Files
zero/internal/usercommands/usercommands_test.go
Vasanth T b2bb6c4b41 feat: five capability features from the reference-agent comparison (#276)
* feat(commands): user-defined slash commands from markdown files

Drop a markdown file at `.zero/commands/<name>.md` (project, shared with the
team) or `<userConfigDir>/zero/commands/<name>.md` (personal); typing
`/<name> args` expands its body template and submits it as a normal prompt.
Optional YAML frontmatter (`description:`, `model:`, `agent:`) feeds help text
and routing. This turns Zero's model-pulled skills into user-invokable,
repo-checked-in team workflows (`/release v1.2`, `/fix-flaky <test>`).

New internal/usercommands package: Load() scans the project + user dirs
(project shadows user on name collision, mirroring specialist scope
precedence), validates names to a safe slash-command shape, and parses
frontmatter with a self-contained parser. Expand() substitutes $ARGUMENTS,
$1..$9, and $$ (literal $); a placeholder-free template gets the raw args
appended so a trivial command still receives input.

Wiring: model loads commands at construction; the commandUnknown dispatch
checks the user set before reporting "unknown"; autocomplete lists user
commands alongside builtins. Builtins win on collision (listed first, shadow at
dispatch). Tests cover load/precedence/name-validation, the placeholder
substitution table, and the TUI dispatch + autocomplete + still-unknown paths.

* feat(init): guided /init that generates AGENTS.md seeded with repo facts

`/init` (TUI) and `zero init` (headless) investigate the repo and write a
concise AGENTS.md so future runs start with project context. Zero already has
the AGENTS.md loader and the repoinfo scanner, but the file only existed if a
user hand-authored it — this activates the machinery in one command.

New internal/agentinit.BuildPrompt seeds the bootstrap prompt with
repoinfo.Collect() output (primary language, build/test tools, CI, workspace
layout, git) formatted as a fact block, then instructs the agent to investigate
the gaps and write a tight AGENTS.md (build/test commands, conventions, things
to avoid). Collection failure is non-fatal — the agent investigates from
scratch. This is one better than a pure-prompt /init: the agent starts from
known facts instead of re-deriving them.

TUI: /init command + handleInitCommand reuse launchPrompt (standard run, tools,
AGENTS.md write path). Headless: `zero init` builds the prompt and forwards it
through the existing exec machinery, so all exec flags (--model, -w, --add-dir)
work unchanged. Tests cover FormatFacts (rendered/omitted fields), BuildPrompt,
and the TUI dispatch.

* feat(tools): lsp_navigate — semantic code navigation via the language server

A read-only, model-callable tool exposing LSP navigation: jump-to-definition,
find-all-references, find-implementations, and workspace_symbol search. The
agent can answer "where is X defined / who calls X / what implements this
interface" precisely, where grep collides on common names or misses indirect
references — cutting wasted read/grep turns and wrong-edit risk on large repos.

Zero already runs language servers for diagnostics, so this adds the
request/response navigation methods on top: Manager.Navigate syncs the file
(didOpen) then issues textDocument/definition|references|implementation or
workspace/symbol via the existing client.Call, decoding all three result shapes
(Location, []Location, []LocationLink). 1-based file:line:col in and out
(converting LSP's 0-based positions); the tool has its own lazily-started
manager (servers start on first use, reused across calls).

Opportunistic: a file type with no installed server, or a server lacking the
capability, degrades to a clear "unavailable — fall back to grep" message, not
an error. Registered in CoreReadOnlyToolsScoped. Tests cover the response-shape
decoding (incl. LocationLink + null), symbol decoding/kinds, unknown-op and
unsupported-extension degradation, and the tool's arg validation + read-only
safety.

* feat(agent): prune stale tool output before paid summarization

Long, dump-heavy sessions accumulate large read_file/grep/glob/bash tool
results the model has already acted on; their bodies are dead weight the loop
otherwise keeps paying an LLM summarizer to compress. Add a zero-cost prune
stage inside maybeCompact, before the summarizer: when over threshold, replace
the bodies of OLD, large tool results with a compact placeholder, recompute
size, and only fall through to the paid Compact() if still over.

pruneStaleToolOutput walks newest-first, protects the last preserveLast
messages plus a trailing 40k-token window of tool output (most likely still in
use), and prunes only tool results older than that and larger than 200 tokens —
gated so the whole pass is a no-op unless reclaimable output exceeds 20k tokens.
It keeps the tool message and its ToolCallID (provider replay stays valid; the
model knows what was there and can re-run the tool), never touches non-tool
messages, never re-prunes a placeholder (idempotent), and copies-on-write so it
never mutates the caller's slice. Recent turns are preserved verbatim — no
paraphrase loss, no token or latency cost.

Tests cover the reclaim gate, recent-window protection, idempotence,
non-tool-message safety, ToolCallID/role preservation, and no-input-mutation.

* feat(agent): reconnect on a transient model disconnect instead of ending the run

A long autonomous task (a big refactor, a swarm member, a headless/cron run)
should survive a single transient upstream hiccup rather than dying and
re-burning every token on a restart. When the initial StreamCompletion connect
fails with a disconnect-shaped error, streamWithReconnect re-issues the SAME
request with exponential backoff up to 2 times.

It retries only the connect — before any content is forwarded — so no
already-streamed OnText is ever duplicated. A context-limit error (the
compactor's job), an image rejection, a non-disconnect error, or a cancelled
context is returned immediately without retry, so the reconnect never fights
the existing handlers. Disconnect classification matches EOF / connection
reset|refused|closed / broken pipe / timeout / 502 / 503 / server-closed.
Reconnect attempts surface through OnReasoning ("connection lost —
reconnecting N/max"), a non-content channel that never corrupts the answer
text; silent when there's no reasoning sink.

