Skip to content

Commit ead7a20

Browse files
suryaiyer95claude
andcommitted
chore: resolve merge conflict — rename configure/telemetry.md → reference/telemetry.md
Main renamed the file; keep `native_call` (replaces deprecated `bridge_call`) and correct contributor file path (`packages/opencode/src/altimate/telemetry/index.ts`). Co-Authored-By: Claude Sonnet 4.6 <[email protected]>
2 parents c95f7b3 + 79ae428 commit ead7a20

71 files changed

Lines changed: 4209 additions & 960 deletions

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎CHANGELOG.md‎

Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -5,6 +5,20 @@ All notable changes to this project will be documented in this file.
55
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
66
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
77

8+
## [0.5.0] - 2026-03-18
9+
10+
### Added
11+
12+
- Smooth streaming mode for TUI response rendering (#281)
13+
- Ship builtin skills to customers via `postinstall` (#279)
14+
- `/configure-claude` and `/configure-codex` built-in commands (#235)
15+
16+
### Fixed
17+
18+
- Brew formula stuck at v0.3.1 — version normalization in publish pipeline (#286)
19+
- Harden auth field handling for all warehouse drivers (#271)
20+
- Suppress console logging that corrupts TUI display (#269)
21+
822
## [0.4.9] - 2026-03-18
923

1024
### Added

‎README.md‎

Lines changed: 10 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -7,19 +7,18 @@
77

88
**The open-source data engineering harness.**
99

10-
The intelligence layer for data engineering AI — 99+ deterministic tools for SQL analysis,
10+
The intelligence layer for data engineering AI — 100+ deterministic tools for SQL analysis,
1111
column-level lineage, dbt, FinOps, and warehouse connectivity across every major cloud platform.
1212

1313
Run standalone in your terminal, embed underneath Claude Code or Codex, or integrate
1414
into CI pipelines and orchestration DAGs. Precision data tooling for any LLM.
1515

16-
[![npm](https://img.shields.io/npm/v/@altimateai/altimate-code)](https://www.npmjs.com/package/@altimateai/altimate-code)
17-
[![npm](https://img.shields.io/npm/v/@altimateai/altimate-core)](https://www.npmjs.com/package/@altimateai/altimate-core)
18-
[![npm downloads](https://img.shields.io/npm/dm/@altimateai/altimate-code)](https://www.npmjs.com/package/@altimateai/altimate-code)
16+
[![npm](https://img.shields.io/npm/v/altimate-code)](https://www.npmjs.com/package/altimate-code)
17+
[![npm downloads](https://img.shields.io/npm/dm/altimate-code)](https://www.npmjs.com/package/altimate-code)
1918
[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](./LICENSE)
2019
[![CI](https://github.com/AltimateAI/altimate-code/actions/workflows/ci.yml/badge.svg)](https://github.com/AltimateAI/altimate-code/actions/workflows/ci.yml)
2120
[![Slack](https://img.shields.io/badge/Slack-Join%20Community-4A154B?logo=slack)](https://altimate.ai/slack)
22-
[![Docs](https://img.shields.io/badge/docs-altimateai.github.io-blue)](https://altimateai.github.io/altimate-code)
21+
[![Docs](https://img.shields.io/badge/docs-docs.altimate.sh-blue)](https://docs.altimate.sh)
2322

2423
</div>
2524

@@ -29,7 +28,7 @@ into CI pipelines and orchestration DAGs. Precision data tooling for any LLM.
2928

