delegate-agent-cli 0.13.0__tar.gz → 0.13.1__tar.gz

{delegate_agent_cli-0.13.0 → delegate_agent_cli-0.13.1}/CHANGELOG.md

@@ -5,6 +5,18 @@ 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).
 
+## [0.13.1] - 2026-07-09
+
+### Added
+
+- Codex-only `--fast` / `--no-fast` per-run service-tier overrides (and a
+  `fast` boolean in run-input JSON). `--fast` emits `service_tier="fast"` plus
+  `features.fast_mode=true` so the tier cannot be silently dropped by ambient
+  Codex config; `--no-fast` emits the explicit `service_tier="default"`
+  standard-routing sentinel; omitting both inherits Codex configuration. The
+  explicit choice is recorded as `requestedFast` in run metadata. The flag and
+  JSON key fail closed on every other engine, including a bare `"fast": null`.
+
 ## [0.13.0] - 2026-07-09
 
 ### Added
@@ -292,6 +304,7 @@ Usage-audit fix wave: 82 sessions and 1,241 delegate invocations from one week o
 
 - Releases before 0.1.3 predate this changelog.
 
+[0.13.1]: https://github.com/treygoff24/delegate-agent/compare/v0.13.0...v0.13.1
 [0.13.0]: https://github.com/treygoff24/delegate-agent/compare/v0.12.0...v0.13.0
 [0.12.0]: https://github.com/treygoff24/delegate-agent/compare/v0.11.0...v0.12.0
 [0.11.0]: https://github.com/treygoff24/delegate-agent/compare/v0.10.0...v0.11.0

{delegate_agent_cli-0.13.0 → delegate_agent_cli-0.13.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: delegate-agent-cli
-Version: 0.13.0
+Version: 0.13.1
 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
@@ -243,6 +243,21 @@ delegate --json dry-run codex safe --reasoning-effort high "Review this reposito
 delegate --json dry-run claude safe --reasoning-effort high "Review this repository. Do not edit files."
 ```
 
+Codex model routing is deliberately model-first rather than aliasing every
+model/effort pair: define model aliases in `codex.models`, then set effort per
+run with `--reasoning-effort`. Per-model effort menus (including any efforts
+newer than the bundled data) belong in the private `reasoning.capabilities`
+config block, which overrides the bundled defaults.
+
+Fast mode is an independent per-run serving choice. `--fast` requests Codex's
+Fast service tier, `--no-fast` explicitly requests Standard, and omitting both
+inherits the active Codex configuration:
+
+```bash
+delegate codex safe --model my-alias --reasoning-effort medium --fast "Explore likely causes."
+delegate codex work --model my-alias --reasoning-effort high --no-fast "Implement and verify."
+```
+
 Inspect tracked output by alias:
 
 ```bash

{delegate_agent_cli-0.13.0 → delegate_agent_cli-0.13.1}/README.md

@@ -210,6 +210,21 @@ delegate --json dry-run codex safe --reasoning-effort high "Review this reposito
 delegate --json dry-run claude safe --reasoning-effort high "Review this repository. Do not edit files."
 ```
 
+Codex model routing is deliberately model-first rather than aliasing every
+model/effort pair: define model aliases in `codex.models`, then set effort per
+run with `--reasoning-effort`. Per-model effort menus (including any efforts
+newer than the bundled data) belong in the private `reasoning.capabilities`
+config block, which overrides the bundled defaults.
+
+Fast mode is an independent per-run serving choice. `--fast` requests Codex's
+Fast service tier, `--no-fast` explicitly requests Standard, and omitting both
+inherits the active Codex configuration:
+
+```bash
+delegate codex safe --model my-alias --reasoning-effort medium --fast "Explore likely causes."
+delegate codex work --model my-alias --reasoning-effort high --no-fast "Implement and verify."
+```
+
 Inspect tracked output by alias:
 
 ```bash

{delegate_agent_cli-0.13.0 → delegate_agent_cli-0.13.1}/docs/cli-reference.md

@@ -28,9 +28,9 @@ delegate droid [MODEL_ALIAS] safe [--model <alias-or-model>] [--reasoning-effort
 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 codex safe [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [--output-schema FILE] [prompt...]
-delegate codex work [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [--output-schema FILE] [prompt...]
-delegate codex call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [--output-schema FILE] [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 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...]
@@ -77,6 +77,8 @@ 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.
 
