delegation-layer 0.1.8 → 0.1.9

package/README.md

@@ -24,6 +24,8 @@ already use instead of replacing them.
   session through a linked successor task.
 - **Runtime compatibility** — the selected provider's executable and advertised
   capabilities are checked when the task is prepared.
+- **Model choice when needed** — native model and effort discovery is available
+  without turning discovery into an admission allowlist.
 - **Native authentication** — provider login stays with the provider CLI; task
   state does not contain copied credentials.
 
@@ -153,6 +155,24 @@ checks static admission without creating a task. Dispatch still performs the
 host-specific runtime probe; catalog discovery alone does not prove
 authentication or supervisor readiness.
 
+When an explicit model or effort choice is needed, query the implemented native
+discovery command:
+
+```sh
+delegate models --provider codex:exec --cwd "$HOME/delegation-workspace" --json
+```
+
+`--cwd` defaults to the current directory. Model discovery uses the
+state-rooted supervisor and a bounded `model-discovery-v1` 60-second inspection,
+creates inspection evidence without admitting a provider task, and may contact
+the provider CLI.
+It is advisory: a discovered model is not an admission guarantee or an
+allowlist. `complete` describes model enumeration. A null effort list means
+unknown metadata; an empty list means the provider explicitly reported no
+choices. Per-model effort metadata is independent of the harness-wide list.
+Discovery exits `0` for `available` or `partial`, `2` for `blocked` or
+`unavailable`, and `1` for `failed`.
+
 If a task reports `status: "timed_out"` and
 `continuation.resumable: true`, continue the exact session:
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "delegation-layer",
-  "version": "0.1.8",
+  "version": "0.1.9",
   "description": "Multi-provider AI agent delegation CLI and Agent Skill for running bounded coding tasks across provider CLIs.",
   "keywords": [
     "ai-agents",

package/skills/agent-integration/SKILL.md

@@ -74,6 +74,33 @@ It does not create a task, start the supervisor, or launch a provider. Do not ke
 retrying preflight when it says
 `blocked` or `unsupported`; report the bounded reason.
 
+If the caller needs an explicit model or effort, use the implemented native
+discovery command for that provider:
+
+```sh
+delegate models --provider PROVIDER_ID --cwd ABSOLUTE_WORKSPACE --json
+```
+
+Omit `--cwd` to use the current directory. Run discovery only when the caller
+needs a non-default choice; provider defaults are valid. The command uses the
+state-rooted supervisor and a bounded `model-discovery-v1` 60-second native
+inspection, creates inspection evidence without admitting a provider task, and may contact the
+provider CLI. It is advisory and never an admission allowlist. Do not reject a
+requested value merely because discovery did not list it, and do not infer
+per-model effort support from the harness-wide list. If a selected model has
+`efforts: null` or `efforts: []`, omit `--effort` unless the caller explicitly
+requested it; do not invent model aliases or combine options by guessing.
+
+The response includes `schema_version`, `command: "models"`, `provider`,
+`observed_at`, `status`, `reason_code`, `complete`, `source`, nullable
+`efforts`, and model rows with exact `id` values plus optional `name`, nullable
+`efforts`, and optional `default_effort`. `complete` describes model
+enumeration, not effort metadata. `null` means effort metadata is unknown;
+`[]` means the provider explicitly reported no choices. Discovery exits `0`
+for `available` or `partial`, `2` for `blocked` or `unavailable`, and `1` for
+`failed`. Preserve a blocked or unavailable discovery result as unresolved;
+defaults remain allowed.
+
 ### 3. Prepare separate paths and a finite brief
 
 Use an existing task brief when one is supplied. Otherwise create a bounded
@@ -119,6 +146,15 @@ the native approval options; do not add provider flags or call its CLI yourself.
 Keep the budget finite. A successful dispatch means the request was durably admitted;
 it does not mean the delegated work finished.
 
