Files
multica/server/internal/daemon/execenv/context.go
devv-eve 9e47b83f02 feat(agent): add Kimi CLI as agent runtime (#1400)
* feat(agent): add Kimi CLI as agent runtime

Adds support for Moonshot AI's Kimi Code CLI (https://github.com/MoonshotAI/kimi-cli)
as a new agent runtime, alongside Claude, Codex, OpenCode, OpenClaw, Hermes,
Gemini, Pi, Cursor and Copilot.

Kimi Code CLI implements the standard Agent Client Protocol (ACP) via the
`kimi acp` subcommand, so the new `kimiBackend` reuses the existing
hermesClient JSON-RPC transport in the agent package — only the binary,
client identity, log prefix, and tool-name extraction differ.

Wiring:
- server/pkg/agent: new kimiBackend + kimi_test.go; registered in New(),
  LaunchHeader map, and the supported-types coverage test.
- server/internal/daemon/config.go: probes `kimi` (overridable via
  MULTICA_KIMI_PATH / MULTICA_KIMI_MODEL).
- server/internal/daemon/execenv: writes AGENTS.md as the runtime context
  file (Kimi reads AGENTS.md natively via /init), and writes skills under
  `.kimi/skills/` so they are auto-discovered by the project-level skill
  loader.
- packages/views/runtimes: ProviderLogo gains a Kimi mark.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* feat(agent/kimi): support per-agent model selection via ACP set_model

Wire Kimi into the model dropdown introduced in #1399:

- ListModels gets a 'kimi' case that drives the same ACP
  initialize + session/new handshake as Hermes; both share a new
  discoverACPModels helper and parseACPSessionNewModels parser
  so future ACP backends only need a small provider entry.
- kimiBackend now issues session/set_model after session/new when
  opts.Model is non-empty, mirroring the Hermes flow. Failures
  fail the task instead of silently falling back to Kimi's
  default model — silent fallback would hide that the dropdown
  pick wasn't honoured.

Verified: go build ./..., go test ./pkg/agent/... ./internal/daemon/... ./internal/handler/..., pnpm typecheck and pnpm test (138 passed).

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* refactor(agent): address code review feedback on Kimi runtime

- Share ACP provider-error sniffer between hermes and kimi. Previously
  only hermes promoted stderr-observed 4xx/5xx into a failed task;
  kimi would report "completed + empty output" when the Moonshot
  upstream rejected a request (expired token, rate limit, …). Rename
  hermesProviderErrorSniffer → acpProviderErrorSniffer and parameterise
  the provider name; wire it into kimiBackend.Execute the same way.
- Rename extractHermesSessionID → extractACPSessionID (shared by all
  ACP backends) so the name matches parseACPSessionNewModels.
- Drop the redundant second argument to kimiToolNameFromTitle; the
  Message struct has only one relevant field (Tool), so passing it
  twice was a dead fallback. Document that the function normalises
  residual capitalised kimi titles not caught by hermesToolNameFromTitle.
- Remove kimi-only cmd.WaitDelay override; the hermes baseline is
  fine for both and divergence adds noise.
- Add TestKimiBackendSetModelFailureFailsTask: fake `kimi acp` binary
  that returns a JSON-RPC error for session/set_model, asserts that
  the task result surfaces status=failed with the model name + upstream
  message and preserves the session id.
- Fix stale agent listings in agent.go / daemon/config.go doc comments
  (missing cursor, gemini, copilot).

All: `go build ./...`, `go vet ./...`, `go test ./pkg/agent/...
./internal/daemon/... ./internal/handler/...` green.

* fix(agent/kimi): pass --yolo so Shell tools don't hang on approval

Kimi's default config has `default_yolo = false`. Every Shell/file-mutating
tool call causes kimi acp to send a `session/request_permission` request
and block (up to 300s) waiting for a response. The daemon's hermesClient
only handles `session/update` notifications — permission requests go
unanswered, the tool call times out, and the UI loop eventually dies
("UI loop timed out"). Observed with the first real kimi task: agent sat
as Live for ~7 minutes before the daemon killed it.

The fix mirrors hermes' HERMES_YOLO_MODE=1 override: pass `--yolo` to
`kimi` so it auto-approves everything. `--yolo` is a top-level flag on
the `kimi` CLI (not a flag on `kimi acp`), so it must come before the
`acp` subcommand in argv. Added to kimiBlockedArgs so user custom_args
can't strip it.