+`--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.
+
 `--progress` enables parent progress heartbeats on stderr for tracked foreground
 runs. `--no-progress` disables them even when `progress.enabled` is true in
 config. When neither flag is set, config `progress.enabled` applies (default
@@ -137,13 +139,14 @@ auth/env selection happens.
 Usage:
 
 ```bash
-delegate [--json] [--isolation auto|none|worktree] codex {safe,work,call} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [--output-schema FILE] [prompt...]
+delegate [--json] [--isolation auto|none|worktree] codex {safe,work,call} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--fast|--no-fast] [--progress] [--forbid-commit] [--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.
 - Prompt text is delivered on stdin to `codex exec`; dry-run argv and tracked run manifests do not contain the prompt.
 - Model selection uses `--model` (alias from `codex.models` or a raw model ID), the run-input JSON `model`, or `codex.defaultModel`.
 - `--reasoning-effort` maps to a Codex `model_reasoning_effort` config override after the model is resolved.
+- `--fast` requests Codex Fast for one run; `--no-fast` explicitly requests Standard; omission inherits Codex configuration. The selected tier is recorded as `requestedFast` when explicit.
 - `--output-schema FILE` is **codex-only**. Every other engine rejects it. `FILE` is a path to a JSON Schema that OpenAI enforces on Codex's final message, for machine-parseable output in fan-outs and JSON run input. Relative paths resolve against the process launch cwd, the same rule as `--prompt-file`. When set, Delegate suppresses the completion-report prompt injection for that run so the schema owns the whole final message. Missing or unreadable files fail fast before launch.
 
 Examples:
@@ -151,6 +154,7 @@ Examples:
 ```bash
 delegate codex safe "Review this repo for regressions; report file/line/severity."
 delegate codex safe --model gpt-5.5 "Review this repo for regressions; report file/line/severity."
+delegate codex safe --model my-alias --reasoning-effort medium --fast "Explore likely causes."
 delegate codex work "Implement the scoped task; report changed files and tests."
 delegate codex call "Summarize this context in three bullets."
 delegate --json codex safe --output-schema findings.schema.json "Return one record per finding."
@@ -513,6 +517,7 @@ Supported input keys:
   "cwd": "/path/to/workspace",
   "isolation": "worktree",
   "reasoningEffort": "high",
+  "fast": false,
   "progress": true,
   "forbidCommit": true,
   "includeDirty": true,
@@ -527,6 +532,7 @@ Supported input keys:
 - `cwd`: optional workspace path. Git directories resolve to the repo root. Omit it for `mode: "call"`, which always uses an empty temporary cwd.
 - `isolation`: optional `auto`, `none`, or `worktree`. `null` is invalid. `mode: "call"` rejects isolation. For Cursor, Claude, Grok, Devin, OpenCode, Droid, and Kimi safe mode, `none` is normalized to `auto` with a warning.
 - `reasoningEffort`: optional non-empty effort string. It overrides provider `defaultReasoningEffort` for that JSON run.
+- `fast`: optional Codex-only boolean or `null`. `true` requests Fast, `false` explicitly requests Standard, and `null`/omission inherits Codex configuration.
 - `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.

{delegate_agent_cli-0.13.0 → delegate_agent_cli-0.13.1}/docs/configuration.md

@@ -138,6 +138,11 @@ layers. This is read-only observability; inspecting it does not modify
 
 Reasoning-effort settings are optional. A per-run `--reasoning-effort LEVEL` or JSON `reasoningEffort` overrides provider defaults. If no effort is requested or defaulted, Delegate emits no reasoning-effort argv and preserves current runtime behavior.
 
+Codex Fast is intentionally not a Delegate config default. Use per-run
+`--fast`, `--no-fast`, or JSON `fast`; omission inherits the active Codex CLI
+configuration. This keeps speed selection independent from model aliases and
+reasoning defaults.
+
 ## Sections
 
 ### `tracking`

{delegate_agent_cli-0.13.0 → delegate_agent_cli-0.13.1}/docs/security-model.md

@@ -118,6 +118,14 @@ combinations before launch. OpenCode is the exception: Delegate passes the value
 through as `--variant`, and OpenCode may silently ignore an unknown variant.
 Treat higher effort as a possible latency/cost change, not as a safety control.
 
