16 0 0 1 6.44-6.46 20 20 0 0 1 9.64-2.26M86.9 36.69l17.24-34.33h10.8L89.96 49.63h-6.12L58.85 2.36h10.81zm71.62-15.55a11 11 0 0 1 2.47-4.48q2.28-2.31 6.38-2.31h3.4v7.26h-3.47q-2.91 0-4.79.8a5.8 5.8 0 0 0-2.77 2.5q-.9 1.72-.9 4.37v20.35h-8.89V14.35h8.33zm101.73 28.5h-8.95V2.35h8.95zM127.62 20.26q-3.7 0-6 2.2-2.32 2.2-2.87 6.2h17.05q-.48-4.34-2.72-6.33a7.8 7.8 0 0 0-5.46-2.07m101.2 0q-3.7 0-6 2.2-2.31 2.2-2.87 6.2H237q-.5-4.34-2.73-6.33a7.8 7.8 0 0 0-5.46-2.07" style="fill:white;fill-opacity:1;"/></svg>
|
||||
|
After Width: | Height: | Size: 1.6 KiB |
@@ -0,0 +1 @@
|
||||
<svg xmlns="http://www.w3.org/2000/svg" width="261" height="52" fill="none" viewBox="0 0 261 52"><path fill="black" d="M59.8 52H0L29.9 0zm67.82-38.45q4.9 0 8.81 2.13a15.5 15.5 0 0 1 6.22 6.32q2.3 4.2 2.38 10.26v2.06h-26.35q.27 4.4 2.58 6.92 2.38 2.47 6.36 2.47a8.4 8.4 0 0 0 7.76-4.93l9.16.67q-1.68 4.98-6.29 7.99t-10.63 3q-5.53 0-9.64-2.27a16 16 0 0 1-6.43-6.46 20 20 0 0 1-2.31-9.72q0-5.52 2.3-9.72a16 16 0 0 1 6.44-6.46 20 20 0 0 1 9.64-2.26m62.55 0q4.47 0 8.18 1.66a15.3 15.3 0 0 1 6.15 4.6q2.38 3 2.87 7.05l-9.23.47a8 8 0 0 0-2.8-5 7.7 7.7 0 0 0-5.17-1.86q-4.33 0-6.7 3-2.4 3-2.39 8.52t2.38 8.52q2.37 3 6.71 3 3.15 0 5.39-1.87 2.24-1.92 2.72-5.46l9.3.4a14.7 14.7 0 0 1-2.87 7.33 16 16 0 0 1-6.15 4.86 21 21 0 0 1-8.39 1.66q-5.53 0-9.64-2.26a16 16 0 0 1-6.44-6.46 20 20 0 0 1-2.3-9.72q0-5.52 2.3-9.72a16 16 0 0 1 6.44-6.46 20 20 0 0 1 9.64-2.26m38.66 0q4.9 0 8.8 2.13a15.5 15.5 0 0 1 6.22 6.32q2.31 4.2 2.38 10.26v2.06h-26.35q.28 4.4 2.58 6.92 2.38 2.47 6.36 2.47a8.4 8.4 0 0 0 7.77-4.93l9.15.67q-1.68 5-6.29 7.99t-10.62 3q-5.53 0-9.65-2.27a16 16 0 0 1-6.43-6.46 20 20 0 0 1-2.31-9.72q0-5.52 2.3-9.72a16 16 0 0 1 6.44-6.46 20 20 0 0 1 9.64-2.26M86.9 36.69l17.24-34.33h10.8L89.96 49.63h-6.12L58.85 2.36h10.81zm71.62-15.55a11 11 0 0 1 2.47-4.48q2.28-2.31 6.38-2.31h3.4v7.26h-3.47q-2.91 0-4.79.8a5.8 5.8 0 0 0-2.77 2.5q-.9 1.72-.9 4.37v20.35h-8.89V14.35h8.33zm101.73 28.5h-8.95V2.35h8.95zM127.62 20.26q-3.7 0-6 2.2-2.32 2.2-2.87 6.2h17.05q-.48-4.34-2.72-6.33a7.8 7.8 0 0 0-5.46-2.07m101.2 0q-3.7 0-6 2.2-2.31 2.2-2.87 6.2H237q-.5-4.34-2.73-6.33a7.8 7.8 0 0 0-5.46-2.07" style="fill:black;fill-opacity:1;"/></svg>
|
||||
|
After Width: | Height: | Size: 1.6 KiB |
@@ -0,0 +1,34 @@
|
||||
package agent
|
||||
|
||||
import "github.com/Twigpine/zero/internal/tools"
|
||||
|
||||
// CheckpointTargets returns the workspace-relative paths a tool call will mutate,
|
||||
// resolving its arguments exactly as executeToolCall does. Freeform apply_patch
|
||||
// input is normalized through the registered built-in tool, so absolute headers
|
||||
// are rewritten relative to the selected write root and cwd is set: checkpoint
|
||||
// capture and execution therefore agree on the files at stake.
|
||||
//
|
||||
// Best-effort: nil when the call has no capture targets or its arguments cannot
|
||||
// be resolved. Checkpoint capture never fails a run.
|
||||
func CheckpointTargets(workspaceRoot string, registry *tools.Registry, call ToolCall) []string {
|
||||
if registry == nil {
|
||||
return nil
|
||||
}
|
||||
args := map[string]any{}
|
||||
if call.Freeform {
|
||||
tool, ok := registry.Get(call.Name)
|
||||
if !ok || !tools.IsBuiltInApplyPatch(tool) {
|
||||
return nil
|
||||
}
|
||||
prepared, err := tools.PrepareFreeformApplyPatchArguments(tool, call.Arguments)
|
||||
if err != nil {
|
||||
return nil
|
||||
}
|
||||
args = prepared
|
||||
} else if call.Arguments != "" {
|
||||
if err := decodeToolArguments(call.Arguments, &args); err != nil {
|
||||
return nil
|
||||
}
|
||||
}
|
||||
return tools.MutationTargets(workspaceRoot, call.Name, args)
|
||||
}
|
||||
@@ -0,0 +1,99 @@
|
||||
package agent
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"slices"
|
||||
"testing"
|
||||
|
||||
"github.com/Twigpine/zero/internal/tools"
|
||||
)
|
||||
|
||||
func TestCheckpointTargets(t *testing.T) {
|
||||
root := t.TempDir()
|
||||
// Absolute headers must be compared against the physical root: t.TempDir
|
||||
// differs from it on macOS (/var -> /private/var) and via Windows short names.
|
||||
if resolved, err := filepath.EvalSymlinks(root); err == nil {
|
||||
root = resolved
|
||||
}
|
||||
if err := os.WriteFile(filepath.Join(root, "main.txt"), []byte("before\n"), 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
relativePatch := "*** Begin Patch\n*** Update File: main.txt\n@@\n-before\n+after\n*** End Patch\n"
|
||||
absolutePatch := "*** Begin Patch\n*** Update File: " + filepath.Join(root, "main.txt") + "\n@@\n-before\n+after\n*** End Patch\n"
|
||||
multiFilePatch := "*** Begin Patch\n*** Update File: main.txt\n@@\n-before\n+after\n*** Add File: notes.txt\n+new\n*** End Patch\n"
|
||||
jsonArgs, err := json.Marshal(map[string]any{"patch": relativePatch})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
registry := tools.NewRegistry()
|
||||
registry.Register(tools.NewScopedApplyPatchTool(root, nil))
|
||||
unbuiltinRegistry := tools.NewRegistry()
|
||||
unbuiltinRegistry.Register(&customApplyPatchTool{})
|
||||
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
registry *tools.Registry
|
||||
call ToolCall
|
||||
want []string
|
||||
}{
|
||||
{
|
||||
name: "freeform relative header",
|
||||
call: ToolCall{Name: "apply_patch", Arguments: relativePatch, Freeform: true},
|
||||
want: []string{"main.txt"},
|
||||
},
|
||||
{
|
||||
name: "freeform absolute header stays workspace-relative",
|
||||
call: ToolCall{Name: "apply_patch", Arguments: absolutePatch, Freeform: true},
|
||||
want: []string{"main.txt"},
|
||||
},
|
||||
{
|
||||
name: "freeform multi-file patch",
|
||||
call: ToolCall{Name: "apply_patch", Arguments: multiFilePatch, Freeform: true},
|
||||
want: []string{"main.txt", "notes.txt"},
|
||||
},
|
||||
{
|
||||
name: "json arguments",
|
||||
call: ToolCall{Name: "apply_patch", Arguments: string(jsonArgs)},
|
||||
want: []string{"main.txt"},
|
||||
},
|
||||
{
|
||||
name: "freeform traversal is rejected",
|
||||
call: ToolCall{Name: "apply_patch", Arguments: "*** Begin Patch\n*** Update File: ../escape.txt\n@@\n-x\n+y\n*** End Patch\n", Freeform: true},
|
||||
want: nil,
|
||||
},
|
||||
{
|
||||
name: "freeform custom apply_patch is not prepared",
|
||||
registry: unbuiltinRegistry,
|
||||
call: ToolCall{Name: "apply_patch", Arguments: relativePatch, Freeform: true},
|
||||
want: nil,
|
||||
},
|
||||
{
|
||||
name: "unknown freeform tool",
|
||||
call: ToolCall{Name: "read_file", Arguments: "raw", Freeform: true},
|
||||
want: nil,
|
||||
},
|
||||
{
|
||||
name: "malformed json arguments",
|
||||
call: ToolCall{Name: "apply_patch", Arguments: "{"},
|
||||
want: nil,
|
||||
},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
reg := registry
|
||||
if tc.registry != nil {
|
||||
reg = tc.registry
|
||||
}
|
||||
got := CheckpointTargets(root, reg, tc.call)
|
||||
if !slices.Equal(got, tc.want) {
|
||||
t.Fatalf("CheckpointTargets() = %#v, want %#v", got, tc.want)
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
if got := CheckpointTargets(root, nil, ToolCall{Name: "apply_patch", Arguments: relativePatch}); got != nil {
|
||||
t.Fatalf("CheckpointTargets(nil registry) = %#v, want nil", got)
|
||||
}
|
||||
}
|
||||
@@ -80,6 +80,9 @@ func TestRunStopsAfterConsecutiveEmptyTurns(t *testing.T) {
|
||||
if result.FinalAnswer == maxTurnsAnswer {
|
||||
t.Fatalf("no-output guard must stop before reaching maxTurns, got max-turns answer")
|
||||
}
|
||||
if result.Incomplete {
|
||||
t.Fatalf("interactive run must not be marked Incomplete; reason=%q", result.IncompleteReason)
|
||||
}
|
||||
}
|
||||
|
||||
func TestRunResetsEmptyTurnCounterOnVisibleOutput(t *testing.T) {
|
||||
@@ -513,6 +516,22 @@ func repeatedFlakyTurns(n int) [][]zeroruntime.StreamEvent {
|
||||
return turns
|
||||
}
|
||||
|
||||
// alwaysSucceedingTool is the successful counterpart to alwaysFailingTool, used
|
||||
// to put a productive tool turn before an empty-turn streak.
|
||||
type alwaysSucceedingTool struct{}
|
||||
|
||||
func (alwaysSucceedingTool) Name() string { return "ok" }
|
||||
func (alwaysSucceedingTool) Description() string { return "always succeeds for testing" }
|
||||
func (alwaysSucceedingTool) Parameters() tools.Schema {
|
||||
return tools.Schema{Type: "object", AdditionalProperties: false}
|
||||
}
|
||||
func (alwaysSucceedingTool) Safety() tools.Safety {
|
||||
return tools.Safety{SideEffect: tools.SideEffectRead, Permission: tools.PermissionAllow}
|
||||
}
|
||||
func (alwaysSucceedingTool) Run(context.Context, map[string]any) tools.Result {
|
||||
return tools.Result{Status: tools.StatusOK, Output: "ok"}
|
||||
}
|
||||
|
||||
func TestRunStopsAfterRepeatedToolFailures(t *testing.T) {
|
||||
registry := tools.NewRegistry()
|
||||
registry.Register(alwaysFailingTool{})
|
||||
@@ -529,6 +548,51 @@ func TestRunStopsAfterRepeatedToolFailures(t *testing.T) {
|
||||
if len(provider.requests) != toolFailureStopAt {
|
||||
t.Fatalf("expected stop at %d failures, made %d requests", toolFailureStopAt, len(provider.requests))
|
||||
}
|
||||
if result.Incomplete {
|
||||
t.Fatalf("interactive run must not be marked Incomplete; reason=%q", result.IncompleteReason)
|
||||
}
|
||||
}
|
||||
|
||||
// Under the headless completion gate both guardrail stops are unfinished runs,
|
||||
// so they must set Result.Incomplete and a reason; exec maps that to exit 4.
|
||||
// Thresholds and stop answers stay pinned by the two tests above.
|
||||
func TestHeadlessGuardStopsAreIncomplete(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
turns [][]zeroruntime.StreamEvent
|
||||
wantTurns int
|
||||
wantReason string
|
||||
}{
|
||||
{"empty_turns", [][]zeroruntime.StreamEvent{emptyTurn(), emptyTurn(), emptyTurn()}, maxEmptyTurns, "3 consecutive turns with no output"},
|
||||
{"empty_turns_after_progress", [][]zeroruntime.StreamEvent{
|
||||
toolTurn("ok-1", "ok", "{}"),
|
||||
emptyTurn(), emptyTurn(), emptyTurn(),
|
||||
}, maxEmptyTurns + 1, "3 consecutive turns with no output"},
|
||||
{"repeated_tool_failures", repeatedFlakyTurns(10), toolFailureStopAt, "flaky"},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
registry := tools.NewRegistry()
|
||||
registry.Register(alwaysFailingTool{})
|
||||
registry.Register(alwaysSucceedingTool{})
|
||||
result, err := Run(context.Background(), "go", &mockProvider{turns: tc.turns}, Options{
|
||||
Registry: registry,
|
||||
MaxTurns: 12,
|
||||
RequireCompletionSignal: true,
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if result.Turns != tc.wantTurns {
|
||||
t.Fatalf("guard did not trigger: turns=%d want=%d", result.Turns, tc.wantTurns)
|
||||
}
|
||||
if !result.Incomplete {
|
||||
t.Fatalf("guardrail stop under the headless gate must be Incomplete; final=%q", result.FinalAnswer)
|
||||
}
|
||||
if !strings.Contains(result.IncompleteReason, tc.wantReason) {
|
||||
t.Fatalf("IncompleteReason = %q, want it to mention %q", result.IncompleteReason, tc.wantReason)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestRunInjectsToolFailureHintWithSchema(t *testing.T) {
|
||||
|
||||
@@ -587,6 +587,14 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
|
||||
// counted toward the runaway cap so we stop before burning maxTurns.
|
||||
if guards.observeTurn(collected) {
|
||||
result.FinalAnswer = noOutputStopAnswer(result.Turns)
|
||||
// Under the headless completion gate this stop is unfinished work,
|
||||
// not a successful final answer: the guard exists precisely because
|
||||
// the model made no progress. Interactive runs keep the gate off, so
|
||||
// their behavior is unchanged.
