mirror of
https://github.com/Twigpine/zero.git
synced 2026-11-11 18:00:54 -10:00
* 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).
123 lines
4.0 KiB
Go
123 lines
4.0 KiB
Go
package agent
|
|
|
|
import (
|
|
"strings"
|
|
"testing"
|
|
|
|
"github.com/Gitlawb/zero/internal/zeroruntime"
|
|
)
|
|
|
|
// bigToolResult builds a tool-result message with approximately tokens worth of
|
|
// body, paired to a tool call id. ApproxTextTokens counts non-space chars / 4,
|
|
// so 4*tokens non-space chars yields ~tokens.
|
|
func bigToolResult(id string, tokens int) zeroruntime.Message {
|
|
return zeroruntime.Message{
|
|
Role: zeroruntime.MessageRoleTool,
|
|
ToolCallID: id,
|
|
Content: strings.Repeat("x", tokens*4),
|
|
}
|
|
}
|
|
|
|
func toolCallMsg(id, name string) zeroruntime.Message {
|
|
return zeroruntime.Message{
|
|
Role: zeroruntime.MessageRoleAssistant,
|
|
ToolCalls: []zeroruntime.ToolCall{{ID: id, Name: name}},
|
|
}
|
|
}
|
|
|
|
func TestPruneSkipsSmallSessions(t *testing.T) {
|
|
// Total reclaimable is under the gate → no pruning.
|
|
msgs := []zeroruntime.Message{
|
|
toolCallMsg("c1", "read_file"),
|
|
bigToolResult("c1", 5000),
|
|
}
|
|
out, reclaimed := pruneStaleToolOutput(msgs, 4)
|
|
if reclaimed != 0 {
|
|
t.Fatalf("small session should reclaim nothing, got %d", reclaimed)
|
|
}
|
|
if out[1].Content != msgs[1].Content {
|
|
t.Fatal("content must be untouched when under the gate")
|
|
}
|
|
}
|
|
|
|
func TestPrunePreservesRecentAndPrunesOld(t *testing.T) {
|
|
// One huge OLD result (beyond the protect window) + recent small ones.
|
|
msgs := []zeroruntime.Message{
|
|
toolCallMsg("old", "grep"),
|
|
bigToolResult("old", 60000), // old, big → prunable
|
|
// Filler to push "old" past the recent-protection window:
|
|
toolCallMsg("mid", "read_file"),
|
|
bigToolResult("mid", 45000), // protected by the 40k recent window
|
|
zeroruntime.Message{Role: zeroruntime.MessageRoleAssistant, Content: "thinking"},
|
|
zeroruntime.Message{Role: zeroruntime.MessageRoleUser, Content: "next"},
|
|
}
|
|
out, reclaimed := pruneStaleToolOutput(msgs, 2)
|
|
if reclaimed <= 0 {
|
|
t.Fatalf("expected the old 60k tool result to be pruned, reclaimed=%d", reclaimed)
|
|
}
|
|
if !isPrunedPlaceholder(out[1].Content) {
|
|
t.Fatalf("old result should be replaced with a placeholder, got %q", out[1].Content[:40])
|
|
}
|
|
// The placeholder names the tool, and the message + id survive (provider replay).
|
|
if !strings.Contains(out[1].Content, "grep") {
|
|
t.Fatalf("placeholder should name the tool, got %q", out[1].Content)
|
|
}
|
|
if out[1].ToolCallID != "old" || out[1].Role != zeroruntime.MessageRoleTool {
|
|
t.Fatal("pruned message must keep its role and ToolCallID for replay")
|
|
}
|
|
// The recent big result stays verbatim.
|
|
if isPrunedPlaceholder(out[3].Content) {
|
|
t.Fatal("a result inside the recent-protection window must not be pruned")
|
|
}
|
|
}
|
|
|
|
func TestPruneIsIdempotent(t *testing.T) {
|
|
msgs := []zeroruntime.Message{
|
|
toolCallMsg("old", "bash"),
|
|
bigToolResult("old", 60000),
|
|
toolCallMsg("mid", "read_file"),
|
|
bigToolResult("mid", 45000),
|
|
zeroruntime.Message{Role: zeroruntime.MessageRoleUser, Content: "go"},
|
|
}
|
|
once, r1 := pruneStaleToolOutput(msgs, 1)
|
|
if r1 == 0 {
|
|
t.Fatal("first pass should prune")
|
|
}
|
|
_, r2 := pruneStaleToolOutput(once, 1)
|
|
if r2 != 0 {
|
|
t.Fatalf("second pass should be a no-op (already pruned), reclaimed=%d", r2)
|
|
}
|
|
}
|
|
|
|
func TestPruneNeverTouchesNonToolMessages(t *testing.T) {
|
|
msgs := []zeroruntime.Message{
|
|
{Role: zeroruntime.MessageRoleUser, Content: strings.Repeat("u ", 60000)},
|
|
{Role: zeroruntime.MessageRoleAssistant, Content: strings.Repeat("a ", 60000)},
|
|
}
|
|
out, reclaimed := pruneStaleToolOutput(msgs, 0)
|
|
if reclaimed != 0 {
|
|
t.Fatalf("non-tool messages must never be pruned, reclaimed=%d", reclaimed)
|
|
}
|
|
if out[0].Content != msgs[0].Content || out[1].Content != msgs[1].Content {
|
|
t.Fatal("non-tool content changed")
|
|
}
|
|
}
|
|
|
|
func TestPruneDoesNotMutateInput(t *testing.T) {
|
|
msgs := []zeroruntime.Message{
|
|
toolCallMsg("old", "grep"),
|
|
bigToolResult("old", 60000),
|
|
toolCallMsg("mid", "read_file"),
|
|
bigToolResult("mid", 45000),
|
|
zeroruntime.Message{Role: zeroruntime.MessageRoleUser, Content: "go"},
|
|
}
|
|
original := msgs[1].Content
|
|
_, reclaimed := pruneStaleToolOutput(msgs, 1)
|
|
if reclaimed == 0 {
|
|
t.Fatal("expected a prune")
|
|
}
|
|
if msgs[1].Content != original {
|
|
t.Fatal("pruneStaleToolOutput must not mutate the caller's slice")
|
|
}
|
|
}
|