-
Notifications
You must be signed in to change notification settings - Fork 136
release: v0.9.4 review-fix bundle (A1-A12 + phase-label flake removal) #1053
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Changes from all commits
79ede24
6ca01ba
739c105
bee9109
d6c389a
89f3946
a77a05a
bc28066
a8d3294
0c91602
2cbc1e8
f9f13bd
6c20407
f75a710
f9581d9
1221911
f5ec426
7cd019e
653f72b
790df9b
4caaee0
9b5d3a3
e82faf5
fa72084
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -14,22 +14,43 @@ npm install -g altimate-code | |
|
|
||
| --- | ||
|
|
||
| ## Step 2: Connect Your LLM | ||
| ## Step 2: Sign in | ||
|
|
||
| ```bash | ||
| altimate # Launch the TUI | ||
| /connect # Interactive setup | ||
| ``` | ||
|
|
||
| Or set an environment variable and skip the prompt: | ||
| On a fresh install, a welcome panel appears with a curated 6-provider picker: | ||
|
|
||
| - **Altimate LLM Gateway** *(recommended)* — 10M tokens free, no API keys. Routes to the best model per task across Sonnet, Opus, GPT-5, and more. Sign-in opens a browser tab; complete Google or email signup and you're back in the TUI. If your terminal can't open a browser (SSH / tmux / WSL), the CLI prints the URL — paste it into a browser on your desktop. | ||
| - **Anthropic** / **OpenAI** / **Google** — paste an API key or OAuth in. | ||
| - **Big Pickle** — free tier, chats work but many data tasks fail; useful for kicking tires. | ||
| - **Search all providers…** — full picker if you need Bedrock, Databricks AI Gateway, Cloudflare AI Gateway, Snowflake Cortex, DigitalOcean Inference, etc. | ||
|
|
||
| Or set an environment variable and skip the picker: | ||
|
|
||
| ```bash | ||
| export ANTHROPIC_API_KEY=sk-ant-... | ||
| altimate | ||
| ``` | ||
|
|
||
| !!! tip "Don't want to manage API keys?" | ||
| The [Altimate LLM Gateway](https://help.altimate.ai/datamates/user-guide/components/llm-gateway/) gives you 10M tokens free — no API keys needed. It dynamically routes to the best model for each task across Sonnet 4.6, Opus 4.6, GPT-5.4, and more. | ||
| The [Altimate LLM Gateway](https://help.altimate.ai/datamates/user-guide/components/llm-gateway/) is the top row of the picker — 10M free tokens, and altimate-code auto-selects the right model per task. First-run sign-in uses a loopback OAuth on `127.0.0.1:7317-7325` (falls back if the preferred port is taken). | ||
|
|
||
| --- | ||
|
|
||
| ## Step 2.5: First-run scan (optional) | ||
|
|
||
| Immediately after model setup, a **"Scan your environment?"** Yes/No dialog appears. Say **Yes** and altimate-code reads local config files (`.dbt/profiles.yml`, `dbt_project.yml`, `.git/config`) — no credentials are read or sent, and no schema, model contents, or queries leave your computer. An anonymous environment summary (e.g. "dbt project detected, no warehouse configured") may be included in the standard telemetry stream if telemetry is enabled; disable via `OPENCODE_DISABLE_TELEMETRY=1` or the [telemetry docs](../usage/telemetry.md) if you want a strictly-offline scan. The scan then routes you into one of four branches: | ||
|
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. P2: The Prompt for AI agents |
||
|
|
||
| - **Found a warehouse** → offers to add + verify each connection, then index its schema. | ||
| - **Found dbt project, no warehouse** → asks which warehouse it runs against and walks you through `warehouse_add`. | ||
| - **In a git repo, no dbt** → suggests you `cd` into the right project and re-run. | ||
| - **Nothing yet** → offers to try Altimate on a sample dbt project (bundled jaffle-shop DuckDB, no warehouse needed) or another exploratory job. | ||
|
|
||
| Every branch ends on a numbered "**What would you like to do?**" menu in the chat — pick a job by typing the number, or free-text if none fit. **The menu is chat text, not an arrow-key picker; type your answer and press Enter.** | ||
|
|
||
| Say **No** to the scan gate and you land on the same activation menu without the scan detail — good for users who already know what they want to run. | ||
|
|
||
| --- | ||
|
|
||
|
|
||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🔒 Security & Privacy | 🟡 Minor | ⚡ Quick win
🧩 Analysis chain
🏁 Script executed:
Repository: AltimateAI/altimate-code
Length of output: 50381
🏁 Script executed:
Repository: AltimateAI/altimate-code
Length of output: 9810
🏁 Script executed:
Repository: AltimateAI/altimate-code
Length of output: 17431
🏁 Script executed:
Repository: AltimateAI/altimate-code
Length of output: 46580
Document collection as skipped before transmitting.
Line 44 claims credentials are not read or sent.
profiles.ymlparsing retains mapped credential fields such as token/private-key fields, so say credentials are not collected or transmitted and update the code to exclude them before serialization if the scan sends telemetry summaries.🧰 Tools
🪛 LanguageTool
[grammar] ~44-~44: Ensure spelling is correct
Context: ... Yes/No dialog appears. Say Yes and altimate-code reads local config files (`.dbt/pro...
(QB_NEW_EN_ORTHOGRAPHY_ERROR_IDS_1)
🤖 Prompt for AI Agents