Add pipeline engine and remove legacy compatibility paths

README.md

@@ -80,8 +80,7 @@ Create `~/.config/aman/config.json` (or let `aman` create it automatically on fi
       { "from": "docker", "to": "Docker" }
     ],
     "terms": ["Systemd", "Kubernetes"]
-  },
-  "domain_inference": { "enabled": true }
+  }
 }
 ```
 
@@ -92,6 +91,9 @@ Hotkey notes:
 
 - Use one key plus optional modifiers (for example `Cmd+m`, `Super+m`, `Ctrl+space`).
 - `Super` and `Cmd` are equivalent aliases for the same modifier.
+- Invalid hotkey syntax in config prevents startup/reload.
+- When `~/.config/aman/pipelines.py` exists, hotkeys come from `HOTKEY_PIPELINES`.
+- `daemon.hotkey` is used as the fallback/default hotkey only when no pipelines file is present.
 
 AI cleanup is always enabled and uses the locked local Llama-3.2-3B GGUF model
 downloaded to `~/.cache/aman/models/` during daemon initialization.
@@ -107,11 +109,6 @@ Vocabulary correction:
 - Wildcards are intentionally rejected (`*`, `?`, `[`, `]`, `{`, `}`) to avoid ambiguous rules.
 - Rules are deduplicated case-insensitively; conflicting replacements are rejected.
 
-Domain inference:
-
-- Domain context is advisory only and is used to improve cleanup prompts.
-- When confidence is low, it falls back to `general` context.
-
 STT hinting:
 
 - Vocabulary is passed to Whisper as `hotwords`/`initial_prompt` only when those
@@ -134,6 +131,12 @@ systemctl --user enable --now aman
 - Press it again to stop and run STT.
 - Press `Esc` while recording to cancel without processing.
 - Transcript contents are logged only when `-v/--verbose` is used.
+- Config changes are hot-reloaded automatically (polled every 1 second).
+- `~/.config/aman/pipelines.py` changes are hot-reloaded automatically (polled every 1 second).
+- Send `SIGHUP` to force an immediate reload of config and pipelines:
+  `systemctl --user kill -s HUP aman` (or send `HUP` to the process directly).
+- Reloads are applied when the daemon is idle; invalid updates are rejected and the last valid config stays active.
+- Reload success/failure is logged, and desktop notifications are shown when available.
 
 Wayland note:
 
@@ -149,6 +152,77 @@ AI processing:
 
 - Local llama.cpp model only (no remote provider configuration).
 
+## Pipelines API
+
+`aman` is split into:
+
+- shell daemon: hotkeys, recording/cancel, and desktop injection
+- pipeline engine: `lib.transcribe(...)` and `lib.llm(...)`
+- pipeline implementation: Python callables mapped per hotkey
+
+Pipeline file path:
+
+- `~/.config/aman/pipelines.py`
+- You can start from [`pipelines.example.py`](./pipelines.example.py).
+- If `pipelines.py` is missing, `aman` uses a built-in reference pipeline bound to `daemon.hotkey`.
+- If `pipelines.py` exists but is invalid, startup fails fast.
+- Pipelines are hot-reloaded automatically when the module file changes.
+- Send `SIGHUP` to force an immediate reload of both config and pipelines.
+
+Expected module exports:
+
+```python
+HOTKEY_PIPELINES = {
+  "Super+m": my_pipeline,
+  "Super+Shift+m": caps_pipeline,
+}
+
+PIPELINE_OPTIONS = {
+  "Super+Shift+m": {"failure_policy": "strict"},  # optional
+}
+```
+
+Pipeline callable signature:
+
+```python
+def my_pipeline(audio, lib) -> str:
+  text = lib.transcribe(audio)
+  context = lib.llm(
+    system_prompt="context system prompt",
+    user_prompt=f"Transcript: {text}",
+  )
+  out = lib.llm(
+    system_prompt="amanuensis prompt",
+    user_prompt=f"context={context}\ntext={text}",
+  )
+  return out
+```
+
+`lib` API:
+
+- `lib.transcribe(audio, hints=None, whisper_opts=None) -> str`
+- `lib.llm(system_prompt=..., user_prompt=..., llm_opts=None) -> str`
+
+Failure policy options:
+
+- `best_effort` (default): pipeline errors return empty output
+- `strict`: pipeline errors abort the current run
+
+Validation:
+
+- `HOTKEY_PIPELINES` must be a non-empty dictionary.
+- Every hotkey key must be a non-empty string.
+- Every pipeline value must be callable.
+- `PIPELINE_OPTIONS` must be a dictionary when provided.
+
+Reference behavior:
+
+- The built-in fallback pipeline (used when `pipelines.py` is missing) uses `lib.llm(...)` twice:
+  - first to infer context
+  - second to run the amanuensis rewrite
+- The second pass requests JSON output and expects `{"cleaned_text": "..."}`.
+- Deterministic dictionary replacements are then applied as part of that reference implementation.
+
 Control:
 
 ```bash