delegate-agent-cli 0.15.0__tar.gz → 0.16.0__tar.gz

{delegate_agent_cli-0.15.0 → delegate_agent_cli-0.16.0}/CHANGELOG.md

@@ -5,6 +5,41 @@ All notable changes to this project are documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+
+## [0.16.0] - 2026-07-16
+
+### Added
+
+- `--timeout` is now accepted and enforced on tracked `safe` and `work` runs
+  across engines. It remains rejected with `--pass-through`, and deadline
+  failures keep the historical `call_timeout` error code.
+- Kimi tool-call activity is normalized into `tool.started`/`tool.completed`
+  events with id correlation; `status` stays unset because Kimi tool results
+  carry no result-status signal.
+
+### Changed
+
+- Persistent-worktree runs that fail after the worktree is realized
+  (child-launch errors, timeouts) now keep `worktreeStatus: present`,
+  `executionCwd`, `branch`, and `worktreeCleanupCommands` in the failed-run
+  record, so the preserved worktree stays inspectable and removable via
+  `delegate worktree show|remove` instead of being orphaned.
+- The Kimi default model is now `kimi-code/k3`, and the bundled Kimi catalog
+  lists exactly the three real model IDs (`kimi-code/k3`,
+  `kimi-code/kimi-for-coding`, `kimi-code/kimi-for-coding-highspeed`); the
+  stale `kimi-k2.7` entry was removed.
+- Docs clarifications: Kimi reasoning-effort wording now states that the Kimi
+  CLI exposes no effort flag (k3 supports effort internally via
+  `~/.kimi-code/config.toml`) and that Delegate rejects `--reasoning-effort`
+  for Kimi; the CLI reference notes that `usage: unavailable` in Kimi run JSON
+  is expected because the Kimi CLI emits no usage/token lines in stream-json
+  output.
+- Kimi work-mode docs restate current behavior: Delegate emits no `--yolo` —
+  Kimi prompt mode auto-approves tool actions, and work mode edits the real
+  workspace by default. Temporary safe isolation or explicit worktree
+  isolation provides a workspace boundary, not a complete host sandbox.
+
 ## [0.15.0] - 2026-07-16
 
 ### Added
@@ -390,6 +425,7 @@ Usage-audit fix wave: 82 sessions and 1,241 delegate invocations from one week o
 
 - Releases before 0.1.3 predate this changelog.
 
+[0.16.0]: https://github.com/treygoff24/delegate-agent/compare/v0.15.0...v0.16.0
 [0.15.0]: https://github.com/treygoff24/delegate-agent/compare/v0.14.0...v0.15.0
 [0.14.0]: https://github.com/treygoff24/delegate-agent/compare/v0.13.1...v0.14.0
 [0.13.1]: https://github.com/treygoff24/delegate-agent/compare/v0.13.0...v0.13.1

{delegate_agent_cli-0.15.0 → delegate_agent_cli-0.16.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: delegate-agent-cli
-Version: 0.15.0
+Version: 0.16.0
 Summary: A tiny CLI for delegating bounded agent tasks to Cursor, Droid, OpenAI Codex, Claude Code, Grok Build, or Kimi Code runtimes.
 Author: Trey Goff
 License-Expression: MIT
@@ -229,7 +229,7 @@ prompt framing, and no session persistence or tools according to the engine
 capability contract. Claude receives the prompt only on stdin and is
 schema-capable via `--output-schema`; `delegate --json describe` reports
 `pureCall`, `structuredOutput`, `noSessionPersistence`, `usageEvents`, and
-`promptStdin` per engine. `--timeout SECONDS` applies to every call-mode engine.
+`promptStdin` per engine. `--timeout SECONDS` applies to every engine in any mode (calls and tracked safe/work runs, but not `--pass-through`).
 