+## Codex Fast boundary
+
+`--fast`, `--no-fast`, and JSON `fast` select a Codex service tier for one run.
+They do not change the selected model, reasoning effort, sandbox, approvals,
+isolation, network policy, credentials, or edit capability. Fast may consume
+plan usage at a different rate; treat it as a latency/usage choice, never a
+security control.
+
 ## Isolation boundaries
 
 ### Temporary safe isolation

{delegate_agent_cli-0.13.0 → delegate_agent_cli-0.13.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "delegate-agent-cli"
-version = "0.13.0"
+version = "0.13.1"
 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-0.13.0 → delegate_agent_cli-0.13.1}/src/delegate_agent/__init__.py

@@ -1,5 +1,5 @@
 """Delegate Agent CLI package."""
 
-VERSION = "0.13.0"
+VERSION = "0.13.1"
 
 __all__ = ["VERSION"]

{delegate_agent_cli-0.13.0 → delegate_agent_cli-0.13.1}/src/delegate_agent/argv_builders.py

@@ -424,6 +424,7 @@ def build_codex_argv(
     workspace_kind: str,
     stream_capture: bool = True,
     reasoning_capability: reasoning.ReasoningCapability | None = None,
+    fast: bool | None = None,
     prompt_transport: str = PROMPT_TRANSPORT_ARGV,
     output_schema: str | None = None,
     call_read_only: bool = False,
@@ -455,6 +456,13 @@ def build_codex_argv(
                 f'model_reasoning_effort="{reasoning_capability.effort}"',
             ]
         )
+    if fast is not None:
+        service_tier = "fast" if fast else "default"
+        argv.extend(["-c", f'service_tier="{service_tier}"'])
+        if fast:
+            # Codex drops a "fast" tier silently when features.fast_mode is off
+            # in the ambient config; enable it so --fast cannot no-op.
+            argv.extend(["-c", "features.fast_mode=true"])
     argv.append("exec")
     argv.extend(["--cd", workspace])
     if output_schema is not None:

{delegate_agent_cli-0.13.0 → delegate_agent_cli-0.13.1}/src/delegate_agent/cli.py

@@ -22,6 +22,7 @@ from delegate_agent import (
     profiles,
     reasoning,
     redaction,
+    run_metadata,
     run_output_commands,
     run_registry,
     wait_cancel_commands,
@@ -305,6 +306,7 @@ def dry_run_payload(request: Request) -> JsonObject:
         "promptInstructionMode": request.prompt_instruction_mode,
     }
     reasoning.add_reasoning_payload_fields(payload, request)
+    run_metadata.add_speed_payload_fields(payload, request)
     if request.warnings:
         payload["warnings"] = list(request.warnings)
     if request.progress:
@@ -554,6 +556,7 @@ def make_run_context(
         reasoning_effort_source=request.reasoning_effort_source,
         reasoning_capability_source=request.reasoning_capability_source,
         reasoning_transport=request.reasoning_transport,
+        fast=request.fast,
         prompt_transport=request.prompt_transport,
         forbid_commit=request.forbid_commit,
         progress_initial_delay_sec=request.progress_initial_delay_sec,
@@ -688,6 +691,7 @@ def execute_request(
                             merged.append(warning)
                     payload["warnings"] = merged
                 reasoning.add_reasoning_payload_fields(payload, request)
+                run_metadata.add_speed_payload_fields(payload, request)
                 if result.exit_code != 0:
                     payload["error"] = "child_failed"
                     payload["message"] = "Child command failed."