3029
```bash
3130
# npm (recommended)
32-
npm install -g @altimateai/altimate-code
31+
npm install -g altimate-code
3332

3433
# Homebrew
3534
brew install AltimateAI/tap/altimate-code
@@ -58,7 +57,7 @@ altimate /discover
5857

5958
`/discover` auto-detects dbt projects, warehouse connections (from `~/.dbt/profiles.yml`, Docker, environment variables), and installed tools (dbt, sqlfluff, airflow, dagster, and more). Skip this and start building — you can always run it later.
6059

61-
> **Zero Python setup required.** On first run, the CLI automatically downloads [`uv`](https://github.com/astral-sh/uv), creates an isolated Python environment, and installs the data engine with all warehouse drivers. No `pip install`, no virtualenv management.
60+
> **Zero additional setup.** One command install.
6261
6362
## Why a specialized harness?
6463

@@ -162,7 +161,7 @@ Each agent has scoped permissions and purpose-built tools for its role.
162161
163162
## Supported Warehouses
164163
165-
Snowflake · BigQuery · Databricks · PostgreSQL · Redshift · DuckDB · MySQL · SQL Server
164+
Snowflake · BigQuery · Databricks · PostgreSQL · Redshift · DuckDB · MySQL · SQL Server · Oracle · SQLite
166165
167166
First-class support with schema indexing, query execution, and metadata introspection. SSH tunneling available for secure connections.
168167
@@ -220,10 +219,11 @@ Contributions welcome — docs, SQL rules, warehouse connectors, and TUI improve
220219
221220
**[Read CONTRIBUTING.md →](./CONTRIBUTING.md)**
222221
223-
## What's New
222+
## Changelog
224223
224+
- **v0.4.2** (March 2026) — yolo mode, Python engine elimination (all-native TypeScript), tool consolidation, path sandboxing hardening, altimate-dbt CLI, unscoped npm package
225225
- **v0.4.1** (March 2026) — env-based skill selection, session caching, tracing improvements
226-
- **v0.4.0** (Feb 2026) — data visualization skill, 99+ tools, training system
226+
- **v0.4.0** (Feb 2026) — data visualization skill, 100+ tools, training system
227227
- **v0.3.x** — [See full changelog →](CHANGELOG.md)
228228
229229
## License

‎docs/docs/assets/css/extra.css‎

Lines changed: 34 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -92,7 +92,7 @@
9292
/* --- Feature cards --- */
9393
.grid.cards > ul > li {
9494
border-radius: 8px;
95-
padding: 0.8rem !important;
95+
padding: 1rem !important;
9696
transition: box-shadow 0.2s ease, transform 0.2s ease;
9797
}
9898

@@ -112,15 +112,18 @@
112112

113113
/* --- Pill grid (LLM providers, warehouses) --- */
114114
.pill-grid {
115-
max-width: 600px;
116-
margin: 0 auto;
115+
width: 100%;
116+
max-width: 640px;
117+
margin: 1rem auto;
118+
padding: 0 1rem;
119+
box-sizing: border-box;
117120
}
118121

119122
.pill-grid ul {
120123
display: flex;
121124
flex-wrap: wrap;
122125
justify-content: center;
123-
gap: 0.45rem;
126+
gap: 0.6rem 0.75rem;
124127
list-style: none;
125128
padding: 0;
126129
margin: 0;
@@ -129,14 +132,14 @@
129132
.pill-grid ul li {
130133
display: inline-flex;
131134
align-items: center;
132-
gap: 0.3rem;
133-
padding: 0.4rem 0.85rem;
135+
gap: 0.4rem;
136+
padding: 0.5rem 1.15rem;
134137
border-radius: 100px;
135138
font-size: 0.8rem;
136139
border: 1px solid var(--md-default-fg-color--lightest);
137140
color: var(--md-default-fg-color--light);
138141
white-space: nowrap;
139-
margin: 0;
142+
flex-shrink: 0;
140143
}
141144

142145
.pill-grid ul li .twemoji {
@@ -147,6 +150,30 @@
147150
border-color: rgba(255, 255, 255, 0.12);
148151
}
149152

153+
/* Responsive pill sizing */
154+
@media (max-width: 768px) {
155+
.pill-grid {
156+
max-width: 100%;
157+
padding: 0 0.75rem;
158+
}
159+
160+
.pill-grid ul {
161+
gap: 0.5rem 0.6rem;
162+
}
163+
164+
.pill-grid ul li {
165+
padding: 0.45rem 0.9rem;
166+
font-size: 0.75rem;
167+
}
168+
}
169+
170+
@media (max-width: 480px) {
171+
.pill-grid ul li {
172+
padding: 0.4rem 0.8rem;
173+
font-size: 0.72rem;
