diff --git a/conductor/tracks/startup_speedup_20260606/metadata.json b/conductor/tracks/startup_speedup_20260606/metadata.json index a02d02ed..6c5956e9 100644 --- a/conductor/tracks/startup_speedup_20260606/metadata.json +++ b/conductor/tracks/startup_speedup_20260606/metadata.json @@ -11,12 +11,14 @@ "src/startup_profiler.py", "scripts/audit_main_thread_imports.py", "scripts/audit_gui2_imports.py", - "tests/test_ai_client_lazy_imports.py", - "tests/test_hook_server_lazy_fastapi.py", + "tests/test_ai_client_no_top_level_sdk_imports.py", + "tests/test_hook_server_no_top_level_fastapi.py", "tests/test_app_controller_io_pool.py", - "tests/test_command_palette_lazy.py", - "tests/test_theme_nerv_lazy.py", - "tests/test_markdown_helper_lazy.py", + "tests/test_warmup_mechanism.py", + "tests/test_command_palette_no_top_level_import.py", + "tests/test_theme_nerv_no_top_level_import.py", + "tests/test_markdown_helper_no_top_level_import.py", + "tests/test_api_hooks_warmup.py", "tests/test_main_thread_purity.py", "tests/test_startup_profiler.py", "tests/test_io_pool_endpoint.py" @@ -42,19 +44,26 @@ "estimated_phases": 9, "spec": "spec.md", "plan": "plan.md", - "architectural_invariant": "The main thread (the one that enters immapp.run()) must NEVER import a module heavier than imgui_bundle and the lean gui_2 skeleton. Enforced by scripts/audit_main_thread_imports.py (static CI gate) and tests/test_main_thread_purity.py (runtime audit-hook test).", - "threading_constraint": "NO new threading.Thread(...) calls in src/. All background work must go through AppController._io_pool (ThreadPoolExecutor, max_workers=4, thread_name_prefix='controller-io').", + "architectural_invariant": "The main thread (the one that enters immapp.run()) must NEVER import a module heavier than imgui_bundle and the lean gui_2 skeleton. Heavy modules are removed from main-thread-reachable files entirely and accessed via _require_warmed(name) at use sites, which assumes the module is in sys.modules because AppController's warmup pre-loaded it on the _io_pool. Enforced by scripts/audit_main_thread_imports.py (static CI gate) and tests/test_main_thread_purity.py (runtime audit-hook test).", + "threading_constraint": "NO new threading.Thread(...) calls in src/. All background work must go through AppController._io_pool (ThreadPoolExecutor, max_workers=4, thread_name_prefix='controller-io'). The _io_pool is also the home of the heavy-module warmup jobs submitted in AppController.__init__.", + "warmup_mechanism": "AppController.__init__ submits one job per heavy module to _io_pool. Each job imports its module and updates a thread-safe warmup_status dict. When the last job completes, _warmup_done_event is set and registered on_warmup_complete callbacks fire. The GUI polls warmup_status() each frame for a status-bar indicator. /api/warmup_status and /api/warmup_wait expose the state to tests and external clients. The user is notified via a toast on completion: 'All providers ready (M modules).'", "verification_criteria": [ "import src.ai_client < 50ms cold start (from ~1800ms)", "import src.gui_2 < 500ms cold start (from ~3000ms)", "import src.app_controller < 300ms cold start (from ~700ms)", "uv run sloppy.py --enable-test-hooks reaches immapp.run() in < 1.5s", "live_gui.wait_for_server(timeout=15) passes for all tests", - "scripts/audit_main_thread_imports.py exits 0 (no main-thread heavy imports)", + "scripts/audit_main_thread_imports.py exits 0 (no heavy imports on main)", "tests/test_main_thread_purity.py passes (runtime audit hook confirms invariant)", + "controller.wait_for_warmup(timeout=10) returns True", + "All warmup modules in sys.modules after warmup completes", + "User-triggered provider switch is INSTANT (proves warmup worked)", + "GUI shows 'Warming up... (N/M)' then 'All imports ready' with green dot, then a toast", + "GET /api/warmup_status returns {pending: [], completed: [...], failed: []}", + "NO `import X` statements inside function bodies for heavy modules (grep-verified)", "No regressions in 273+ existing tests", "ZERO new threading.Thread(...) calls in src/ (after Phase 6 migration)", - "Startup profile + io_pool status visible via /api/startup_profile and /api/io_pool_status" + "Startup profile + io_pool status visible via /api/startup_profile, /api/io_pool_status" ], "links": { "backlog_entry": "conductor/tracks.md:152", diff --git a/conductor/tracks/startup_speedup_20260606/plan.md b/conductor/tracks/startup_speedup_20260606/plan.md index d1d53733..d137f991 100644 --- a/conductor/tracks/startup_speedup_20260606/plan.md +++ b/conductor/tracks/startup_speedup_20260606/plan.md @@ -19,11 +19,15 @@ --- -## Phase 2: Job Pool Foundation (the "no new threads" rule) +## Phase 2: Job Pool + Warmup Foundation (the "no new threads" + "no lazy-loading" rules) -The user constraint: no new `threading.Thread(...)` per task, per import, per -ad-hoc job. The codebase gets ONE shared `ThreadPoolExecutor` on `AppController`, -named `_io_pool`, used by any subsystem that needs background work. +Two user constraints, addressed together: +1. **No new `threading.Thread(...)`** per task, per import, per ad-hoc job. +2. **No lazy-loading** in function bodies. Heavy imports are warmed on bg + threads at startup, not loaded on first use. + +The codebase gets ONE shared `ThreadPoolExecutor` on `AppController` named +`_io_pool`, used for warmup AND any future background work. - [ ] **T2.1 (Red)** `tests/test_app_controller_io_pool.py`: - `test_app_controller_has_io_pool`: instantiate `AppController`, assert `hasattr(controller, '_io_pool')` and it's a `ThreadPoolExecutor` @@ -32,81 +36,94 @@ named `_io_pool`, used by any subsystem that needs background work. - `test_io_pool_shuts_down_on_close`: call `controller.shutdown()`, assert the pool is shut down - Confirm FAIL (no `_io_pool` yet) - [ ] **T2.2 (Green)** In `src/app_controller.py`: - - Add `from concurrent.futures import ThreadPoolExecutor` at top + - Add `from concurrent.futures import ThreadPoolExecutor` and `import importlib` at top - In `__init__`, after the asyncio loop starts and BEFORE the existing HookServer block: `self._io_pool = ThreadPoolExecutor(max_workers=4, thread_name_prefix="controller-io")` + - Add warmup state: `self._warmup_lock`, `self._warmup_done_event`, `self._warmup_status` (dict with `pending`/`completed`/`failed` lists), `self._warmup_callbacks` + - Call `self._submit_warmup_jobs()` at the end of `__init__` - In `shutdown()` (already exists in `App.shutdown` for the GUI; ensure the AppController has a matching shutdown that calls `self._io_pool.shutdown(wait=False)`) - - Add `controller.submit_io(fn, *args)` helper: `return self._io_pool.submit(fn, *args)` (with a docstring saying "use this instead of `threading.Thread` for new background work") -- [ ] **T2.3** Run T2.1 tests; confirm PASS -- [ ] **T2.4** Commit: `feat(app_controller): add shared _io_pool ThreadPoolExecutor` + git note +- [ ] **T2.3 (Red)** `tests/test_warmup_mechanism.py`: + - `test_warmup_jobs_submitted_on_init`: after `AppController.__init__`, assert `len(controller.warmup_status()['pending']) > 0` + - `test_warmup_jobs_complete_within_timeout`: call `controller.wait_for_warmup(timeout=10.0)`, assert True + - `test_warmup_status_reflects_completion`: after `wait_for_warmup`, assert `controller.is_warmup_done() == True` and `len(warmup_status()['pending']) == 0` + - `test_warmup_callback_fires_on_completion`: register a callback via `controller.on_warmup_complete(cb)`, assert it was called once warmup done + - `test_warmup_does_not_block_init`: time `__init__` with a 4-worker pool, assert it returns in < 200ms even though warmup takes longer + - Confirm FAIL (no warmup yet) +- [ ] **T2.4 (Green)** Implement `_submit_warmup_jobs()`, `_compute_warmup_list()`, `_warmup_one()`, `warmup_status()`, `is_warmup_done()`, `wait_for_warmup()`, `on_warmup_complete()` per spec §3.2. Warmup list includes: `google.genai`, `anthropic`, `openai`, `requests`, `src.command_palette`, `src.theme_nerv`, `src.theme_nerv_fx`, `src.markdown_table`, `numpy`. Conditionally adds `fastapi`, `fastapi.security.api_key` if `enable_test_hooks` or `web_host` is set. +- [ ] **T2.5** Run T2.1 and T2.3 tests; confirm PASS +- [ ] **T2.6** Commit: `feat(app_controller): add _io_pool + proactive warmup mechanism` + git note -**Phase 2 checkpoint:** `AppController` owns a 4-thread named pool. `controller.submit_io(fn)` is the sanctioned way to do background work. Existing ad-hoc threads still exist (will be migrated in Phase 5). +**Phase 2 checkpoint:** `AppController` owns a 4-thread named pool. Warmup jobs are submitted in `__init__` and complete in the background. `controller.wait_for_warmup()`, `controller.warmup_status()`, and `controller.on_warmup_complete(cb)` are the public API. Main thread does NOT block waiting for warmup. --- -## Phase 3: Lazy-load AI Provider SDKs (TDD) +## Phase 3: Remove top-level heavy imports from `src/ai_client.py` (TDD) -- [ ] **T3.1 (Red)** Write `tests/test_ai_client_lazy_imports.py`: - - `test_ai_client_does_not_import_genai_at_module_level`: spawn fresh subprocess, `import src.ai_client`, assert `'google.genai' not in sys.modules` (or `google.genai` in modules but `_gemini_client` is `None`) +The current `src/ai_client.py` has `from google import genai` etc. at the top, +which puts the main thread in the import chain. Phase 3 removes these