@trybullet/cli 1.4.16 → 1.4.17

package/README.md

@@ -6,18 +6,20 @@ everything live. Connect a cloud provider or explicitly download the optional on
 
 ## How it works
 
-- **Agent loop** (custom, ~200 lines — no framework): plan → tool calls
-  (read / edit / write / delete / run) → observations → verify → done. Hardened
-  with failure-retry directives, stuck detection, duplicate suppression, a 45s
-  wall-clock cap, and a definition-of-done verification gate.
+- **Agent loop** (no framework): plan → tool calls
+  (read / edit / write / delete / run) → observations → verify → done. Tool
+  evidence, bounded correction, and duplicate suppression keep completion
+  claims grounded without imposing a fixed duration on interactive tasks.
 - **Router:** a nano-model semantic classifier (hard 4s cap — routing is never
   the wait) rates each prompt on five difficulty levels. The optional local route
-  runs Ministral 3 8B via Metal after an explicit Settings download. With a key
-  → each level buys a deeper model *and* more thinking effort: quick asks run
-  on fast models (Haiku / Codex-low), harder work escalates (Sonnet 5 / Codex
-  at rising effort), and *extreme* tasks go to Fable 5 / Sol at full effort
-  (say "use fable", "use sol", or "think hard" to force the level). The debug
-  badge shows the exact model, tier, and effort used.
+  runs Ministral 3 8B via Metal after an explicit Settings download. With a cloud
+  connection, each level matches the model and thinking effort to the task:
+  quick asks use Sonnet 5 / Terra, complex work uses Opus 5 / Terra at rising
+  effort, *hard* tasks use Fable 5 / Sol, and *extreme* tasks use
+  Fable 5.1 / GPT-6 Astra. If a frontier model is unavailable, routing falls
+  back to the earlier tiers. Select either new model directly in the model
+  picker, or say "use Fable 5.1" or "use Astra". The debug badge shows the
+  exact model, tier, and effort used.
 - **Plan gate:** asking to plan ("help me plan X", "let's figure out the
   approach first") is its own classifier answer — those turns draft a plan and
   stop instead of working. Difficulty alone never triggers it: a big task you
@@ -153,6 +155,18 @@ OpenRouter API keys; Ollama and LM Studio local servers; and a custom
 OpenAI-compatible endpoint. Each connection keeps its own encrypted key,
 endpoint, and selected model, so adding one never replaces another.
 
+Claude Fable 5.1 (`claude-fable-5-1`) and GPT-6 Astra (`gpt-6-astra`)
+are available as explicit model choices with the matching provider connection.
+The cost estimate includes Fable 5.1's reduced cache-read rate and Astra's
+long-context rates above 272K input tokens.
+
+Opening the model picker refreshes additional subscription model options:
+Claude checks its model catalog, while ChatGPT connections imported from Codex
+read Codex's local model catalog. Bundled and saved choices stay usable if
+discovery fails, including after a restart; the provider verifies access when
+you send a message. This refresh updates Bullet's choices; model access still
+depends on the connected subscription, and its billing plan is unchanged.
+
 Provider presets are used when you press Enter at the base-URL prompt:
 
 ```bash
@@ -172,6 +186,8 @@ thinking level per run or per session:
 ```bash
 bullet --provider openrouter --model openai/gpt-5.2 --thinking high "review this"
 bullet --provider ollama --model qwen3-coder "fix the tests"
+bullet --provider openai --model gpt-6-astra --thinking high "review this migration"
+bullet --provider anthropic --model claude-fable-5-1 --thinking high "trace this regression"
 # in a session — unconfigured providers connect before becoming active
 /providers gemini
 /model gemini-2.5-pro

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@trybullet/cli",
-  "version": "1.4.16",
+  "version": "1.4.17",
   "description": "The fastest coding agent — terminal edition. Same router, tools and agent loop as the Bullet desktop app, in your shell.",
   "license": "UNLICENSED",
   "homepage": "https://codewithbullet.com",
@@ -24,11 +24,11 @@
     "bin/bullet.js"
   ],
   "optionalDependencies": {
-    "@trybullet/cli-darwin-arm64": "1.4.16",
-    "@trybullet/cli-darwin-x64": "1.4.16",
-    "@trybullet/cli-linux-x64": "1.4.16",
-    "@trybullet/cli-linux-arm64": "1.4.16",
-    "@trybullet/cli-win32-x64": "1.4.16"
+    "@trybullet/cli-darwin-arm64": "1.4.17",
+    "@trybullet/cli-darwin-x64": "1.4.17",
+    "@trybullet/cli-linux-x64": "1.4.17",
+    "@trybullet/cli-linux-arm64": "1.4.17",
+    "@trybullet/cli-win32-x64": "1.4.17"
   },
   "engines": {
     "node": ">=18"