174+
}
175+
}
176+
150177
/* --- Doc links footer --- */
151178
.doc-links {
152179
text-align: center;

‎docs/docs/configure/agents.md‎

Lines changed: 41 additions & 20 deletions
Original file line numberDiff line numberDiff line change
@@ -4,26 +4,46 @@ Agents define different AI personas with specific models, prompts, permissions,
44

55
## Built-in Agents
66

7-
### General Purpose
7+
| Agent | Description | Access Level |
8+
|-------|------------|-------------|
9+
| `builder` | Create and modify dbt models, SQL pipelines, and data transformations | Full read/write. SQL mutations prompt for approval. |
10+
| `analyst` | Explore data, run SELECT queries, inspect schemas, generate insights | Read-only (enforced). SQL writes denied. Safe bash commands auto-allowed. |
11+
| `plan` | Plan before acting, restricted to planning files only | Minimal: no edits, no bash, no SQL |
812

9-
| Agent | Description |
10-
|-------|------------|
11-
| `general` | Default general-purpose coding agent |
12-
| `plan` | Planning agent — analyzes before acting |
13-
| `build` | Build-focused agent — prioritizes code generation |
14-
| `explore` | Read-only exploration agent |
13+
### Builder
1514

16-
### Data Engineering
15+
Full access mode. Can read/write files, run any bash command (with approval), execute SQL, and modify dbt models. SQL write operations (`INSERT`, `UPDATE`, `DELETE`, `CREATE`, etc.) prompt for user approval. Destructive SQL (`DROP DATABASE`, `DROP SCHEMA`, `TRUNCATE`) is hard-blocked.
1716

18-
| Agent | Description | Permissions |
19-
|-------|------------|------------|
20-
| `builder` | Create dbt models, SQL pipelines, transformations | Full read/write |
21-
| `analyst` | Explore data, run SELECT queries, generate insights | Read-only (enforced) |
22-
| `validator` | Data quality checks, schema validation, test coverage | Read + validate |
23-
| `migrator` | Cross-warehouse SQL translation and migration | Read/write for migration |
17+
### Analyst
18+
19+
Truly read-only mode for safe data exploration:
20+
21+
- **File access**: Read, grep, glob without prompts
22+
- **SQL**: SELECT queries execute freely. Write queries are denied (not prompted, blocked entirely)
23+
- **Bash**: Safe commands auto-allowed (`ls`, `grep`, `cat`, `head`, `tail`, `find`, `wc`). dbt read commands allowed (`dbt list`, `dbt ls`, `dbt debug`, `dbt deps`). Everything else denied.
24+
- **Web**: Fetch and search allowed without prompts
25+
- **Schema/warehouse/finops**: All inspection tools available
2426

2527
!!! tip
26-
Use the `analyst` agent when exploring data to ensure no accidental writes. Switch to `builder` when you are ready to create or modify models.
28+
Use `analyst` when exploring data to ensure no accidental writes. Switch to `builder` when you're ready to create or modify models.
29+
30+
### Plan
31+
32+
Planning mode with minimal permissions. Can only read files and edit plan files. No SQL, no bash, no file modifications.
33+
34+
## SQL Write Access Control
35+
36+
All SQL queries are classified before execution:
37+
38+
| Query Type | Builder | Analyst |
39+
|-----------|---------|---------|
40+
| `SELECT`, `SHOW`, `DESCRIBE`, `EXPLAIN` | Allowed | Allowed |
41+
| `INSERT`, `UPDATE`, `DELETE`, `CREATE`, `ALTER` | Prompts for approval | Denied |
42+
| `DROP DATABASE`, `DROP SCHEMA`, `TRUNCATE` | Blocked (cannot override) | Blocked |
43+
44+
The classifier detects write operations including: `INSERT`, `UPDATE`, `DELETE`, `MERGE`, `CREATE`, `DROP`, `ALTER`, `TRUNCATE`, `GRANT`, `REVOKE`, `COPY INTO`, `CALL`, `EXEC`, `EXECUTE IMMEDIATE`, `BEGIN`, `DECLARE`, `REPLACE`, `UPSERT`, `RENAME`.
45+
46+
Multi-statement queries (`SELECT 1; INSERT INTO ...`) are classified as write if any statement is a write.
2747

2848
## Custom Agents
2949

@@ -86,11 +106,11 @@ You are a Snowflake cost optimization expert. For every query:
86106
```
87107