 For multi-step fan-out or gated review flows, use Delegate Workflows. A workflow
 is a Python script that launches normal Delegate child runs, journals progress,

{delegate_agent_cli-0.15.0 → delegate_agent_cli-0.16.0}/README.md

@@ -196,7 +196,7 @@ prompt framing, and no session persistence or tools according to the engine
 capability contract. Claude receives the prompt only on stdin and is
 schema-capable via `--output-schema`; `delegate --json describe` reports
 `pureCall`, `structuredOutput`, `noSessionPersistence`, `usageEvents`, and
-`promptStdin` per engine. `--timeout SECONDS` applies to every call-mode engine.
+`promptStdin` per engine. `--timeout SECONDS` applies to every engine in any mode (calls and tracked safe/work runs, but not `--pass-through`).
 
 For multi-step fan-out or gated review flows, use Delegate Workflows. A workflow
 is a Python script that launches normal Delegate child runs, journals progress,

{delegate_agent_cli-0.15.0 → delegate_agent_cli-0.16.0}/config.example.json

@@ -95,7 +95,7 @@
   },
   "kimi": {
     "binary": "kimi",
-    "defaultModel": "kimi-code/kimi-for-coding",
+    "defaultModel": "kimi-code/k3",
     "defaultReasoningEffort": null
   },
   "isolation": {

{delegate_agent_cli-0.15.0 → delegate_agent_cli-0.16.0}/docs/cli-reference.md

@@ -20,33 +20,33 @@ Use `delegate --help` for the exact command list from the installed version. Glo
 ### Direct runtime commands
 
 ```bash
-delegate cursor safe [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]
-delegate cursor work [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]
-delegate cursor call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]
+delegate cursor safe [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [prompt...]
+delegate cursor work [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [prompt...]
+delegate cursor call [--read-only] [--timeout SECONDS] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]
 
-delegate droid [MODEL_ALIAS] safe [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]
-delegate droid [MODEL_ALIAS] work [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]
-delegate droid [MODEL_ALIAS] call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]
+delegate droid [MODEL_ALIAS] safe [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [prompt...]
+delegate droid [MODEL_ALIAS] work [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [prompt...]
+delegate droid [MODEL_ALIAS] call [--read-only] [--timeout SECONDS] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]
 
-delegate codex safe [--model <alias-or-model>] [--reasoning-effort LEVEL] [--fast|--no-fast] [--progress] [--forbid-commit] [--prompt-file PATH] [--output-schema FILE] [prompt...]
-delegate codex work [--model <alias-or-model>] [--reasoning-effort LEVEL] [--fast|--no-fast] [--progress] [--forbid-commit] [--prompt-file PATH] [--output-schema FILE] [prompt...]
-delegate codex call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--fast|--no-fast] [--prompt-file PATH] [--output-schema FILE] [prompt...]
+delegate codex safe [--model <alias-or-model>] [--reasoning-effort LEVEL] [--fast|--no-fast] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [--output-schema FILE] [prompt...]
+delegate codex work [--model <alias-or-model>] [--reasoning-effort LEVEL] [--fast|--no-fast] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [--output-schema FILE] [prompt...]
+delegate codex call [--read-only] [--timeout SECONDS] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--fast|--no-fast] [--prompt-file PATH] [--output-schema FILE] [prompt...]
 
-delegate claude safe [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]
-delegate claude work [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]
-delegate claude call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]
+delegate claude safe [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [prompt...]
+delegate claude work [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [prompt...]
+delegate claude call [--read-only] [--timeout SECONDS] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]
 
-delegate grok safe [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]
-delegate grok work [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]
-delegate grok call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]
+delegate grok safe [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [prompt...]
+delegate grok work [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [prompt...]
+delegate grok call [--read-only] [--timeout SECONDS] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]
 
-delegate opencode safe [--model <alias-or-model>] [--reasoning-effort LEVEL] [--agent NAME] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]
-delegate opencode work [--model <alias-or-model>] [--reasoning-effort LEVEL] [--agent NAME] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]
-delegate opencode call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--agent NAME] [--prompt-file PATH] [prompt...]
+delegate opencode safe [--model <alias-or-model>] [--reasoning-effort LEVEL] [--agent NAME] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [prompt...]
+delegate opencode work [--model <alias-or-model>] [--reasoning-effort LEVEL] [--agent NAME] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [prompt...]
+delegate opencode call [--read-only] [--timeout SECONDS] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--agent NAME] [--prompt-file PATH] [prompt...]
 
-delegate kimi safe [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]
-delegate kimi work [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]
-delegate kimi call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]
+delegate kimi safe [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [prompt...]
+delegate kimi work [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [prompt...]
+delegate kimi call [--read-only] [--timeout SECONDS] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]
 ```
 