{delegate_agent_cli-0.13.0 → delegate_agent_cli-0.13.1}/src/delegate_agent/cli_parser.py

@@ -703,6 +703,7 @@ def parse_modeless_engine(
         prompt_file,
         output_schema,
         reasoning_effort,
+        fast,
         progress_intent,
         forbid_commit,
         prompt_parts,
@@ -715,6 +716,8 @@ def parse_modeless_engine(
     ) = parse_prompt_tail(rest[1:], json_mode, isolation, command_prefix=[engine, mode])
     if agent is not None and engine != "opencode":
         raise DelegateError("unsupported_agent", "--agent is only supported by opencode.")
+    if fast is not None and engine != "codex":
+        raise DelegateError("unsupported_fast", "--fast and --no-fast are only supported by codex.")
     forbid_commit_implied_isolation = False
     if forbid_commit and mode == "work" and isolation is None:
         isolation = "worktree"
@@ -743,6 +746,7 @@ def parse_modeless_engine(
             prompt_file=prompt_file,
             output_schema=output_schema,
             reasoning_effort=reasoning_effort,
+            fast=fast,
             progress_intent=progress_intent,
             forbid_commit=forbid_commit,
             forbid_commit_implied_isolation=forbid_commit_implied_isolation,
@@ -813,6 +817,7 @@ def parse_droid(
         prompt_file,
         output_schema,
         reasoning_effort,
+        fast,
         progress_intent,
         forbid_commit,
         prompt_parts,
@@ -825,6 +830,8 @@ def parse_droid(
     ) = parse_prompt_tail(tail, json_mode, isolation, command_prefix=command_prefix)
     if agent is not None:
         raise DelegateError("unsupported_agent", "--agent is only supported by opencode.")
+    if fast is not None:
+        raise DelegateError("unsupported_fast", "--fast and --no-fast are only supported by codex.")
     forbid_commit_implied_isolation = False
     if forbid_commit and mode == "work" and isolation is None:
         isolation = "worktree"
@@ -855,6 +862,7 @@ def parse_droid(
             prompt_file=prompt_file,
             output_schema=output_schema,
             reasoning_effort=reasoning_effort,
+            fast=fast,
             progress_intent=progress_intent,
             forbid_commit=forbid_commit,
             forbid_commit_implied_isolation=forbid_commit_implied_isolation,
@@ -933,6 +941,7 @@ def parse_prompt_tail(
     str | None,
     str | None,
     str | None,
+    bool | None,
     str | None,
     bool,
     list[str],
@@ -946,6 +955,7 @@ def parse_prompt_tail(
     prompt_file: str | None = None
     output_schema: str | None = None
     reasoning_effort: str | None = None
+    fast: bool | None = None
     progress_intent: str | None = None
     forbid_commit = False
     include_dirty = False
@@ -1022,6 +1032,28 @@ def parse_prompt_tail(
                 raise DelegateError(exc.error, f"{exc.message}{corrected}") from exc
             i += 2
             continue
+        if token == "--fast":
+            if fast is not None:
+                detail = (
+                    "Only one --fast flag is allowed."
+                    if fast
+                    else "--fast and --no-fast cannot be combined."
+                )
+                raise DelegateError("invalid_option_combination", detail)
+            fast = True
+            i += 1
+            continue
+        if token == "--no-fast":
+            if fast is not None:
+                detail = (
+                    "Only one --no-fast flag is allowed."
+                    if not fast
+                    else "--fast and --no-fast cannot be combined."
+                )
+                raise DelegateError("invalid_option_combination", detail)
+            fast = False
+            i += 1
+            continue
         if token == "--model":
             if model is not None:
                 raise DelegateError(
@@ -1132,6 +1164,7 @@ def parse_prompt_tail(
         prompt_file,
         output_schema,
         reasoning_effort,
+        fast,
         progress_intent,
         forbid_commit,
         prompt_parts,

{delegate_agent_cli-0.13.0 → delegate_agent_cli-0.13.1}/src/delegate_agent/command_help.py