and +swaps to `_require_warmed(name)`. + +- [ ] **T3.1 (Red)** Write `tests/test_ai_client_no_top_level_sdk_imports.py`: + - `test_ai_client_does_not_import_genai_at_module_level`: spawn fresh subprocess, `import src.ai_client`, assert `'google.genai' not in sys.modules` (warmup hasn't run in this subprocess) - `test_ai_client_does_not_import_anthropic_at_module_level` - `test_ai_client_does_not_import_openai_at_module_level` - `test_ai_client_does_not_import_requests_at_module_level` - Confirm tests FAIL (proves the imports are currently eager) - [ ] **T3.2 (Green)** In `src/ai_client.py`: - - Remove `from google import genai` from top - - Remove `import anthropic` from top - - Remove `import openai` from top - - Remove `import requests` from top - - Add lazy imports inside `_send_gemini`, `_send_anthropic`, `_send_deepseek`, `_send_minimax` - - Provider client globals stay as `None` until first `_ensure__client()` call -- [ ] **T3.3** Run existing `tests/test_ai_client.py`; fix any breakage. Most likely issue: tests that rely on top-level import side effects need a fixture that triggers lazy init. + - Add `import sys, importlib, threading` at top + - Remove `from google import genai`, `import anthropic`, `import openai`, `import requests` from top + - Add `_require_warmed(name)` helper: returns `sys.modules[name]` or raises `RuntimeError` + - Each `_send_*` function calls `_require_warmed("google.genai")` etc. instead of using the module directly + - Provider client globals stay as `None` until first `_send_*` initializes them via `_ensure__client()` (extracted from current top-level logic, uses the warmed module) +- [ ] **T3.3** Run existing `tests/test_ai_client.py`; fix any breakage. Tests that relied on top-level import side effects need a fixture that warms the modules (or a fallback for test mode). - [ ] **T3.4** Re-run T3.1 tests, confirm PASS -- [ ] **T3.5** Commit: `git commit -m "refactor(ai_client): lazy-load provider SDKs to defer ~1800ms off main thread"` + git note +- [ ] **T3.5** Commit: `refactor(ai_client): remove top-level SDK imports; use _require_warmed` + git note - [ ] **T3.6** Update `conductor/tracks.md` T3 row with SHA -**Phase 3 checkpoint:** `import src.ai_client` < 50ms cold. All 273 existing tests still pass. +**Phase 3 checkpoint:** `import src.ai_client` < 50ms cold. When run inside an `AppController` whose warmup has completed, `_send_*` functions find the SDKs in `sys.modules` and execute instantly. --- -## Phase 4: Lazy-load FastAPI in HookServer (TDD) +## Phase 4: Remove top-level FastAPI imports from `src/api_hooks.py` (TDD) -- [ ] **T4.1 (Red)** Write `tests/test_hook_server_lazy_fastapi.py`: +Same pattern as Phase 3, for the FastAPI imports. + +- [ ] **T4.1 (Red)** Write `tests/test_hook_server_no_top_level_fastapi.py`: - `test_hook_server_does_not_import_fastapi_at_module_level`: subprocess test - `test_hook_server_does_not_import_fastapi_security_at_module_level` - Confirm FAIL - [ ] **T4.2 (Green)** In `src/api_hooks.py`: - - Remove `from fastapi import ...` from top - - Remove `from fastapi.security.api_key import APIKeyHeader` from top - - Add lazy imports inside the methods that need them (FastAPI app construction, route registration) -- [ ] **T4.3** Run existing `tests/test_api_hooks.py`; fix breakage + - Remove `from fastapi import ...`, `from fastapi.security.api_key import ...` from top + - Add `_require_warmed(name)` calls inside the methods that need them (FastAPI app construction, route registration) +- [ ] **T4.3** Run existing `tests/test_api_hooks.py`; fix breakage (similar fallback strategy as Phase 3) - [ ] **T4.4** Confirm T4.1 tests PASS -- [ ] **T4.5** Commit: `git commit -m "refactor(api_hooks): lazy-load fastapi to defer ~470ms off main thread"` + git note +- [ ] **T4.5** Commit: `refactor(api_hooks): remove top-level fastapi imports; use _require_warmed` + git note -**Phase 4 checkpoint:** `from src.api_hooks import HookServer` does not import fastapi. +**Phase 4 checkpoint:** `from src.api_hooks import HookServer` does not import fastapi. The HookServer is fully constructed only after AppController's warmup has loaded fastapi (or after `_require_warmed("fastapi")` triggers the import in test mode). --- -## Phase 5: Lazy-load Feature-gated GUI Modules (TDD per module) +## Phase 5: Remove top-level imports for feature-gated GUI modules (TDD per module) ### 5A: Command Palette -- [ ] **T5A.1 (Red)** `tests/test_command_palette_lazy.py`: `from src.commands import COMMANDS` (or whatever the eager import is) does not import `src.command_palette`. Confirm FAIL. -- [ ] **T5A.2 (Green)** In `src/commands.py`: move `from src.command_palette import ...` inside the command functions that open the palette (`_open_command_palette`, `_toggle_command_palette`). +- [ ] **T5A.1 (Red)** `tests/test_command_palette_no_top_level_import.py`: `from src.commands import COMMANDS` does not import `src.command_palette`. Confirm FAIL. +- [ ] **T5A.2 (Green)** In `src/commands.py`: remove `from src.command_palette import ...` from top. The command functions (`_open_command_palette`, `_toggle_command_palette`) call `_require_warmed("src.command_palette")` to access the module. - [ ] **T5A.3** Run `tests/test_command_palette.py`; fix. -- [ ] **T5A.4** Commit: `refactor(commands): lazy-load command_palette to defer 244ms` +- [ ] **T5A.4** Commit: `refactor(commands): remove top-level command_palette import; use _require_warmed` ### 5B: NERV Theme -- [ ] **T5B.1 (Red)** `tests/test_theme_nerv_lazy.py`: `from src.theme_2 import *` (or whatever) does not import `src.theme_nerv` or `src.theme_nerv_fx`. Confirm FAIL. -- [ ] **T5B.2 (Green)** In `src/theme_2.py`: move `from src.theme_nerv import ...` and `from src.theme_nerv_fx import ...` inside `apply_nerv_theme()` (or whichever function activates the theme). +- [ ] **T5B.1 (Red)** `tests/test_theme_nerv_no_top_level_import.py`: `from src.theme_2 import *` does not import `src.theme_nerv` or `src.theme_nerv_fx`. Confirm FAIL. +- [ ] **T5B.2 (Green)** In `src/theme_2.py`: remove `from src.theme_nerv import ...` and `from src.theme_nerv_fx import ...` from top. `apply_nerv_theme()` (or whichever function activates the theme) calls `_require_warmed("src.theme_nerv")` and `_require_warmed("src.theme_nerv_fx")`. - [ ] **T5B.3** Run `tests/test_theme_2.py` and `tests/test_theme_nerv.py`; fix. -- [ ] **T5B.4** Commit: `refactor(theme): lazy-load nerv theme to defer 485ms off non-nerv path` +- [ ] **T5B.4** Commit: `refactor(theme): remove top-level nerv theme imports; use _require_warmed` ### 5C: Markdown Table -- [ ] **T5C.1 (Red)** `tests/test_markdown_helper_lazy.py`: `from src.markdown_helper import MarkdownRenderer` does not import `src.markdown_table`. Confirm FAIL. -- [ ] **T5C.2 (Green)** In `src/markdown_helper.py`: move `from src.markdown_table import ...` inside the table-detection branch of `render()`. +- [ ] **T5C.1 (Red)** `tests/test_markdown_helper_no_top_level_import.py`: `from src.markdown_helper import MarkdownRenderer` does not import `src.markdown_table`. Confirm FAIL. +- [ ] **T5C.2 (Green)** In `src/markdown_helper.py`: remove `from src.markdown_table import ...` from top. The table-detection branch of `render()` calls `_require_warmed("src.markdown_table")`. - [ ] **T5C.3** Run `tests/test_markdown_helper.py`; fix. -- [ ] **T5C.4** Commit: `refactor(markdown): lazy-load markdown_table to defer 250ms off non-table markdown` +- [ ] **T5C.4** Commit: `refactor(markdown): remove top-level markdown_table import; use _require_warmed` ### 5D: GUI module feature-gated imports @@ -115,16 +132,14 @@ named `_io_pool`, used by any subsystem that needs background work. - [ ] **T5D.3** Run full GUI test suite; fix. - [ ] **T5D.4** Commit per feature group -**Phase 5 checkpoint:** Feature-gated imports are lazy. Default-theme / non-palette / non-table path is lean. +**Phase 5 checkpoint:** All heavy imports removed from main-thread-reachable source files. Default-theme / non-palette / non-table path is lean. Warmup pre-loads all of them in the background. --- ## Phase 6: Migrate Ad-hoc Threads to `_io_pool` The codebase has several ad-hoc `threading.Thread(...)` calls. Per the user -constraint, these should migrate to `controller.submit_io(fn)`. **This phase -audits and migrates them, but does NOT add new prefetch threads** (the heavy -SDKs are lazy-only per spec §2.2 Layer 3). +constraint, these should migrate to `controller.submit_io(fn)`. - [ ] **T6.1** Audit: `grep -rn "threading.Thread(" src/` to find all ad-hoc thread spawns. Document each in `state.toml` (a new `[ad_hoc_threads]` section). - [ ] **T6.2** For each ad-hoc thread in `src/log_pruner.py`, `src/project_manager.py`, etc., refactor to use `controller.submit_io(fn)` instead. Wrap the callable body in a try/except (the pool's default behavior is to surface exceptions via the Future; preserve existing error logging). @@ -135,36 +150,55 @@ SDKs are lazy-only per spec §2.2 Layer 3). --- -## Phase 7: Enforcement (Runtime Audit Hook) +## Phase 7: Warmup Notification (Hook API + GUI) + +The user said: *"the app controller should post to test clients or the user +when its threads are warmed up with imports — that way the user knows 'hey +you have the ui first, but now you have all the functionality.'"