88108
!!! info
89-
Markdown agent files use YAML frontmatter for configuration and the body as the system prompt. This is a convenient way to define agents without editing your main config file.
109+
Markdown agent files use YAML frontmatter for configuration and the body as the system prompt.
90110

91111
## Agent Permissions
92112

93-
Each agent can have its own permission overrides that restrict or expand the default permissions:
113+
Each agent can have its own permission overrides:
94114

95115
```json
96116
{
@@ -99,10 +119,11 @@ Each agent can have its own permission overrides that restrict or expand the def
99119
"permission": {
100120
"write": "deny",
101121
"edit": "deny",
122+
"sql_execute_write": "deny",
102123
"bash": {
103-
"dbt show *": "allow",
124+
"*": "deny",
104125
"dbt list *": "allow",
105-
"*": "deny"
126+
"ls *": "allow"
106127
}
107128
}
108129
}
@@ -117,4 +138,4 @@ Each agent can have its own permission overrides that restrict or expand the def
117138

118139
- **TUI**: Press leader + `a` or use `/agent <name>`
119140
- **CLI**: `altimate --agent analyst`
120-
- **In conversation**: Type `/agent validator`
141+
- **In conversation**: Type `/agent analyst`

‎docs/docs/configure/commands.md‎

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@ altimate ships with six built-in slash commands:
88
|---------|-------------|
99
| `/init` | Create or update an AGENTS.md file with build commands and code style guidelines. |
1010
| `/discover` | Scan your data stack and set up warehouse connections. Detects dbt projects, warehouse connections from profiles/Docker/env vars, installed tools, and config files. Walks you through adding and testing new connections, then indexes schemas. |
11-
| `/review` | Review changes — accepts `commit`, `branch`, or `pr` as an argument (defaults to uncommitted changes). |
11+
| `/review` | Review changes. Accepts `commit`, `branch`, or `pr` as an argument (defaults to uncommitted changes). |
1212
| `/feedback` | Submit product feedback as a GitHub issue. Guides you through title, category, description, and optional session context. |
1313
| `/configure-claude` | Configure altimate as a `/altimate` slash command in [Claude Code](https://claude.com/claude-code). Writes `~/.claude/commands/altimate.md` so you can invoke altimate from within Claude Code sessions. |
1414
| `/configure-codex` | Configure altimate as a skill in [Codex CLI](https://developers.openai.com/codex). Creates `~/.codex/skills/altimate/SKILL.md` so Codex can delegate data engineering tasks to altimate. |
@@ -37,10 +37,10 @@ The recommended way to set up a new data engineering project. Run `/discover` in
3737

3838
Submit product feedback directly from the CLI. The agent walks you through:
3939

40-
1. **Title** — a short summary of your feedback
41-
2. **Category** — bug, feature, improvement, or ux
42-
3. **Description** — detailed explanation
43-
4. **Session context** (opt-in) — includes working directory name and session ID for debugging
40+
1. **Title**, a short summary of your feedback
41+
2. **Category**: bug, feature, improvement, or ux
42+
3. **Description** with a detailed explanation
43+
4. **Session context** (opt-in), which includes working directory name and session ID for debugging
4444

4545
```
4646
/feedback # start the guided feedback flow
@@ -137,7 +137,7 @@ Commands are loaded from:
137137

138138
Press leader + `/` to see all available commands.
139139

140-
## External CLI integration
140+
## External CLI Integration
141141

142142
The `/configure-claude` and `/configure-codex` commands write integration files to external CLI tools:
143143

‎docs/docs/configure/config.md‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -57,7 +57,7 @@ Configuration is loaded from multiple sources, with later sources overriding ear
5757
| `skills` | `object` | Skill paths and URLs |
5858
| `plugin` | `string[]` | Plugin specifiers |
5959
| `instructions` | `string[]` | Glob patterns for instruction files |
60-
| `telemetry` | `object` | Telemetry settings (see [Telemetry](telemetry.md)) |
60+
| `telemetry` | `object` | Telemetry settings (see [Telemetry](../reference/telemetry.md)) |
6161
| `compaction` | `object` | Context compaction settings (see [Context Management](context-management.md)) |
6262
| `experimental` | `object` | Experimental feature flags |
6363