@@ -133,6 +133,16 @@ _OUTPUT_SCHEMA_OPTION = OptionSpec(
     "FILE",
     "Codex-only JSON Schema for the final message; also suppresses the completion-report instruction.",
 )
+_FAST_OPTION = OptionSpec(
+    "--fast",
+    None,
+    "Codex only: request the Fast service tier for this run (higher usage).",
+)
+_NO_FAST_OPTION = OptionSpec(
+    "--no-fast",
+    None,
+    "Codex only: request the Standard service tier for this run, overriding inherited Fast mode.",
+)
 _PROGRESS_OPTION = OptionSpec(
     "--progress",
     None,
@@ -258,14 +268,16 @@ COMMAND_SPECS: dict[str, CommandSpec] = {
         usage=(
             "delegate [--json] [--isolation auto|none|worktree] "
             "codex {safe,work} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] "
-            "[--output-schema FILE] [--forbid-commit] [--include-dirty] [--prompt-file PATH] [prompt...]",
+            "[--fast|--no-fast] [--output-schema FILE] [--forbid-commit] [--include-dirty] [--prompt-file PATH] [prompt...]",
             "delegate [--json] codex call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] "
-            "[--output-schema FILE] [--prompt-file PATH] [prompt...]",
+            "[--fast|--no-fast] [--output-schema FILE] [--prompt-file PATH] [prompt...]",
         ),
         arguments=(_MODE_ARG, _PROMPT_ARG),
         options=(
             _MODEL_OPTION,
             _REASONING_EFFORT_OPTION,
+            _FAST_OPTION,
+            _NO_FAST_OPTION,
             _OUTPUT_SCHEMA_OPTION,
             _PROGRESS_OPTION,
             _NO_PROGRESS_OPTION,
@@ -287,6 +299,8 @@ COMMAND_SPECS: dict[str, CommandSpec] = {
             "Reasoning effort is validated against the resolved model and emitted as a Codex "
             "config override; with no codex.defaultModel, explicit --reasoning-effort applies "
             "to the Codex harness default model.",
+            "--fast and --no-fast are per-run service-tier overrides. Omitting both inherits "
+            "the active Codex configuration; neither changes permissions or reasoning effort.",
             "--output-schema resolves relative paths from the launch cwd and is native Codex "
             "schema enforcement for the final message.",
             "codex.profile is a Codex CLI config overlay; top-level profiles selects "
@@ -519,10 +533,10 @@ COMMAND_SPECS: dict[str, CommandSpec] = {
             "[--prompt-file PATH] [prompt...]",
             "delegate [--json] [--isolation auto|none|worktree] "
             "dry-run codex {safe,work} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--output-schema FILE] "
-            "[--progress] [--forbid-commit] [--include-dirty] [--prompt-file PATH] [prompt...]",
+            "[--fast|--no-fast] [--progress] [--forbid-commit] [--include-dirty] [--prompt-file PATH] [prompt...]",
             "delegate [--json] [--isolation auto|none|worktree] "
             "dry-run codex call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--output-schema FILE] "
-            "[--prompt-file PATH] [prompt...]",
+            "[--fast|--no-fast] [--prompt-file PATH] [prompt...]",
             "delegate [--json] [--isolation auto|none|worktree] "
             "dry-run droid [MODEL_ALIAS] {safe,work} [--model <alias-or-model>] [--reasoning-effort LEVEL] "
             "[--progress] [--forbid-commit] [--include-dirty] [--prompt-file PATH] [prompt...]",
@@ -542,6 +556,8 @@ COMMAND_SPECS: dict[str, CommandSpec] = {
             _MODEL_OPTION,
             _REASONING_EFFORT_OPTION,
             _AGENT_OPTION,
+            _FAST_OPTION,
+            _NO_FAST_OPTION,
             _OUTPUT_SCHEMA_OPTION,
             _PROGRESS_OPTION,
             _NO_PROGRESS_OPTION,
@@ -562,6 +578,7 @@ COMMAND_SPECS: dict[str, CommandSpec] = {
         notes=(
             "dry-run shares the full engine grammar but launches no child process.",
             "--output-schema is accepted only for codex dry-runs.",
+            "--fast and --no-fast are accepted only for codex dry-runs.",
             "Reasoning effort is resolved from config/cache/bundled capabilities without invoking child binaries.",
         ),
         see_also=("cursor", "codex", "droid", "kimi", "claude", "grok", "opencode", "describe"),
@@ -582,7 +599,7 @@ COMMAND_SPECS: dict[str, CommandSpec] = {
         examples=("delegate run --input-json task.json",),
         notes=(
             "Accepted JSON keys: engine, mode, model, cwd, prompt, isolation, "
-            "reasoningEffort, outputSchema, progress, forbidCommit.",
+            "reasoningEffort, fast, outputSchema, progress, forbidCommit.",
             "Use this for long prompts or programmatic invocation.",
         ),
         see_also=("cursor", "codex", "droid", "claude", "grok", "agent-help"),
@@ -1376,8 +1393,8 @@ def render_overview_text() -> str:
         f"delegate [--cwd PATH] [--json] {iso} cursor call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]",
         f"delegate [--cwd PATH] [--json] {iso} droid [MODEL_ALIAS] {{safe,work}} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]",
         f"delegate [--cwd PATH] [--json] {iso} droid [MODEL_ALIAS] call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]",
-        f"delegate [--cwd PATH] [--json] {iso} codex {{safe,work}} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--output-schema FILE] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]",
-        f"delegate [--cwd PATH] [--json] {iso} codex call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--output-schema FILE] [--prompt-file PATH] [prompt...]",
+        f"delegate [--cwd PATH] [--json] {iso} codex {{safe,work}} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--fast|--no-fast] [--output-schema FILE] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]",
+        f"delegate [--cwd PATH] [--json] {iso} codex call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--fast|--no-fast] [--output-schema FILE] [--prompt-file PATH] [prompt...]",
         f"delegate [--cwd PATH] [--json] {iso} claude {{safe,work}} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]",
         f"delegate [--cwd PATH] [--json] {iso} claude call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]",
         f"delegate [--cwd PATH] [--json] {iso} grok {{safe,work}} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]",
@@ -1392,8 +1409,8 @@ def render_overview_text() -> str:
         f"delegate [--cwd PATH] [--json] {iso} dry-run cursor call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]",
         f"delegate [--cwd PATH] [--json] {iso} dry-run droid [MODEL_ALIAS] {{safe,work}} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]",
         f"delegate [--cwd PATH] [--json] {iso} dry-run droid [MODEL_ALIAS] call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]",
-        f"delegate [--cwd PATH] [--json] {iso} dry-run codex {{safe,work}} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--output-schema FILE] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]",
-        f"delegate [--cwd PATH] [--json] {iso} dry-run codex call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--output-schema FILE] [--prompt-file PATH] [prompt...]",
+        f"delegate [--cwd PATH] [--json] {iso} dry-run codex {{safe,work}} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--fast|--no-fast] [--output-schema FILE] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]",
+        f"delegate [--cwd PATH] [--json] {iso} dry-run codex call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--fast|--no-fast] [--output-schema FILE] [--prompt-file PATH] [prompt...]",
         f"delegate [--cwd PATH] [--json] {iso} dry-run claude {{safe,work}} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]",
         f"delegate [--cwd PATH] [--json] {iso} dry-run claude call [--read-only] [--model <alias-or-model>] [--reasoning-effort LEVEL] [--prompt-file PATH] [prompt...]",
         f"delegate [--cwd PATH] [--json] {iso} dry-run grok {{safe,work}} [--model <alias-or-model>] [--reasoning-effort LEVEL] [--progress] [--forbid-commit] [--prompt-file PATH] [prompt...]",