 Prompt sources are direct arguments, `--prompt-file`, or Delegate stdin. Raw C0 control characters other than newline, carriage return, and tab are stripped before launch; a prompt that becomes empty fails fast. After
@@ -82,7 +82,7 @@ and advisory catalogs with `delegate models`, `delegate models <engine>`, and
 `delegate models <engine> --live` (live probes for cursor/droid/devin/opencode; other
 engines report live unsupported).
 
-`--reasoning-effort LEVEL` is optional and parsed only before prompt text begins. Engines with capability metadata reject unsupported model/effort pairs before launch with `unsupported_reasoning_effort`. It affects only model reasoning depth, cost, or latency; it does not change `safe`/`work`/`call` permissions, sandboxing, approvals, network policy, or edit capability. Cursor effort is model-selection based and requires `cursor.reasoningEffortModels`; an explicit `--model` wins over effort→model routing. Droid emits `--reasoning-effort LEVEL`; Codex emits a `model_reasoning_effort` config override for the resolved model, or for the Codex harness default model when no `codex.defaultModel` is configured and the request was explicit; Claude emits Claude Code `--effort LEVEL`; Grok emits Grok `--effort LEVEL` (`low`, `medium`, `high`, `xhigh`, `max`); OpenCode emits `--variant LEVEL` without validating it against the selected model. Kimi does not support reasoning effort in v1.
+`--reasoning-effort LEVEL` is optional and parsed only before prompt text begins. Engines with capability metadata reject unsupported model/effort pairs before launch with `unsupported_reasoning_effort`. It affects only model reasoning depth, cost, or latency; it does not change `safe`/`work`/`call` permissions, sandboxing, approvals, network policy, or edit capability. Cursor effort is model-selection based and requires `cursor.reasoningEffortModels`; an explicit `--model` wins over effort→model routing. Droid emits `--reasoning-effort LEVEL`; Codex emits a `model_reasoning_effort` config override for the resolved model, or for the Codex harness default model when no `codex.defaultModel` is configured and the request was explicit; Claude emits Claude Code `--effort LEVEL`; Grok emits Grok `--effort LEVEL` (`low`, `medium`, `high`, `xhigh`, `max`); OpenCode emits `--variant LEVEL` without validating it against the selected model. The Kimi CLI exposes no effort flag; k3 supports effort internally via `~/.kimi-code/config.toml`, so Delegate rejects `--reasoning-effort` for Kimi.
 
 `--fast` and `--no-fast` are Codex-only, mutually exclusive per-run service-tier overrides. `--fast` emits `service_tier="fast"` plus `features.fast_mode=true` (Codex silently drops a Fast tier when that feature flag is off in the ambient config, so Delegate enables it explicitly); `--no-fast` emits `service_tier="default"` so a globally enabled Fast setting can be turned off for one child. Omitting both emits no override and inherits Codex configuration. Fast is orthogonal to model selection, reasoning effort, and Delegate safety policy. Two upstream caveats: Codex strips the service tier when authenticated with an API key (Fast is a ChatGPT-plan feature), and neither Codex nor the API fails on a tier the model does not offer — Delegate's flag validation is the only fail-closed layer, so an unsupported combination degrades silently to standard routing rather than erroring.
 
