Feat/global distiller

CHANGELOG.md

@@ -11,24 +11,33 @@ caveat that pre-1.0 minor bumps may include breaking changes
 ADDED
   * **Credentialed SessionEnd distiller (opt-in).** A second, deterministic
     memory-harvest path alongside the v0.9.0 in-agent harvester. `kimetsu plugin
-    install claude-code` now runs an interactive wizard (on a TTY; skip with
-    `--no-setup`, force with `--setup-harvest`) that configures a cheap distiller
-    model — Anthropic (recommended `claude-haiku-4-5`) or any Anthropic-compatible
-    endpoint incl. **LiteLLM** via `ANTHROPIC_BASE_URL`. The key + base URL are
-    written to a gitignored `.env`; the selection lands in `[learning.distiller]`
-    in `project.toml`. A new `SessionEnd` hook then runs `kimetsu brain
-    session-end-hook`, which (when enabled + credentialed) distills the
+    install claude-code` and `kimetsu plugin install codex` now run an
+    interactive wizard (on a TTY; skip with `--no-setup`, force with
+    `--setup-harvest`) that configures a cheap distiller
+    model: Anthropic (recommended `claude-haiku-4-5`), OpenAI (recommended
+    `gpt-5.4-mini`), or compatible endpoints via `ANTHROPIC_BASE_URL` /
+    `OPENAI_BASE_URL`. The key + base URL are written to a gitignored `.env`;
+    the selection lands in `[learning.distiller]`
+    in `project.toml`. A new `SessionEnd` hook for Claude Code runs
+    `kimetsu brain session-end-hook`; Codex uses its supported `Stop` hook with
+    `--distill-on-stop`. When enabled + credentialed, the distiller reads the
     transcript with that model and records lessons through the confidence-gated
     `propose_or_merge_memory`. When the distiller is enabled, the Stop hook's
     end-of-session cue is suppressed (the distiller owns end-of-session; the
     mid-session PostToolUse resolved-failure cue stays). `AnthropicProvider`
-    gained an optional base URL for the LiteLLM case.
+    gained an optional base URL for the LiteLLM case, and the distiller gained
+    an OpenAI Responses API provider. With `--scope global` the
+    wizard configures the distiller once in `~/.kimetsu/` (config + `.env`); that
+    global distiller then runs in every project and records into the user brain
+    (`~/.kimetsu/brain.db`, available everywhere), with a per-project distiller
+    taking precedence when one is configured.
   * **Auto-harvested memories (in-agent).** The hooks now drive memory
     *generation*, not just retrieval. When a command that failed earlier in the
     session succeeds (PostToolUse), or a non-trivial session ends with nothing
     recorded (Stop), Kimetsu emits a `[kimetsu-harvest]` cue telling the agent to
     dispatch a new background **`kimetsu-memory-harvester`** subagent (installed
-    at `.claude/agents/`, pinned to a cheap model). The subagent distills 0–3
+    at `.claude/agents/` for Claude Code and `.codex/agents/` for Codex, pinned
+    to a cheap model). The subagent distills 0–3
     generalizable lessons and records them through the confidence-gated
     `kimetsu_brain_record` path — no separate API key or kimetsu-side model
     credentials, billed in-agent at the cheap model's rate, non-blocking. Cues

README.md

@@ -182,7 +182,7 @@ cover Claude Code and Codex:
 
 ```bash
 kimetsu plugin install claude --workspace .    # writes .mcp.json + .claude/settings.json
-kimetsu plugin install codex  --workspace .    # writes .codex/config.toml + .codex/hooks.json + skill
+kimetsu plugin install codex  --workspace .    # writes .codex/config.toml + .codex/hooks.json + skill + agent
 
 # Install globally for every project (writes to ~/.claude, ~/.claude.json, ~/.codex):
 kimetsu plugin install claude --scope global
@@ -205,11 +205,16 @@ in-agent distiller) that records the lesson for next time — no extra API key.
 Turn it off with `[learning] auto_harvest = false` in `.kimetsu/project.toml`.
 
 For a deterministic harvest that doesn't depend on the agent, `kimetsu plugin
-install claude-code` offers to set up a **SessionEnd distiller**: a cheap
-configured model (Anthropic `claude-haiku-4-5`, or a LiteLLM endpoint via
-`ANTHROPIC_BASE_URL`) that distills each session itself at the end and records
-the lessons. The wizard stores the key in a gitignored `.env`; skip it with
-`--no-setup`.
+install claude-code` and `kimetsu plugin install codex` offer to set up a
+**SessionEnd distiller**: a cheap configured model (Anthropic
+`claude-haiku-4-5`, OpenAI `gpt-5.4-mini`, or a compatible endpoint via
+`ANTHROPIC_BASE_URL` / `OPENAI_BASE_URL`) that distills each session itself at
+the end and records the lessons. Claude Code runs it from `SessionEnd`; Codex
+runs it from the supported `Stop` hook with `--distill-on-stop`. The wizard
+stores the key in a gitignored `.env`; skip it with `--no-setup`. Run it with
+`--scope global` to configure the distiller once in
+`~/.kimetsu/` — it then distills every project's sessions into your user brain
+(available everywhere), unless that project has its own distiller.
 
 ```bash
 kimetsu brain search "build failures"

crates/kimetsu-agent/Cargo.toml

@@ -9,8 +9,8 @@ homepage.workspace = true
 documentation.workspace = true
 readme.workspace = true
 rust-version.workspace = true
-description = "Transport-neutral agent runtime for kimetsu: tools, prompts, verify-loop, providers (claude_code, anthropic)."
-keywords = ["kimetsu", "agent", "llm", "anthropic", "claude"]
+description = "Transport-neutral agent runtime for kimetsu: tools, prompts, verify-loop, providers (claude_code, anthropic, openai)."
+keywords = ["kimetsu", "agent", "llm", "anthropic", "openai"]
 categories = ["development-tools"]
 
 [features]

crates/kimetsu-agent/src/lib.rs

@@ -4,6 +4,7 @@ pub mod bench;
 pub mod claude_code;
 pub mod harness;
 pub mod model;
+pub mod openai;
 pub mod pipeline;
 pub mod swe_bench;
 pub mod tools;