While here, fix a related bug that made kimi tool names show up empty
in the daemon log ("tool #1: "): hermesToolNameFromTitle's fallback
returned `kind` when neither title-with-colon nor kind matched a known
tool. Kimi's ACP `tool_call` emits bare titles like "Shell" or "Read
file" with no `kind` at all, so we'd drop the title on the floor before
kimiToolNameFromTitle ever got a chance to map it. Now: preserve the
title when kind is unclassified; hermes titles always carry a colon so
this branch never fires for hermes.

Tests:
- TestKimiBackendPassesYoloFlag — fake binary that records its argv,
  asserts --yolo comes before acp.
- TestHermesToolNameFromTitle rows for bare kimi-style titles.
- Existing suite green: go build, go vet, full pkg/agent + daemon +
  handler test packages.

* fix(agent/acp): auto-approve session/request_permission from agent

The previous attempt (`kimi --yolo acp`) was a no-op. Inspected the
kimi-cli source: the `acp` Typer subcommand takes no parameters, so
flags on the root `kimi` command are dropped before `acp_main()` runs
— it's impossible to opt into YOLO mode through CLI flags for ACP.

The real fix is on our side: respond to session/request_permission.

ACP is bidirectional. When kimi runs a Shell or file-write tool, it
sends `session/request_permission` (agent → client, JSON-RPC request
with id + method) and waits up to 300s for a response. Our existing
hermesClient.handleLine only dispatched: (id + result/error) →
handleResponse, and (no id + method) → handleNotification. A request
with BOTH id and method fell through and got silently dropped — kimi
timed out, UI loop died, task sat stuck for 7 minutes.

Add handleAgentRequest: for session/request_permission, echo the id
and respond with outcome=selected, optionId=approve_for_session. The
daemon is headless; there's no user to prompt. `approve_for_session`
lets the agent remember the action so subsequent identical calls
(every Shell, every file write) skip the round-trip entirely. For any
other agent → client method, reply with standard -32601 method-not-
found so the agent doesn't block.

Also:
- Add writeMu so request() (main goroutine) and handleAgentRequest
  (reader goroutine) don't interleave JSON frames on stdin.
- Revert the `--yolo acp` flag — it's a no-op, and carrying it in
  kimiBlockedArgs gives the wrong impression that it does something.
  Comment in kimi.go now points at handleAgentRequest as the real fix.

Tests:
- TestHermesClientAutoApprovesPermissionRequest: inject a
  session/request_permission, assert the reply echoes the id and
  carries {outcome: selected, optionId: approve_for_session}.
- TestHermesClientReplesMethodNotFoundForUnknownAgentRequest: confirm
  unknown agent → client methods get JSON-RPC -32601 instead of silence.
- TestKimiBackendInvokesACPSubcommand replaces the yolo-flag assertion
  with a negative assertion: no dead --yolo / --auto-approve / -y on
  argv, since they'd pretend to do something they can't.

All: go build ./..., go vet ./..., go test ./pkg/agent/... green.

* fix(agent/acp): surface kimi tool input/output via content blocks

Kimi-cli emits tool_call and tool_call_update ACP frames with the
input/output inside a `content` array of ContentToolCallContent
blocks (shape: {type:"content", content:{type:"text", text:"..."}}),
not in the hermes-style `rawInput` map / `rawOutput` string. Our
parser only looked at rawInput/rawOutput, so the daemon recorded
empty Input and Output for every kimi tool — the execution-history
UI showed blank terminal panels even for commands that ran fine.

Add extractACPToolCallText() and a fallback in handleToolCallStart /
handleToolCallUpdate: when rawInput is nil / rawOutput is empty, pull
the text out of the content blocks. rawInput / rawOutput still take
precedence so hermes' behaviour is untouched. Terminal /
FileEditToolCallContent blocks are skipped (we have nothing to render
them as — kimi only emits TerminalToolCallContent when the client
advertises terminal capability, which we don't).

Tests:
- TestHermesClientHandleToolCallStartKimiContent — content array →
  Input.text populated.
- TestHermesClientHandleToolCallCompleteKimiContent — multi-block
  content → Output concatenated with newline separator.
- TestHermesClientHandleToolCallRawOutputTakesPrecedence — hermes
  rawOutput still wins when both are present.
- TestExtractACPToolCallText — unit coverage for the helper
  (single/multiple text blocks, terminal-block skip, empty input).