@@ -150,8 +150,8 @@ auth/env selection happens.
 Usage:
 
 ```bash
-delegate [--json] [--isolation auto|none|worktree] codex {safe,work} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--fast|--no-fast] [--progress] [--forbid-commit] [--prompt-file PATH] [--output-schema FILE] [prompt...]
-delegate [--json] codex call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--fast|--no-fast] [--prompt-file PATH] [--output-schema FILE] [prompt...]
+delegate [--json] [--isolation auto|none|worktree] codex {safe,work} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--fast|--no-fast] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [--output-schema FILE] [prompt...]
+delegate [--json] codex call [--read-only] [--timeout SECONDS] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--fast|--no-fast] [--prompt-file PATH] [--output-schema FILE] [prompt...]
 ```
 
 - Safe mode reviews your **current working tree** — uncommitted tracked edits and untracked, non-ignored files are mirrored into an isolated throwaway copy (only gitignored paths are excluded), so you can review local changes without committing first or pasting a diff. Codex safe always uses `--sandbox read-only`. Under `--isolation auto`, Codex safe is the only safe harness that may opt out with `--isolation none`, because Codex still keeps its read-only sandbox active.
@@ -178,8 +178,8 @@ delegate --isolation worktree codex work "Implement the feature in a persistent
 Usage:
 
 ```bash
-delegate [--json] [--isolation auto|none|worktree] claude {safe,work} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]
-delegate [--json] claude call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]
+delegate [--json] [--isolation auto|none|worktree] claude {safe,work} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [prompt...]
+delegate [--json] claude call [--read-only] [--timeout SECONDS] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]
 ```
 
 - Safe mode reviews your **current working tree** — uncommitted tracked edits and untracked, non-ignored files are mirrored into an isolated throwaway copy (only gitignored paths are excluded), so you can review local changes without committing first or pasting a diff. Under `--isolation auto`, Claude safe uses `--permission-mode plan`, `--strict-mcp-config`, Read/Grep/Glob, and selected read-only Bash tools such as `git diff`/`git status`.
@@ -204,8 +204,8 @@ delegate --isolation worktree claude work "Implement the feature in a persistent
 Usage:
 
 ```bash
-delegate [--json] [--isolation auto|none|worktree] grok {safe,work} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]
-delegate [--json] grok call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]
+delegate [--json] [--isolation auto|none|worktree] grok {safe,work} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [prompt...]
+delegate [--json] grok call [--read-only] [--timeout SECONDS] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]
 ```
 
 - Safe mode reviews your **current working tree** in an isolated throwaway copy plus Grok read-only controls (`--sandbox read-only`, `--permission-mode dontAsk` by default). Delegate does not use Grok `plan` mode for safe review.
@@ -229,8 +229,8 @@ delegate --isolation worktree grok work "Implement the feature in a persistent w
 Wraps OpenCode's non-interactive `run` command.
 
 ```bash
-delegate [--json] [--isolation auto|none|worktree] opencode {safe,work} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--agent NAME] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]
-delegate [--json] opencode call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--agent NAME] [--prompt-file PATH] [prompt...]
+delegate [--json] [--isolation auto|none|worktree] opencode {safe,work} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--agent NAME] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [prompt...]
+delegate [--json] opencode call [--read-only] [--timeout SECONDS] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--agent NAME] [--prompt-file PATH] [prompt...]
 ```
 
 - Safe mode reviews the current working tree in an isolated throwaway copy. It
@@ -272,7 +272,8 @@ delegate [--json] opencode call [--read-only] [--model <alias-or-model>] [--reas
   `workflows.engineCaps` like other engines.
 - OpenCode currently buffers stdout until completion, so progress can remain
   silent even though `--print-logs` stderr is visible. Sessions accumulate in
-  the user's global OpenCode state. Call mode has no Delegate timeout.
+  the user's global OpenCode state. Call mode has no Delegate timeout unless
+  `--timeout` is set.
 
