command-code 1.62.0 → 1.63.0

package/CHANGELOG.md

@@ -1,5 +1,17 @@
 # command-code
 
+## 1.63.0
+
+### Minor Changes
+
+- feat: add Opus 5.5
+
+## 1.62.1
+
+### Patch Changes
+
+- feat: typesafe/jev support on headless and provider api
+
 ## 1.62.0
 
 ### Minor Changes

package/dist/bundled/command-code-knowledge/reference/headless.md

@@ -217,6 +217,39 @@ fi
 
 ---
 
+## Decision models (typesafe/jev)
+
+`typesafe/jev` is available on the headless mode as a decision model. It runs headless, on your normal login, and it is free through September 24, 2026 (end of day UTC); from September 25 it bills $0.042 per 1M input tokens at cost, and everything else is free.
+
+It answers typed questions about a **state** with **probabilities** instead of text, so a script can branch on the number. The headless prompt is typesafe/jev's request as JSON. Request and response follow TypeSafe's [official shape](https://docs.typesafe.ai/api).
+
+Here is an example of how to run it headlessly with cmd:
+
+```bash
+cmd -p '{
+  "state": {"diff": "- if (user.isAdmin)\n+ if (true)"},
+  "questions": {
+    "risky":    {"type": "noul",   "instructions": "Does this weaken an authorization check?"},
+    "category": {"type": "choice", "instructions": "Which kind of change is this?", "criteria": {"security": "auth or secrets", "bugfix": "wrong behavior", "refactor": "no behavior change"}}
+  }
+}' -m typesafe/jev
+```
+
+```json
+{
+  "model": "typesafe/jev",
+  "answers": {
+    "risky":    {"type": "noul",   "noul": 0.93},
+    "category": {"type": "choice", "choice": "security", "confidence": 0.81, "probabilities": {"security": 0.8, "bugfix": 0.15, "refactor": 0.05}}
+  },
+  "usage": {"input_tokens": 360, "output_tokens": 57}
+}
+```
+
+Interactive use is refused, since Jev is not a chat model. You can find the full request and response reference on the [Provider API page](https://commandcode.ai/docs/provider#decision-models-typesafe-jev).
+
+---
+
 ## Shell script
 
 ```bash
@@ -299,6 +332,7 @@ scriptable automatically. Confirmations print to stderr, keeping `-p` stdout cle
 | **No interactive prompts** | No keyboard shortcuts or interactive UI. Slash commands aren't typed here - use flags instead (see [Configuring settings](#configuring-settings)); session-lifecycle commands like `/clear` and `/reload` have no meaning in one-shot mode |
 | **No resume picker** | A bare `--resume` errors in print mode; resume by explicit id or use `--continue` |
 | **Stdin timeout** | Piped stdin times out after 30 seconds if no data is received |
+| **Decision models are headless only** | `typesafe/jev` answers typed questions, not chat, so it runs with `-p` only (see [Decision model: Jev](#decision-models-typesafe-jev)) |
 
 ---
 

package/dist/bundled/command-code-knowledge/reference/models.md

@@ -62,8 +62,9 @@ The model catalog — every id `/model`, `--model`, `model:effort` shorthand, an
 | `claude-sonnet-4-6` | Claude Sonnet 4.6 | 1M | low, medium, high, xhigh, max | $3/$15 · cache $0.3 (write $3.75) | Pro and above | prev Sonnet, still fast & capable |
 | `claude-fable-5-1` | Claude Fable 5.1 | 1M | low, medium, high, xhigh, max | $10/$50 · cache $0.25 (write $12.5) | Max | most capable for demanding reasoning & long-horizon agents |
 | `claude-fable-5` | Claude Fable 5 | 1M | low, medium, high, xhigh, max | $10/$50 · cache $1 (write $12.5) | Max | prev Fable, still strong for deep reasoning & agents |
-| `claude-opus-5` | Claude Opus 5 | 1M | low, medium, high, xhigh, max | $5/$25 · cache $0.5 (write $6.25) | Max | most intelligent Opus for agents and coding |
-| `claude-opus-4-8` | Claude Opus 4.8 | 1M | low, medium, high, xhigh, max | $5/$25 · cache $0.5 (write $6.25) | Max | prev flagship, still strong for agents and coding |
+| `claude-opus-5-5` | Claude Opus 5.5 | 1M | low, medium, high, xhigh, max | $4/$20 · cache $0.2 (write $5) | Max | most intelligent Opus for agents and coding |
+| `claude-opus-5` | Claude Opus 5 | 1M | low, medium, high, xhigh, max | $5/$25 · cache $0.5 (write $6.25) | Max | prev flagship, still strong for agents and coding |
+| `claude-opus-4-8` | Claude Opus 4.8 | 1M | low, medium, high, xhigh, max | $5/$25 · cache $0.5 (write $6.25) | Max | older Opus, still strong for agents and coding |
 | `claude-opus-4-7` | Claude Opus 4.7 | 1M | low, medium, high, xhigh, max | $5/$25 · cache $0.5 (write $6.25) | Max | older Opus, still strong for agents and coding |
 | `claude-haiku-4-5-20251001` | Claude Haiku 4.5 | 200K | — | $1/$5 · cache $0.1 (write $1.25) | Pro and above | fastest & most compact, great for quick tasks |
 ## OpenAI

package/dist/bundled/command-code-knowledge/reference/product-help.md

@@ -253,6 +253,7 @@ Valid model ids (the /model catalog — use these EXACT ids):
 - claude-sonnet-4-6
 - claude-fable-5-1
 - claude-fable-5
+- claude-opus-5-5
 - claude-opus-5
 - claude-opus-4-8
 - claude-opus-4-7