{delegate_agent_cli-0.13.0 → delegate_agent_cli-0.13.1}/src/delegate_agent/describe_payload.py

@@ -534,7 +534,13 @@ def _policy_field_support_matrix() -> JsonObject:
 
 
 def _engine_capabilities() -> JsonObject:
-    return {engine: {"outputSchema": engine == "codex"} for engine in KNOWN_ENGINES}
+    return {
+        engine: {
+            "outputSchema": engine == "codex",
+            "fast": engine == "codex",
+        }
+        for engine in KNOWN_ENGINES
+    }
 
 
 def _runtime_policy(config: JsonObject, mode: str, engine: str, bypass_check) -> JsonObject:
@@ -832,11 +838,12 @@ def describe_payload(
                     "signature": (
                         "agent(prompt, engine=None, mode=None, model=None, effort=None, "
                         "schema=None, label=None, phase=None, isolation=None, "
-                        "passthrough=False, timeout=None, retries=None)"
+                        "passthrough=False, timeout=None, retries=None, fast=None)"
                     ),
                     "returns": "parent-facing output string, schema object, or None",
                     "notes": [
                         "engine may be a fallback list; child runs are tagged --group <wfId>.",
+                        "fast is a Codex-only per-run service-tier preference; non-Codex fallbacks ignore it.",
                         "passthrough=True is explicit and mutually exclusive with schema= and mode='call'.",
                         "cursor/kimi argv transport rejects prompts around 100KB; route large stages to codex/claude/droid/opencode.",
                     ],