 Examples:
 
@@ -288,15 +289,16 @@ delegate --isolation worktree opencode work "Implement the feature in a persiste
 Usage:
 
 ```bash
-delegate [--json] [--isolation auto|none|worktree] kimi {safe,work} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]
-delegate [--json] kimi call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]
+delegate [--json] [--isolation auto|none|worktree] kimi {safe,work} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--timeout SECONDS] [--forbid-commit] [--prompt-file PATH] [prompt...]
+delegate [--json] kimi call [--read-only] [--timeout SECONDS] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]
 ```
 
 - Safe mode reviews your **current working tree** — uncommitted tracked edits and untracked, non-ignored files are mirrored into an isolated throwaway copy (only gitignored paths are excluded), so you can review local changes without committing first or pasting a diff. Under `--isolation auto`, Kimi safe uses a read-only safety prompt. Delegate intentionally avoids Kimi `--plan` in safe mode. Kimi prompt mode auto-approves tool actions, so the isolation is the effective write boundary; the safety prompt is advisory.
 - Work mode uses Kimi prompt mode and runs in the real workspace unless you opt into worktree isolation. Delegate does not emit `--yolo` because Kimi rejects combining `--yolo` with `--prompt`.
 - Model selection uses `--model` (alias from `kimi.models` or a raw model ID), the run-input JSON `model`, or `kimi.defaultModel`.
-- `--reasoning-effort` is unsupported for Kimi in v1.
+- `--reasoning-effort` is rejected for Kimi: the Kimi CLI exposes no effort flag, and k3 supports effort internally via `~/.kimi-code/config.toml`.
 - Kimi prompt text is passed via argv.
+- Run JSON reports `usage: unavailable` for Kimi — expected: the Kimi CLI (verified 0.26.0) emits no usage/token lines in stream-json output, so there is nothing to parse.
 
 Examples:
 
@@ -430,11 +432,13 @@ and ambient customization, disables session persistence, and receives the prompt
 only on stdin. Use `--output-schema FILE` with Claude (schema contents inline)
 or with ordinary Codex call mode (schema path).
 
-`--timeout SECONDS` is a positive integer available on every call-mode engine.
-On expiry Delegate terminates the whole child process group and returns
-`call_timeout` with exit code 1.
+`--timeout SECONDS` is a positive integer accepted in every mode. It bounds
+calls and tracked `safe`/`work` runs alike: on expiry Delegate terminates the
+whole child process group and returns `call_timeout` (a historical error-code
+name kept for API stability) with exit code 1. `--timeout` is not supported
+with `--pass-through`, which streams the child without a tracked deadline.
 
-`--read-only`, `--pure`, and `--timeout` apply only to `call`; passing them with
+`--read-only` and `--pure` apply only to `call`; passing them with
 `safe`/`work` is rejected. Empty-result retry applies to safe runs and read-only
 calls when the prompt can be safely extended; write-capable, pure, and verbatim
 calls are not retried.
@@ -579,6 +583,7 @@ Supported input keys:
   "progress": true,
   "forbidCommit": true,
   "includeDirty": true,
+  "timeout": 30,
   "outputSchema": "/path/to/schema.json",
   "prompt": "Implement the scoped task and report changed files."
 }
@@ -595,6 +600,7 @@ Supported input keys:
 - `progress`: optional boolean. `true` enables parent progress heartbeats on stderr; `false` disables them even when `progress.enabled` is true in config. When omitted, config `progress.enabled` applies (default `false`). `mode: "call"` rejects progress.
 - `forbidCommit`: optional boolean. `true` requires `mode: "work"` with persistent worktree isolation and fails the run if the child creates commits. `mode: "call"` rejects commit policy.
 - `includeDirty`: optional boolean. `true` requires `mode: "work"` with persistent worktree isolation and syncs tracked edits plus untracked non-ignored files into the new worktree before launch.
+- `timeout`: optional positive integer seconds, with the same semantics as `--timeout`. Non-integer, boolean, or non-positive values fail with `invalid_timeout`; combining it with pass-through is rejected.
 - `outputSchema`: optional path to a JSON Schema for the final message. Supported for Codex and Claude call mode (same semantics as `--output-schema`). Other engines fail with `unsupported_output_schema`.
 - `prompt`: required task prompt.
 

