Our history is just-every's with author emails rewritten, so the graphs are
disjoint and git finds no merge base. Supplied one by hand: d1f1f51a41, the
just-every commit matching our Oct-2025 fork point (22 files apart). 9618
upstream commits, 7004 files, +1.81M/-159k, 37 conflicts.
Resolution:
- Upstream code where our side was the Oct-2025 prototype of a feature they
have since reimplemented 3-5x larger (agent_runs, browser_sessions,
history_cell/{agent,browser}, the vt100 harness and its snapshots).
- Upstream's config.rs module split (builder/defaults/sources/validation)
kept; zen5-coder and the provider-follows-model rule re-applied on top.
- Ours where the file IS the identity: README, package.json, postinstall,
release notes pipeline, integration-zed.
- Hybrid where upstream improved a file we had branded: updates.rs (their
release-repo migration, our hanzoai/dev), release.yml (their fail-fast npm
auth check, our package name), chatwidget.rs (their turn handling, our
HANZO_USER_KEY hint), exec human output (their 237 lines, our banner).
Superseded and dropped deliberately: our resume_command_name() coder-alias
hack — upstream's derive_resume_command_name() reads the invocation basename
generically, which yields "dev" for us.
LLM.md now records the real topology and the sync point; AGENTS.md and
CLAUDE.md are symlinks to it again. Single parent on purpose: adopting
jecode/main as a second parent would re-import 13,742 commits carrying the
upstream author emails a prior rewrite deliberately removed.
Version 0.2.188 -> 0.2.189.
Co-authored-by: Hanzo Dev <[email protected]>
[mcp_servers.hanzo] wires CODE to the one hanzo-mcp stdio server so the coding
agent gets code_search/context/ask/index (/v1/code), web_search (/v1/websearch),
web_read (/v1/crawl), and research (/v1/ask mode=research) natively.
Co-authored-by: Hanzo Dev <[email protected]>
- core/agent_tool: recognize "cloud" model and append prompt positionally; honor per‑mode args
- core/codex(agent_run): include "cloud" in command resolution + PATH check
- core/slash_commands: default /plan,/solve models now include "cloud"; test asserts prompt includes it
- core/agent_defaults: add cloud case (no default flags); unit test ensures empty defaults
- docs: note default agent set includes "cloud"; add config example
Build passes via ./build-fast.sh. Full test suite currently fails on unrelated preexisting test drift (protocol/test-support imports, enum shapes).
- Add AgentConfig struct to define agent settings (name, command, args, read-only, enabled, env)
- Update Config and Session to include agent configurations
- Modify agent_tool.rs to use configured agents with their settings
- Update slash commands to dynamically use enabled agents from config
- Create comprehensive config.toml.example with agent examples
- Support both configured and unconfigured agents for backward compatibility
- Allow per-agent read-only override and environment variables
- Pass agent configuration through Session for proper access control
This allows users to:
- Define which AI agents are available
- Set custom commands and arguments for each agent
- Control read-only/write permissions per agent
- Enable/disable specific agents
- Configure environment variables for agents
Co-authored-by: Hanzo Dev <[email protected]>
zeekayandHanzo Dev