* This phase +implements the notification surfaces. + +### 7A: Hook API endpoints + +- [ ] **T7A.1 (Red)** `tests/test_api_hooks_warmup.py`: + - `test_warmup_status_endpoint`: hit `GET /api/warmup_status`, assert response has `pending`/`completed`/`failed` keys + - `test_warmup_wait_endpoint`: hit `GET /api/warmup_wait?timeout=10`, assert response includes the completion state + - Confirm FAIL (endpoints don't exist yet) +- [ ] **T7A.2 (Green)** In `src/api_hooks.py`: + - Add `GET /api/warmup_status` returning `controller.warmup_status()` + - Add `GET /api/warmup_wait` accepting `?timeout=N` (default 30s), calling `controller.wait_for_warmup(timeout)` then returning the final status + - Register `warmup_status` in `_gettable_fields` so the existing Hook API client can fetch it +- [ ] **T7A.3** Run T7A.1 tests; confirm PASS +- [ ] **T7A.4** Commit: `feat(api_hooks): add /api/warmup_status and /api/warmup_wait` + git note + +### 7B: GUI status indicator + toast + +- [ ] **T7B.1** In `src/gui_2.py` (in the status bar render function), poll `controller.warmup_status()` once per frame. While `pending` is non-empty: show "Warming up... (N/M)" text. When `pending` is empty AND `failed` is empty: show "All imports ready" with a green dot. When `failed` is non-empty: show "Imports: N failed" with a yellow dot. +- [ ] **T7B.2** Register a callback via `controller.on_warmup_complete(cb)` that: + - On transition to done (with no failures): queue a toast notification "All providers ready (M modules)" via the existing toast system + - On transition to done (with failures): queue a warning toast "Warmup finished with N failures — see Diagnostics" +- [ ] **T7B.3** Update `docs/guide_gui_2.md` (or wherever status bar is documented) to describe the new indicator +- [ ] **T7B.4** Commit: `feat(gui_2): warmup status indicator + completion toast` + git note + +**Phase 7 checkpoint:** Tests can poll `/api/warmup_status` to know when the system is fully ready. The GUI shows progress during startup and a toast when complete. + +--- + +## Phase 8: Enforcement (Runtime Audit Hook) The static gate (T1.4) catches known imports at audit time. This phase adds empirical enforcement: a test that spawns `sloppy.py` and verifies NO heavy import happens on the main thread at runtime. -- [ ] **T7.1 (Red)** `tests/test_main_thread_purity.py`: +- [ ] **T8.1 (Red)** `tests/test_main_thread_purity.py`: - `test_headless_startup_no_heavy_imports_on_main`: spawn `uv run python sloppy.py --headless --enable-test-hooks` with a `sitecustomize.py` shim that installs `sys.addaudithook` to log every `import` event with the calling thread. The hook writes to a temp file as JSON-L. - Wait for headless server ready (5s timeout via `ApiHookClient`). - - Read the audit log. Assert: no event with `thread_name == "MainThread"` for any module in the heavy denylist (`google.genai`, `anthropic`, `openai`, `fastapi`, `requests`, `numpy`, `tkinter`, `psutil`, `pydantic`, `tree_sitter_*`, `src.command_palette`, `src.theme_nerv`, `src.theme_nerv_fx`, `src.markdown_table`, `src.ai_client.send_*`-direct). + - Read the audit log. Assert: no event with `thread_name == "MainThread"` for any module in the heavy denylist (`google.genai`, `anthropic`, `openai`, `fastapi`, `requests`, `numpy`, `tkinter`, `psutil`, `pydantic`, `tree_sitter_*`, `src.command_palette`, `src.theme_nerv`, `src.theme_nerv_fx`, `src.markdown_table`). - Kill subprocess. Confirm FAIL (current state imports these on main). -- [ ] **T7.2** Once Phase 3-5 land and the static gate passes, this test should start passing. If it doesn't, debug and add more lazy imports. -- [ ] **T7.3** Wire `test_main_thread_purity.py` into CI as a gating test (it'll be slow, ~10s, so mark with `@pytest.mark.slow` and only run in batched CI). -- [ ] **T7.4** Commit: `test: empirical main-thread purity check via sys.audit hook` + git note +- [ ] **T8.2** Once Phase 3-5 land and the static gate passes, this test should start passing. If it doesn't, debug and add more top-level import removals. +- [ ] **T8.3** Wire `test_main_thread_purity.py` into CI as a gating test (it'll be slow, ~10s, so mark with `@pytest.mark.slow` and only run in batched CI). +- [ ] **T8.4** Commit: `test: empirical main-thread purity check via sys.audit hook` + git note -**Phase 7 checkpoint:** CI fails if a future commit re-introduces a heavy main-thread import. - ---- - -## Phase 8: Hook API + Diagnostics - -- [ ] **T8.1** Add `/api/startup_profile` endpoint in `src/api_hooks.py` returning `controller.startup_profiler.snapshot()` -- [ ] **T8.2** Register `startup_profile` in `_gettable_fields` -- [ ] **T8.3** Add a "Startup Profile" section to the Diagnostics panel (`src/gui_2.py` `_render_diagnostics` or similar). Show: phase name, duration, % of total. -- [ ] **T8.4** Add `/api/io_pool_status` endpoint returning `{max_workers, active_threads, queued, completed}` so the user can see the job pool is alive. -- [ ] **T8.5** Update `docs/guide_api_hooks.md` with both new endpoints. -- [ ] **T8.6** Tests: extend `tests/test_api_hooks.py` + new `tests/test_startup_profiler.py` + new `tests/test_io_pool_endpoint.py`. -- [ ] **T8.7** Commit: `feat(diagnostics): expose startup profile and io_pool status via Hook API` + git note - -**Phase 8 checkpoint:** User can see per-phase startup cost + job-pool liveness in the GUI. +**Phase 8 checkpoint:** CI fails if a future commit re-introduces a heavy main-thread import. --- @@ -175,30 +209,36 @@ import happens on the main thread at runtime. - `import src.gui_2` < 500ms - `import src.app_controller` < 300ms (includes `_io_pool` creation; should still be < 300ms) - [ ] **T9.2** Re-run `scripts/audit_main_thread_imports.py` (T1.4). Confirm exit 0. No violations. -- [ ] **T9.3** Run `live_gui` test batch (per `conductor/workflow.md:147-150`: max 4 test files per batch, long timeout): +- [ ] **T9.3** Run `tests/test_warmup_mechanism.py` (T2.3); confirm warmup completes and notifications fire +- [ ] **T9.4** Run `live_gui` test batch (per `conductor/workflow.md:147-150`: max 4 test files per batch, long timeout): - `uv run pytest tests/test_live_gui_*.py --timeout=60 -v` in batches - Confirm `wait_for_server(timeout=15)` does not time out -- [ ] **T9.4** Manual smoke: - - `uv run sloppy.py` (normal mode): time-to-first-frame - - `uv run sloppy.py --enable-test-hooks` (test mode): time-to-first-frame + - Optionally: tests can call `controller.wait_for_warmup()` before exercising functionality that depends on warmed modules +- [ ] **T9.5** Manual smoke: + - `uv run sloppy.py` (normal mode): time-to-first-frame, observe "Warming up... (N/M)" status, then "All imports ready" toast + - `uv run sloppy.py --enable-test-hooks` (test mode): same observations, plus `/api/warmup_status` returns `completed` - `uv run sloppy.py --headless` (headless): time-to-server-ready -- [ ] **T9.5** Phase checkpoint commit: `conductor(checkpoint): Phase 9 complete - sloppy.py startup speedup track` + git note with full verification report -- [ ] **T9.6** Update `conductor/tracks.md`: mark track complete, link to archived folder + - Verify a user action that switches provider (or other warmup-dependent operation) is INSTANT, not 1s-delayed +- [ ] **T9.6** Phase checkpoint commit: `conductor(checkpoint): Phase 9 complete - sloppy.py startup speedup track` + git note with full verification report +- [ ] **T9.7** Update `conductor/tracks.md`: mark track complete, link to archived folder -**Phase 9 checkpoint:** All verification criteria in `spec.md:6` met. +**Phase 9 checkpoint:** All verification criteria in `spec.md:6` met. User can switch providers with zero perceptible lag because warmup already loaded the SDK. --- ## Definition of Done - [ ] All Phase 1-9 tasks checked -- [ ] All tests pass (273+ existing + new TDD tests including `test_main_thread_purity`) +- [ ] All tests pass (273+ existing + new TDD tests including `test_main_thread_purity` and `test_warmup_mechanism`) - [ ] `uv run ruff check .` and `uv run mypy --explicit-package-bases .` clean (per `mma-tier2-tech-lead` skill) - [ ] `uv run python scripts/audit_main_thread_imports.py` exits 0 - [ ] `docs/startup_baseline_20260606.txt` and `docs/startup_after_20260606.txt` archived - [ ] Phase 9 git note contains: baseline diff, audit script result, runtime audit hook result, full test batch results, manual smoke timings, file inventory - [ ] Track moved to `conductor/tracks/archive/` - [ ] **NO new `threading.Thread(...)` calls in `src/`** (verified by `grep -rn "threading.Thread(" src/`) +- [ ] **NO `import X` statements in function bodies for heavy modules** — verified by `grep -rn "^\s*import \(google\|anthropic\|openai\|fastapi\|src\.command_palette\|src\.theme_nerv\|src\.markdown_table\)" src/` +- [ ] **Warmup completion notification works** — GUI shows toast, Hook API returns `completed`, `controller.is_warmup_done()` returns True within 10s of startup +- [ ] **User action latency is zero for warmup-dependent operations** — manual smoke test switching providers / opening palette / rendering NERV is instant --- diff --git a/conductor/tracks/startup_speedup_20260606/spec.md b/conductor/tracks/startup_speedup_20260606/spec.md index 8f5a982a..254fd1c4 100644 --- a/conductor/tracks/startup_speedup_20260606/spec.md +++ b/conductor/tracks/startup_speedup_20260606/spec.md @@ -88,9 +88,11 @@ mechanism that does not run on the main thread. ### 2.2 Four layers of protection -#### Layer 1 — Pure lazy loading (the load-bearing wall, non-negotiable) +#### Layer 1 — Explicit warmup-aware module access (the load-bearing wall, non-negotiable) -Move heavy imports from module top-level into the function body that needs them: +Remove heavy imports from the top of source files reachable from the main +thread. Functions that need them use a `_require_warmed(name)` helper that +assumes the module is already in `sys.modules` (because warmup put it there): ```python # BEFORE (src/ai_client.py, current) @@ -100,18 +102,44 @@ import openai # ... 