autopreso 0.1.4 → 0.1.6

package/README.md

@@ -11,6 +11,10 @@
 
 <h3 align="center">Let the whiteboard whiteboard itself.</h3>
 
+<p align="center">
+  <img src="https://raw.githubusercontent.com/kunchenguid/autopreso/main/assets/autopreso.png" alt="autopreso whiteboard hero screenshot" width="960" />
+</p>
+
 > [!WARNING]
 > autopreso is in **alpha** and under active development. Expect rough edges, breaking changes, and the occasional weird drawing. Bug reports welcome.
 
@@ -101,6 +105,8 @@ npm start
 
 Settings persist at `~/.config/autopreso/settings.json` and are managed from the in-app status panel.
 Agent instructions are saved automatically from staging, can be up to 100,000 characters, and take effect on the next Start Preso.
+The live Session cost card estimates agent token costs and OpenAI Realtime audio costs for the current presentation, resetting on Start Preso or session reset.
+OpenAI prices use the built-in May 2026 rate table; local providers show `$0.0000`, Codex shows token volume because it routes through your subscription, and unknown models show `n/a`.
 
 ### Defaults on first run
 
@@ -110,8 +116,8 @@ When no settings file exists, autopreso picks providers based on what it finds i
 | ------------------------------------------ | ------------------------------ | -------------------------- |
 | Nothing                                    | OpenAI `gpt-5.5` (needs a key) | Moonshine `medium` (macOS) |
 | `OPENAI_API_KEY` in env                    | OpenAI `gpt-5.5`               | OpenAI Realtime            |
-| Codex CLI signed in (`~/.codex/auth.json`) | Codex `gpt-5.5`                | Moonshine `medium`         |
-| Codex CLI signed in + `OPENAI_API_KEY`     | Codex `gpt-5.5`                | OpenAI Realtime            |
+| Codex CLI signed in (`~/.codex/auth.json`) | Codex `gpt-5.5-fast`           | Moonshine `medium`         |
+| Codex CLI signed in + `OPENAI_API_KEY`     | Codex `gpt-5.5-fast`           | OpenAI Realtime            |
 | `OLLAMA_MODEL` set                         | Ollama (your model)            | Moonshine `medium`         |
 
 Auto-detection precedence: **Codex CLI auth wins over `OLLAMA_MODEL` wins over `OPENAI_API_KEY`** for the agent. Transcription flips to OpenAI Realtime any time an OpenAI key is present, otherwise Moonshine. After first run, this auto-detection no longer applies - change providers from the in-app status panel.
@@ -125,6 +131,7 @@ Provider variables only seed `settings.json` on first run. Once the file exists,
 | `PORT`                 | Port to listen on. Default: `3210`.                   |
 | `OPENAI_API_KEY`       | Seeds the OpenAI key for both agent and Realtime STT. |
 | `OPENAI_MODEL`         | Seeds the OpenAI agent model.                         |
+| `OPENAI_BASE_URL`      | Seeds the OpenAI agent API base URL.                  |
 | `CODEX_MODEL`          | Seeds the Codex model.                                |
 | `OLLAMA_MODEL`         | Seeds the Ollama model.                               |
 | `AUTOPRESO_CACHE_LOG`  | Cache usage log path. Default: `~/.config/autopreso/logs/cache.log`. |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "autopreso",
-  "version": "0.1.4",
+  "version": "0.1.6",
   "description": "Realtime speech to presentation. Let the whiteboard whiteboard itself.",
   "license": "MIT",
   "author": "Kun Chen <kun@kunchenguid.com>",
@@ -32,6 +32,7 @@
     "autopreso": "src/cli.js"
   },
   "files": [
+    "assets/",
     "LICENSE",
     "public/",
     "src/"