|
||||
if options.RequireCompletionSignal {
|
||||
result.Incomplete = true
|
||||
result.IncompleteReason = "stopped after " + strconv.Itoa(guards.emptyTurns) + " consecutive turns with no output"
|
||||
}
|
||||
result.Messages = copyMessages(messages)
|
||||
return result, nil
|
||||
}
|
||||
@@ -808,6 +816,13 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
|
||||
messages = appendAbortedToolResults(messages, collected.ToolCalls[index+1:])
|
||||
messages = append(messages, buildToolImageMessages()...)
|
||||
result.FinalAnswer = toolFailureStopAnswer(call.Name, outcome.Count)
|
||||
// Same headless contract as the empty-turn guard: halting on a
|
||||
// repeated failure is an unfinished run, not success. Gate-off
|
||||
// (interactive / --no-completion-gate) keeps the old behavior.
|
||||
if options.RequireCompletionSignal {
|
||||
result.Incomplete = true
|
||||
result.IncompleteReason = "the " + call.Name + " tool failed " + strconv.Itoa(outcome.Count) + " times in a row with the same error"
|
||||
}
|
||||
result.Messages = copyMessages(messages)
|
||||
return result, nil
|
||||
}
|
||||
|
||||
@@ -92,13 +92,25 @@ func runSkillAdd(args []string, dir string, stdout io.Writer, stderr io.Writer)
|
||||
lines := []string{}
|
||||
if result.Updated {
|
||||
lines = append(lines, fmt.Sprintf("Updated skill %q.", result.Name))
|
||||
lines = append(lines, fmt.Sprintf(" hash: %s -> %s", shortHash(result.PreviousHash), shortHash(result.Hash)))
|
||||
switch {
|
||||
case result.PreviousHash != result.Hash:
|
||||
lines = append(lines, fmt.Sprintf(" hash: %s -> %s", shortHash(result.PreviousHash), shortHash(result.Hash)))
|
||||
case result.PreviousTreeHash == "":
|
||||
// The install this replaced predates tree hashes and copied SKILL.md
|
||||
// alone, so the bundled files are new rather than changed.
|
||||
lines = append(lines, " SKILL.md is unchanged; the files bundled with it are now installed too")
|
||||
default:
|
||||
lines = append(lines, " SKILL.md is unchanged; the files bundled with it changed")
|
||||
}
|
||||
} else {
|
||||
lines = append(lines, fmt.Sprintf("Installed skill %q.", result.Name))
|
||||
lines = append(lines, " hash: "+result.Hash)
|
||||
}
|
||||
lines = append(lines, " source: "+result.Source)
|
||||
lines = append(lines, " path: "+result.Path)
|
||||
if len(result.SkippedLinks) > 0 {
|
||||
lines = append(lines, " not copied (symlinks): "+strings.Join(result.SkippedLinks, ", "))
|
||||
}
|
||||
if _, err := fmt.Fprintln(stdout, redaction.RedactString(strings.Join(lines, "\n"), redaction.Options{})); err != nil {
|
||||
return exitCrash
|
||||
}
|
||||
|
||||
@@ -7,6 +7,8 @@ import (
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/Twigpine/zero/internal/skills"
|
||||
)
|
||||
|
||||
func writeSourceSkillDir(t *testing.T, dir string, content string) string {
|
||||
@@ -391,3 +393,133 @@ func TestRunDistributionCommandsDoNotLaunchTUI(t *testing.T) {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// A reinstall that only changed a bundled script must still read as an update
|
||||
// (#584): the SKILL.md hash is the same, so "hash: X -> X" would say nothing.
|
||||
func TestRunSkillAddReportsAnUpdateToBundledFilesOnly(t *testing.T) {
|
||||
skillsDir := t.TempDir()
|
||||
src := writeSourceSkillDir(t, filepath.Join(t.TempDir(), "src"),
|
||||
"---\nname: pdf\ndescription: Fill forms.\n---\nRun scripts/fill.py.\n")
|
||||
script := filepath.Join(src, "scripts", "fill.py")
|
||||
if err := os.MkdirAll(filepath.Dir(script), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.WriteFile(script, []byte("print('v1')\n"), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
deps := appDeps{skillsDir: func() string { return skillsDir }}
|
||||
|
||||
var stdout, stderr bytes.Buffer
|
||||
if exit := runWithDeps([]string{"skill", "add", src}, &stdout, &stderr, deps); exit != 0 {
|
||||
t.Fatalf("first skill add exit = %d, stderr = %s", exit, stderr.String())
|
||||
}
|
||||
if err := os.WriteFile(script, []byte("print('v2')\n"), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
stdout.Reset()
|
||||
stderr.Reset()
|
||||
if exit := runWithDeps([]string{"skill", "add", src}, &stdout, &stderr, deps); exit != 0 {
|
||||
t.Fatalf("second skill add exit = %d, stderr = %s", exit, stderr.String())
|
||||
}
|
||||
for _, want := range []string{`Updated skill "pdf".`, "SKILL.md is unchanged; the files bundled with it changed"} {
|
||||
if !strings.Contains(stdout.String(), want) {
|
||||
t.Fatalf("second add output does not say %q:\n%s", want, stdout.String())
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// An install from before tree hashes copied SKILL.md alone and recorded no tree
|
||||
// hash. Adding the skill again over that entry must not claim bundled files
|
||||
// changed: there are none, or they are installed for the first time.
|
||||
func TestRunSkillAddOverAnEntryWithoutATreeHash(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
script bool
|
||||
want []string
|
||||
notWant []string
|
||||
}{
|
||||
{
|
||||
name: "SKILL.md only",
|
||||
want: []string{`Installed skill "pdf".`},
|
||||
notWant: []string{"Updated skill", "files bundled with it"},
|
||||
},
|
||||
{
|
||||
name: "with a bundled script",
|
||||
script: true,
|
||||
want: []string{`Updated skill "pdf".`, "SKILL.md is unchanged; the files bundled with it are now installed too"},
|
||||
notWant: []string{"files bundled with it changed"},
|
||||
},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
skillsDir := t.TempDir()
|
||||
src := writeSourceSkillDir(t, filepath.Join(t.TempDir(), "src"),
|
||||
"---\nname: pdf\ndescription: Fill forms.\n---\nRun scripts/fill.py.\n")
|
||||
if tc.script {
|
||||
script := filepath.Join(src, "scripts", "fill.py")
|
||||
if err := os.MkdirAll(filepath.Dir(script), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.WriteFile(script, []byte("print('fill')\n"), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
deps := appDeps{skillsDir: func() string { return skillsDir }}
|
||||
|
||||
var stdout, stderr bytes.Buffer
|
||||
if exit := runWithDeps([]string{"skill", "add", src}, &stdout, &stderr, deps); exit != 0 {
|
||||
t.Fatalf("first skill add exit = %d, stderr = %s", exit, stderr.String())
|
||||
}
|
||||
lock, err := skills.ReadLock(skillsDir)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
entry := lock["pdf"]
|
||||
entry.TreeHash = ""
|
||||
lock["pdf"] = entry
|
||||
data, err := json.Marshal(lock)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.WriteFile(filepath.Join(skillsDir, skills.LockFileName), data, 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
stdout.Reset()
|
||||
stderr.Reset()
|
||||
if exit := runWithDeps([]string{"skill", "add", src}, &stdout, &stderr, deps); exit != 0 {
|
||||
t.Fatalf("second skill add exit = %d, stderr = %s", exit, stderr.String())
|
||||
}
|
||||
for _, want := range tc.want {
|
||||
if !strings.Contains(stdout.String(), want) {
|
||||
t.Fatalf("second add output does not say %q:\n%s", want, stdout.String())
|
||||
}
|
||||
}
|
||||
for _, notWant := range tc.notWant {
|
||||
if strings.Contains(stdout.String(), notWant) {
|
||||
t.Fatalf("second add output says %q:\n%s", notWant, stdout.String())
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestRunSkillAddListsTheSymlinksItDidNotCopy(t *testing.T) {
|
||||
skillsDir := t.TempDir()
|
||||
src := writeSourceSkillDir(t, filepath.Join(t.TempDir(), "src"),
|
||||
"---\nname: pdf\ndescription: Fill forms.\n---\nbody\n")
|
||||
outside := filepath.Join(t.TempDir(), "notes.md")
|
||||
if err := os.WriteFile(outside, []byte("outside\n"), 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.Symlink(outside, filepath.Join(src, "notes.md")); err != nil {
|
||||
t.Skipf("symlinks unavailable: %v", err)
|
||||
}
|
||||
var stdout, stderr bytes.Buffer
|
||||
deps := appDeps{skillsDir: func() string { return skillsDir }}
|
||||
if exit := runWithDeps([]string{"skill", "add", src}, &stdout, &stderr, deps); exit != 0 {
|
||||
t.Fatalf("skill add exit = %d, stderr = %s", exit, stderr.String())
|
||||
}
|
||||
if !strings.Contains(stdout.String(), "not copied (symlinks): notes.md") {
|
||||
t.Fatalf("add output does not list the skipped symlink:\n%s", stdout.String())
|
||||
}
|
||||
}
|
||||
@@ -712,7 +712,7 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
|
||||
"arguments": call.Arguments,
|
||||
})
|
||||
// Snapshot before-state of files this call will mutate (safe rewind).
|
||||
if checkpoint, ok := sessionRecorder.captureCheckpoint(workspaceRoot, call); ok {
|
||||
if checkpoint, ok := sessionRecorder.captureCheckpoint(workspaceRoot, registry, call); ok {
|
||||
writer.checkpoint(checkpoint)
|
||||
}
|
||||
},
|
||||
|
||||
@@ -0,0 +1,206 @@
|
||||
package cli
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"context"
|
||||
"encoding/json"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
|
||||
"github.com/Twigpine/zero/internal/agent"
|
||||
"github.com/Twigpine/zero/internal/config"
|
||||
"github.com/Twigpine/zero/internal/sessions"
|
||||
"github.com/Twigpine/zero/internal/tools"
|
||||
"github.com/Twigpine/zero/internal/zeroruntime"
|
||||
)
|
||||
|
||||
func freeformApplyPatchArguments(root string, absolute bool) string {
|
||||
target := "main.txt"
|
||||
if absolute {
|
||||
target = filepath.Join(root, "main.txt")
|
||||
}
|
||||
return "*** Begin Patch\n*** Update File: " + target + "\n@@\n-before\n+after\n*** End Patch\n"
|
||||
}
|
||||
|
||||
// captureCheckpoint must resolve a freeform apply_patch call through the same
|
||||
// preparation execution uses, so the before-state is captured and rewind can
|
||||
// restore it. The JSON control pins the unchanged path.
|
||||
func TestCaptureCheckpointFreeformApplyPatch(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
freeform bool
|
||||
absolute bool
|
||||
jsonArgs bool
|
||||
}{
|
||||
{name: "freeform", freeform: true},
|
||||
{name: "freeform absolute header", freeform: true, absolute: true},
|
||||
{name: "json arguments", jsonArgs: true},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
t.Setenv("XDG_DATA_HOME", t.TempDir())
|
||||
t.Setenv("ZERO_CHECKPOINTS", "on")
|
||||
root := t.TempDir()
|
||||
// The absolute-header case needs the physical root spelling the tool
|
||||
// resolves (macOS /var vs /private/var, Windows short names).
|
||||
if resolved, err := filepath.EvalSymlinks(root); err == nil {
|
||||
root = resolved
|
||||
}
|
||||
if err := os.WriteFile(filepath.Join(root, "main.txt"), []byte("before\n"), 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
store := sessions.NewStore(sessions.StoreOptions{})
|
||||
session, err := store.Create(sessions.CreateInput{Title: "freeform checkpoint"})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := store.AppendEvent(session.SessionID, sessions.AppendEventInput{
|
||||
Type: sessions.EventMessage,
|
||||
Payload: map[string]string{"role": "user", "content": "apply the patch"},
|
||||
}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
recorder := &execSessionRecorder{prepared: sessions.PreparedExec{Store: store, Session: session}}
|
||||
registry := tools.NewRegistry()
|
||||
registry.Register(tools.NewScopedApplyPatchTool(root, nil))
|
||||
|
||||
call := agent.ToolCall{ID: "call", Name: "apply_patch", Freeform: tc.freeform}
|
||||
if tc.jsonArgs {
|
||||
encoded, err := json.Marshal(map[string]string{"patch": freeformApplyPatchArguments(root, false)})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
call.Arguments = string(encoded)
|
||||
} else {
|
||||
call.Arguments = freeformApplyPatchArguments(root, tc.absolute)
|
||||
}
|
||||
|
||||
event, ok := recorder.captureCheckpoint(root, registry, call)
|
||||
if !ok || event.Type != sessions.EventSessionCheckpoint {
|
||||
t.Fatalf("captureCheckpoint() = %#v, %t; want a checkpoint event", event, ok)
|
||||
}
|
||||
var payload sessions.CheckpointPayload
|
||||
if err := json.Unmarshal(event.Payload, &payload); err != nil {
|
||||
t.Fatalf("decode checkpoint payload: %v", err)
|
||||
}
|
||||
if len(payload.Files) != 1 || payload.Files[0].Path != "main.txt" || payload.Files[0].Blob == "" {
|
||||
t.Fatalf("checkpoint files = %#v, want main.txt with a blob", payload.Files)
|
||||
}
|
||||
|
||||
// Simulate the tool's mutation, then rewind past it.
|
||||
if err := os.WriteFile(filepath.Join(root, "main.txt"), []byte("after\n"), 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
report, err := store.ApplyRewind(session.SessionID, root, 1)
|
||||
if err != nil {
|
||||
t.Fatalf("ApplyRewind: %v", err)
|
||||
}
|
||||
if report.FilesRestored != 1 {
|
||||
t.Fatalf("restore report = %#v, want one restored file", report)
|
||||
}
|
||||
content, err := os.ReadFile(filepath.Join(root, "main.txt"))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if string(content) != "before\n" {
|
||||
t.Fatalf("restored content = %q, want before newline", content)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// freeformPatchExecProvider emits one native freeform apply_patch call, then a
|
||||
// final text turn.
|
||||
type freeformPatchExecProvider struct {
|
||||
patch string
|
||||
calls int
|
||||
}
|
||||
|
||||
func (provider *freeformPatchExecProvider) StreamCompletion(ctx context.Context, request zeroruntime.CompletionRequest) (<-chan zeroruntime.StreamEvent, error) {
|
||||
ch := make(chan zeroruntime.StreamEvent, 5)
|
||||
calls := provider.calls
|
||||
provider.calls++
|
||||
if calls == 0 {
|
||||
ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventToolCallStart, ToolCallID: "call_patch", ToolName: "apply_patch", ToolCallFreeform: true}
|
||||
ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventToolCallDelta, ToolCallID: "call_patch", ArgumentsFragment: provider.patch}
|
||||
ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventToolCallEnd, ToolCallID: "call_patch"}
|
||||
} else {
|
||||
ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventText, Content: "patched"}
|
||||
}
|
||||
ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone}
|
||||
close(ch)
|
||||
return ch, nil
|
||||
}
|
||||
|
||||
// End-to-end: exec captures the freeform checkpoint and `sessions rewind`
|
||||
// restores the pre-patch content.