5 provider SDKs loaded unconditionally # AFTER -def _send_gemini(md_content, user_message, ...): - from google import genai # 955ms, paid once, on the first call's thread - ... +import sys +import importlib +from typing import Any -def _send_anthropic(...): - import anthropic - ... +def _require_warmed(name: str) -> Any: + """Get a module that AppController's warmup should have loaded. + + Raises RuntimeError if the module is not in sys.modules. This is the + explicit contract: heavy modules MUST be warmed at startup. No lazy + loading on first use — the import is paid upfront on a bg thread. + """ + mod = sys.modules.get(name) + if mod is None: + raise RuntimeError( + f"Module {name!r} is not warmed. " + f"AppController.__init__ must have run first (which submits warmup jobs)." + ) + return mod + +def _send_gemini(md_content, user_message, ...): + genai = _require_warmed("google.genai") + # ... use genai ... ``` -**Main-thread cost: zero.** First call still pays the latency, but it happens on -the asyncio worker thread (per `guide_architecture.md:215-234`), so the GUI never -sees it. +**Why no `import X` inside the function body?** Because that would be lazy +loading on first use. If the first use is triggered by a user UI action +(e.g. switching the provider from MiniMax to Gemini, the controller enqueues +an action that propagates to the first call), the user sees a 955ms lag +between their click and any visible response. That's the bad case the user +called out: *"lazy loading introduces latencies when interacting with the UI +state vs the bg state."* + +By warming proactively, the first user-triggered call is instant. The cost +is paid during startup on a bg thread, before the user can interact. + +**Main-thread cost: zero.** The main thread's import chain is fully lean +(none of the heavy modules are imported top-level). The warmup jobs run on +`_io_pool` workers in parallel with the main thread's remaining init. #### Layer 2 — Shared job pool on AppController (no new threads per task) @@ -124,22 +152,22 @@ The codebase already has these dedicated / shared threads: - Ad-hoc `threading.Thread` calls — used for one-off tasks; the user wants to **MINIMIZE** these -**User constraint:** no new daemon threads per import prefetch, per I/O task, per +**User constraint:** no new daemon threads per import warmup, per I/O task, per log-prune. We add ONE shared `ThreadPoolExecutor` to `AppController` named `_io_pool`, and any subsystem that needs background work submits jobs to it. This includes: - Initial RAG index warm-up (if applicable) - Log pruning (currently a one-shot thread — refactor to use the pool) - Disk-bound subsystem initialization (e.g., TOML re-read on persona switch) -- Any other ad-hoc I/O +- **Heavy module warmup (the primary use case for this track)** ```python # In AppController.__init__ from concurrent.futures import ThreadPoolExecutor self._io_pool = ThreadPoolExecutor( - max_workers=4, - thread_name_prefix="controller-io", + max_workers=4, + thread_name_prefix="controller-io", ) ``` @@ -147,25 +175,95 @@ self._io_pool = ThreadPoolExecutor( import, not 1 per subsystem. Just 4 long-lived threads that all background work shares. Future work that needs a bg thread should `controller._io_pool.submit(fn)`. -#### Layer 3 — NO prefetch of the heaviest SDKs (deliberate) +#### Layer 3 — Proactive warmup + completion notification (the new mechanism) -The original Phase 5 of this plan proposed a `import-prefetch` daemon thread that -warms `google.genai` (~955ms) on a background thread. **This has been explicitly -rejected** for the heavy SDKs, and the reasoning is sound: +This is the core of the track. In `AppController.__init__`, immediately after +`_io_pool` is created, the controller submits a job to the pool for each heavy +module that needs warming. The main thread does NOT wait for these to complete. -- A 955ms import on a background thread holds the GIL for ~10-50ms at a time - during C extension init. Each hold stalls the main thread's render loop. -- The user pays 955ms total either way: prefetch = 955ms of background stutter - + instant first call; lazy-only = 955ms of stutter on the first call only, - with the GUI fully interactive in between. -- Prefetching wastes the import cost when the user never uses that provider - (e.g., default is Gemini but the user actually only uses Anthropic). +```python +# In AppController.__init__, right after self._io_pool is created +self._warmup_status: dict[str, list[str]] = { + "pending": [], "completed": [], "failed": [], +} +self._warmup_lock = threading.Lock() +self._warmup_done_event = threading.Event() +self._warmup_callbacks: list[Callable] = [] +self._submit_warmup_jobs() +``` -**Rule: heavy SDKs (`google.genai`, `anthropic`, `openai`, `fastapi`) are -lazy-only, never prefetched.** Lighter modules (themes, command palette, -markdown table) MAY be optionally warmed on the `_io_pool` if profiling shows -they're commonly used, but it's not a hard requirement and the default is -"don't warm." +```python +def _submit_warmup_jobs(self) -> None: + """Submit bg jobs to import heavy modules. Notifies subscribers on completion.""" + heavy = self._compute_warmup_list() + with self._warmup_lock: + self._warmup_status["pending"] = list(heavy) + self._warmup_status["completed"] = [] + self._warmup_status["failed"] = [] + self._warmup_done_event.clear() + for module_name in heavy: + self._io_pool.submit(self._warmup_one, module_name) + +def _compute_warmup_list(self) -> list[str]: + result = [ + # AI provider SDKs + "google.genai", "anthropic", "openai", "requests", + # Feature-gated GUI (used by main thread but not on first frame) + "src.command_palette", + "src.theme_nerv", "src.theme_nerv_fx", + "src.markdown_table", + ] + if self._enable_test_hooks or self._web_host: + result.extend(["fastapi", "fastapi.security.api_key"]) + return result + +def _warmup_one(self, module_name: str) -> None: + try: + importlib.import_module(module_name) + with self._warmup_lock: + self._warmup_status["pending"].remove(module_name) + self._warmup_status["completed"].append(module_name) + except Exception as e: + with self._warmup_lock: + self._warmup_status["pending"].remove(module_name) + self._warmup_status["failed"].append(module_name) + finally: + with self._warmup_lock: + done = not self._warmup_status["pending"] + callbacks = list(self._warmup_callbacks) if done else [] + if done: + self._warmup_done_event.set() + for cb in callbacks: + try: + cb(self._warmup_status) + except Exception: + pass +``` + +**Completion notification** is critical for the user-visible UX. Three surfaces: + +1. **GUI status indicator** — the status bar shows "Warming up... (5/8)" while + the bg jobs run, then "All imports ready" with a green dot when complete. + The GUI never blocks waiting; the indicator is updated by polling + `controller.warmup_status()` once per frame (cheap, lock-guarded). + +2. **GUI toast notification** — when warmup completes, show a toast: + "All providers ready" with the count of modules loaded. User can dismiss. + +3. **Hook API endpoint** — `GET /api/warmup_status` returns the current state; + `GET /api/warmup_wait?timeout=N` blocks until done (for tests). + +The user said: *"the app controller should post to test clients or the user +when its threads are warmed up with imports — that way the user knows 'hey +you have the ui first, but now you have all the functionality.'"* This is +exactly what the notification surfaces achieve. + +**Why this beats lazy-loading:** if a user clicks "switch to Gemini" and the +controller lazy-loads `google.genai` on that action, the user sees ~1s of +nothing happening between the click and the visible response. With warmup, +the click is instant because `google.genai` is already in `sys.modules`. The +1s of cost was paid during startup, when the user was looking at a splash or +otherwise not waiting on input. #### Layer 4 — Worker-process isolation (future, out of scope) @@ -181,18 +279,19 @@ the GUI's thread?"