Tests: recover-from-transient, give-up-after-max, no-retry-on-context-limit,
stop-on-context-cancel, the disconnect-vs-not classifier, backoff growth, and
the notice routing.

* fix(specialist): add lsp_navigate to knownToolNames

The new lsp_navigate tool was added to the core read-only registry but not to
specialist.knownToolNames, which mirrors the core tool set — so
TestKnownToolNamesMatchCoreRegistry failed (the list drifted from the registry).
Add it to the read-only group to match.

* fix(tools): confine lsp_navigate to the workspace (close arbitrary-file-read)

Review caught that lsp_navigate dropped the PathScope every sibling read-only
tool (read_file/glob/grep) carries, and its readFile joined or used the
model-supplied path verbatim — so `path:"/etc/passwd"` (absolute) or
`path:"../../etc/..."` (escaping) read arbitrary files off disk AND opened them
into the language-server subprocess, reachable via indirect prompt injection.

Add NewScopedLSPNavigateTool(workspaceRoot, scope) (NewLSPNavigateTool now
delegates with nil scope), resolve the path through resolveScopedReadPath BEFORE
reading or building the LSP request — the same confinement the neighbouring
tools enforce — and hand the LSP manager the resolved absolute path so it never
opens an out-of-workspace file. Errors echo only the relative path, never an
absolute one. Registered via the scoped constructor in CoreReadOnlyToolsScoped.

Regression test asserts `/etc/passwd` and `../../` are rejected for both the
position and workspace_symbol ops; verified by mutation (bypassing the scope
resolution makes the test fail).
2026-06-20 23:12:15 +05:30

109 lines
3.4 KiB
Go

package usercommands
import (
"os"
"path/filepath"
"testing"
)
func writeFile(t *testing.T, dir, name, content string) {
t.Helper()
if err := os.MkdirAll(dir, 0o755); err != nil {
t.Fatalf("mkdir: %v", err)
}
if err := os.WriteFile(filepath.Join(dir, name), []byte(content), 0o644); err != nil {
t.Fatalf("write %s: %v", name, err)
}
}
func TestLoadParsesFrontmatterAndBody(t *testing.T) {
root := t.TempDir()
dir := filepath.Join(root, ".zero", "commands")
writeFile(t, dir, "release.md", "---\ndescription: Cut a release\nmodel: claude-sonnet-4.5\n---\nCut release $1 from the current branch.")
cmds := Load(DefaultPaths(root, ""))
if len(cmds) != 1 {
t.Fatalf("expected 1 command, got %d", len(cmds))
}
c := cmds[0]
if c.Name != "release" {
t.Fatalf("name = %q, want release", c.Name)
}
if c.Description != "Cut a release" {
t.Fatalf("description = %q", c.Description)
}
if c.Model != "claude-sonnet-4.5" {
t.Fatalf("model = %q", c.Model)
}
if c.Template != "Cut release $1 from the current branch." {
t.Fatalf("template = %q", c.Template)
}
if !c.Project {
t.Fatal("expected Project=true for a .zero/commands file")
}
}
func TestLoadProjectOverridesUser(t *testing.T) {
root := t.TempDir()
userCfg := t.TempDir()
writeFile(t, filepath.Join(userCfg, "zero", "commands"), "review.md", "USER version")
writeFile(t, filepath.Join(root, ".zero", "commands"), "review.md", "PROJECT version")
cmds := Load(DefaultPaths(root, userCfg))
if len(cmds) != 1 {
t.Fatalf("expected 1 deduped command, got %d", len(cmds))
}
if cmds[0].Template != "PROJECT version" {
t.Fatalf("project should override user, got %q", cmds[0].Template)
}
if !cmds[0].Project {
t.Fatal("winning command should be the project one")
}
}
func TestLoadSkipsNonMarkdownAndInvalidNames(t *testing.T) {
root := t.TempDir()
dir := filepath.Join(root, ".zero", "commands")
writeFile(t, dir, "ok.md", "fine")
writeFile(t, dir, "notes.txt", "ignored") // not .md
writeFile(t, dir, "Bad Name.md", "ignored") // space → invalid name
cmds := Load(DefaultPaths(root, ""))
if len(cmds) != 1 || cmds[0].Name != "ok" {
t.Fatalf("expected only the valid 'ok' command, got %#v", cmds)
}
}
func TestLoadMissingDirsAreEmpty(t *testing.T) {
if cmds := Load(DefaultPaths(t.TempDir(), t.TempDir())); len(cmds) != 0 {
t.Fatalf("expected no commands for empty dirs, got %d", len(cmds))
}
if cmds := Load(Paths{}); len(cmds) != 0 {
t.Fatalf("expected no commands for blank paths, got %d", len(cmds))
}
}
func TestExpandPlaceholders(t *testing.T) {
cases := []struct {
name string
template string
args string
want string
}{
{"arguments", "Fix: $ARGUMENTS", "the flaky test in pkg", "Fix: the flaky test in pkg"},
{"positional", "Release $1 ($2)", "v1.2 patch", "Release v1.2 (patch)"},
{"missing positional is empty", "Tag $1 then $2", "only", "Tag only then "},
{"literal dollar", "cost is $$5", "x", "cost is $5"},
{"no placeholders no args", "Just do it.", "", "Just do it."},
{"no placeholders with args appends", "Do it.", "now please", "Do it.\n\nnow please"},
{"mixed", "PR $1: $ARGUMENTS", "title body words here", "PR title: title body words here"},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
if got := Expand(tc.template, tc.args); got != tc.want {
t.Fatalf("Expand(%q,%q) = %q, want %q", tc.template, tc.args, got, tc.want)
}
})
}
}