|
||||
func TestRunExecFreeformApplyPatchCheckpointsForRewind(t *testing.T) {
|
||||
isolateCLIUserState(t)
|
||||
t.Setenv("ZERO_CHECKPOINTS", "on")
|
||||
root := t.TempDir()
|
||||
if err := os.WriteFile(filepath.Join(root, "main.txt"), []byte("before\n"), 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
provider := &freeformPatchExecProvider{patch: freeformApplyPatchArguments(root, false)}
|
||||
var stdout, stderr bytes.Buffer
|
||||
exitCode := runWithDeps([]string{
|
||||
"exec", "--init-session-id", "freeform_rewind", "--skip-permissions-unsafe",
|
||||
"--output-format", "stream-json", "apply the patch",
|
||||
}, &stdout, &stderr, appDeps{
|
||||
getwd: func() (string, error) { return root, nil },
|
||||
resolveConfig: func(string, config.Overrides) (config.ResolvedConfig, error) {
|
||||
return execResolvedConfig(), nil
|
||||
},
|
||||
newProvider: func(config.ProviderProfile) (zeroruntime.Provider, error) {
|
||||
return provider, nil
|
||||
},
|
||||
})
|
||||
if exitCode != exitSuccess {
|
||||
t.Fatalf("exit = %d, want %d; stderr=%q stdout=%q", exitCode, exitSuccess, stderr.String(), stdout.String())
|
||||
}
|
||||
content, err := os.ReadFile(filepath.Join(root, "main.txt"))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if string(content) != "after\n" {
|
||||
t.Fatalf("patched content = %q, want after newline", content)
|
||||
}
|
||||
|
||||
store := sessions.NewStore(sessions.StoreOptions{})
|
||||
events, err := store.ReadEvents("freeform_rewind")
|
||||
if err != nil {
|
||||
t.Fatalf("ReadEvents: %v", err)
|
||||
}
|
||||
checkpoints := 0
|
||||
for _, event := range events {
|
||||
if event.Type == sessions.EventSessionCheckpoint {
|
||||
checkpoints++
|
||||
}
|
||||
}
|
||||
if checkpoints != 1 {
|
||||
t.Fatalf("checkpoint events = %d, want 1; events=%v", checkpoints, sessionEventTypes(events))
|
||||
}
|
||||
|
||||
report, err := store.ApplyRewind("freeform_rewind", root, 1)
|
||||
if err != nil {
|
||||
t.Fatalf("ApplyRewind: %v", err)
|
||||
}
|
||||
if report.FilesRestored != 1 {
|
||||
t.Fatalf("restore report = %#v, want one restored file", report)
|
||||
}
|
||||
content, err = os.ReadFile(filepath.Join(root, "main.txt"))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if string(content) != "before\n" {
|
||||
t.Fatalf("rewound content = %q, want before newline", content)
|
||||
}
|
||||
}
|
||||
|
||||
func sessionEventTypes(events []sessions.Event) []string {
|
||||
types := make([]string, 0, len(events))
|
||||
for _, event := range events {
|
||||
types = append(types, string(event.Type))
|
||||
}
|
||||
return types
|
||||
}
|
||||
@@ -0,0 +1,90 @@
|
||||
package cli
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"context"
|
||||
"slices"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/Twigpine/zero/internal/config"
|
||||
"github.com/Twigpine/zero/internal/zeroruntime"
|
||||
)
|
||||
|
||||
// guardStopExecProvider emits turns with no visible text and no tool calls, so
|
||||
// the empty-turn guardrail stops the run after its consecutive-empty-turn cap.
|
||||
type guardStopExecProvider struct{}
|
||||
|
||||
func (guardStopExecProvider) StreamCompletion(ctx context.Context, request zeroruntime.CompletionRequest) (<-chan zeroruntime.StreamEvent, error) {
|
||||
ch := make(chan zeroruntime.StreamEvent, 1)
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
close(ch)
|
||||
return ch, ctx.Err()
|
||||
case ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone}:
|
||||
}
|
||||
close(ch)
|
||||
return ch, nil
|
||||
}
|
||||
|
||||
// A guardrail stop in headless exec must use the existing INCOMPLETE contract
|
||||
// (exit 4, error event, run_end status), and --no-completion-gate must keep
|
||||
// reporting success. isolateCLIUserState also turns off the models.dev refresh
|
||||
// that runExec starts in the background (see the #1152/#1161 flake).
|
||||
func TestRunExecGuardrailStopIncompleteContract(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
args []string
|
||||
wantExit int
|
||||
wantStatus string
|
||||
}{
|
||||
{"gate on", []string{"exec", "--output-format", "stream-json", "complete the task"}, exitIncomplete, "incomplete"},
|
||||
{"gate off", []string{"exec", "--no-completion-gate", "--output-format", "stream-json", "complete the task"}, exitSuccess, "success"},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
isolateCLIUserState(t)
|
||||
cwd := t.TempDir()
|
||||
var stdout, stderr bytes.Buffer
|
||||
exitCode := runWithDeps(tc.args, &stdout, &stderr, appDeps{
|
||||
getwd: func() (string, error) { return cwd, nil },
|
||||
resolveConfig: func(string, config.Overrides) (config.ResolvedConfig, error) {
|
||||
return execResolvedConfig(), nil
|
||||
},
|
||||
newProvider: func(config.ProviderProfile) (zeroruntime.Provider, error) {
|
||||
return guardStopExecProvider{}, nil
|
||||
},
|
||||
})
|
||||
if exitCode != tc.wantExit {
|
||||
t.Fatalf("exit code = %d, want %d; stderr=%q", exitCode, tc.wantExit, stderr.String())
|
||||
}
|
||||
|
||||
events := decodeJSONLines(t, stdout.String())
|
||||
if len(events) == 0 || events[len(events)-1]["type"] != "run_end" {
|
||||
t.Fatalf("expected run_end as the last event, got %#v", events)
|
||||
}
|
||||
runEnd := events[len(events)-1]
|
||||
if runEnd["status"] != tc.wantStatus {
|
||||
t.Fatalf("run_end status = %v, want %q", runEnd["status"], tc.wantStatus)
|
||||
}
|
||||
if runEnd["exitCode"] != float64(tc.wantExit) {
|
||||
t.Fatalf("run_end exitCode = %v, want %d", runEnd["exitCode"], tc.wantExit)
|
||||
}
|
||||
finalEvent := findJSONEvent(t, events, "final")
|
||||
if text, _ := finalEvent["text"].(string); !strings.Contains(text, "no output") {
|
||||
t.Fatalf("final text = %q, want the guard stop answer", text)
|
||||
}
|
||||
|
||||
if tc.wantStatus == "incomplete" {
|
||||
errorEvent := findJSONEvent(t, events, "error")
|
||||
if errorEvent["code"] != "incomplete" {
|
||||
t.Fatalf("error code = %v, want incomplete", errorEvent["code"])
|
||||
}
|
||||
if message, _ := errorEvent["message"].(string); !strings.Contains(message, "no output") {
|
||||
t.Fatalf("error message = %q, want the guard reason", message)
|
||||
}
|
||||
} else if slices.Contains(jsonEventTypes(events), "error") {
|
||||
t.Fatalf("gate-off run must not emit an error event: %#v", events)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -1,7 +1,6 @@
|
||||
package cli
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"io"
|
||||
"strings"
|
||||
@@ -19,15 +18,11 @@ type execSessionRecorder struct {
|
||||
// captureCheckpoint snapshots the before-state of files a tool call will mutate.
|
||||
// Best-effort: failures never affect the run. Returns the checkpoint event and
|
||||
// true when one was recorded.
|
||||
func (recorder *execSessionRecorder) captureCheckpoint(workspaceRoot string, call agent.ToolCall) (sessions.Event, bool) {
|
||||
func (recorder *execSessionRecorder) captureCheckpoint(workspaceRoot string, registry *tools.Registry, call agent.ToolCall) (sessions.Event, bool) {
|
||||
if recorder.prepared.Store == nil || recorder.prepared.Session.SessionID == "" {
|
||||
return sessions.Event{}, false
|
||||
}
|
||||
var args map[string]any
|
||||
if call.Arguments != "" {
|
||||
_ = json.Unmarshal([]byte(call.Arguments), &args)
|
||||
}
|
||||
targets := tools.MutationTargets(workspaceRoot, call.Name, args)
|
||||
targets := agent.CheckpointTargets(workspaceRoot, registry, call)
|
||||
if len(targets) == 0 {
|
||||
return sessions.Event{}, false
|
||||
}
|
||||
|
||||
@@ -148,7 +148,7 @@ func runExecSpecDraft(run execSpecDraftRun) int {
|
||||
"name": call.Name,
|
||||
"arguments": call.Arguments,
|
||||
})
|
||||
if checkpoint, ok := sessionRecorder.captureCheckpoint(run.workspaceRoot, call); ok {
|
||||
if checkpoint, ok := sessionRecorder.captureCheckpoint(run.workspaceRoot, run.registry, call); ok {
|
||||
writer.checkpoint(checkpoint)
|
||||
}
|
||||
},
|
||||
|
||||
@@ -0,0 +1,51 @@
|
||||
package config
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestEnsureChatGPTDefaultPreservesSavedSelection(t *testing.T) {
|
||||
for _, saved := range []string{"", "gpt-explicit-saved"} {
|
||||
name := "new profile"
|
||||
if saved != "" {
|
||||
name = "saved selection"
|
||||
}
|
||||
t.Run(name, func(t *testing.T) {
|
||||
path := filepath.Join(t.TempDir(), "config.json")
|
||||
if saved != "" {
|
||||
body, err := json.Marshal(FileConfig{ActiveProvider: "codex", Providers: []ProviderProfile{{Name: "codex", CatalogID: "chatgpt", Model: saved}}})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.WriteFile(path, body, 0600); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
ensured, err := EnsureCatalogProvider(path, "chatgpt")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
body, err := os.ReadFile(path)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var cfg FileConfig
|
||||
if err := json.Unmarshal(body, &cfg); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
want := "gpt-6.1-sol"
|
||||
if saved != "" {
|
||||
want = saved
|
||||
}
|
||||
if len(cfg.Providers) != 1 || cfg.Providers[0].Model != want {
|
||||
t.Fatalf("ChatGPT default/selection = %#v, want model %q", cfg.Providers, want)
|
||||
}
|
||||
if saved != "" && (ensured.Name != "codex" || ensured.Created) {
|
||||
t.Fatalf("saved subscription profile was replaced: %#v", ensured)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -374,7 +374,7 @@ func (tool skillTool) Run(_ context.Context, args map[string]any) tools.Result {
|
||||
available := make([]string, 0, len(merged))
|
||||
for _, skill := range merged {
|
||||
if skill.Name == name {
|
||||
return tools.Result{Status: tools.StatusOK, Output: skill.Content}
|
||||
return tools.Result{Status: tools.StatusOK, Output: skills.ToolOutput(skill)}
|
||||
}
|
||||
available = append(available, skill.Name)
|
||||
}
|
||||
|
||||
@@ -673,3 +673,28 @@ func TestExpandPluginRootPathRelative(t *testing.T) {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The multi-root skill tool is the one the CLI registers, so it has to point at
|
||||
// a skill's bundled files the same way the core tool does (#584).
|
||||
func TestNewSkillToolPointsAtTheSkillsBundledFiles(t *testing.T) {
|
||||
home := t.TempDir()
|
||||
t.Setenv("HOME", home)
|
||||
t.Setenv("USERPROFILE", home)
|
||||
dir := t.TempDir()
|
||||
writeTestSkill(t, dir, "pdf", "Run scripts/fill.py.")
|
||||
script := filepath.Join(dir, "pdf", "scripts", "fill.py")
|
||||
if err := os.MkdirAll(filepath.Dir(script), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.WriteFile(script, []byte("print('fill')\n"), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
got := NewSkillTool(dir, nil).Run(context.Background(), map[string]any{"name": "pdf"})
|
||||
if got.Status != tools.StatusOK {
|
||||
t.Fatalf("Status = %s (output: %s)", got.Status, got.Output)
|
||||
}
|
||||
if !strings.Contains(got.Output, "- scripts/fill.py") || !strings.Contains(got.Output, filepath.Join(dir, "pdf")) {
|
||||
t.Fatalf("output does not point at the bundled script:\n%s", got.Output)
|
||||
}
|
||||
}
|
||||
@@ -132,7 +132,9 @@ var descriptors = []Descriptor{
|
||||
// way in; RequiresAuth is forced true so catalog consumers know the provider
|
||||
// needs an interactive login before a request will succeed.
|
||||
func() Descriptor {
|
||||
d := openAICompat("chatgpt", "ChatGPT", "https://chatgpt.com/backend-api/codex", "gpt-5.5", nil)
|
||||
// New ChatGPT profiles follow the vendor's GPT-5.5 replacement guidance:
|
||||
// https://learn.chatgpt.com/docs/models#gpt-55-retirement
|
||||
d := openAICompat("chatgpt", "ChatGPT", "https://chatgpt.com/backend-api/codex", "gpt-6.1-sol", nil)
|
||||
d.RequiresAuth = true
|
||||
return oauthProvider(d, false, false)
|
||||
}(),
|
||||
|
||||
@@ -44,6 +44,20 @@ var minimaxCuratedModels = []Model{
|
||||
OutputModalities: []string{"text"},
|
||||
Source: minimaxModelSource,
|
||||
},
|
||||
{
|
||||
ID: "MiniMax-M3.1-Flash",
|
||||
Description: "fast reasoning model",
|
||||
ContextWindow: 1_000_000,
|
||||
ToolCall: true,
|
||||
Reasoning: true,
|
||||
ReasoningEfforts: []string{"low", "medium", "high", "xhigh", "max"},
|
||||
DefaultReasoningEffort: "max",
|
||||
InputModalities: []string{"text", "image", "video"},
|
||||
OutputModalities: []string{"text"},
|
||||
InputCost: 0.15,
|
||||
OutputCost: 0.60,
|
||||
Source: minimaxModelSource,
|
||||
},
|
||||
{
|
||||
ID: "MiniMax-M2.7",
|
||||
Description: "agentic coding model",
|
||||
@@ -113,10 +127,12 @@ var curatedModels = map[string][]Model{
|
||||
{ID: "deepseek/deepseek-chat", Description: "coding model"},
|
||||
},
|
||||
"chatgpt": {
|
||||
{ID: "gpt-5.5", Description: "recommended Codex model"},
|
||||
{ID: "gpt-5.4", Description: "strong Codex model"},
|
||||
{ID: "gpt-5.4-mini", Description: "fast Codex model"},
|
||||
{ID: "gpt-5.3-codex-spark", Description: "research preview fast Codex model"},
|
||||
// Suggestions only: availability comes from the authenticated Codex catalog.