* fix(agent/acp): buffer streaming tool args so Input isn't empty in UI

kimi-cli streams tool args token-by-token via tool_call_update frames
— the initial tool_call carries an empty content block and each
subsequent in_progress update carries the cumulative JSON so far
(`{`, `{"comma`, `{"command": "echo`, …). The final completed update
then carries the tool's stdout, not the args. Observed per kimi-cli
acp/session.py::_send_tool_call{,_part,_result} and confirmed by
driving a real Shell call end-to-end: 10 in_progress frames, last
with `{"command": "echo hello world"}`, then completed with `hello
world\n`.

Our previous handleToolCallStart emitted MessageToolUse on the first
tool_call frame, capturing the empty content — so every kimi tool
appeared in the execution-history UI with a blank input. Output was
correct (fix 4335c198) but command was missing.

Changes:
- hermesClient now tracks pending tool calls per toolCallId. Hermes
  path is unchanged — rawInput is present at tool_call time, so
  emit-immediately-then-flag-emitted still fires on the initial frame.
- kimi path defers MessageToolUse until status=completed / failed.
  tool_call_update in_progress frames update the buffered argsText
  (cumulative, so overwrite); on completion we parse the accumulated
  JSON into Message.Input. Malformed JSON falls back to `{"text": …}`
  so non-JSON tool args still render.
- Orphan completion frames (no matching tool_call seen — e.g. daemon
  restarted mid-task) synthesise ToolUse from the update's own
  title/kind/rawInput so the UI still gets a header.
- extractACPToolCallText now also renders FileEditToolCallContent
  blocks as a compact header ("--- path / +++ path / (edited: N → M
  bytes)"). kimi emits these for Write / StrReplaceFile / Patch when
  the tool's display block is a DiffDisplayBlock.

Tests:
- TestHermesClientKimiStreamingToolCall: empty tool_call + 5 streaming
  in_progress + completed. Asserts no emission until complete, then
  [ToolUse(Input.command="echo hi"), ToolResult(Output="hi\n")].
- TestHermesClientKimiMalformedArgsFallback: non-JSON argsText → falls
  back to Input.text.
- TestHermesClientHandleToolCallCompleteOrphan: completed frame
  without a start → ToolUse synthesised from update's rawInput.
- TestExtractACPToolCallText: diff + new-file-diff cases.

All agent / daemon / handler test packages green.

---------

Co-authored-by: Eve <8b0578a3-cf72-4394-9e38-b328eca92463@users.noreply.multica.ai>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Eve <eve@multica.ai>
Co-authored-by: Lambda <f252c2c5-7d1d-4f3c-b394-a61abfe673fc@users.noreply.multica.ai>
2026-04-21 02:18:30 +08:00