{delegate_agent_cli-0.15.0 → delegate_agent_cli-0.16.0}/docs/configuration.md

@@ -123,7 +123,7 @@ layers. This is read-only observability; inspecting it does not modify
   },
   "kimi": {
     "binary": "kimi",
-    "defaultModel": "kimi-code/kimi-for-coding",
+    "defaultModel": "kimi-code/k3",
     "defaultReasoningEffort": null
   },
   "workflows": {
@@ -353,7 +353,7 @@ Controls local run recording.
 {
   "kimi": {
     "binary": "kimi",
-    "defaultModel": "kimi-code/kimi-for-coding",
+    "defaultModel": "kimi-code/k3",
     "defaultReasoningEffort": null,
     "models": {}
   }
@@ -361,7 +361,7 @@ Controls local run recording.
 ```
 
 - `binary`: path to the `kimi` executable.
-- `defaultModel`: default Kimi model alias (e.g. `kimi-code/kimi-for-coding`). Set to `null` to let Kimi use its own configured default.
+- `defaultModel`: default Kimi model alias (e.g. `kimi-code/k3`). Set to `null` to let Kimi use its own configured default.
 - `models`: optional map of local aliases to Kimi model IDs for `--model` / JSON `model`. Alias keys must not collide with mode names, equal the engine's own name, or start with `-`.
 - `defaultReasoningEffort`: not supported in v1; must be `null`.
 - Kimi's thinking/effort level is configured in `~/.kimi-code/config.toml`, not through Delegate.

{delegate_agent_cli-0.15.0 → delegate_agent_cli-0.16.0}/docs/troubleshooting.md

@@ -99,7 +99,7 @@ Common causes:
 - Droid or Codex model support is not in config, the workspace cache, or bundled fallback data.
 - The effort string is misspelled. Delegate treats labels literally and does not translate between provider naming schemes.
 
-These failures apply to explicit per-run effort (`--reasoning-effort` or JSON run input). For Cursor, Droid, and Codex, a config `defaultReasoningEffort` that cannot be satisfied does not fail the run; the run proceeds without reasoning effort and records a warning in the dry-run payload, manifest, and snapshot. Claude config defaults are validated against its static native labels at config load. Kimi does not support reasoning effort, so `kimi.defaultReasoningEffort` must stay `null`.
+These failures apply to explicit per-run effort (`--reasoning-effort` or JSON run input). For Cursor, Droid, and Codex, a config `defaultReasoningEffort` that cannot be satisfied does not fail the run; the run proceeds without reasoning effort and records a warning in the dry-run payload, manifest, and snapshot. Claude config defaults are validated against its static native labels at config load. For Kimi, `--reasoning-effort` is rejected outright: the Kimi CLI exposes no effort flag (k3 supports effort internally via `~/.kimi-code/config.toml`), so `kimi.defaultReasoningEffort` must stay `null`.
 
 For private or newly released models, declare support in `reasoning.capabilities` in config. Inspect first with plain `capabilities`. To refresh workspace-local discovered data, run:
 

delegate_agent_cli-0.16.0/examples/task.kimi.json

@@ -0,0 +1,7 @@
+{
+  "engine": "kimi",
+  "mode": "safe",
+  "cwd": "/path/to/workspace",
+  "isolation": "auto",
+  "prompt": "Review this workspace for correctness risks. Do not edit files. Report findings with file, line, severity, and rationale."
+}

{delegate_agent_cli-0.15.0 → delegate_agent_cli-0.16.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "delegate-agent-cli"
-version = "0.15.0"
+version = "0.16.0"
 description = "A tiny CLI for delegating bounded agent tasks to Cursor, Droid, OpenAI Codex, Claude Code, Grok Build, or Kimi Code runtimes."
 readme = "README.md"
 requires-python = ">=3.11"

{delegate_agent_cli-0.15.0 → delegate_agent_cli-0.16.0}/src/delegate_agent/__init__.py

@@ -1,5 +1,5 @@
 """Delegate Agent CLI package."""
 
-VERSION = "0.15.0"