|
||||
// https://learn.chatgpt.com/docs/models
|
||||
{ID: "gpt-6.1-sol", Description: "balanced Codex model"},
|
||||
{ID: "gpt-6.1-terra", Description: "fast model for writing, visual understanding, and computer use"},
|
||||
{ID: "gpt-6-astra", Description: "advanced reasoning model"},
|
||||
{ID: "gpt-6-luna", Description: "efficient coding model"},
|
||||
},
|
||||
"deepseek": {
|
||||
{ID: "deepseek-chat", Description: "catalog default"},
|
||||
|
||||
@@ -35,8 +35,8 @@ func TestModelsAreProviderScoped(t *testing.T) {
|
||||
},
|
||||
{
|
||||
provider: "chatgpt",
|
||||
want: []string{"gpt-5.5", "gpt-5.4", "gpt-5.4-mini", "gpt-5.3-codex-spark"},
|
||||
notWant: []string{"gpt-5", "gpt-4.1", "openai/gpt-4.1"},
|
||||
want: []string{"gpt-6.1-sol", "gpt-6.1-terra", "gpt-6-astra", "gpt-6-luna"},
|
||||
notWant: []string{"gpt-5.5", "gpt-5.4", "gpt-5.4-mini", "gpt-5.3-codex-spark", "openai/gpt-4.1"},
|
||||
},
|
||||
{
|
||||
provider: "aimlapi",
|
||||
@@ -65,7 +65,7 @@ func TestModelsAreProviderScoped(t *testing.T) {
|
||||
},
|
||||
{
|
||||
provider: "minimaxi-cn",
|
||||
want: []string{"MiniMax-M3", "MiniMax-M2.7", "MiniMax-M2.1"},
|
||||
want: []string{"MiniMax-M3", "MiniMax-M3.1-Flash", "MiniMax-M2.7", "MiniMax-M2.1"},
|
||||
notWant: []string{"gpt-4.1", "claude-sonnet-4.5"},
|
||||
},
|
||||
{
|
||||
@@ -165,8 +165,8 @@ func TestMiniMaxModelsExposeCurrentCapabilities(t *testing.T) {
|
||||
t.Fatal("provider minimax missing from catalog")
|
||||
}
|
||||
models := Models(descriptor)
|
||||
if len(models) < 2 || models[0].ID != "MiniMax-M3" || models[1].ID != "MiniMax-M2.7" {
|
||||
t.Fatalf("MiniMax current models = %#v, want MiniMax-M3 followed by MiniMax-M2.7", modelIDs(models))
|
||||
if len(models) < 3 || models[0].ID != "MiniMax-M3" || models[1].ID != "MiniMax-M3.1-Flash" || models[2].ID != "MiniMax-M2.7" {
|
||||
t.Fatalf("MiniMax current models = %#v, want MiniMax-M3, MiniMax-M3.1-Flash, then MiniMax-M2.7", modelIDs(models))
|
||||
}
|
||||
|
||||
m3 := models[0]
|
||||
@@ -178,7 +178,23 @@ func TestMiniMaxModelsExposeCurrentCapabilities(t *testing.T) {
|
||||
t.Fatalf("MiniMax-M3 modalities = input:%#v output:%#v", m3.InputModalities, m3.OutputModalities)
|
||||
}
|
||||
|
||||
m27 := models[1]
|
||||
m31Flash := models[1]
|
||||
if m31Flash.ContextWindow != 1_000_000 || !m31Flash.ToolCall || !m31Flash.Reasoning {
|
||||
t.Fatalf("MiniMax-M3.1-Flash capabilities = %#v, want 1M context with tools and reasoning", m31Flash)
|
||||
}
|
||||
if !reflect.DeepEqual(m31Flash.ReasoningEfforts, []string{"low", "medium", "high", "xhigh", "max"}) ||
|
||||
m31Flash.DefaultReasoningEffort != "max" {
|
||||
t.Fatalf("MiniMax-M3.1-Flash reasoning efforts = %#v default %q", m31Flash.ReasoningEfforts, m31Flash.DefaultReasoningEffort)
|
||||
}
|
||||
if !reflect.DeepEqual(m31Flash.InputModalities, []string{"text", "image", "video"}) ||
|
||||
!reflect.DeepEqual(m31Flash.OutputModalities, []string{"text"}) {
|
||||
t.Fatalf("MiniMax-M3.1-Flash modalities = input:%#v output:%#v", m31Flash.InputModalities, m31Flash.OutputModalities)
|
||||
}
|
||||
if m31Flash.InputCost != 0.15 || m31Flash.OutputCost != 0.60 {
|
||||
t.Fatalf("MiniMax-M3.1-Flash costs = %f/%f, want 0.15/0.60", m31Flash.InputCost, m31Flash.OutputCost)
|
||||
}
|
||||
|
||||
m27 := models[2]
|
||||
if m27.ContextWindow != 204_800 || !m27.ToolCall || !m27.Reasoning {
|
||||
t.Fatalf("MiniMax-M2.7 capabilities = %#v, want 204.8K context with tools and reasoning", m27)
|
||||
}
|
||||
|
||||
@@ -0,0 +1,31 @@
|
||||
package providermodeldiscovery
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"testing"
|
||||
|
||||
"github.com/Twigpine/zero/internal/config"
|
||||
)
|
||||
|
||||
func TestChatGPTDiscoveryUsesCurrentCompatibilityVersion(t *testing.T) {
|
||||
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
if got := r.URL.Query().Get("client_version"); got != "0.159.0" {
|
||||
t.Errorf("client_version = %q, want documented GPT-6.1 Terra compatibility floor 0.159.0", got)
|
||||
}
|
||||
_, _ = w.Write([]byte(`{"models":[{"slug":"gpt-future-coder"}]}`))
|
||||
}))
|
||||
defer server.Close()
|
||||
profile := config.ProviderProfile{
|
||||
CatalogID: "chatgpt", ProviderKind: config.ProviderKindOpenAICompatible,
|
||||
BaseURL: server.URL + "/backend-api/codex", APIKey: "test-bearer",
|
||||
}
|
||||
models, err := Discover(context.Background(), profile, Options{HTTPClient: server.Client()})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(models) != 1 || models[0].ID != "gpt-future-coder" {
|
||||
t.Fatalf("models = %#v, want only gpt-future-coder", models)
|
||||
}
|
||||
}
|
||||
@@ -20,8 +20,9 @@ import (
|
||||
)
|
||||
|
||||
const (
|
||||
anthropicVersion = "2023-06-01"
|
||||
chatGPTModelsProtocolVersion = "0.146.0"
|
||||
anthropicVersion = "2023-06-01"
|
||||
// GPT-6.1 Terra's documented Codex client floor: https://learn.chatgpt.com/docs/models.
|
||||
chatGPTModelsProtocolVersion = "0.159.0"
|
||||
)
|
||||
|
||||
type Model struct {
|
||||
|
||||
@@ -49,6 +49,19 @@ func thinkingBudgetForEffort(effort string) int {
|
||||
}
|
||||
}
|
||||
|
||||
func miniMaxM31FlashEffort(model, effort string) string {
|
||||
if !strings.EqualFold(strings.TrimSpace(model), "MiniMax-M3.1-Flash") {
|
||||
return ""
|
||||
}
|
||||
effort = strings.ToLower(strings.TrimSpace(effort))
|
||||
switch effort {
|
||||
case "low", "medium", "high", "xhigh", "max":
|
||||
return effort
|
||||
default:
|
||||
return ""
|
||||
}
|
||||
}
|
||||
|
||||
// resolveThinking returns the thinking budget and the max_tokens to send. When a
|
||||
// budget is requested, max_tokens is raised if needed so the budget plus a
|
||||
// minimum response both fit (Anthropic rejects budget >= max_tokens). enabled is
|
||||
@@ -377,11 +390,15 @@ func (provider *Provider) anthropicRequest(request zeroruntime.CompletionRequest
|
||||
Messages: messages,
|
||||
Stream: true,
|
||||
}
|
||||
// Extended thinking: enable when a reasoning effort was requested. The budget
|
||||
// is counted against max_tokens, so raise max_tokens to leave room for the
|
||||
// response. Temperature is intentionally left unset (Anthropic requires the
|
||||
// default when thinking is on).
|
||||
if budget, effectiveMax, enabled := resolveThinking(request.ReasoningEffort, provider.maxTokens); enabled {
|
||||
// MiniMax-M3.1-Flash uses adaptive thinking with output_config.effort instead
|
||||
// of Anthropic's token budget. For other models, the budget is counted against
|
||||
// max_tokens, so raise max_tokens to leave room for the response. Temperature
|
||||
// is intentionally left unset (Anthropic requires the default when thinking
|
||||
// is on).
|
||||
if effort := miniMaxM31FlashEffort(provider.model, request.ReasoningEffort); effort != "" {
|
||||
mapped.Thinking = &thinkingConfig{Type: "adaptive"}
|
||||
mapped.OutputConfig = &outputConfig{Effort: effort}
|
||||
} else if budget, effectiveMax, enabled := resolveThinking(request.ReasoningEffort, provider.maxTokens); enabled {
|
||||
mapped.MaxTokens = effectiveMax
|
||||
mapped.Thinking = &thinkingConfig{Type: "enabled", BudgetTokens: budget}
|
||||
}
|
||||
|
||||
@@ -266,6 +266,53 @@ func TestStreamCompletionEnablesThinkingWhenEffortRequested(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestStreamCompletionUsesMiniMaxAdaptiveEffort(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
for _, effort := range []string{"low", "xhigh"} {
|
||||
effort := effort
|
||||
t.Run(effort, func(t *testing.T) {
|
||||
t.Parallel()
|
||||
var gotBody map[string]any
|
||||
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
if err := json.NewDecoder(r.Body).Decode(&gotBody); err != nil {
|
||||
t.Fatalf("decode request body: %v", err)
|
||||
}
|
||||
writeSSEEvent(w, "message_stop", `{"type":"message_stop"}`)
|
||||
}))
|
||||
defer server.Close()
|
||||
|
||||
provider, err := New(Options{BaseURL: server.URL + "/", Model: "MiniMax-M3.1-Flash", MaxTokens: 64_000})
|
||||
if err != nil {
|
||||
t.Fatalf("New returned error: %v", err)
|
||||
}
|
||||
stream, err := provider.StreamCompletion(context.Background(), zeroruntime.CompletionRequest{
|
||||
Messages: []zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "hi"}},
|
||||
ReasoningEffort: effort,
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("StreamCompletion returned error: %v", err)
|
||||
}
|
||||
drain(stream)
|
||||
|
||||
thinking, ok := gotBody["thinking"].(map[string]any)
|
||||
if !ok || thinking["type"] != "adaptive" {
|
||||
t.Fatalf("thinking = %#v, want adaptive", gotBody["thinking"])
|
||||
}
|
||||
if _, ok := thinking["budget_tokens"]; ok {
|
||||
t.Fatalf("MiniMax thinking must not include budget_tokens: %#v", thinking)
|
||||
}
|
||||
outputConfig, ok := gotBody["output_config"].(map[string]any)
|
||||
if !ok || outputConfig["effort"] != effort {
|
||||
t.Fatalf("output_config = %#v, want effort %q", gotBody["output_config"], effort)
|
||||
}
|
||||
if mt, _ := gotBody["max_tokens"].(float64); int(mt) != 64_000 {
|
||||
t.Fatalf("max_tokens = %#v, want unchanged 64000", gotBody["max_tokens"])
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestStreamCompletionOmitsThinkingWithoutEffort(t *testing.T) {
|
||||
t.Parallel()
|
||||
var gotBody map[string]any
|
||||
|
||||
@@ -10,17 +10,21 @@ type messagesRequest struct {
|
||||
System any `json:"system,omitempty"`
|
||||
// Thinking enables extended thinking when a reasoning effort was requested.
|
||||
// Omitted (nil) for normal requests so behavior is unchanged.
|
||||
Thinking *thinkingConfig `json:"thinking,omitempty"`
|
||||
Tools []anthropicTool `json:"tools,omitempty"`
|
||||
Stream bool `json:"stream"`
|
||||
Thinking *thinkingConfig `json:"thinking,omitempty"`
|
||||
OutputConfig *outputConfig `json:"output_config,omitempty"`
|
||||
Tools []anthropicTool `json:"tools,omitempty"`
|
||||
Stream bool `json:"stream"`
|
||||
}
|
||||
|
||||
// thinkingConfig requests extended thinking with a token budget. Type is always
|
||||
// "enabled"; BudgetTokens is how many tokens the model may spend thinking (it is
|
||||
// counted against max_tokens).
|
||||
// thinkingConfig requests extended thinking. Anthropic uses "enabled" with a
|
||||
// token budget; MiniMax-M3.1-Flash uses "adaptive" with output_config.effort.
|
||||
type thinkingConfig struct {
|
||||
Type string `json:"type"`
|
||||
BudgetTokens int `json:"budget_tokens"`
|
||||
BudgetTokens int `json:"budget_tokens,omitempty"`
|
||||
}
|
||||
|
||||
type outputConfig struct {
|
||||
Effort string `json:"effort"`
|
||||
}
|
||||
|
||||
type anthropicMessage struct {
|
||||
|
||||
@@ -288,10 +288,11 @@ func TestScanSSEDataWithContextContentResetsOnData(t *testing.T) {
|
||||
pr, pw := io.Pipe()
|
||||
|
||||
go func() {
|
||||
// One data line every 30ms for ~300ms (well past the 120ms content window,
|
||||
// with comfortable slack under the 100ms idle timeout), so the content
|
||||
// watchdog keeps resetting, then close cleanly.
|
||||
for i := 0; i < 10; i++ {
|
||||
// One data line every 30ms for ~750ms (well past the 600ms content window,
|
||||
// with ~470ms of slack under the 500ms idle timeout, so a scheduling stall
|
||||
// on a busy shared runner does not trip it), so the content watchdog keeps
|
||||
// resetting, then close cleanly.
|
||||
for i := 0; i < 25; i++ {
|
||||
if _, err := io.WriteString(pw, "data: chunk\n\n"); err != nil {
|
||||
return
|
||||
}
|
||||
@@ -303,7 +304,7 @@ func TestScanSSEDataWithContextContentResetsOnData(t *testing.T) {
|
||||
n := 0
|
||||
done := make(chan error, 1)
|
||||
go func() {
|
||||
done <- ScanSSEDataWithContext(context.Background(), func() {}, pr, 100*time.Millisecond, func(string) bool { n++; return true })
|
||||
done <- ScanSSEDataWithContext(context.Background(), func() {}, pr, 500*time.Millisecond, func(string) bool { n++; return true })
|
||||
}()
|
||||
|
||||
select {
|
||||
@@ -314,8 +315,8 @@ func TestScanSSEDataWithContextContentResetsOnData(t *testing.T) {
|
||||
case <-time.After(3 * time.Second):
|
||||
t.Fatal("ScanSSEDataWithContext hung on a producing stream")
|
||||
}
|
||||
if n != 10 {
|
||||
t.Fatalf("handled %d data lines, want 10", n)
|
||||
if n != 25 {
|
||||
t.Fatalf("handled %d data lines, want 25", n)
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,258 @@
|
||||
package skills
|
||||
|
||||
import (
|
||||
"crypto/sha256"
|
||||
"encoding/hex"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"io/fs"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"sort"
|
||||
"strings"
|
||||
)
|
||||
|
||||
// A skill is a directory, not just its SKILL.md: the instructions often point at
|
||||
// scripts, references or assets that sit beside them (the agentskills.io
|
||||
// layout). Install copies that directory, and the skill tool says where it is.
|
||||
|
||||
// Install refuses a skill tree larger than this. A skill is a handful of
|
||||
// scripts and documents; a source that is really a whole repository or a pile
|
||||
// of binaries should fail loudly instead of filling the skills directory.
