You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit ead7a20
Browse filesBrowse the repository at this point in the historyBrowse files
Copy file name to clipboardExpand all lines: CHANGELOG.md
+14Lines changed: 14 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -5,6 +5,20 @@ All notable changes to this project will be documented in this file.
5
5
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
6
6
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
7
7
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)
@@ -29,7 +28,7 @@ into CI pipelines and orchestration DAGs. Precision data tooling for any LLM.
29
28
30
29
```bash
31
30
# npm (recommended)
32
-
npm install -g @altimateai/altimate-code
31
+
npm install -g altimate-code
33
32
34
33
# Homebrew
35
34
brew install AltimateAI/tap/altimate-code
@@ -58,7 +57,7 @@ altimate /discover
58
57
59
58
`/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.
60
59
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.
62
61
63
62
## Why a specialized harness?
64
63
@@ -162,7 +161,7 @@ Each agent has scoped permissions and purpose-built tools for its role.
162
161
163
162
## Supported Warehouses
164
163
165
-
Snowflake · BigQuery · Databricks · PostgreSQL · Redshift · DuckDB · MySQL · SQL Server
164
+
Snowflake · BigQuery · Databricks · PostgreSQL · Redshift · DuckDB · MySQL · SQL Server · Oracle · SQLite
166
165
167
166
First-class support with schema indexing, query execution, and metadata introspection. SSH tunneling available for secure connections.
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.
Multi-statement queries (`SELECT 1; INSERT INTO ...`) are classified as write if any statement is a write.
27
47
28
48
## Custom Agents
29
49
@@ -86,11 +106,11 @@ You are a Snowflake cost optimization expert. For every query:
86
106
```
87
107
88
108
!!! 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.
90
110
91
111
## Agent Permissions
92
112
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:
94
114
95
115
```json
96
116
{
@@ -99,10 +119,11 @@ Each agent can have its own permission overrides that restrict or expand the def
99
119
"permission": {
100
120
"write": "deny",
101
121
"edit": "deny",
122
+
"sql_execute_write": "deny",
102
123
"bash": {
103
-
"dbt show *": "allow",
124
+
"*": "deny",
104
125
"dbt list *": "allow",
105
-
"*": "deny"
126
+
"ls *": "allow"
106
127
}
107
128
}
108
129
}
@@ -117,4 +138,4 @@ Each agent can have its own permission overrides that restrict or expand the def
117
138
118
139
-**TUI**: Press leader + `a` or use `/agent <name>`
Copy file name to clipboardExpand all lines: docs/docs/configure/commands.md
+6-6Lines changed: 6 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -8,7 +8,7 @@ altimate ships with six built-in slash commands:
8
8
|---------|-------------|
9
9
|`/init`| Create or update an AGENTS.md file with build commands and code style guidelines. |
10
10
|`/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). |
12
12
|`/feedback`| Submit product feedback as a GitHub issue. Guides you through title, category, description, and optional session context. |
13
13
|`/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. |
14
14
|`/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
37
37
38
38
Submit product feedback directly from the CLI. The agent walks you through:
39
39
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
44
44
45
45
```
46
46
/feedback # start the guided feedback flow
@@ -137,7 +137,7 @@ Commands are loaded from:
137
137
138
138
Press leader + `/` to see all available commands.
139
139
140
-
## External CLI integration
140
+
## External CLI Integration
141
141
142
142
The `/configure-claude` and `/configure-codex` commands write integration files to external CLI tools:
@@ -149,7 +149,7 @@ Control how context is managed when conversations grow long:
149
149
|-------|---------|-------------|
150
150
|`auto`|`true`| Auto-compact when context is full |
151
151
|`prune`|`true`| Prune old tool outputs |
152
-
|`reserved`|—| Token buffer to reserve |
152
+
|`reserved`|(none)| Token buffer to reserve |
153
153
154
154
!!! info
155
155
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.
Copy file name to clipboardExpand all lines: docs/docs/configure/context-management.md
+11-11Lines changed: 11 additions & 11 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,14 +1,14 @@
1
1
# Context Management
2
2
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.
4
4
5
5
## How It Works
6
6
7
7
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:
8
8
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
12
12
13
13
This happens automatically by default. You do not need to manually manage context.
14
14
@@ -38,7 +38,7 @@ When a tool output is pruned, it is replaced with a brief fingerprint:
38
38
[Tool output cleared — read_file(file: src/main.ts) returned 42 lines, 1.2 KB — "import { App } from './app'"]
39
39
```
40
40
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.
42
42
43
43
**Pruning rules:**
44
44
@@ -51,12 +51,12 @@ This tells the model what tool was called, what arguments were used, how much ou
51
51
52
52
Compaction is aware of data engineering workflows. When summarizing a conversation, the compaction prompt preserves:
53
53
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
60
60
61
61
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.
0 commit comments