{delegate_agent_cli-0.13.0 → delegate_agent_cli-0.13.1}/src/delegate_agent/request_build.py

@@ -87,6 +87,7 @@ RUN_INPUT_KEYS = {
     "prompt",
     "isolation",
     "reasoningEffort",
+    "fast",
     "outputSchema",
     "progress",
     "forbidCommit",
@@ -925,6 +926,7 @@ def request_from_parsed(parsed: ParsedCommand, config: JsonObject, stdin: TextIO
                 isolation_context=None,
                 reasoning_effort=launch.reasoning_effort,
                 reasoning_effort_source="cli" if launch.reasoning_effort is not None else None,
+                fast=launch.fast,
                 progress=False,
                 forbid_commit=False,
                 auth_profile_override=global_options.auth_profile,
@@ -1042,6 +1044,7 @@ def request_from_parsed(parsed: ParsedCommand, config: JsonObject, stdin: TextIO
         isolation_context=isolation_context,
         reasoning_effort=launch.reasoning_effort,
         reasoning_effort_source="cli" if launch.reasoning_effort is not None else None,
+        fast=launch.fast,
         progress=effective_progress,
         progress_initial_delay_sec=progress_initial_delay_sec,
         progress_interval_sec=progress_interval_sec,
@@ -1113,6 +1116,12 @@ def request_from_input_json(parsed: ParsedCommand, config: JsonObject) -> Reques
             raise DelegateError(exc.error, "reasoningEffort must be a non-empty string.") from exc
     else:
         reasoning_effort = None
+    if "fast" in raw and engine != "codex":
+        raise DelegateError("unsupported_fast", "fast is only supported by codex.")
+    raw_fast = raw.get("fast")
+    if raw_fast is not None and not isinstance(raw_fast, bool):
+        raise DelegateError("invalid_fast", "fast must be true, false, null, or omitted.")
+    fast = raw_fast if isinstance(raw_fast, bool) else None
     raw_progress_intent: ProgressIntent
     if "progress" in raw:
         raw_progress = raw["progress"]
@@ -1211,6 +1220,7 @@ def request_from_input_json(parsed: ParsedCommand, config: JsonObject) -> Reques
                 isolation_context=None,
                 reasoning_effort=reasoning_effort,
                 reasoning_effort_source="input-json" if reasoning_effort is not None else None,
+                fast=fast,
                 progress=False,
                 forbid_commit=False,
                 auth_profile_override=global_options.auth_profile,
@@ -1348,6 +1358,7 @@ def request_from_input_json(parsed: ParsedCommand, config: JsonObject) -> Reques
         isolation_context=isolation_context,
         reasoning_effort=reasoning_effort,
         reasoning_effort_source="input-json" if reasoning_effort is not None else None,
+        fast=fast,
         progress=effective_progress,
         progress_initial_delay_sec=progress_initial_delay_sec,
         progress_interval_sec=progress_interval_sec,
@@ -1377,6 +1388,7 @@ def build_request(
     isolation_context: IsolationContext | None = None,
     reasoning_effort: str | None = None,
     reasoning_effort_source: str | None = None,
+    fast: bool | None = None,
     progress: bool = False,
     progress_initial_delay_sec: float = delegate_runner.PROGRESS_INITIAL_DELAY_SEC,
     progress_interval_sec: float = delegate_runner.PROGRESS_HEARTBEAT_INTERVAL_SEC,
@@ -1405,6 +1417,8 @@ def build_request(
         reasoning_effort,
         reasoning_effort_source=reasoning_effort_source,
     )
+    if fast is not None and engine != "codex":
+        raise DelegateError("unsupported_fast", "fast is only supported by codex.")
     output_schema = resolve_output_schema(engine, output_schema)
 
