delegation-layer 0.1.9 → 0.1.10

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -163,7 +163,8 @@ delegate models --provider codex:exec --cwd "$HOME/delegation-workspace" --json
163
163
  ```
164
164
 
165
165
  `--cwd` defaults to the current directory. Model discovery uses the
166
- state-rooted supervisor and a bounded `model-discovery-v1` 60-second inspection,
166
+ state-rooted supervisor and a bounded `model-discovery-v1` five-minute
167
+ inspection to allow a provider's first-run model/cache initialization. It
167
168
  creates inspection evidence without admitting a provider task, and may contact
168
169
  the provider CLI.
169
170
  It is advisory: a discovered model is not an admission guarantee or an
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "delegation-layer",
3
- "version": "0.1.9",
3
+ "version": "0.1.10",
4
4
  "description": "Multi-provider AI agent delegation CLI and Agent Skill for running bounded coding tasks across provider CLIs.",
5
5
  "keywords": [
6
6
  "ai-agents",
@@ -83,8 +83,9 @@ delegate models --provider PROVIDER_ID --cwd ABSOLUTE_WORKSPACE --json
83
83
 
84
84
  Omit `--cwd` to use the current directory. Run discovery only when the caller
85
85
  needs a non-default choice; provider defaults are valid. The command uses the
86
- state-rooted supervisor and a bounded `model-discovery-v1` 60-second native
87
- inspection, creates inspection evidence without admitting a provider task, and may contact the
86
+ state-rooted supervisor and a bounded `model-discovery-v1` five-minute native
87
+ inspection to allow first-run provider model/cache initialization. It creates
88
+ inspection evidence without admitting a provider task, and may contact the
88
89
  provider CLI. It is advisory and never an admission allowlist. Do not reject a
89
90
  requested value merely because discovery did not list it, and do not infer
90
91
  per-model effort support from the harness-wide list. If a selected model has