* The answer is: | Scenario | Blocks GUI? | |---|---| -| Module top-level import of heavy X, then main imports X | **YES** (X's import is in main's chain) | -| Lazy import of X inside a function called from the asyncio thread | **NO** (asyncio thread blocks, not main) | -| Lazy import of X inside a function called from the main thread | **YES** (first call only; the function caller blocks) | -| `_io_pool` worker importing X while main thread renders | **NO direct block, but GIL contention causes micro-stutters** (~5-50ms each). Acceptable because the pool is capped at 4 threads. | -| `_io_pool` worker imports X; main thread later imports X (same module) | **YES** (main blocks on per-module import lock until worker finishes). This is why Layer 1 must come first. | -| Spawning a new `threading.Thread` for each import prefetch | **Wasteful** (thread creation ~1-5ms each; thread count explodes). Use the `_io_pool` instead. | +| Module top-level import of heavy X, then main imports X | **YES** (X's import is in main's chain). This is why we remove heavy imports from main-thread-reachable files. | +| `_io_pool` worker warming X while main thread renders | **NO direct block, but GIL contention causes micro-stutters** (~5-50ms each). Acceptable because the pool is capped at 4 threads and the main thread is mostly idle in `immapp.run()`. | +| `_io_pool` worker warms X; main thread later calls `_require_warmed("X")` (X already in `sys.modules`) | **NO** (the lookup is a `dict.get()` — instant, no import lock contention). | +| User-triggered UI action (e.g. provider switch) propagates to controller which calls `_require_warmed` on a warmed module | **NO** (lookup is instant). This is the win the user explicitly called out: no user-perceptible lag. | +| `wait_for_warmup()` blocks the asyncio thread waiting for warmup | **NO direct block on GUI** (different thread). Asyncio thread waits; main thread renders. Acceptable but rarely needed if user waits for warmup notification first. | +| Spawning a new `threading.Thread` for each import warmup | **Wasteful** (thread creation ~1-5ms each; thread count explodes). Use the `_io_pool` instead. | -This means: **Layer 1 is non-negotiable.** Even with the `_io_pool`, if the -heavy import is also in the main thread's import chain, the main thread will -block on the import lock the moment it tries to use the module. Layer 1 removes -the heavy imports from the main thread's chain; Layer 2 reuses threads -efficiently; Layer 3 deliberately avoids prefetching the heaviest. +This means: **Layer 1 is non-negotiable.** Even with warmup on `_io_pool`, if +the heavy import is also in the main thread's import chain, the main thread +will block on the import lock the moment it tries to use the module. Layer 1 +removes the heavy imports from the main thread's chain; Layer 2 reuses +threads efficiently; Layer 3 proactively warms on bg threads so the FIRST +user-triggered use is instant. ### 2.4 Enforcement: the "main thread purity" audit @@ -236,95 +335,119 @@ not just at static analysis time. ### 3.1 Per-file import plan +For each source file reachable from the main thread's import chain, we +**remove top-level heavy imports** and have functions access them via +`_require_warmed(name)`. The warmup jobs (§3.2) put the modules in +`sys.modules` before any function is called. + #### `src/ai_client.py` (the biggest win: ~1800ms) Top-level today: `from google import genai`, `import anthropic`, `import openai`, `import requests` (used by deepseek/minimax). After: -- Drop `from google import genai` from top — lazy in `_send_gemini()` -- Drop `import anthropic` from top — lazy in `_send_anthropic()` -- Drop `import openai` from top — lazy in `_send_deepseek()` and `_send_minimax()` -- Drop `import requests` from top — lazy in those two providers' HTTP code -- Provider client objects (`_gemini_client`, `_anthropic_client`, etc.) stay as - module globals but are now `None` until first use -- The `_send_*` functions check their provider client is initialized and call a - new `_ensure__client()` lazy initializer (extracted from the current - top-level logic) +- **Drop all four heavy imports from the top.** Add `_require_warmed(name)` + helper at the top. +- `_send_gemini()` calls `_require_warmed("google.genai")` to get the module +- `_send_anthropic()` calls `_require_warmed("anthropic")` +- `_send_deepseek()` and `_send_minimax()` call `_require_warmed("openai")` and `_require_warmed("requests")` +- Provider client objects (`_gemini_client`, `_anthropic_client`, etc.) stay + as module globals but are now `None` until `_send_*` initializes them + (extracted from current top-level logic into a new + `_ensure__client()` that uses the warmed module) +- The warmup list in `AppController._compute_warmup_list()` includes + `google.genai`, `anthropic`, `openai`, `requests` (always warmed) -**Result:** ~1800ms off the main thread. First AI call still pays it, but on -the asyncio worker. +**Result:** ~1800ms off the main thread. The bg threads pay this cost during +startup. By the time the first AI call happens (which is always async, on +the asyncio thread), the modules are in `sys.modules` and the lookup is +instant. No user-perceptible lag. -#### `src/app_controller.py` (FastAPI in headless/web only) +#### `src/api_hooks.py` (FastAPI in headless/web only) Top-level today: `from fastapi import ...`, `from fastapi.security.api_key import ...` (only needed if `--enable-test-hooks` or `--web-host`). After: -- Drop these from top — lazy inside `HookServer.__init__` (which is itself lazy - in the controller: `if enable_test_hooks: from src.api_hooks import HookServer; ...`) +- **Drop these from top.** Add `_require_warmed(name)` calls inside the + methods that need them. +- The warmup list in `AppController._compute_warmup_list()` includes + `fastapi`, `fastapi.security.api_key` **conditionally** — only when + `enable_test_hooks` or `web_host` is set -**Result:** ~470ms off the main thread for non-test, non-web launches. Critical -because `live_gui` tests launch with `--enable-test-hooks` but the FastAPI work -can be deferred until the asyncio loop is ready. +**Result:** ~470ms off the main thread for non-test, non-web launches. +For `live_gui` tests (`--enable-test-hooks`), the warmup loads fastapi +during the same startup window, so the hook server is ready when the +process announces readiness. -#### `src/commands.py` and `src/command_palette.py` (command palette lazy) +#### `src/commands.py` (command palette warmup-aware) Top-level today: `from src.command_palette import ...` at `src/commands.py:1`. After: -- Lazy in each `_*_command()` function in `src/commands.py` that actually - opens the palette -- The CommandRegistry decorator can keep module-level function references, but - the *body* of the command does the heavy import +- **Drop the top-level import.** The command functions call + `_require_warmed("src.command_palette")` to access the module +- The warmup list includes `src.command_palette` -**Result:** ~244ms off if user doesn't open palette during the first session. +**Result:** ~244ms off the main thread's import chain. The bg thread +warms it during startup; the first `Ctrl+Shift+P` is instant. -#### `src/theme_2.py` and `src/theme_nerv.py` / `src/theme_nerv_fx.py` (NERV theme lazy) +#### `src/theme_2.py` (NERV theme warmup-aware) -Top-level today: NERV modules imported at `src/theme_2.py` module top. +Top-level today: `from src.theme_nerv import ...`, `from src.theme_nerv_fx import ...` +at the top of `src/theme_2.py`. After: -- Lazy in `apply_nerv_theme()` (the function that activates NERV) -- The default theme path stays lean (uses only `src/theme_2.py` + `src/theme_models.py`) +- **Drop the top-level imports.** `apply_nerv_theme()` (or the function + that activates NERV) calls `_require_warmed("src.theme_nerv")` and + `_require_warmed("src.theme_nerv_fx")` +- The warmup list includes both NERV modules -**Result:** ~485ms off if user doesn't pick NERV theme (the default path). +**Result:** ~485ms off the main thread's import chain (the default +non-NERV path is lean). User pays the cost during startup; theme switch +is instant when they pick NERV. -#### `src/markdown_helper.py` (markdown table lazy) +#### `src/markdown_helper.py` (markdown table warmup-aware) Top-level today: `from src.markdown_table import ...` at `src/markdown_helper.py:1`. After: -- Lazy in `_render_table_block()` (or wherever GFM table detection happens) -- The first markdown render that hits a table pays the 250ms; subsequent hits are - cached in `sys.modules` +- **Drop the top-level import.** The table-detection branch of `render()` + calls `_require_warmed("src.markdown_table")` +- The warmup list includes `src.markdown_table` -**Result:** ~250ms off the first markdown render that lacks tables (typical). +**Result:** ~250ms off the main thread's import chain. First markdown +table render is instant. #### `src/imgui_scopes.py`, `src/gui_2.py`, `src/bg_shader.py` (KEEP `imgui_bundle`) -These MUST keep `import imgui_bundle` at top — the ImGui render loop is the hot -path and needs the module on first frame. There is no way to defer this without -breaking the render loop. +These MUST keep `import imgui_bundle` at top — the ImGui render loop is the +hot path and needs the module on first frame. There is no way to defer +this without breaking the render loop. What CAN be deferred inside `src/gui_2.py`: -- `import numpy` (only needed for `bg_shader`; the GUI itself doesn't need numpy - on the first frame) -- Other feature-gated imports +- `import numpy` (only needed for `bg_shader`; the GUI itself doesn't + need numpy on the first frame) — move to `_require_warmed("numpy")` in + the bg shader call site, add `numpy` to the warmup list +- Other feature-gated imports — same pattern #### `src/gui_2.py` direct heavy imports (audit) -We will use AST to audit which `import X` statements at `src/gui_2.py` top-level -are reachable from the first-frame render path (`render_main_window`, -`render_main_menu_bar`, etc.) and which are feature-gated. Feature-gated ones -move inside the function that gates them. +We will use AST to audit which `import X` statements at `src/gui_2.py` +top-level are reachable from the first-frame render path +(`render_main_window`, `render_main_menu_bar`, etc.) and which are +feature-gated. First-frame imports stay top-level. Feature-gated ones +move to `_require_warmed(...)