+VERSION = "0.16.0"
 
 __all__ = ["VERSION"]

{delegate_agent_cli-0.15.0 → delegate_agent_cli-0.16.0}/src/delegate_agent/bundled_models.py

@@ -70,8 +70,9 @@ BUNDLED_MODELS: dict[str, tuple[BundledModelEntry, ...]] = {
         {"id": "grok-4.5-fast"},
     ),
     "kimi": (
+        {"id": "kimi-code/k3"},
         {"id": "kimi-code/kimi-for-coding"},
-        {"id": "kimi-k2.7"},
+        {"id": "kimi-code/kimi-for-coding-highspeed"},
     ),
     "opencode": (
         {"id": "opencode/claude-opus-4-5"},

{delegate_agent_cli-0.15.0 → delegate_agent_cli-0.16.0}/src/delegate_agent/cli.py

@@ -669,7 +669,7 @@ def execute_request(
                         timeout=request.timeout,
                     )
                 except delegate_runner.RunnerLaunchError as exc:
-                    raise DelegateError(exc.error, exc.message) from exc
+                    raise DelegateError(exc.error, exc.message, exc.exit_code) from exc
             try:
                 sensitive_texts = [request.prompt]
                 if "--json-schema" in request.argv:
@@ -802,7 +802,7 @@ def execute_request(
                 )
             )
         except worktree_execution.PersistentWorktreeError as exc:
-            raise DelegateError(exc.error, exc.message) from exc
+            raise DelegateError(exc.error, exc.message, exc.exit_code) from exc
 
     with safe_isolated_request(request) as isolated_request:
         _set_child_root_env(isolated_request, source_workspace)
@@ -879,9 +879,10 @@ def execute_request(
                 progress=isolated_request.progress,
                 progress_initial_delay_sec=isolated_request.progress_initial_delay_sec,
                 progress_interval_sec=isolated_request.progress_interval_sec,
+                timeout=isolated_request.timeout,
             )
         except delegate_runner.RunnerLaunchError as exc:
-            raise DelegateError(exc.error, exc.message) from exc
+            raise DelegateError(exc.error, exc.message, exc.exit_code) from exc
 
 
 def shell_join(argv: list[str]) -> str:

{delegate_agent_cli-0.15.0 → delegate_agent_cli-0.16.0}/src/delegate_agent/cli_parser.py

@@ -727,8 +727,12 @@ def parse_modeless_engine(
     if fast is not None and engine != "codex":
         raise DelegateError("unsupported_fast", "--fast and --no-fast are only supported by codex.")
     _validate_pure_options(engine, mode, pure=pure, read_only=read_only, group=group)
-    if timeout is not None and mode != "call":
-        raise DelegateError("invalid_option_combination", "--timeout only applies to call mode.")
+    if timeout is not None and pass_through:
+        raise DelegateError(
+            "invalid_option_combination",
+            "--timeout is not supported with --pass-through; "
+            "pass-through runs have no tracked deadline.",
+        )
     forbid_commit_implied_isolation = False
     if forbid_commit and mode == "work" and isolation is None:
         isolation = "worktree"
@@ -848,8 +852,12 @@ def parse_droid(
     if fast is not None:
         raise DelegateError("unsupported_fast", "--fast and --no-fast are only supported by codex.")
     _validate_pure_options("droid", mode, pure=pure, read_only=read_only, group=group)
-    if timeout is not None and mode != "call":
-        raise DelegateError("invalid_option_combination", "--timeout only applies to call mode.")
+    if timeout is not None and pass_through:
+        raise DelegateError(
+            "invalid_option_combination",
+            "--timeout is not supported with --pass-through; "
+            "pass-through runs have no tracked deadline.",
+        )
     forbid_commit_implied_isolation = False
     if forbid_commit and mode == "work" and isolation is None:
         isolation = "worktree"