🎯 Major directory restructure and publication preparation:
**Directory Rename:**
- Renamed code-rs/ → hanzo-dev/ for better branding alignment
- Updated all build scripts, GitHub workflows, and documentation
- Fixed all path references across the codebase
**Publication Setup:**
- Updated workspace version to 0.6.0 (production ready)
- Configured main CLI crate as 'hanzo-dev' (available on crates.io)
- Set publish = true for core crates (hanzo-core, hanzo-tui)
- Added proper package metadata (description, license, repository, etc.)
- Maintained internal crate names to minimize dependency changes
**Updated Components:**
- package.json build scripts now reference hanzo-dev/
- GitHub Actions workflows updated for new directory structure
- build-fast.sh and related scripts updated
- Documentation and README references updated
- All Cargo.toml manifests updated with publication metadata
**Publishing Strategy:**
- Main binary: hanzo-dev (new, available for publication)
- Core library: hanzo-core (existing name, ready to publish)
- TUI library: hanzo-tui (existing name, ready to publish)
- Avoids conflict with existing Hanzo AI infrastructure crates
This prepares the codebase for official publication to crates.io while
maintaining full compatibility with the existing build system and
providing clear branding as 'Hanzo Dev' CLI tool.
3.0 KiB
Execution policy
Hanzo Dev can enforce your own rules-based execution policy before it runs shell commands. Policies live in Starlark .codexpolicy files under ~/.hanzo/policy (Hanzo Dev still reads legacy ~/.code/policy or ~/.codex/policy for backward compatibility).
How to create and edit rules
TUI interactions
Hanzo Dev CLI will present the option to whitelist commands when a command causes a prompt.
Whitelisted commands will no longer require your permission to run in current and subsequent sessions.
Under the hood, when you approve and whitelist a command, Hanzo Dev will edit ~/.hanzo/rules/default.rules (legacy: ~/.code/rules/default.rules or ~/.codex/rules/default.rules).
Editing .rules files
- Create a policy directory:
mkdir -p ~/.hanzo/policy. - Add one or more
.codexpolicyfiles in that folder. Hanzo Dev automatically loads every.codexpolicyfile in there on startup. - Write
prefix_ruleentries to describe the commands you want to allow, prompt, or block:
prefix_rule(
pattern = ["git", ["push", "fetch"]],
decision = "prompt", # allow | prompt | forbidden
match = [["git", "push", "origin", "main"]], # examples that must match
not_match = [["git", "status"]], # examples that must not match
)
patternis a list of shell tokens, evaluated from left to right; wrap tokens in a nested list to express alternatives (for example, match bothpushandfetch).decisionsets the severity; Hanzo Dev picks the strictest decision when multiple rules match (forbidden > prompt > allow).matchandnot_matchact as optional unit tests. Hanzo Dev validates them when it loads your policy, so you get feedback if an example has unexpected behavior.
In this example rule, if Hanzo Dev wants to run commands with the prefix git push or git fetch, it will first ask for user approval.
Preview decisions
Use the dev execpolicy check subcommand to preview decisions before you save a rule (see the dev-execpolicy README for syntax details):
dev execpolicy check --policy ~/.hanzo/policy/default.codexpolicy git push origin main
Pass multiple --policy flags to test how several files combine, and use --pretty for formatted JSON output. See the hanzo-dev/execpolicy README for a more detailed walkthrough of the available syntax.
Example output when a rule matches:
{
"matchedRules": [
{
"prefixRuleMatch": {
"matchedPrefix": ["git", "push"],
"decision": "prompt"
}
}
],
"decision": "prompt"
}
When no rules match, matchedRules is an empty array and decision is omitted.
{
"matchedRules": []
}
Status
execpolicy commands are still in preview. The API may have breaking changes in the future.