Files
zero/internal/tools/lsp_navigate_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

88 lines
3.0 KiB
Go

package tools
import (
"context"
"os"
"path/filepath"
"strings"
"testing"
)
func TestLSPNavigateConfinesPathToWorkspace(t *testing.T) {
// Regression: lsp_navigate must enforce the same workspace confinement its
// sibling read-only tools do — an absolute or `..`-escaping path must be
// rejected before any read or LSP open, so it can't exfiltrate files off disk
// (reachable via indirect prompt injection).
root := t.TempDir()
tool := NewLSPNavigateTool(root) // workspace-only scope (nil)
escapes := []string{
"/etc/passwd",
"../../../../etc/passwd",
"../../../../../../etc/ssh/id_rsa",
}
for _, p := range escapes {
for _, op := range []string{"definition", "workspace_symbol"} {
args := map[string]any{"op": op, "path": p}
if op == "definition" {
args["line"], args["character"] = 1, 1
} else {
args["query"] = "x"
}
got := tool.Run(context.Background(), args)
if got.Status != StatusError {
t.Fatalf("path %q op %s: expected StatusError (confinement), got %s: %s", p, op, got.Status, got.Output)
}
// The error must not leak the resolved absolute path.
if strings.Contains(got.Output, "/etc/") && strings.Contains(got.Output, root) {
t.Fatalf("path %q: error should not echo an absolute out-of-workspace path: %q", p, got.Output)
}
}
}
}
func TestLSPNavigateRejectsBadArgs(t *testing.T) {
tool := NewLSPNavigateTool(t.TempDir())
cases := []map[string]any{
{}, // missing op + path
{"op": "definition"}, // missing path
{"op": "workspace_symbol", "path": "x.go"}, // missing query
{"op": "definition", "path": "x.go"}, // missing line
{"op": "bogus", "path": "x.go", "line": 1, "character": 1}, // unknown op
}
for i, args := range cases {
if got := tool.Run(context.Background(), args); got.Status != StatusError {
t.Fatalf("case %d: expected StatusError for %#v, got %s: %s", i, args, got.Status, got.Output)
}
}
}
func TestLSPNavigateUnsupportedFileDegrades(t *testing.T) {
root := t.TempDir()
// A file type with no language server → the tool returns OK with a clear
// "unavailable, fall back to grep" message rather than an error.
path := filepath.Join(root, "notes.unknownext")
if err := os.WriteFile(path, []byte("hello"), 0o644); err != nil {
t.Fatal(err)
}
tool := NewLSPNavigateTool(root)
got := tool.Run(context.Background(), map[string]any{
"op": "definition", "path": "notes.unknownext", "line": 1, "character": 1,
})
if got.Status != StatusOK {
t.Fatalf("unsupported file should degrade to StatusOK, got %s: %s", got.Status, got.Output)
}
if !strings.Contains(got.Output, "unavailable") {
t.Fatalf("expected an 'unavailable' message, got %q", got.Output)
}
}
func TestLSPNavigateIsReadOnly(t *testing.T) {
tool := NewLSPNavigateTool(t.TempDir())
if s := tool.Safety(); s.SideEffect != SideEffectRead || s.Permission != PermissionAllow {
t.Fatalf("lsp_navigate should be read-only/allow, got %+v", s)
}
if tool.Name() != "lsp_navigate" {
t.Fatalf("name = %q", tool.Name())
}
}