` calls at the use site, with the module +added to the warmup list. -### 3.2 Job pool scaffolding +### 3.2 Job pool + warmup scaffolding New code in `src/app_controller.py`: ```python from concurrent.futures import ThreadPoolExecutor +import importlib +import threading # In AppController.__init__, after the asyncio loop starts: self._io_pool = ThreadPoolExecutor( @@ -332,16 +455,108 @@ self._io_pool = ThreadPoolExecutor( thread_name_prefix="controller-io", ) -def submit_io(self, fn, *args, **kwargs): - """Submit a background job to the shared I/O pool. Use this instead of - threading.Thread for new background work. - - Returns a concurrent.futures.Future. Caller can .result() if they need - to block, or .add_done_callback for fire-and-forget with error handling. - """ - return self._io_pool.submit(fn, *args, **kwargs) +# Warmup state +self._warmup_lock = threading.Lock() +self._warmup_done_event = threading.Event() +self._warmup_status: dict[str, list[str]] = { + "pending": [], "completed": [], "failed": [], +} +self._warmup_callbacks: list[Callable] = [] +self._submit_warmup_jobs() ``` +`_submit_warmup_jobs()` computes the warmup list and submits one job per +module to the pool: + +```python +def _submit_warmup_jobs(self) -> None: + heavy = self._compute_warmup_list() + with self._warmup_lock: + self._warmup_status["pending"] = list(heavy) + self._warmup_status["completed"] = [] + self._warmup_status["failed"] = [] + self._warmup_done_event.clear() + for name in heavy: + self._io_pool.submit(self._warmup_one, name) + +def _compute_warmup_list(self) -> list[str]: + result = [ + "google.genai", "anthropic", "openai", "requests", + "src.command_palette", + "src.theme_nerv", "src.theme_nerv_fx", + "src.markdown_table", + "numpy", # used by bg_shader; warmed for first invocation + ] + if self._enable_test_hooks or self._web_host: + result.extend(["fastapi", "fastapi.security.api_key"]) + return result +``` + +Each warmup worker imports the module, updates the status, and on the +last one fires the completion callbacks (so the GUI status indicator and +toast notification can react): + +```python +def _warmup_one(self, name: str) -> None: + try: + importlib.import_module(name) + with self._warmup_lock: + self._warmup_status["pending"].remove(name) + self._warmup_status["completed"].append(name) + except Exception: + with self._warmup_lock: + self._warmup_status["pending"].remove(name) + self._warmup_status["failed"].append(name) + finally: + with self._warmup_lock: + done = not self._warmup_status["pending"] + cbs = list(self._warmup_callbacks) if done else [] + if done: + self._warmup_done_event.set() + for cb in cbs: + try: + cb(dict(self._warmup_status)) + except Exception: + pass +``` + +Public API on `AppController`: + +```python +def warmup_status(self) -> dict[str, list[str]]: + """Snapshot the current warmup state. Cheap (lock-guarded copy).""" + with self._warmup_lock: + return {k: list(v) for k, v in self._warmup_status.items()} + +def is_warmup_done(self) -> bool: + return self._warmup_done_event.is_set() + +def wait_for_warmup(self, timeout: float | None = None) -> bool: + """Block until warmup completes. Returns True on done, False on timeout.""" + return self._warmup_done_event.wait(timeout=timeout) + +def on_warmup_complete(self, callback: Callable[[dict], None]) -> None: + """Register a callback for warmup completion. If already done, fires immediately.""" + with self._warmup_lock: + if self._warmup_done_event.is_set(): + snap = {k: list(v) for k, v in self._warmup_status.items()} + if "snap" in dir(): # already done + callback(snap) + else: + with self._warmup_lock: + self._warmup_callbacks.append(callback) +``` + +Hook API endpoints (added in `src/api_hooks.py`): + +- `GET /api/warmup_status` → `controller.warmup_status()` +- `GET /api/warmup_wait?timeout=N` → blocks until done, returns final status + +GUI integration (in `src/gui_2.py`): + +- Status bar: "Warming up... (5/8)" while in flight, "All imports ready" + green dot when done. Polled once per frame from `controller.warmup_status()` (cheap, ~microseconds). +- On transition to done: show a toast notification "All providers ready (8 modules)" for 5 seconds. + In `AppController.shutdown()` (or wherever lifecycle cleanup lives): `self._io_pool.shutdown(wait=False)`. Non-blocking because the pool's workers are daemon threads and will die with the process anyway. @@ -381,37 +596,50 @@ Used at every major init step in `AppController.__init__` and `App.__init__`. - T1.4: Add `scripts/audit_main_thread_imports.py` (static gate) - T1.5: Commit baseline + audit script -### Phase 2: Job Pool Foundation (Day 1) — the "no new threads" rule -- T2.1 (TDD Red): Write `tests/test_app_controller_io_pool.py` asserting - `AppController` has a `_io_pool: ThreadPoolExecutor` with 4 workers, named - `controller-io-*` -- T2.2 (Green): Add `self._io_pool = ThreadPoolExecutor(max_workers=4, - thread_name_prefix="controller-io")` to `AppController.__init__`. Add - `submit_io(fn, *args)` helper. Wire shutdown into `controller.shutdown()`. -- T2.3: Verify T2.1 tests pass + full suite still passes +### Phase 2: Job Pool + Warmup Foundation (Day 1) +- T2.1 (TDD Red): `tests/test_app_controller_io_pool.py` — assert + `AppController` has a 4-worker `_io_pool` named `controller-io-*` +- T2.2 (Green): Add `_io_pool` to `AppController.__init__` with named threads +- T2.3 (TDD Red): `tests/test_warmup_mechanism.py` — assert warmup jobs are + submitted in `__init__`, complete within 10s, fire the done event, support + callbacks, don't block init +- T2.4 (Green): Implement `_submit_warmup_jobs()`, `_compute_warmup_list()`, + `_warmup_one()`, `warmup_status()`, `is_warmup_done()`, `wait_for_warmup()`, + `on_warmup_complete()` per spec §3.2 +- T2.5: Run T2.1 + T2.3 tests, confirm PASS +- T2.6: Commit -### Phase 3: Lazy-load AI provider SDKs (Day 2) -- T3.1 (TDD Red): Write `tests/test_ai_client_lazy_imports.py` asserting - `import src.ai_client` does NOT import any provider SDK -- T3.2 (Green): Move `from google import genai` / `import anthropic` / - `import openai` / `import requests` into their respective `_send_*` functions -- T3.3: Verify existing `tests/test_ai_client.py` still passes -- T3.4: Commit, re-run benchmark, expect `import src.ai_client` < 50ms +### Phase 3: Remove top-level heavy SDK imports from `src/ai_client.py` (Day 2) +- T3.1 (TDD Red): `tests/test_ai_client_no_top_level_sdk_imports.py` — assert + `import src.ai_client` does NOT load `google.genai` / `anthropic` / `openai` / + `requests` (warmup hasn't run in the subprocess) +- T3.2 (Green): Remove the four heavy imports from the top of `ai_client.py`. + Add `_require_warmed(name)` helper. Each `_send_*` uses + `_require_warmed("google.genai")` etc. +- T3.3: Run existing `tests/test_ai_client.py`; fix any breakage (tests + relying on top-level import side effects need a fixture that warms or a + fallback for test mode) +- T3.4: Confirm T3.1 tests PASS +- T3.5: Commit -### Phase 4: Lazy-load FastAPI in `HookServer` (Day 2) -- T4.1 (TDD Red): Write `tests/test_hook_server_lazy_fastapi.py` asserting +### Phase 4: Remove top-level FastAPI imports from `src/api_hooks.py` (Day 2) +- T4.1 (TDD Red): `tests/test_hook_server_no_top_level_fastapi.py` — assert `from src.api_hooks import HookServer` does NOT import fastapi -- T4.2 (Green): Move `from fastapi import ...` inside the methods that need them -- T4.3: Verify existing `tests/test_api_hooks.py` still passes +- T4.2 (Green): Remove the fastapi imports from top. Use `_require_warmed` + inside the methods that need them +- T4.3: Run existing `tests/test_api_hooks.py`; fix - T4.4: Commit -### Phase 5: Lazy-load feature-gated GUI modules (Day 3) -- T5.1: Lazy-load `src.command_palette` in `src/commands.py` -- T5.2: Lazy-load `src.theme_nerv` and `src.theme_nerv_fx` in `src/theme_2.py` -- T5.3: Lazy-load `src.markdown_table` in `src/markdown_helper.py` -- T5.4: Audit and lazy-load feature-gated imports in `src/gui_2.py` -- T5.5: Run all GUI tests; fix any circular imports -- T5.6: Commit per task +### Phase 5: Remove top-level imports for feature-gated GUI modules (Day 3) +- T5A: Command Palette — `tests/test_command_palette_no_top_level_import.py` + + remove from `src/commands.py` + use `_require_warmed("src.command_palette")` +- T5B: NERV Theme — `tests/test_theme_nerv_no_top_level_import.py` + remove + from `src/theme_2.py` + use `_require_warmed("src.theme_nerv")` etc. +- T5C: Markdown Table — `tests/test_markdown_helper_no_top_level_import.py` + + remove from `src/markdown_helper.py` + use `_require_warmed("src.markdown_table")` +- T5D: GUI feature-gated — audit `src/gui_2.py` via the T1.2 script, apply + same pattern. `numpy` migrates to `_require_warmed` in `bg_shader` call site. +- T5E: Commit per module (4 atomic commits) ### Phase 6: Migrate ad-hoc threads to `_io_pool` (Day 4) - T6.1: Audit: `grep -rn "threading.Thread(" src/` to find all ad-hoc @@ -419,30 +647,49 @@ Used at every major init step in `AppController.__init__` and `App.