|
||||
var (
|
||||
maxSkillTreeFiles = 1000
|
||||
maxSkillTreeBytes = int64(32 << 20)
|
||||
)
|
||||
|
||||
// bundledFileListLimit caps how many bundled files the skill tool lists, so a
|
||||
// large skill does not crowd the instructions out of the tool output.
|
||||
const bundledFileListLimit = 50
|
||||
|
||||
// skipSkillEntry reports whether a skill tree entry is left out of an install,
|
||||
// a tree hash and a listing alike. Hidden entries cover VCS metadata (.git,
|
||||
// which a cloned source always has) and local clutter such as .DS_Store or
|
||||
// .env; they are not part of what a skill ships.
|
||||
func skipSkillEntry(name string) bool {
|
||||
return strings.HasPrefix(name, ".")
|
||||
}
|
||||
|
||||
// copySkillTree copies the skill directory src into dst, which must exist.
|
||||
// Regular files are copied with normalized permissions (0o755 when the source
|
||||
// is executable, 0o644 otherwise), so a script stays runnable without carrying
|
||||
// over group- or world-writable bits. Symlinks are not followed or copied:
|
||||
// their relative paths come back in skipped, so the caller can say so. Other
|
||||
// non-regular entries (devices, sockets, pipes) are left out. bundled counts
|
||||
// the files copied besides SKILL.md.
|
||||
func copySkillTree(src, dst string) (bundled int, skipped []string, err error) {
|
||||
files := 0
|
||||
var total int64
|
||||
err = filepath.WalkDir(src, func(path string, entry fs.DirEntry, walkErr error) error {
|
||||
if walkErr != nil {
|
||||
return walkErr
|
||||
}
|
||||
if path == src {
|
||||
return nil
|
||||
}
|
||||
rel, err := filepath.Rel(src, path)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if skipSkillEntry(entry.Name()) {
|
||||
if entry.IsDir() {
|
||||
return filepath.SkipDir
|
||||
}
|
||||
return nil
|
||||
}
|
||||
if entry.Type()&fs.ModeSymlink != 0 {
|
||||
skipped = append(skipped, filepath.ToSlash(rel))
|
||||
return nil
|
||||
}
|
||||
target := filepath.Join(dst, rel)
|
||||
if entry.IsDir() {
|
||||
return os.MkdirAll(target, 0o755)
|
||||
}
|
||||
if !entry.Type().IsRegular() {
|
||||
return nil
|
||||
}
|
||||
info, err := entry.Info()
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
files++
|
||||
total += info.Size()
|
||||
if files > maxSkillTreeFiles {
|
||||
return fmt.Errorf("skill has more than %d files; a skill directory should hold only what the skill uses", maxSkillTreeFiles)
|
||||
}
|
||||
if total > maxSkillTreeBytes {
|
||||
return fmt.Errorf("skill is larger than %d MiB; a skill directory should hold only what the skill uses", maxSkillTreeBytes>>20)
|
||||
}
|
||||
if filepath.ToSlash(rel) != skillFileName {
|
||||
bundled++
|
||||
}
|
||||
mode := os.FileMode(0o644)
|
||||
if info.Mode().Perm()&0o111 != 0 {
|
||||
mode = 0o755
|
||||
}
|
||||
return copySkillFile(path, target, mode)
|
||||
})
|
||||
if err != nil {
|
||||
return 0, nil, err
|
||||
}
|
||||
return bundled, skipped, nil
|
||||
}
|
||||
|
||||
func copySkillFile(src, dst string, mode os.FileMode) error {
|
||||
in, err := os.Open(src)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer in.Close()
|
||||
out, err := os.OpenFile(dst, os.O_WRONLY|os.O_CREATE|os.O_EXCL, mode)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if _, err := io.Copy(out, in); err != nil {
|
||||
_ = out.Close()
|
||||
return err
|
||||
}
|
||||
if err := out.Close(); err != nil {
|
||||
return err
|
||||
}
|
||||
// The create mode is filtered by the umask; set it outright so an
|
||||
// executable script is still executable wherever the install ran.
|
||||
return os.Chmod(dst, mode)
|
||||
}
|
||||
|
||||
// skillTreeHash hashes every file a skill ships, with the same entries
|
||||
// copySkillTree copies: its relative path, whether it is executable, and its
|
||||
// content. Sorted by path, so the hash depends only on the tree.
|
||||
func skillTreeHash(dir string) (string, error) {
|
||||
type entry struct {
|
||||
rel string
|
||||
exec bool
|
||||
sum string
|
||||
}
|
||||
var entries []entry
|
||||
err := filepath.WalkDir(dir, func(path string, item fs.DirEntry, walkErr error) error {
|
||||
if walkErr != nil {
|
||||
return walkErr
|
||||
}
|
||||
if path == dir {
|
||||
return nil
|
||||
}
|
||||
if skipSkillEntry(item.Name()) {
|
||||
if item.IsDir() {
|
||||
return filepath.SkipDir
|
||||
}
|
||||
return nil
|
||||
}
|
||||
if !item.Type().IsRegular() {
|
||||
return nil
|
||||
}
|
||||
info, err := item.Info()
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
data, err := os.ReadFile(path)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
rel, err := filepath.Rel(dir, path)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
sum := sha256.Sum256(data)
|
||||
entries = append(entries, entry{rel: filepath.ToSlash(rel), exec: info.Mode().Perm()&0o111 != 0, sum: hex.EncodeToString(sum[:])})
|
||||
return nil
|
||||
})
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
sort.Slice(entries, func(i, j int) bool { return entries[i].rel < entries[j].rel })
|
||||
hash := sha256.New()
|
||||
for _, item := range entries {
|
||||
flag := "-"
|
||||
if item.exec {
|
||||
flag = "x"
|
||||
}
|
||||
// Length-prefixed, so no path can be read as the start of another entry.
|
||||
fmt.Fprintf(hash, "%d:%s|%s|%s;", len(item.rel), item.rel, flag, item.sum)
|
||||
}
|
||||
return "sha256:" + hex.EncodeToString(hash.Sum(nil)), nil
|
||||
}
|
||||
|
||||
// BundledFiles lists the files a skill ships besides its SKILL.md, as
|
||||
// slash-separated paths relative to the skill's directory, sorted. Hidden
|
||||
// entries and symlinks are left out: the listing tells the model what the
|
||||
// skill brings, and is not a way to reach anything outside it. total is the
|
||||
// number of files found; at most limit come back.
|
||||
func BundledFiles(skill Skill, limit int) (files []string, total int, err error) {
|
||||
dir := filepath.Dir(skill.Path)
|
||||
if strings.TrimSpace(skill.Path) == "" {
|
||||
return nil, 0, errors.New("skill has no path")
|
||||
}
|
||||
err = filepath.WalkDir(dir, func(path string, entry fs.DirEntry, walkErr error) error {
|
||||
if walkErr != nil {
|
||||
return walkErr
|
||||
}
|
||||
if path == dir {
|
||||
return nil
|
||||
}
|
||||
if skipSkillEntry(entry.Name()) {
|
||||
if entry.IsDir() {
|
||||
return filepath.SkipDir
|
||||
}
|
||||
return nil
|
||||
}
|
||||
if !entry.Type().IsRegular() {
|
||||
return nil
|
||||
}
|
||||
rel, err := filepath.Rel(dir, path)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
rel = filepath.ToSlash(rel)
|
||||
if rel == skillFileName {
|
||||
return nil
|
||||
}
|
||||
total++
|
||||
if total > maxSkillTreeFiles {
|
||||
// A directory this large is not something the listing should walk
|
||||
// to the end of; the count stops being exact past the cap.
|
||||
return filepath.SkipAll
|
||||
}
|
||||
files = append(files, rel)
|
||||
return nil
|
||||
})
|
||||
if err != nil {
|
||||
return nil, 0, err
|
||||
}
|
||||
sort.Strings(files)
|
||||
if limit >= 0 && len(files) > limit {
|
||||
files = files[:limit]
|
||||
}
|
||||
return files, total, nil
|
||||
}
|
||||
|
||||
// ToolOutput is what the skill tool returns for a loaded skill: its SKILL.md
|
||||
// body and, when the skill ships other files, the directory they are in and
|
||||
// what they are, so instructions that say "run scripts/extract.py" can be
|
||||
// followed. A skill that is only a SKILL.md gets its body back unchanged.
|
||||
func ToolOutput(skill Skill) string {
|
||||
files, total, err := BundledFiles(skill, bundledFileListLimit)
|
||||
if err != nil || total == 0 {
|
||||
return skill.Content
|
||||
}
|
||||
var builder strings.Builder
|
||||
builder.WriteString(strings.TrimRight(skill.Content, "\n"))
|
||||
builder.WriteString("\n\n---\n")
|
||||
fmt.Fprintf(&builder, "This skill's files are in %s. Paths in the instructions above are relative to that directory.\n", filepath.Dir(skill.Path))
|
||||
for _, file := range files {
|
||||
builder.WriteString("- " + file + "\n")
|
||||
}
|
||||
if more := total - len(files); more > 0 {
|
||||
fmt.Fprintf(&builder, "- (and %d more)\n", more)
|
||||
}
|
||||
return builder.String()
|
||||
}
|
||||
@@ -0,0 +1,351 @@
|
||||
package skills
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"runtime"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
const bundledSkillManifest = "---\nname: pdf\ndescription: fill PDF forms\n---\nRun scripts/fill.py with the form path.\n"
|
||||
|
||||
// writeBundledSourceSkill lays down a skill in the agentskills.io shape: a
|
||||
// SKILL.md plus the scripts, references and assets it points at, and the hidden
|
||||
// clutter a cloned source carries.
|
||||
func writeBundledSourceSkill(t *testing.T, dir string) string {
|
||||
t.Helper()
|
||||
writeSourceSkill(t, dir, bundledSkillManifest)
|
||||
files := map[string]string{
|
||||
"scripts/fill.py": "print('fill')\n",
|
||||
"references/form.md": "# Form fields\n",
|
||||
"assets/logo.svg": "<svg/>\n",
|
||||
"LICENSE.txt": "MIT\n",
|
||||
".git/config": "[core]\n",
|
||||
".env": "TOKEN=local-only\n",
|
||||
"scripts/.cache/tmp": "scratch\n",
|
||||
}
|
||||
for rel, content := range files {
|
||||
path := filepath.Join(dir, filepath.FromSlash(rel))
|
||||
if err := os.MkdirAll(filepath.Dir(path), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
mode := os.FileMode(0o644)
|
||||
if strings.HasPrefix(rel, "scripts/") {
|
||||
mode = 0o755
|
||||
}
|
||||
if err := os.WriteFile(path, []byte(content), mode); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
return dir
|
||||
}
|
||||
|
||||
func TestInstallCopiesTheSkillDirectory(t *testing.T) {
|
||||
destDir := t.TempDir()
|
||||
src := writeBundledSourceSkill(t, filepath.Join(t.TempDir(), "pdf"))
|
||||
|
||||
result, err := Install(context.Background(), InstallOptions{Source: src, Dir: destDir})
|
||||
if err != nil {
|
||||
t.Fatalf("Install: %v", err)
|
||||
}
|
||||
installed := filepath.Join(destDir, "pdf")
|
||||
for _, rel := range []string{"SKILL.md", "scripts/fill.py", "references/form.md", "assets/logo.svg", "LICENSE.txt"} {
|
||||
if _, err := os.Stat(filepath.Join(installed, filepath.FromSlash(rel))); err != nil {
|
||||
t.Errorf("%s was not installed: %v", rel, err)
|
||||
}
|
||||
}
|
||||
for _, rel := range []string{".git", ".env", "scripts/.cache"} {
|
||||
if _, err := os.Stat(filepath.Join(installed, filepath.FromSlash(rel))); err == nil {
|
||||
t.Errorf("hidden %s was installed; it is not part of the skill", rel)
|
||||
}
|
||||
}
|
||||
if !strings.HasPrefix(result.TreeHash, "sha256:") {
|
||||
t.Fatalf("TreeHash = %q, want a sha256 tree hash", result.TreeHash)
|
||||
}
|
||||
lock, err := ReadLock(destDir)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if lock["pdf"].TreeHash != result.TreeHash || lock["pdf"].Hash != result.Hash {
|
||||
t.Fatalf("lock entry = %+v, want the install's hashes %q and %q", lock["pdf"], result.Hash, result.TreeHash)
|
||||
}
|
||||
if runtime.GOOS == "windows" {
|
||||
return
|
||||
}
|
||||
script, err := os.Stat(filepath.Join(installed, "scripts", "fill.py"))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if script.Mode().Perm() != 0o755 {
|
||||
t.Errorf("installed script mode = %v, want 0755 so the skill can still run it", script.Mode().Perm())
|
||||
}
|
||||
reference, err := os.Stat(filepath.Join(installed, "references", "form.md"))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if reference.Mode().Perm() != 0o644 {
|
||||
t.Errorf("installed reference mode = %v, want 0644", reference.Mode().Perm())
|
||||
}
|
||||
}
|
||||
|
||||
func TestInstallSkipsSymlinksAndSaysSo(t *testing.T) {
|
||||
destDir := t.TempDir()
|
||||
src := writeBundledSourceSkill(t, filepath.Join(t.TempDir(), "pdf"))
|
||||
outside := filepath.Join(t.TempDir(), "secret.txt")
|
||||
if err := os.WriteFile(outside, []byte("not part of the skill\n"), 0o600); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.Symlink(outside, filepath.Join(src, "references", "linked.md")); err != nil {
|
||||
t.Skipf("symlinks unavailable: %v", err)
|
||||
}
|
||||
|
||||
result, err := Install(context.Background(), InstallOptions{Source: src, Dir: destDir})
|
||||
if err != nil {
|
||||
t.Fatalf("Install: %v", err)
|
||||
}
|
||||
if len(result.SkippedLinks) != 1 || result.SkippedLinks[0] != "references/linked.md" {
|
||||
t.Fatalf("SkippedLinks = %v, want [references/linked.md]", result.SkippedLinks)
|
||||
}
|
||||
if _, err := os.Lstat(filepath.Join(destDir, "pdf", "references", "linked.md")); err == nil {
|
||||
t.Fatal("a symlink from the source was installed")
|
||||
}
|
||||
}
|
||||
|
||||
func TestInstallRefusesAnOversizedSkill(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
name string
|
||||
files int
|
||||
bytes int64
|
||||
want string
|
||||
}{
|
||||
{name: "too many files", files: 3, bytes: maxSkillTreeBytes, want: "more than 3 files"},
|
||||
{name: "too many bytes", files: maxSkillTreeFiles, bytes: 1 << 20, want: "larger than 1 MiB"},
|
||||
} {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
files, bytes := maxSkillTreeFiles, maxSkillTreeBytes
|
||||
t.Cleanup(func() { maxSkillTreeFiles, maxSkillTreeBytes = files, bytes })
|
||||
maxSkillTreeFiles, maxSkillTreeBytes = tc.files, tc.bytes
|
||||
|
||||
destDir := t.TempDir()
|
||||
src := writeBundledSourceSkill(t, filepath.Join(t.TempDir(), "pdf"))
|
||||
big := make([]byte, 2<<20)
|
||||
if err := os.WriteFile(filepath.Join(src, "assets", "big.bin"), big, 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
_, err := Install(context.Background(), InstallOptions{Source: src, Dir: destDir})
|
||||
if err == nil || !strings.Contains(err.Error(), tc.want) {
|
||||
t.Fatalf("Install error = %v, want %q", err, tc.want)
|
||||
}
|
||||
if _, statErr := os.Stat(filepath.Join(destDir, "pdf")); statErr == nil {
|
||||
t.Fatal("a refused install left a skill directory behind")
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestReinstallWithOnlyABundledFileChangedIsAnUpdate(t *testing.T) {
|
||||
destDir := t.TempDir()
|
||||
src := writeBundledSourceSkill(t, filepath.Join(t.TempDir(), "pdf"))
|
||||
first, err := Install(context.Background(), InstallOptions{Source: src, Dir: destDir})
|
||||
if err != nil {
|
||||
t.Fatalf("first Install: %v", err)
|
||||
}
|
||||
if err := os.WriteFile(filepath.Join(src, "scripts", "fill.py"), []byte("print('fill v2')\n"), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
second, err := Install(context.Background(), InstallOptions{Source: src, Dir: destDir})
|
||||
if err != nil {
|
||||
t.Fatalf("second Install: %v", err)
|
||||
}
|
||||
if !second.Updated {
|
||||
t.Fatal("a reinstall that changed a bundled script was not reported as an update")
|
||||
}
|
||||
if second.Hash != first.Hash || second.TreeHash == first.TreeHash {
|
||||
t.Fatalf("hashes = %q/%q after %q/%q, want the same SKILL.md hash and a new tree hash", second.Hash, second.TreeHash, first.Hash, first.TreeHash)
|
||||
}
|
||||
if second.PreviousHash != first.Hash || second.PreviousTreeHash != first.TreeHash {
|
||||
t.Fatalf("previous hashes = %q/%q, want the first install's %q/%q", second.PreviousHash, second.PreviousTreeHash, first.Hash, first.TreeHash)
|
||||
}
|
||||
got, err := os.ReadFile(filepath.Join(destDir, "pdf", "scripts", "fill.py"))
|
||||
if err != nil || string(got) != "print('fill v2')\n" {
|
||||
t.Fatalf("installed script = %q, %v; want the new version", got, err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestInfoReportsDriftInABundledFile(t *testing.T) {
|
||||
destDir := t.TempDir()
|
||||
src := writeBundledSourceSkill(t, filepath.Join(t.TempDir(), "pdf"))
|
||||
if _, err := Install(context.Background(), InstallOptions{Source: src, Dir: destDir}); err != nil {
|
||||
t.Fatalf("Install: %v", err)
|
||||
}
|
||||
if info, ok := Info(destDir, "pdf"); !ok || info.HashDrift {
|
||||
t.Fatalf("a fresh install reports drift: %+v, %v", info, ok)
|
||||
}
|
||||
script := filepath.Join(destDir, "pdf", "scripts", "fill.py")
|
||||
if err := os.WriteFile(script, []byte("print('edited by hand')\n"), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if info, _ := Info(destDir, "pdf"); !info.HashDrift {
|
||||
t.Fatal("an edited bundled script is not reported as drift")
|
||||
}
|
||||
}
|
||||
|
||||
// A lock entry written before installs carried their bundled files has no tree
|
||||
// hash. Checking its tree would report every such skill as drifted, so only
|
||||
// its SKILL.md is checked, as before.