161 lines
5.5 KiB
Go

package execenv
import (
"fmt"
"os"
"path/filepath"
"regexp"
"strings"
)
// writeContextFiles renders and writes .agent_context/issue_context.md and
// skills into the appropriate provider-native location.
//
// Claude: skills → {workDir}/.claude/skills/{name}/SKILL.md (native discovery)
// Codex: skills → handled separately in Prepare via codex-home
// Copilot: skills → {workDir}/.github/skills/{name}/SKILL.md (native project-level discovery)
// OpenCode: skills → {workDir}/.config/opencode/skills/{name}/SKILL.md (native discovery)
// Pi: skills → {workDir}/.pi/agent/skills/{name}/SKILL.md (native discovery)
// Cursor: skills → {workDir}/.cursor/skills/{name}/SKILL.md (native discovery)
// Kimi: skills → {workDir}/.kimi/skills/{name}/SKILL.md (native discovery)
// Default: skills → {workDir}/.agent_context/skills/{name}/SKILL.md
func writeContextFiles(workDir, provider string, ctx TaskContextForEnv) error {
contextDir := filepath.Join(workDir, ".agent_context")
if err := os.MkdirAll(contextDir, 0o755); err != nil {
return fmt.Errorf("create .agent_context dir: %w", err)
}
content := renderIssueContext(provider, ctx)
path := filepath.Join(contextDir, "issue_context.md")
if err := os.WriteFile(path, []byte(content), 0o644); err != nil {
return fmt.Errorf("write issue_context.md: %w", err)
}
if len(ctx.AgentSkills) > 0 {
skillsDir, err := resolveSkillsDir(workDir, provider)
if err != nil {
return fmt.Errorf("resolve skills dir: %w", err)
}
// Codex skills are written to codex-home in Prepare; skip here.
if provider != "codex" {
if err := writeSkillFiles(skillsDir, ctx.AgentSkills); err != nil {
return fmt.Errorf("write skill files: %w", err)
}
}
}
return nil
}
// resolveSkillsDir returns the directory where skills should be written
// based on the agent provider.
func resolveSkillsDir(workDir, provider string) (string, error) {
var skillsDir string
switch provider {
case "claude":
// Claude Code natively discovers skills from .claude/skills/ in the workdir.
skillsDir = filepath.Join(workDir, ".claude", "skills")
case "copilot":
// GitHub Copilot CLI natively discovers project-level skills from
// .github/skills/<name>/SKILL.md (takes precedence over user-level
// skills in ~/.copilot/skills/).
// See: https://docs.github.com/en/copilot/reference/copilot-cli-reference/cli-config-dir-reference
skillsDir = filepath.Join(workDir, ".github", "skills")
case "opencode":
// OpenCode natively discovers skills from .config/opencode/skills/ in the workdir.
skillsDir = filepath.Join(workDir, ".config", "opencode", "skills")
case "pi":
// Pi natively discovers skills from .pi/agent/skills/ in the workdir.
skillsDir = filepath.Join(workDir, ".pi", "agent", "skills")
case "cursor":
// Cursor natively discovers skills from .cursor/skills/ in the workdir.
skillsDir = filepath.Join(workDir, ".cursor", "skills")
case "kimi":
// Kimi Code CLI auto-discovers project-level skills from .kimi/skills/
// in the workdir. See https://moonshotai.github.io/kimi-cli/en/customization/skills.html
skillsDir = filepath.Join(workDir, ".kimi", "skills")
default:
// Fallback: write to .agent_context/skills/ (referenced by meta config).
skillsDir = filepath.Join(workDir, ".agent_context", "skills")
}
if err := os.MkdirAll(skillsDir, 0o755); err != nil {
return "", err
}
return skillsDir, nil
}
var nonAlphaNum = regexp.MustCompile(`[^a-z0-9]+`)
// sanitizeSkillName converts a skill name to a safe directory name.
func sanitizeSkillName(name string) string {
s := strings.ToLower(strings.TrimSpace(name))
s = nonAlphaNum.ReplaceAllString(s, "-")
s = strings.Trim(s, "-")
if s == "" {
s = "skill"
}
return s
}
// writeSkillFiles writes skill directories into the given parent directory.
// Each skill gets its own subdirectory containing SKILL.md and supporting files.
func writeSkillFiles(skillsDir string, skills []SkillContextForEnv) error {
if err := os.MkdirAll(skillsDir, 0o755); err != nil {
return fmt.Errorf("create skills dir: %w", err)
}
for _, skill := range skills {
dir := filepath.Join(skillsDir, sanitizeSkillName(skill.Name))
if err := os.MkdirAll(dir, 0o755); err != nil {
return err
}
// Write main SKILL.md
if err := os.WriteFile(filepath.Join(dir, "SKILL.md"), []byte(skill.Content), 0o644); err != nil {
return err
}
// Write supporting files
for _, f := range skill.Files {
fpath := filepath.Join(dir, f.Path)
if err := os.MkdirAll(filepath.Dir(fpath), 0o755); err != nil {
return err
}
if err := os.WriteFile(fpath, []byte(f.Content), 0o644); err != nil {
return err
}
}
}
return nil
}
// renderIssueContext builds the markdown content for issue_context.md.
func renderIssueContext(provider string, ctx TaskContextForEnv) string {
var b strings.Builder
b.WriteString("# Task Assignment\n\n")
fmt.Fprintf(&b, "**Issue ID:** %s\n\n", ctx.IssueID)
if ctx.TriggerCommentID != "" {
b.WriteString("**Trigger:** Comment Reply\n")
b.WriteString("**Triggering comment ID:** `" + ctx.TriggerCommentID + "`\n\n")
} else {
b.WriteString("**Trigger:** New Assignment\n\n")
}
b.WriteString("## Quick Start\n\n")
fmt.Fprintf(&b, "Run `multica issue get %s --output json` to fetch the full issue details.\n\n", ctx.IssueID)
if len(ctx.AgentSkills) > 0 {
b.WriteString("## Agent Skills\n\n")
b.WriteString("The following skills are available to you:\n\n")
for _, skill := range ctx.AgentSkills {
fmt.Fprintf(&b, "- **%s**\n", skill.Name)
}
b.WriteString("\n")
}
return b.String()
}