+When an explicit selection is supplied, pass it through the public fields:
+`--model MODEL` and `--effort VALUE`. Codex encodes effort as its native TOML
+`model_reasoning_effort` setting; Claude and AGY use their native effort flags;
+Pi maps effort to `--thinking`; and OpenCode maps effort to `--variant`. An
+omitted or `default` effort is omitted from native argv. For AGY read-only,
+`--permission read-only` selects the exact native `--sandbox --mode plan` path
+without a bypass. Authorized AGY workspace-write retains its existing native
+bypass. Do not add these native flags yourself.
+
 Save the exact `task_id` from the JSON response. If dispatch returns an error,
 use its `status`, `capability`, and `error` fields to report whether the request
 was invalid, unsupported, blocked by authentication, or operationally

package/skills/agent-integration/evals/evals.json

@@ -12,6 +12,16 @@
       "prompt": "Run one bounded task through the available agent provider.",
       "expected": ["dispatch --auto", "--json", "save task_id", "status", "collect"]
     },
+    {
+      "name": "model-discovery-when-needed",
+      "prompt": "The caller needs an explicit model and effort for codex:exec.",
+      "expected": ["delegate models --provider codex:exec", "--json", "preserve null versus empty efforts", "advisory", "pass --model and --effort"]
+    },
+    {
+      "name": "model-default-without-discovery",
+      "prompt": "Run a task without an explicit model or effort.",
+      "expected": ["provider defaults are valid", "do not run models unnecessarily", "dispatch --auto"]
+    },
     {
       "name": "timeout",
       "prompt": "The result says status timed_out and continuation.resumable is true.",

package/skills/agent-integration/references/command-reference.md

@@ -8,6 +8,7 @@ All paths passed to `--root`, `--cwd`, and `--brief` must be absolute. Add
 | `delegate --version` | Confirm the installed control CLI | No |
 | `delegate providers --json` | List compiled provider metadata | No |
 | `delegate capabilities --provider ID --json` | Read the catalog contract | No |
+| `delegate models --provider ID [--cwd ABS] --json` | Discover advisory native model and effort facts | Native inspection only; no admitted task |
 | `delegate preflight --provider ID --cwd ABS --json` | Check static provider admission | No |
 | `delegate dispatch --auto ... --json` | Select and admit one bounded turn | Yes, at most once |
 | `delegate status TASK --json` | Reconcile and observe task state | No provider launch |
@@ -29,8 +30,19 @@ Dispatch flags:
 - `--auto`: let the CLI select a ready provider;
 - `--provider ID`: use only when the caller explicitly selected an ID;
 - `--model MODEL` and `--effort VALUE`: optional provider-advertised choices;
+  Codex maps effort to TOML `model_reasoning_effort`, while Claude and AGY
+  pass native effort flags; Pi maps effort to `--thinking`; OpenCode maps it to
+  `--variant`; `default` is omitted;
 - `--native-timeout DURATION`: optional provider-native timeout where advertised.
 
+Model discovery uses the same `--provider ID` profiles and accepts an optional
+absolute `--cwd` (default: current directory). Its JSON has `status` values
+`available`, `partial`, `blocked`, `unavailable`, or `failed`; exits are `0`,
+`0`, `2`, `2`, and `1` respectively. `complete` describes model enumeration.
+Top-level or per-model `efforts: null` means unknown, while `[]` means no
+choices were explicitly reported. Discovery is advisory and never an admission
+allowlist; defaults remain valid when it is not run.
+
 Continuation flags:
 
 - `--task TASK`: predecessor task ID;

package/skills/agent-integration/references/result-handling.md

@@ -23,6 +23,15 @@ the same as a successful provider result.
    with `status` and `collect` before considering any action. Never relaunch an
    uncertain task by guessing.
 
+For `delegate models`, validate the complete JSON envelope before using any
+fact. Treat `available` and `partial` with exit `0` as observations, preserve
+`blocked` and `unavailable` with exit `2` as unresolved prerequisites, and
+preserve `failed` with exit `1` as a discovery failure. `complete` refers to
+model enumeration. Keep `efforts: null` distinct from `efforts: []`, and do not
+apply harness-wide effort choices to every model. Discovery is advisory and
+never an admission allowlist; a provider default remains valid and a listed
+model is not an execution guarantee.
+
 Exit codes are bounded control signals: `0` is a completed command, `1` is an
 operational error, `2` is an invalid or unsupported request, `3` is a pending
 collection watch, and `4` is a validated rejected outcome.