     return _build_request_for_workspace(
@@ -1419,6 +1433,7 @@ def build_request(
         isolation_context=isolation_context,
         requested_effort=requested_effort,
         effort_source=effort_source,
+        fast=fast,
         progress=progress,
         progress_initial_delay_sec=progress_initial_delay_sec,
         progress_interval_sec=progress_interval_sec,
@@ -1612,6 +1627,7 @@ def _codex_request_parts(build: EngineBuildInput) -> EngineRequestParts:
         workspace_kind=build.resolved.kind,
         stream_capture=build.stream_capture,
         reasoning_capability=capability,
+        fast=build.fast,
         prompt_transport=PROMPT_TRANSPORT_STDIN,
         output_schema=build.output_schema,
         call_read_only=build.call_read_only,
@@ -1874,6 +1890,7 @@ def _build_request_for_workspace(
     isolation_context: IsolationContext | None,
     requested_effort: str | None,
     effort_source: str | None,
+    fast: bool | None,
     progress: bool,
     progress_initial_delay_sec: float,
     progress_interval_sec: float,
@@ -1912,6 +1929,7 @@ def _build_request_for_workspace(
             requested_effort=requested_effort,
             effort_source=effort_source,
             cache=cache,
+            fast=fast,
             output_schema=output_schema,
             call_read_only=call_read_only,
             model_override=model_override,
@@ -1935,6 +1953,7 @@ def _build_request_for_workspace(
             reasoning_effort_source=parts.reasoning_effort_source,
             reasoning_capability_source=parts.reasoning_capability_source,
             reasoning_transport=parts.reasoning_transport,
+            fast=fast,
             progress=progress,
             progress_initial_delay_sec=progress_initial_delay_sec,
             progress_interval_sec=progress_interval_sec,

{delegate_agent_cli-0.13.0 → delegate_agent_cli-0.13.1}/src/delegate_agent/request_models.py

@@ -47,6 +47,7 @@ class LaunchOptions:
     prompt_file: str | None = None
     output_schema: str | None = None
     reasoning_effort: str | None = None
+    fast: bool | None = None
     progress_intent: str | None = None
     forbid_commit: bool = False
     forbid_commit_implied_isolation: bool = False
@@ -149,6 +150,7 @@ class Request:
     reasoning_effort_source: str | None = None
     reasoning_capability_source: str | None = None
     reasoning_transport: str | None = None
+    fast: bool | None = None
     progress: bool = False
     progress_initial_delay_sec: float = 30.0
     progress_interval_sec: float = 60.0
@@ -201,6 +203,7 @@ class EngineBuildInput:
     requested_effort: str | None
     effort_source: str | None
     cache: JsonObject | None
+    fast: bool | None = None
     output_schema: str | None = None
     call_read_only: bool = False
     model_override: str | None = None

{delegate_agent_cli-0.13.0 → delegate_agent_cli-0.13.1}/src/delegate_agent/run_metadata.py

@@ -30,6 +30,8 @@ REASONING_METADATA_KEYS: MetadataKeyGroup = (
     "reasoningTransport",
 )
 
+SPEED_METADATA_KEYS: MetadataKeyGroup = ("requestedFast",)
+
 SNAPSHOT_STATE_FALLBACK_KEYS: MetadataKeyGroup = (
     "worktreeStatus",
     "safeWorkspaceMethod",
@@ -40,9 +42,19 @@ SNAPSHOT_MANIFEST_FALLBACK_KEYS: MetadataKeyGroup = (
     *PERSISTENT_WORKTREE_METADATA_KEYS,
     "worktreeCleanupCommands",
     *REASONING_METADATA_KEYS,
+    *SPEED_METADATA_KEYS,
 )
 
 
+class SpeedMetadataCarrier(Protocol):
+    fast: bool | None
+
+
+def add_speed_payload_fields(payload: JsonObject, carrier: SpeedMetadataCarrier) -> None:
+    if carrier.fast is not None:
+        payload["requestedFast"] = carrier.fast
+
+
 class RunMetadataCarrier(Protocol):
     isolated_workspace: bool
     isolation_mode: str