|
||||
func TestLockEntryWithoutATreeHashChecksOnlySKILLmd(t *testing.T) {
|
||||
destDir := t.TempDir()
|
||||
src := writeBundledSourceSkill(t, filepath.Join(t.TempDir(), "pdf"))
|
||||
if _, err := Install(context.Background(), InstallOptions{Source: src, Dir: destDir}); err != nil {
|
||||
t.Fatalf("Install: %v", err)
|
||||
}
|
||||
dropTreeHash(t, destDir, "pdf")
|
||||
|
||||
if err := os.WriteFile(filepath.Join(destDir, "pdf", "scripts", "fill.py"), []byte("print('edited')\n"), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if info, _ := Info(destDir, "pdf"); info.HashDrift {
|
||||
t.Fatal("an entry without a tree hash reported drift for a bundled file")
|
||||
}
|
||||
if err := os.WriteFile(filepath.Join(destDir, "pdf", skillFileName), []byte(bundledSkillManifest+"edited\n"), 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if info, _ := Info(destDir, "pdf"); !info.HashDrift {
|
||||
t.Fatal("an edited SKILL.md under an old lock entry is not reported as drift")
|
||||
}
|
||||
}
|
||||
|
||||
// Reinstalling over an entry from before tree hashes compares with what that
|
||||
// install left, SKILL.md alone: an unchanged skill that is only a SKILL.md is
|
||||
// not an update, and one whose bundled files this install adds is.
|
||||
func TestReinstallOverAnEntryWithoutATreeHash(t *testing.T) {
|
||||
t.Run("SKILL.md only", func(t *testing.T) {
|
||||
destDir := t.TempDir()
|
||||
src := writeSourceSkill(t, filepath.Join(t.TempDir(), "pdf"), bundledSkillManifest)
|
||||
if _, err := Install(context.Background(), InstallOptions{Source: src, Dir: destDir}); err != nil {
|
||||
t.Fatalf("first Install: %v", err)
|
||||
}
|
||||
dropTreeHash(t, destDir, "pdf")
|
||||
|
||||
result, err := Install(context.Background(), InstallOptions{Source: src, Dir: destDir})
|
||||
if err != nil {
|
||||
t.Fatalf("second Install: %v", err)
|
||||
}
|
||||
if result.Updated {
|
||||
t.Fatalf("reinstalling an unchanged SKILL.md-only skill over an old entry was reported as an update: %+v", result)
|
||||
}
|
||||
lock, err := ReadLock(destDir)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if lock["pdf"].TreeHash != result.TreeHash {
|
||||
t.Fatalf("lock tree hash = %q after the reinstall, want %q", lock["pdf"].TreeHash, result.TreeHash)
|
||||
}
|
||||
})
|
||||
t.Run("with bundled files", func(t *testing.T) {
|
||||
destDir := t.TempDir()
|
||||
src := writeBundledSourceSkill(t, filepath.Join(t.TempDir(), "pdf"))
|
||||
first, err := Install(context.Background(), InstallOptions{Source: src, Dir: destDir})
|
||||
if err != nil {
|
||||
t.Fatalf("first Install: %v", err)
|
||||
}
|
||||
dropTreeHash(t, destDir, "pdf")
|
||||
|
||||
result, err := Install(context.Background(), InstallOptions{Source: src, Dir: destDir})
|
||||
if err != nil {
|
||||
t.Fatalf("second Install: %v", err)
|
||||
}
|
||||
if !result.Updated || result.Hash != first.Hash || result.PreviousHash != first.Hash || result.PreviousTreeHash != "" {
|
||||
t.Fatalf("result = %+v, want an update with SKILL.md hash %q unchanged and no previous tree hash", result, first.Hash)
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
// dropTreeHash rewrites the lock entry for name the way an install from before
|
||||
// tree hashes left it: a source and a SKILL.md hash, nothing for the tree.
|
||||
func dropTreeHash(t *testing.T, destDir, name string) {
|
||||
t.Helper()
|
||||
lock, err := ReadLock(destDir)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
entry := lock[name]
|
||||
entry.TreeHash = ""
|
||||
lock[name] = entry
|
||||
data, err := json.Marshal(lock)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.WriteFile(filepath.Join(destDir, LockFileName), data, 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestToolOutputSaysWhereTheBundledFilesAre(t *testing.T) {
|
||||
root := t.TempDir()
|
||||
writeBundledSourceSkill(t, filepath.Join(root, "pdf"))
|
||||
skill, ok := Get(root, "pdf")
|
||||
if !ok {
|
||||
t.Fatal("skill not loaded")
|
||||
}
|
||||
|
||||
output := ToolOutput(skill)
|
||||
if !strings.HasPrefix(output, strings.TrimRight(skill.Content, "\n")) {
|
||||
t.Fatalf("the instructions do not come first:\n%s", output)
|
||||
}
|
||||
if !strings.Contains(output, filepath.Dir(skill.Path)) {
|
||||
t.Fatalf("the output does not say where the skill's files are:\n%s", output)
|
||||
}
|
||||
for _, want := range []string{"- LICENSE.txt", "- assets/logo.svg", "- references/form.md", "- scripts/fill.py"} {
|
||||
if !strings.Contains(output, want+"\n") {
|
||||
t.Errorf("output does not list %q:\n%s", want, output)
|
||||
}
|
||||
}
|
||||
for _, hidden := range []string{".env", ".git", ".cache", "SKILL.md\n"} {
|
||||
if strings.Contains(output, "- "+hidden) {
|
||||
t.Errorf("output lists %q:\n%s", hidden, output)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestToolOutputCapsALongListing(t *testing.T) {
|
||||
root := t.TempDir()
|
||||
dir := writeSourceSkill(t, filepath.Join(root, "many"), "---\nname: many\n---\nbody\n")
|
||||
for i := 0; i < bundledFileListLimit+7; i++ {
|
||||
path := filepath.Join(dir, "references", fmt.Sprintf("part-%03d.md", i))
|
||||
if err := os.MkdirAll(filepath.Dir(path), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.WriteFile(path, []byte("x\n"), 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
skill, ok := Get(root, "many")
|
||||
if !ok {
|
||||
t.Fatal("skill not loaded")
|
||||
}
|
||||
output := ToolOutput(skill)
|
||||
if got := strings.Count(output, "\n- references/"); got != bundledFileListLimit {
|
||||
t.Fatalf("listed %d files, want the first %d:\n%s", got, bundledFileListLimit, output)
|
||||
}
|
||||
if !strings.Contains(output, "- (and 7 more)\n") {
|
||||
t.Fatalf("output does not say how many more there are:\n%s", output)
|
||||
}
|
||||
}
|
||||
|
||||
func TestToolOutputOfAManifestOnlySkillIsItsContent(t *testing.T) {
|
||||
root := t.TempDir()
|
||||
writeSourceSkill(t, filepath.Join(root, "plain"), "---\nname: plain\n---\nJust instructions.\n")
|
||||
skill, ok := Get(root, "plain")
|
||||
if !ok {
|
||||
t.Fatal("skill not loaded")
|
||||
}
|
||||
if got := ToolOutput(skill); got != skill.Content {
|
||||
t.Fatalf("ToolOutput = %q, want the unchanged content %q", got, skill.Content)
|
||||
}
|
||||
}
|
||||
@@ -15,9 +15,10 @@ func Info(dir string, name string) (SkillInfo, bool) {
|
||||
if entry, found := lock[skill.Name]; found {
|
||||
info.Source = entry.Source
|
||||
info.Hash = entry.Hash
|
||||
info.TreeHash = entry.TreeHash
|
||||
}
|
||||
}
|
||||
info.HashDrift = skillHashDrift(skill, info.Hash)
|
||||
info.HashDrift = skillHashDrift(skill, info.Hash, info.TreeHash)
|
||||
return info, true
|
||||
}
|
||||
|
||||
|
||||
+93
-28
@@ -1,9 +1,9 @@
|
||||
package skills
|
||||
|
||||
// Distribution: install a skill from a git URL or a local path into the skills
|
||||
// directory, with a content hash recorded in a lockfile (skills.lock) so every
|
||||
// install/update is verifiable. Skills are markdown, so install NEVER executes
|
||||
// fetched content — it copies and validates the SKILL.md and nothing else.
|
||||
// directory, with content hashes recorded in a lockfile (skills.lock) so every
|
||||
// install/update is verifiable. Install copies the skill's directory, its
|
||||
// SKILL.md and the files beside it, and NEVER executes fetched content.
|
||||
|
||||
import (
|
||||
"context"
|
||||
@@ -61,16 +61,30 @@ type InstallResult struct {
|
||||
Hash string `json:"hash"`
|
||||
// Source echoes the source the skill was installed from.
|
||||
Source string `json:"source"`
|
||||
// TreeHash covers every file the skill ships, SKILL.md included; Hash is
|
||||
// still the SKILL.md hash alone.
|
||||
TreeHash string `json:"treeHash"`
|
||||
// Updated is true when an existing install was replaced; PreviousHash then
|
||||
// carries the prior recorded hash so a caller can show the change.
|
||||
Updated bool `json:"updated"`
|
||||
PreviousHash string `json:"previousHash,omitempty"`
|
||||
// PreviousTreeHash is the tree hash the replaced install recorded. It is
|
||||
// empty when that install predates tree hashes, and so copied SKILL.md
|
||||
// alone.
|
||||
PreviousTreeHash string `json:"previousTreeHash,omitempty"`
|
||||
// SkippedLinks lists symlinks in the source, relative to the skill
|
||||
// directory. Install neither follows nor copies them.
|
||||
SkippedLinks []string `json:"skippedLinks,omitempty"`
|
||||
}
|
||||
|
||||
// LockEntry records the source and content hash for one installed skill.
|
||||
type LockEntry struct {
|
||||
Source string `json:"source"`
|
||||
Hash string `json:"hash"`
|
||||
// TreeHash covers the whole installed skill directory. Entries written
|
||||
// before skills installed their bundled files have none, and are checked on
|
||||
// their SKILL.md alone.
|
||||
TreeHash string `json:"treeHash,omitempty"`
|
||||
}
|
||||
|
||||
// SkillInfo bundles a discovered skill with its recorded source and hash, for
|
||||
@@ -79,12 +93,14 @@ type SkillInfo struct {
|
||||
Skill Skill `json:"skill"`
|
||||
Source string `json:"source,omitempty"`
|
||||
Hash string `json:"hash,omitempty"`
|
||||
TreeHash string `json:"treeHash,omitempty"`
|
||||
HashDrift bool `json:"hashDrift"`
|
||||
}
|
||||
|
||||
// Install fetches the skill at options.Source and copies its SKILL.md into
|
||||
// options.Dir/<name>/, validating the frontmatter and recording a content hash
|
||||
// in the lockfile. A git URL is fetched via the (injectable) GitRunner into a
|
||||
// Install fetches the skill at options.Source and copies its directory into
|
||||
// options.Dir/<name>/: SKILL.md and the scripts, references and assets beside
|
||||
// it. It validates the frontmatter and records the SKILL.md hash and a hash of
|
||||
// the whole tree in the lockfile. A git URL is fetched via the (injectable) GitRunner into a
|
||||
// temp dir; a local path is read in place. Fetched content is never executed.