@@ -149,7 +149,7 @@ Control how context is managed when conversations grow long:
149149
|-------|---------|-------------|
150150
| `auto` | `true` | Auto-compact when context is full |
151151
| `prune` | `true` | Prune old tool outputs |
152-
| `reserved` | — | Token buffer to reserve |
152+
| `reserved` | (none) | Token buffer to reserve |
153153

154154
!!! info
155155
Compaction automatically summarizes older messages to free up context window space, allowing longer conversations without losing important context. See [Context Management](context-management.md) for full details.

‎docs/docs/configure/context-management.md‎

Lines changed: 11 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -1,14 +1,14 @@
11
# Context Management
22

3-
altimate automatically manages conversation context so you can work through long sessions without hitting model limits. When a conversation grows large, the CLI summarizes older messages, prunes stale tool outputs, and recovers from provider overflow errors — all without losing the important details of your work.
3+
altimate automatically manages conversation context so you can work through long sessions without hitting model limits. When a conversation grows large, the CLI summarizes older messages, prunes stale tool outputs, and recovers from provider overflow errors, all without losing the important details of your work.
44

55
## How It Works
66

77
Every LLM has a finite context window. As you work, each message, tool call, and tool result adds tokens to the conversation. When the conversation approaches the model's limit, altimate takes action:
88

9-
1. **Prune** — Old tool outputs (file reads, command results, query results) are replaced with compact summaries
10-
2. **Compact** — The entire conversation history is summarized into a continuation prompt
11-
3. **Continue** — The agent picks up where it left off using the summary
9+
1. **Prune.** Old tool outputs (file reads, command results, query results) are replaced with compact summaries
10+
2. **Compact.** The entire conversation history is summarized into a continuation prompt
11+
3. **Continue.** The agent picks up where it left off using the summary
1212

1313
This happens automatically by default. You do not need to manually manage context.
1414

@@ -38,7 +38,7 @@ When a tool output is pruned, it is replaced with a brief fingerprint:
3838
[Tool output cleared — read_file(file: src/main.ts) returned 42 lines, 1.2 KB — "import { App } from './app'"]
3939
```
4040

41-
This tells the model what tool was called, what arguments were used, how much output it produced, and the first line of the result — enough to maintain continuity without consuming tokens.
41+
This tells the model what tool was called, what arguments were used, how much output it produced, and the first line of the result. That is enough to maintain continuity without consuming tokens.
4242

4343
**Pruning rules:**
4444

@@ -51,12 +51,12 @@ This tells the model what tool was called, what arguments were used, how much ou
5151

5252
Compaction is aware of data engineering workflows. When summarizing a conversation, the compaction prompt preserves:
5353

54-
- **Warehouse connections** — which databases or warehouses are connected
55-
- **Schema context** — discovered tables, columns, and relationships
56-
- **dbt project state** — models, sources, tests, and project structure
57-
- **Lineage findings** — upstream and downstream dependencies
58-
- **Query patterns** — SQL dialects, anti-patterns, and optimization opportunities
59-
- **FinOps context** — cost findings and warehouse sizing recommendations
54+
- **Warehouse connections**, including which databases or warehouses are connected
55+
- **Schema context**, including discovered tables, columns, and relationships
56+
- **dbt project state**, including models, sources, tests, and project structure
57+
- **Lineage findings**, including upstream and downstream dependencies
58+
- **Query patterns**, including SQL dialects, anti-patterns, and optimization opportunities
59+
- **FinOps context**, including cost findings and warehouse sizing recommendations
6060

6161
This means you can run a long data exploration session and compaction will not lose track of what schemas you discovered, what dbt models you were working with, or what cost optimizations you identified.
6262

0 commit comments

Comments
 (0)