__init__`. - T6.2: Refactor each ad-hoc thread to use `controller.submit_io(fn)` instead - T6.3: Per-migration commit - T6.4: Final `grep -rn "threading.Thread(" src/` shows ZERO new spawns - (the grep result should be identical to the T6.1 audit list, no new entries) -### Phase 7: Enforcement — Runtime Audit Hook (Day 4) -- T7.1 (TDD Red): `tests/test_main_thread_purity.py` — spawn `sloppy.py +### Phase 7: Warmup Notification (Hook API + GUI) (Day 4) +- T7A.1 (TDD Red): `tests/test_api_hooks_warmup.py` — assert + `GET /api/warmup_status` and `GET /api/warmup_wait` work +- T7A.2 (Green): Add the two endpoints in `src/api_hooks.py` and register + `warmup_status` in `_gettable_fields` +- T7B.1: In `src/gui_2.py`, add a status-bar indicator that polls + `controller.warmup_status()` each frame: "Warming up... (N/M)" while + pending, "All imports ready" with green dot on completion +- T7B.2: Register a callback via `controller.on_warmup_complete(cb)` that + shows a toast "All providers ready (M modules)" on success +- T7B.3: Update docs (status bar, toast, hook API) +- T7B.4: Commit + +### Phase 8: Enforcement — Runtime Audit Hook (Day 4) +- T8.1 (TDD Red): `tests/test_main_thread_purity.py` — spawn `sloppy.py --headless --enable-test-hooks` with a `sys.addaudithook` shim, verify no heavy import happens on the main thread -- T7.2: Once Phase 3-5 land, this test should start passing. Wire into CI. -- T7.3: Commit - -### Phase 8: Hook API + Diagnostics (Day 5) -- T8.1: Add `/api/startup_profile` endpoint -- T8.2: Add `/api/io_pool_status` endpoint -- T8.3: Add to `_gettable_fields` and the Diagnostics panel -- T8.4: Document in `docs/guide_api_hooks.md` -- T8.5: Tests + commit +- T8.2: Once Phase 3-5 land, this test should start passing. Wire into CI + as a gating test (`@pytest.mark.slow`). +- T8.3: Commit ### Phase 9: Verify + Checkpoint (Day 5) -- T9.1: Re-run `scripts/benchmark_imports.py`; confirm `import src.gui_2` and - `import src.ai_client` are now < 100ms each +- T9.1: Re-run `scripts/benchmark_imports.py --runs=3`; confirm + `import src.ai_client` < 50ms, `import src.gui_2` < 500ms, + `import src.app_controller` < 300ms - T9.2: Re-run `scripts/audit_main_thread_imports.py`; exit 0 -- T9.3: Run `tests/test_main_thread_purity.py`; pass -- T9.4: Run full `live_gui` test batch; `wait_for_server(timeout=15)` no - longer times out -- T9.5: Manual smoke test: `uv run sloppy.py` and +- T9.3: Run `tests/test_warmup_mechanism.py`; warmup completes and notifications fire +- T9.4: Run `tests/test_main_thread_purity.py`; pass +- T9.5: Run full `live_gui` test batch; `wait_for_server(timeout=15)` no + longer times out. Tests can call `controller.wait_for_warmup()` before + exercising warmup-dependent functionality. +- T9.6: Manual smoke: + - `uv run sloppy.py`: time-to-first-frame < 1.5s, observe status indicator + "Warming up... (N/M)" → "All imports ready" + toast + - `uv run sloppy.py --enable-test-hooks`: same, plus `/api/warmup_status` + returns `completed` after a brief wait + - `uv run sloppy.py --headless`: time-to-server-ready + - **Provider switch test**: switch from MiniMax to Gemini in the GUI + after warmup. The action must be INSTANT, not 1s-delayed (proves + warmup did its job) +- T9.7: Phase checkpoint commit + git note with full verification report +- T9.8: Update `conductor/tracks.md`; archive track `uv run sloppy.py --enable-test-hooks` both feel snappier - T9.6: Phase checkpoint commit with full verification report @@ -486,9 +733,22 @@ The track is complete when: - [ ] `scripts/audit_main_thread_imports.py` exits 0 (no heavy imports on main) - [ ] `tests/test_main_thread_purity.py` passes (runtime audit hook confirms invariant) - [ ] `scripts/benchmark_imports.py` shows no new red entries in the top-20 -- [ ] First AI call latency on the asyncio thread is < 1500ms (pays the SDK load once, - then the user has a snappy first call forever after). Main thread sees ZERO - of this cost. +- [ ] **`controller.wait_for_warmup(timeout=10.0)` returns True** — warmup completed + within 10s of `AppController.__init__` +- [ ] **All modules in the warmup list are in `sys.modules` after warmup** — + `controller.warmup_status()['pending']` is empty, `'completed'` contains + all expected module names +- [ ] **User-triggered actions on warmed modules are instant** — manual test + switching providers (e.g. MiniMax → Gemini) after warmup completes shows + NO perceptible lag (was ~1s with lazy-loading) +- [ ] **GUI status indicator transitions** — observe "Warming up... (N/M)" in + the status bar, then "All imports ready" with green dot, then a toast + notification fires via `controller.on_warmup_complete(...)` +- [ ] **Hook API exposes warmup state** — `GET /api/warmup_status` returns + `{pending: [], completed: [...], failed: []}`; `GET /api/warmup_wait?timeout=10` + returns the final state +- [ ] **NO `import X` statements inside function bodies for heavy modules** — + verified by `grep -rn "^\s*import \(google\|anthropic\|openai\|fastapi\|src\.command_palette\|src\.theme_nerv\|src\.markdown_table\)" src/` - [ ] No regressions in the existing 272/273 passing tests - [ ] `grep -rn "threading.Thread(" src/` shows ZERO new spawns after Phase 6 migration (only the existing project scaffolding threads like `HookServer` @@ -505,9 +765,8 @@ The track is complete when: - Importing on the main thread for the lean `gui_2` skeleton (~300ms unavoidable) - `pydantic` lazy loading (used by `src/models.py` which is imported by 16 files; the cost is already amortized and deferring it would cascade) -- Prefetch / warm-up of the heavy SDKs in the background (Layer 3 in §2.2 is - deliberately the "do nothing" layer; the user pays the import cost once on - first use, on the asyncio thread, not in the background) +- Lazy-loading heavy modules in function bodies (Layer 1 in §2.2 — explicitly + rejected by the user; warmup is the only mechanism) --- diff --git a/conductor/tracks/startup_speedup_20260606/state.toml b/conductor/tracks/startup_speedup_20260606/state.toml index 2ea532ec..ec39257d 100644 --- a/conductor/tracks/startup_speedup_20260606/state.toml +++ b/conductor/tracks/startup_speedup_20260606/state.toml @@ -10,13 +10,13 @@ last_updated = "2026-06-06" [phases] phase_1 = { status = "in_progress", checkpoint_sha = "", name = "Audit + Benchmark + Foundation" } -phase_2 = { status = "pending", checkpoint_sha = "", name = "Job Pool Foundation (no new threads)" } -phase_3 = { status = "pending", checkpoint_sha = "", name = "Lazy-load AI provider SDKs" } -phase_4 = { status = "pending", checkpoint_sha = "", name = "Lazy-load FastAPI in HookServer" } -phase_5 = { status = "pending", checkpoint_sha = "", name = "Lazy-load feature-gated GUI modules" } +phase_2 = { status = "pending", checkpoint_sha = "", name = "Job Pool + Warmup Foundation" } +phase_3 = { status = "pending", checkpoint_sha = "", name = "Remove top-level SDK imports (ai_client)" } +phase_4 = { status = "pending", checkpoint_sha = "", name = "Remove top-level FastAPI imports" } +phase_5 = { status = "pending", checkpoint_sha = "", name = "Remove top-level feature-gated GUI imports" } phase_6 = { status = "pending", checkpoint_sha = "", name = "Migrate ad-hoc threads to _io_pool" } -phase_7 = { status = "pending", checkpoint_sha = "", name = "Enforcement: runtime audit hook" } -phase_8 = { status = "pending", checkpoint_sha = "", name = "Hook API + Diagnostics" } +phase_7 = { status = "pending", checkpoint_sha = "", name = "Warmup Notification (Hook API + GUI)" } +phase_8 = { status = "pending", checkpoint_sha = "", name = "Enforcement: runtime audit hook" } phase_9 = { status = "pending", checkpoint_sha = "", name = "Verify + Checkpoint" } [tasks] @@ -26,42 +26,41 @@ t1_2 = { status = "pending", commit_sha = "", description = "Audit src/gui_2.py t1_3 = { status = "pending", commit_sha = "", description = "Add StartupProfiler and instrument init" } t1_4 = { status = "pending", commit_sha = "", description = "Write scripts/audit_main_thread_imports.py (static CI gate)" } t1_5 = { status = "pending", commit_sha = "", description = "Commit baseline + audit script" } -# Phase 2: Job Pool Foundation +# Phase 2: Job Pool + Warmup Foundation t2_1 = { status = "pending", commit_sha = "", description = "Red: tests/test_app_controller_io_pool.py" } -t2_2 = { status = "pending", commit_sha = "", description = "Green: add _io_pool ThreadPoolExecutor + submit_io helper to AppController" } -t2_3 = { status = "pending", commit_sha = "", description = "Confirm T2.1 tests pass + full suite still passes" } -t2_4 = { status = "pending", commit_sha = "", description = "Commit T2" } -# Phase 3: Lazy-load AI Provider SDKs -t3_1 = { status = "pending", commit_sha = "", description = "Red: tests/test_ai_client_lazy_imports.py" } -t3_2 = { status = "pending", commit_sha = "", description = "Green: move provider SDK imports into _send_* funcs" } +t2_2 = { status = "pending", commit_sha = "", description = "Green: add _io_pool ThreadPoolExecutor to AppController" } +t2_3 = { status = "pending", commit_sha = "", description = "Red: tests/test_warmup_mechanism.py" } +t2_4 = { status = "pending", commit_sha = "", description = "Green: implement _submit_warmup_jobs, _compute_warmup_list, _warmup_one, warmup_status, is_warmup_done, wait_for_warmup, on_warmup_complete" } +t2_5 = { status = "pending", commit_sha = "", description = "Confirm T2.1 + T2.3 tests pass" } +t2_6 = { status = "pending", commit_sha = "", description = "Commit T2" } +# Phase 3: Remove top-level SDK imports +t3_1 = { status = "pending", commit_sha = "", description = "Red: tests/test_ai_client_no_top_level_sdk_imports.py" } +t3_2 = { status = "pending", commit_sha = "", description = "Green: remove top-level SDK imports from src/ai_client.py; add _require_warmed helper; update _send_* to use it" } t3_3 = { status = "pending", commit_sha = "", description = "Fix existing test_ai_client.py breakage" } t3_4 = { status = "pending", commit_sha = "", description = "Confirm T3.1 tests PASS" } t3_5 = { status = "pending", commit_sha = "", description = "Commit T3" } t3_6 = { status = "pending", commit_sha = "", description = "Update tracks.md T3 row" } -# Phase 4: Lazy-load FastAPI -t4_1 = { status = "pending", commit_sha = "", description = "Red: tests/test_hook_server_lazy_fastapi.py" } -t4_2 = { status = "pending", commit_sha = "", description = "Green: move fastapi imports into HookServer methods" } +# Phase 4: Remove top-level FastAPI imports +t4_1 = { status = "pending", commit_sha = "", description = "Red: tests/test_hook_server_no_top_level_fastapi.py" } +t4_2 = { status = "pending", commit_sha = "", description = "Green: remove fastapi imports from src/api_hooks.py; use _require_warmed" } t4_3 = { status = "pending", commit_sha = "", description = "Fix existing test_api_hooks.py breakage" } t4_4 = { status = "pending", commit_sha = "", description = "Confirm T4.1 tests PASS" } t4_5 = { status = "pending", commit_sha = "", description = "Commit T4" } -# Phase 5A: Command Palette -t5a_1 = { status = "pending", commit_sha = "", description = "Red: tests/test_command_palette_lazy.py" } -t5a_2 = { status = "pending", commit_sha = "", description = "Green: lazy-load in src/commands.py" } +# Phase 5: Remove top-level feature-gated GUI imports +t5a_1 = { status = "pending", commit_sha = "", description = "Red: tests/test_command_palette_no_top_level_import.py" } +t5a_2 = { status = "pending", commit_sha = "", description = "Green: remove from src/commands.py; use _require_warmed" } t5a_3 = { status = "pending", commit_sha = "", description = "Fix existing test_command_palette.py" } t5a_4 = { status = "pending", commit_sha = "", description = "Commit T5A" } -# Phase 5B: NERV Theme -t5b_1 = { status = "pending", commit_sha = "", description = "Red: tests/test_theme_nerv_lazy.py" } -t5b_2 = { status = "pending", commit_sha = "", description = "Green: lazy-load in src/theme_2.py" } +t5b_1 = { status = "pending", commit_sha = "", description = "Red: tests/test_theme_nerv_no_top_level_import.py" } +t5b_2 = { status = "pending", commit_sha = "", description = "Green: remove from src/theme_2.py; use _require_warmed" } t5b_3 = { status = "pending", commit_sha = "", description = "Fix existing test_theme_2.py + test_theme_nerv.py" } t5b_4 = { status = "pending", commit_sha = "", description = "Commit T5B" } -# Phase 5C: Markdown Table -t5c_1 = { status = "pending", commit_sha = "", description = "Red: tests/test_markdown_helper_lazy.py" } -t5c_2 = { status = "pending", commit_sha = "", description = "Green: lazy-load in src/markdown_helper.py" } +t5c_1 = { status = "pending", commit_sha = "", description = "Red: tests/test_markdown_helper_no_top_level_import.py" } +t5c_2 = { status = "pending", commit_sha = "", description = "Green: remove from src/markdown_helper.py; use _require_warmed" } t5c_3 = { status = "pending", commit_sha = "", description = "Fix existing test_markdown_helper.py" } t5c_4 = { status = "pending", commit_sha = "", description = "Commit T5C" } -# Phase 5D: gui_2 feature-gated imports t5d_1 = { status = "pending", commit_sha = "", description = "Run audit_gui2_imports.py and collect feature-gated list" } -t5d_2 = { status = "pending", commit_sha = "", description = "Apply TDD pattern per feature-gated import" } +t5d_2 = { status = "pending", commit_sha = "", description = "Apply same pattern per feature-gated import in src/gui_2.py; numpy in bg_shader" } t5d_3 = { status = "pending", commit_sha = "", description = "Run full GUI test suite; fix" } t5d_4 = { status = "pending", commit_sha = "", description = "Commit per feature group" } # Phase 6: Migrate ad-hoc threads @@ -69,26 +68,29 @@ t6_1 = { status = "pending", commit_sha = "", description = "Audit threading.Thr t6_2 = { status = "pending", commit_sha = "", description = "Refactor each ad-hoc thread to use controller.submit_io" } t6_3 = { status = "pending", commit_sha = "", description = "Run full test suite; fix" } t6_4 = { status = "pending", commit_sha = "", description = "Commit per migration; final grep shows zero new spawns" } -# Phase 7: Enforcement - Runtime Audit Hook -t7_1 = { status = "pending", commit_sha = "", description = "Red: tests/test_main_thread_purity.py" } -t7_2 = { status = "pending", commit_sha = "", description = "Confirm test passes after Phase 3-5" } -t7_3 = { status = "pending", commit_sha = "", description = "Wire into CI as @pytest.mark.slow gating test" } -t7_4 = { status = "pending", commit_sha = "", description = "Commit T7" } -# Phase 8: Hook API + Diagnostics -t8_1 = { status = "pending", commit_sha = "", description = "Add /api/startup_profile endpoint" } -t8_2 = { status = "pending", commit_sha = "", description = "Add /api/io_pool_status endpoint" } -t8_3 = { status = "pending", commit_sha = "", description = "Add startup profile + io_pool status to Diagnostics panel" } -t8_4 = { status = "pending", commit_sha = "", description = "Update docs/guide_api_hooks.md" } -t8_5 = { status = "pending", commit_sha = "", description = "Tests for endpoints + profiler round-trip" } -t8_6 = { status = "pending", commit_sha = "", description = "Commit T8" } +# Phase 7: Warmup Notification (Hook API + GUI) +t7a_1 = { status = "pending", commit_sha = "", description = "Red: tests/test_api_hooks_warmup.py" } +t7a_2 = { status = "pending", commit_sha = "", description = "Green: add /api/warmup_status and /api/warmup_wait endpoints" } +t7a_3 = { status = "pending", commit_sha = "", description = "Register warmup_status in _gettable_fields" } +t7a_4 = { status = "pending", commit_sha = "", description = "Commit T7A" } +t7b_1 = { status = "pending", commit_sha = "", description = "Add status-bar indicator in src/gui_2.py that polls warmup_status each frame" } +t7b_2 = { status = "pending", commit_sha = "", description = "Register on_warmup_complete callback that shows toast on success" } +t7b_3 = { status = "pending", commit_sha = "", description = "Update docs for status bar + hook API" } +t7b_4 = { status = "pending", commit_sha = "", description = "Commit T7B" } +# Phase 8: Enforcement - Runtime Audit Hook +t8_1 = { status = "pending", commit_sha = "", description = "Red: tests/test_main_thread_purity.py" } +t8_2 = { status = "pending", commit_sha = "", description = "Confirm test passes after Phase 3-5" } +t8_3 = { status = "pending", commit_sha = "", description = "Wire into CI as @pytest.mark.slow gating test" } +t8_4 = { status = "pending", commit_sha = "", description = "Commit T8" } # Phase 9: Verify + Checkpoint t9_1 = { status = "pending", commit_sha = "", description = "Re-run benchmark; diff vs baseline" } t9_2 = { status = "pending", commit_sha = "", description = "Re-run audit_main_thread_imports.py; exit 0" } -t9_3 = { status = "pending", commit_sha = "", description = "Run test_main_thread_purity.py; pass" } -t9_4 = { status = "pending", commit_sha = "", description = "Run live_gui test batch; confirm wait_for_server passes" } -t9_5 = { status = "pending", commit_sha = "", description = "Manual smoke (normal, test-hooks, headless modes)" } -t9_6 = { status = "pending", commit_sha = "", description = "Phase checkpoint commit + git note" } -t9_7 = { status = "pending", commit_sha = "", description = "Update tracks.md; archive track" } +t9_3 = { status = "pending", commit_sha = "", description = "Run test_warmup_mechanism.py; warmup completes and notifications fire" } +t9_4 = { status = "pending", commit_sha = "", description = "Run test_main_thread_purity.py; pass" } +t9_5 = { status = "pending", commit_sha = "", description = "Run live_gui test batch; confirm wait_for_server passes" } +t9_6 = { status = "pending", commit_sha = "", description = "Manual smoke: provider-switch is INSTANT after warmup" } +t9_7 = { status = "pending", commit_sha = "", description = "Phase checkpoint commit + git note" } +t9_8 = { status = "pending", commit_sha = "", description = "Update tracks.md; archive track" } [verification] # To be filled at Phase 9 @@ -98,13 +100,31 @@ baseline_gui_2_ms = 0 after_gui_2_ms = 0 baseline_app_controller_ms = 0 after_app_controller_ms = 0 +warmup_completes_within_seconds = 0 +warmup_modules_in_sys_modules = 0 +provider_switch_latency_ms_after_warmup = 0 live_gui_passed = 0 live_gui_failed = 0 audit_main_thread_violations = 0 io_pool_max_workers = 4 io_pool_thread_name_prefix = "controller-io" new_threading_thread_calls = 0 +function_body_heavy_imports = 0 [ad_hoc_threads] # Filled in Phase 6 T6.1 audit # Format: {file = "src/foo.py", line = 42, current_target = "lambda", proposed_target = "controller.submit_io(...)"} + +[warmup_list] +# Filled in Phase 2 T2.4 implementation +google_genai = true +anthropic = true +openai = true +requests = true +src_command_palette = true +src_theme_nerv = true +src_theme_nerv_fx = true +src_markdown_table = true +numpy = true +fastapi = "conditional" # only when enable_test_hooks or web_host +fastapi_security_api_key = "conditional"