|
||||
func Install(ctx context.Context, options InstallOptions) (InstallResult, error) {
|
||||
source := strings.TrimSpace(options.Source)
|
||||
@@ -133,10 +149,11 @@ func Install(ctx context.Context, options InstallOptions) (InstallResult, error)
|
||||
if err := os.MkdirAll(staged, 0o755); err != nil {
|
||||
return InstallResult{}, fmt.Errorf("create staged skill dir: %w", err)
|
||||
}
|
||||
stagedManifest := filepath.Join(staged, skillFileName)
|
||||
if err := os.WriteFile(stagedManifest, data, 0o644); err != nil {
|
||||
return InstallResult{}, fmt.Errorf("stage SKILL.md: %w", err)
|
||||
bundled, skippedLinks, err := copySkillTree(skillDir, staged)
|
||||
if err != nil {
|
||||
return InstallResult{}, fmt.Errorf("stage skill directory: %w", err)
|
||||
}
|
||||
stagedManifest := filepath.Join(staged, skillFileName)
|
||||
stagedData, err := os.ReadFile(stagedManifest)
|
||||
if err != nil || hashContent(stagedData) != hash {
|
||||
if err != nil {
|
||||
@@ -169,8 +186,13 @@ func Install(ctx context.Context, options InstallOptions) (InstallResult, error)
|
||||
return InstallResult{}, fmt.Errorf("%w: %q is installed from %s (use --force to overwrite)", ErrNameClash, name, previous.Source)
|
||||
}
|
||||
|
||||
treeHash, err := skillTreeHash(staged)
|
||||
if err != nil {
|
||||
return InstallResult{}, fmt.Errorf("hash staged skill directory: %w", err)
|
||||
}
|
||||
|
||||
target := filepath.Join(dir, name)
|
||||
lock[name] = LockEntry{Source: source, Hash: hash}
|
||||
lock[name] = LockEntry{Source: source, Hash: hash, TreeHash: treeHash}
|
||||
if err := installtxn.CommitDir(target, staged, func() error {
|
||||
return writeLock(dir, lock)
|
||||
}); err != nil {
|
||||
@@ -178,14 +200,26 @@ func Install(ctx context.Context, options InstallOptions) (InstallResult, error)
|
||||
}
|
||||
|
||||
result := InstallResult{
|
||||
Name: name,
|
||||
Path: filepath.Join(target, skillFileName),
|
||||
Hash: hash,
|
||||
Source: source,
|
||||
Name: name,
|
||||
Path: filepath.Join(target, skillFileName),
|
||||
Hash: hash,
|
||||
TreeHash: treeHash,
|
||||
Source: source,
|
||||
SkippedLinks: skippedLinks,
|
||||
}
|
||||
if existed {
|
||||
result.Updated = previous.Hash != hash
|
||||
result.PreviousHash = previous.Hash
|
||||
result.PreviousTreeHash = previous.TreeHash
|
||||
if previous.TreeHash == "" {
|
||||
// An entry from before tree hashes is from an install that copied
|
||||
// SKILL.md alone. Against that, this install is an update when
|
||||
// SKILL.md changed or it now brings bundled files; a skill that is
|
||||
// still only its unchanged SKILL.md is not.
|
||||
result.Updated = previous.Hash != hash || bundled > 0
|
||||
} else {
|
||||
// A changed script with the same SKILL.md is still an update.
|
||||
result.Updated = previous.Hash != hash || previous.TreeHash != treeHash
|
||||
}
|
||||
}
|
||||
return result, nil
|
||||
}
|
||||
@@ -193,8 +227,8 @@ func Install(ctx context.Context, options InstallOptions) (InstallResult, error)
|
||||
// lockReconciler answers, for one interrupted workspace, which of the two trees
|
||||
// beside each other the lockfile records. A kill between the tree swap and the
|
||||
// lockfile publish leaves exactly what a kill after both leaves, so filesystem
|
||||
// shape cannot tell them apart and only the recorded hash can: the tree it
|
||||
// describes is the one the user was told they had.
|
||||
// shape cannot tell them apart and only the recorded hashes can: the tree they
|
||||
// describe is the one the user was told they had.
|
||||
func lockReconciler(dir string) installtxn.Reconciler {
|
||||
return func(name string, target string, backup string) (installtxn.Phase, error) {
|
||||
lock, err := ReadLock(dir)
|
||||
@@ -215,24 +249,45 @@ func lockReconciler(dir string) installtxn.Reconciler {
|
||||
// recorded one and recovery must not pick between them.
|
||||
return installtxn.PhaseUnknown, nil
|
||||
}
|
||||
targetHash, err := manifestHash(target)
|
||||
committed, err := treeMatchesEntry(target, entry)
|
||||
if err != nil {
|
||||
return installtxn.PhaseUnknown, err
|
||||
}
|
||||
if targetHash == entry.Hash {
|
||||
if committed {
|
||||
return installtxn.PhaseCommitted, nil
|
||||
}
|
||||
backupHash, err := manifestHash(backup)
|
||||
prePublish, err := treeMatchesEntry(backup, entry)
|
||||
if err != nil {
|
||||
return installtxn.PhaseUnknown, err
|
||||
}
|
||||
if backupHash == entry.Hash {
|
||||
if prePublish {
|
||||
return installtxn.PhasePrePublish, nil
|
||||
}
|
||||
return installtxn.PhaseUnknown, nil
|
||||
}
|
||||
}
|
||||
|
||||
// treeMatchesEntry reports whether the skill tree at path is the one entry
|
||||
// records. A reinstall that changes only a bundled file leaves SKILL.md the same
|
||||
// in both trees of an interrupted workspace, so an entry with a tree hash has to
|
||||
// match on that as well. An entry from before tree hashes records SKILL.md
|
||||
// alone, and that is all it can be matched on. As in manifestHash, a tree with
|
||||
// no SKILL.md is a non-match and any other read error is returned.
|
||||
func treeMatchesEntry(path string, entry LockEntry) (bool, error) {
|
||||
sum, err := manifestHash(path)
|
||||
if err != nil || sum != entry.Hash {
|
||||
return false, err
|
||||
}
|
||||
if entry.TreeHash == "" {
|
||||
return true, nil
|
||||
}
|
||||
tree, err := skillTreeHash(path)
|
||||
if err != nil {
|
||||
return false, err
|
||||
}
|
||||
return tree == entry.TreeHash, nil
|
||||
}
|
||||
|
||||
// manifestHash hashes the SKILL.md under path the same way an install records
|
||||
// it. A tree with no SKILL.md is a non-match rather than a failure: an install
|
||||
// killed mid-copy can leave one, and it simply is not the tree the lockfile
|
||||
@@ -346,9 +401,10 @@ func InfoFromRoots(primaryDir string, roots []string, name string) (SkillInfo, b
|
||||
if entry, found := lock[skill.Name]; found {
|
||||
info.Source = entry.Source
|
||||
info.Hash = entry.Hash
|
||||
info.TreeHash = entry.TreeHash
|
||||
}
|
||||
}
|
||||
info.HashDrift = skillHashDrift(skill, info.Hash)
|
||||
info.HashDrift = skillHashDrift(skill, info.Hash, info.TreeHash)
|
||||
return info, true
|
||||
}
|
||||
|
||||
@@ -556,11 +612,12 @@ func hashContent(data []byte) string {
|
||||
return "sha256:" + hex.EncodeToString(sum[:])
|
||||
}
|
||||
|
||||
// skillHashDrift reports whether the on-disk SKILL.md no longer matches the
|
||||
// lockfile hash recorded at install time. Missing lock hashes never count as
|
||||
// drift (agents-only / unlocked skills). A locked skill whose SKILL.md cannot
|
||||
// be read is treated as drifted — not as a clean match.
|
||||
func skillHashDrift(skill Skill, lockHash string) bool {
|
||||
// skillHashDrift reports whether the installed skill no longer matches the
|
||||
// lockfile hashes recorded at install time: the SKILL.md hash, and the tree
|
||||
// hash when the entry has one, so an edited script counts as drift too. Missing
|
||||
// lock hashes never count as drift (skills Zero did not install). A locked
|
||||
// skill that cannot be read is treated as drifted, not as a clean match.
|
||||
func skillHashDrift(skill Skill, lockHash string, lockTreeHash string) bool {
|
||||
lockHash = strings.TrimSpace(lockHash)
|
||||
if lockHash == "" {
|
||||
return false
|
||||
@@ -569,5 +626,13 @@ func skillHashDrift(skill Skill, lockHash string) bool {
|
||||
if err != nil {
|
||||
return true
|
||||
}
|
||||
return hashContent(data) != lockHash
|
||||
if hashContent(data) != lockHash {
|
||||
return true
|
||||
}
|
||||
lockTreeHash = strings.TrimSpace(lockTreeHash)
|
||||
if lockTreeHash == "" {
|
||||
return false
|
||||
}
|
||||
treeHash, err := skillTreeHash(filepath.Dir(skill.Path))
|
||||
return err != nil || treeHash != lockTreeHash
|
||||
}
|
||||
@@ -364,10 +364,11 @@ func TestInstallGitSourceUsesRunnerAndDoesNotExecuteContent(t *testing.T) {
|
||||
if _, err := os.Stat(filepath.Join(cloneRoot, "PWNED")); err == nil {
|
||||
t.Fatalf("install must never execute fetched content")
|
||||
}
|
||||
// The fetched executable must not be copied into the skills dir either (skills
|
||||
// are markdown — only SKILL.md is installed, not arbitrary fetched files).
|
||||
if _, err := os.Stat(filepath.Join(destDir, "remote", "install.sh")); err == nil {
|
||||
t.Fatalf("install must not copy fetched executable into the skills dir")
|
||||
// A script beside SKILL.md is part of the skill (#584), so it is installed,
|
||||
// and still only copied: running it is up to whoever uses the skill later,
|
||||
// through the normal tool permissions.
|
||||
if _, err := os.Stat(filepath.Join(destDir, "remote", "install.sh")); err != nil {
|
||||
t.Fatalf("the skill's bundled script was not installed: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -440,10 +441,10 @@ func TestInfoReturnsFrontmatterSourceAndHash(t *testing.T) {
|
||||
|
||||
func TestSkillHashDriftUnreadableLockedPath(t *testing.T) {
|
||||
missing := filepath.Join(t.TempDir(), "missing", "SKILL.md")
|
||||
if !skillHashDrift(Skill{Path: missing}, "sha256:deadbeef") {
|
||||
if !skillHashDrift(Skill{Path: missing}, "sha256:deadbeef", "") {
|
||||
t.Fatal("expected drift when locked SKILL.md cannot be read")
|
||||
}
|
||||
if skillHashDrift(Skill{Path: missing}, "") {
|
||||
if skillHashDrift(Skill{Path: missing}, "", "") {
|
||||
t.Fatal("missing lock hash must not count as drift")
|
||||
}
|
||||
}
|
||||
@@ -861,6 +862,146 @@ func TestRecoveryResolvesEveryInterruptedUpdateStep(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
const (
|
||||
bundledScriptV1 = "print('v1')\n"
|
||||
bundledScriptV2 = "print('v2')\n"
|
||||
)
|
||||
|
||||
func writeBundledScript(t *testing.T, skillDir string, content string) string {
|
||||
t.Helper()
|
||||
path := filepath.Join(skillDir, "scripts", "run.py")
|
||||
if err := os.MkdirAll(filepath.Dir(path), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.WriteFile(path, []byte(content), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return path
|
||||
}
|
||||
|
||||
// plantInterruptedBundledUpdate is plantInterruptedAlphaUpdate for a reinstall
|
||||
// that changes only a bundled script, killed after the tree swap: alpha's
|
||||
// SKILL.md is the same in the live tree and the backup, and only the tree hash
|
||||
// in the lockfile tells them apart. published says whether the lockfile was
|
||||
// rewritten for the new tree before the kill (S4) or not (S3).
|
||||
func plantInterruptedBundledUpdate(t *testing.T, published bool) interruptedUpdate {
|
||||
t.Helper()
|
||||
dir := t.TempDir()
|
||||
source := writeSourceSkill(t, filepath.Join(t.TempDir(), "alpha"), oldAlphaSkill)
|
||||
writeBundledScript(t, source, bundledScriptV1)
|
||||
if _, err := Install(context.Background(), InstallOptions{Source: source, Dir: dir}); err != nil {
|
||||
t.Fatalf("seed alpha: %v", err)
|
||||
}
|
||||
gammaSource := writeSourceSkill(t, filepath.Join(t.TempDir(), "gamma"), gammaSkill)
|
||||
if _, err := Install(context.Background(), InstallOptions{Source: gammaSource, Dir: dir}); err != nil {
|
||||
t.Fatalf("seed gamma: %v", err)
|
||||
}
|
||||
|
||||
staged, _, err := installtxn.StageDir(dir)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
workspace := filepath.Dir(staged)
|
||||
writeWorkspaceMarker(t, workspace, "alpha")
|
||||
writeSourceSkill(t, staged, oldAlphaSkill)
|
||||
writeBundledScript(t, staged, bundledScriptV2)
|
||||
|
||||
target := filepath.Join(dir, "alpha")
|
||||
if err := os.Rename(target, filepath.Join(workspace, "previous")); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.Rename(staged, target); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if published {
|
||||
treeHash, err := skillTreeHash(target)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
publishLockEntry(t, dir, "alpha", LockEntry{Source: canonicalSource(source), Hash: hashContent([]byte(oldAlphaSkill)), TreeHash: treeHash})
|
||||
}
|
||||
return interruptedUpdate{dir: dir, workspace: workspace, oldSource: canonicalSource(source), newSource: canonicalSource(source)}
|
||||
}
|
||||
|
||||
// SKILL.md cannot say which tree of an interrupted bundled-only update the
|
||||
// lockfile records, since both carry the same one. The tree hash can: before the
|
||||
// publish it still describes the backup, after it the live tree.
|
||||
func TestRecoveryTellsABundledOnlyUpdateApartByTreeHash(t *testing.T) {
|
||||
steps := []struct {
|
||||
step string
|
||||
published bool
|
||||
want string
|
||||
}{
|
||||
{step: "S3", published: false, want: bundledScriptV1},
|
||||
{step: "S4", published: true, want: bundledScriptV2},
|
||||
}
|
||||
for _, step := range steps {
|
||||
for _, driver := range recoveryDrivers {
|
||||
t.Run(step.step+"/"+driver.name, func(t *testing.T) {
|
||||
update := plantInterruptedBundledUpdate(t, step.published)
|
||||
|
||||
if err := driver.run(t, update.dir); err != nil {
|
||||
t.Fatalf("%s over a recoverable state: %v", driver.name, err)
|
||||
}
|
||||
|
||||
target := filepath.Join(update.dir, "alpha")
|
||||
got, err := os.ReadFile(filepath.Join(target, "scripts", "run.py"))
|
||||
if err != nil || string(got) != step.want {
|
||||
t.Fatalf("recovered script = %q, %v; want %q", got, err, step.want)
|
||||
}
|
||||
lock, err := ReadLock(update.dir)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
tree, err := skillTreeHash(target)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if lock["alpha"].TreeHash != tree {
|
||||
t.Errorf("lock tree hash %q does not describe the recovered tree %q", lock["alpha"].TreeHash, tree)
|
||||
}
|
||||
if _, err := os.Stat(update.workspace); !os.IsNotExist(err) {
|
||||
t.Errorf("a resolved workspace must be cleared, got %v", err)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// A live tree whose files cannot be read cannot be shown to be the one the
|
||||
// lockfile records, or not to be. Recovery reports it, as it does for a SKILL.md
|
||||
// it cannot read, and decides nothing until a later pass can read it.
|
||||
func TestRecoveryReportsALiveTreeItCannotHash(t *testing.T) {
|
||||
for _, driver := range recoveryDrivers {
|
||||
t.Run(driver.name, func(t *testing.T) {
|
||||
update := plantInterruptedBundledUpdate(t, false)
|
||||
lockBefore := readLockBytes(t, update.dir)
|
||||
dirBefore := treeSnapshot(t, update.dir)
|
||||
release := holdUnreadable(t, filepath.Join(update.dir, "alpha", "scripts", "run.py"))
|
||||
|
||||
err := driver.run(t, update.dir)
|
||||
release()
|
||||
if err == nil || !strings.Contains(err.Error(), "classify interrupted install alpha") {
|
||||
t.Fatalf("%s over a live tree it cannot hash: %v, want the classification error", driver.name, err)
|
||||
}
|
||||
assertSnapshotUnchanged(t, dirBefore, treeSnapshot(t, update.dir))
|
||||
if got := readLockBytes(t, update.dir); got != lockBefore {
|
||||
t.Errorf("the lockfile was rewritten by a caller that must have aborted:\n%s", got)
|
||||
}
|
||||
|
||||
// Once the tree can be read, the next pass resolves it: the lockfile
|
||||
// still describes the backup, so the backup comes back.
|
||||
if err := driver.run(t, update.dir); err != nil {
|
||||
t.Fatalf("%s once the tree is readable: %v", driver.name, err)
|
||||
}
|
||||
got, err := os.ReadFile(filepath.Join(update.dir, "alpha", "scripts", "run.py"))
|
||||
if err != nil || string(got) != bundledScriptV1 {
|
||||
t.Fatalf("recovered script = %q, %v; want %q", got, err, bundledScriptV1)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// A recovery that could not be made is not the same as nothing to recover.
|
||||
// Installing over or reporting the removal of a tree that is still owed a
|
||||
// restore destroys the only copy of it, so the caller has to stop before it
|
||||
|
||||
@@ -0,0 +1,30 @@
|
||||
//go:build !windows
|
||||
|
||||
package skills
|
||||
|
||||
import (
|
||||
"os"
|
||||
"sync"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// holdUnreadable takes every permission off path, so reading it fails until
|
||||
// release puts them back. Cleanup releases it too. Root reads a file whatever
|
||||
// its mode, so a test that needs the read to fail is skipped there.
|
||||
func holdUnreadable(t *testing.T, path string) (release func()) {
|
||||
t.Helper()
|
||||
if os.Geteuid() == 0 {
|
||||
t.Skip("root reads a file whatever its mode")
|
||||
}
|
||||
info, err := os.Stat(path)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.Chmod(path, 0); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var once sync.Once
|
||||
release = func() { once.Do(func() { _ = os.Chmod(path, info.Mode().Perm()) }) }
|
||||
t.Cleanup(release)
|
||||
return release
|
||||
}
|
||||
@@ -0,0 +1,28 @@
|
||||
//go:build windows
|
||||
|
||||
package skills
|
||||
|
||||
import (
|
||||
"sync"
|
||||
"testing"
|
||||
|
||||
"golang.org/x/sys/windows"
|
||||
)
|
||||
|
||||
// holdUnreadable keeps path open with no sharing, so every other open of it
|
||||
// fails until release runs. Cleanup releases it too.
|
||||
func holdUnreadable(t *testing.T, path string) (release func()) {
|
||||
t.Helper()
|
||||
name, err := windows.UTF16PtrFromString(path)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
handle, err := windows.CreateFile(name, windows.GENERIC_READ, 0, nil, windows.OPEN_EXISTING, windows.FILE_ATTRIBUTE_NORMAL, 0)
|
||||
if err != nil {
|
||||
t.Fatalf("hold %s open: %v", path, err)
|
||||
}
|
||||
var once sync.Once
|
||||
release = func() { once.Do(func() { _ = windows.CloseHandle(handle) }) }
|
||||
t.Cleanup(release)
|
||||
return release
|
||||
}
|
||||
@@ -148,10 +148,13 @@ func TestConcurrencyCapAndQueueDrains(t *testing.T) {
|
||||
}
|
||||
// Release everyone; the queue should drain one-per-slot until all are done.
|
||||
close(gate)
|
||||
testutil.WaitFor(t, "all tasks done", func() bool { return sw.Coordinator().Summarize().Done == 5 })
|
||||
if team.Running() != 0 || team.QueueDepth() != 0 {
|
||||
t.Fatalf("after drain running=%d queue=%d, want 0/0", team.Running(), team.QueueDepth())
|
||||
}
|
||||
// A member's task reads Done before its slot is released: the supervisor
|
||||
// completes the task, then removes the member and only then frees the slot
|
||||
// in afterExit. So the counts are settled once the drain has finished, not
|
||||
// the moment the fifth task reads Done, and the wait covers both.
|
||||
testutil.WaitFor(t, "all tasks done and every slot released", func() bool {
|
||||
return sw.Coordinator().Summarize().Done == 5 && team.Running() == 0 && team.QueueDepth() == 0
|
||||
})
|
||||
if got := len(l.recorded()); got != 5 {
|
||||
t.Fatalf("launched %d members, want 5", got)
|
||||
}
|
||||
|
||||
@@ -936,8 +936,15 @@ func TestExecCommandInteractiveBlockSuggestsTTY(t *testing.T) {
|
||||
}
|
||||
|
||||
func TestExecCommandTTYSkipsInteractiveBlock(t *testing.T) {
|
||||
tool := NewScopedExecCommandTool(t.TempDir(), nil, newExecSessionManager())
|
||||
// ssh to a bogus host fails fast on its own; the point is that the
|
||||
// The ssh can still be resolving the bogus host when the 250ms yield
|
||||
// returns, which leaves its session running in the test root. Stop it
|
||||
// before the root goes, and use execTestRoot for the moment Windows still
|
||||
// holds the directory after the stop.
|
||||
root := execTestRoot(t)
|
||||
manager := newExecSessionManager()
|
||||
t.Cleanup(func() { manager.StopAll() })
|
||||
tool := NewScopedExecCommandTool(root, nil, manager)
|
||||
// ssh to a bogus host fails on its own; the point is that the
|
||||
// interactive guard must not fire ahead of the tty path.
|
||||
result := tool.Run(context.Background(), map[string]any{
|
||||
"cmd": "ssh host.example.com", "tty": true, "yield_time_ms": 250,
|
||||
|
||||
@@ -73,7 +73,7 @@ func (tool *skillTool) Run(_ context.Context, args map[string]any) Result {
|
||||
names := make([]string, 0, len(loaded))
|
||||
for _, skill := range loaded {
|
||||
if skill.Name == name {
|
||||
return okResult(skill.Content)
|
||||
return okResult(skills.ToolOutput(skill))
|
||||
}
|
||||
names = append(names, skill.Name)
|
||||
}
|
||||
|
||||
@@ -96,3 +96,27 @@ func TestSkillToolNoSkillsAvailable(t *testing.T) {
|
||||
t.Fatalf("expected a no-skills message, got: %q", result.Output)
|
||||
}
|
||||
}
|
||||
|
||||
// A skill that ships files beside its SKILL.md (#584) is no use if the model
|
||||
// cannot find them, so the output names their directory and lists them.
|
||||
func TestSkillToolPointsAtTheSkillsBundledFiles(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
writeSkillFile(t, dir, "pdf", "---\nname: pdf\n---\nRun scripts/fill.py.")
|
||||
script := filepath.Join(dir, "pdf", "scripts", "fill.py")
|
||||
if err := os.MkdirAll(filepath.Dir(script), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.WriteFile(script, []byte("print('fill')\n"), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
result := NewSkillTool(dir).Run(context.Background(), map[string]any{"name": "pdf"})
|
||||
if result.Status != StatusOK {
|
||||
t.Fatalf("Status = %s (output: %s)", result.Status, result.Output)
|
||||
}
|
||||
for _, want := range []string{"Run scripts/fill.py.", filepath.Join(dir, "pdf"), "- scripts/fill.py"} {
|
||||
if !strings.Contains(result.Output, want) {
|
||||
t.Fatalf("output does not contain %q:\n%s", want, result.Output)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -2,7 +2,6 @@ package tui
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
@@ -5965,11 +5964,7 @@ func (m model) runAgentWithOptions(runID int, runCtx context.Context, prompt str
|
||||
// them is flushed at end-of-run AND on cancel (flushRunIDs), so the blobs
|
||||
// never stay orphaned — see its contract in internal/sessions.
|
||||
if m.sessionStore != nil && m.activeSession.SessionID != "" {
|
||||
var args map[string]any
|
||||
if call.Arguments != "" {
|
||||
_ = json.Unmarshal([]byte(call.Arguments), &args)
|
||||
}
|
||||
if targets := tools.MutationTargets(m.cwd, call.Name, args); len(targets) > 0 {
|
||||
if targets := agent.CheckpointTargets(m.cwd, options.Registry, call); len(targets) > 0 {
|
||||
if payload, ok := m.sessionStore.SnapshotForCheckpoint(m.activeSession.SessionID, m.cwd, call.Name, targets); ok {
|
||||
sessionEvents = append(sessionEvents, pendingSessionEvent{
|
||||
Type: sessions.EventSessionCheckpoint,
|
||||
|
||||
@@ -258,7 +258,7 @@ func TestProviderWizardChatGPTOAuthModelsUseCodexSet(t *testing.T) {
|
||||
for _, model := range models {
|
||||
got[model.ID] = true
|
||||
}
|
||||
for _, want := range []string{"gpt-5.5", "gpt-5.4", "gpt-5.4-mini", "gpt-5.3-codex-spark"} {
|
||||
for _, want := range []string{"gpt-6.1-sol", "gpt-6.1-terra", "gpt-6-astra", "gpt-6-luna"} {
|
||||
if !got[want] {
|
||||
t.Fatalf("ChatGPT OAuth models missing %q; got %#v", want, providerWizardModelIDs(models))
|
||||
}
|
||||
@@ -266,8 +266,8 @@ func TestProviderWizardChatGPTOAuthModelsUseCodexSet(t *testing.T) {
|
||||
if got["gpt-5"] {
|
||||
t.Fatalf("ChatGPT OAuth models should not include stale gpt-5 fallback; got %#v", providerWizardModelIDs(models))
|
||||
}
|
||||
if models[0].ID != "gpt-5.5" {
|
||||
t.Fatalf("default ChatGPT OAuth model = %q, want gpt-5.5", models[0].ID)
|
||||
if models[0].ID != "gpt-6.1-sol" {
|
||||
t.Fatalf("default ChatGPT OAuth model = %q, want gpt-6.1-sol", models[0].ID)
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -492,6 +492,54 @@ func TestPermissionPromptAllowWritesFileAndRecordsDecision(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestPermissionPromptFreeformApplyPatchRecordsCheckpoint(t *testing.T) {
|
||||
store := testSessionStore(t)
|
||||
root := t.TempDir()
|
||||
writeTestFile(t, root, "main.txt", "before\n")
|
||||
patch := "*** Begin Patch\n*** Update File: main.txt\n@@\n-before\n+after\n*** End Patch\n"
|
||||
provider := &scriptedProvider{scripts: [][]zeroruntime.StreamEvent{
|
||||
freeformApplyPatchToolScript("call_patch", patch),
|
||||
textScript("patched"),
|
||||
}}
|
||||
registry := tools.NewRegistry()
|
||||
registry.Register(tools.NewScopedApplyPatchTool(root, nil))
|
||||
runtimeMessageCh := make(chan tea.Msg, 8)
|
||||
m := newPermissionTestModel(root, provider, registry, store, nil, runtimeMessageCh)
|
||||
|
||||
next := submitAndDrivePermissionRun(t, m, "apply the patch", "a", runtimeMessageCh, 4)
|
||||
|
||||
content, err := os.ReadFile(filepath.Join(root, "main.txt"))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if string(content) != "after\n" {
|
||||
t.Fatalf("patched content = %q, want after newline", content)
|
||||
}
|
||||
events := readOnlySessionEvents(t, store)
|
||||
if got := eventTypes(events); !equalEventTypes(got, []sessions.EventType{
|
||||
sessions.EventMessage,
|
||||
sessions.EventToolCall,
|
||||
sessions.EventSessionCheckpoint,
|
||||
sessions.EventPermissionRequest,
|
||||
sessions.EventPermissionDecision,
|
||||
sessions.EventToolResult,
|
||||
sessions.EventMessage,
|
||||
}) {
|
||||
t.Fatalf("unexpected event sequence: %#v", got)
|
||||
}
|
||||
checkpoint := nthSessionEvent(t, events, sessions.EventSessionCheckpoint, 1)
|
||||
var payload sessions.CheckpointPayload
|
||||
if err := json.Unmarshal(checkpoint.Payload, &payload); err != nil {
|
||||
t.Fatalf("decode checkpoint payload: %v", err)
|
||||
}
|
||||
if len(payload.Files) != 1 || payload.Files[0].Path != "main.txt" || payload.Files[0].Blob == "" {
|
||||
t.Fatalf("checkpoint files = %#v, want main.txt with a blob", payload.Files)
|
||||
}
|
||||
if !transcriptContains(next.transcript, "permission: apply_patch allow") {
|
||||
t.Fatalf("expected allow decision in transcript, got %#v", next.transcript)
|
||||
}
|
||||
}
|
||||
|
||||
func TestPermissionPromptAlwaysPersistsGrantAndSkipsLaterPrompt(t *testing.T) {
|
||||
store := testSessionStore(t)
|
||||
root := t.TempDir()
|
||||
@@ -652,6 +700,17 @@ func writeFileToolScript(callID string, path string, content string) []zerorunti
|
||||
}
|
||||
}
|
||||
|
||||
// freeformApplyPatchToolScript emits a native freeform apply_patch call: the raw
|
||||
// patch rides in ArgumentsFragment instead of a JSON object.
|
||||
func freeformApplyPatchToolScript(callID string, patch string) []zeroruntime.StreamEvent {
|
||||
return []zeroruntime.StreamEvent{
|
||||
{Type: zeroruntime.StreamEventToolCallStart, ToolCallID: callID, ToolName: "apply_patch", ToolCallFreeform: true},
|
||||
{Type: zeroruntime.StreamEventToolCallDelta, ToolCallID: callID, ArgumentsFragment: patch},
|
||||
{Type: zeroruntime.StreamEventToolCallEnd, ToolCallID: callID},
|
||||
{Type: zeroruntime.StreamEventDone},
|
||||
}
|
||||
}
|
||||
|
||||
func textScript(text string) []zeroruntime.StreamEvent {
|
||||
return []zeroruntime.StreamEvent{
|
||||
{Type: zeroruntime.StreamEventText, Content: text},
|
||||
|
||||
Generated
+2
-2
@@ -1,12 +1,12 @@
|
||||
{
|
||||
"name": "@twigpine/zero",
|
||||
"version": "0.11.0",
|
||||
"version": "0.12.0",
|
||||
"lockfileVersion": 3,
|
||||
"requires": true,
|
||||
"packages": {
|
||||
"": {
|
||||
"name": "@twigpine/zero",
|
||||
"version": "0.11.0",
|
||||
"version": "0.12.0",
|
||||
"cpu": [
|
||||
"x64",
|
||||
"arm64"
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@twigpine/zero",
|
||||
"version": "0.11.0",
|
||||
"version": "0.12.0",
|
||||
"description": "Zero — a fast, multi-provider terminal coding agent.",
|
||||
"type": "module",
|
||||
"module": "bin/zero.js",
|
||||
|
||||
Reference in new issue
Block a user