Release 2.1.0 — Quill meetings, notifications, quality digests, audit fixes

.gitignore

@@ -56,3 +56,6 @@ Thumbs.db
 ehthumbs.db
 .DS_Store
 desktop.ini
+
+# Serena agent artifacts
+.serena/

CHANGELOG.md

@@ -2,9 +2,31 @@
 
 ## Unreleased
 
+## 2.1.0
+
+**Meetings, on your own time.** Flowkey can now read your local Quill meetings and answer questions about them on the local model — and an after-hours scheduler pre-computes each meeting's digest (summary / goals / action items) during your idle window, so daytime reads are instant.
+
 ### Added
 
 - **Meetings (Quill integration) + after-hours digest processing.** Flowkey can connect to the local [Quill](https://quillapp.com) note-taking app over MCP to search your meetings and answer questions about them — entirely on the local model. Because asking a model about a full transcript costs real prefill time (~15–17 s of time-to-first-token for a ~7k-token transcript on the NPU), a background **scheduler** pre-computes a digest (summary / goals / action items) for each meeting during a configurable idle window (default 17:00–21:00, only when the machine has been idle), caching it in `data/meeting_digests.jsonl` so daytime reads are instant. New **Meetings** dashboard tab (search → read cached digest, "Process now", or "Ask about this meeting") and a Config card for all the settings (enable, Quill MCP URL, content source, schedule window, idle gating, max-per-run) with a "Run batch now" button. Off by default (opt-in). New modules `ffp_quill` (stdlib MCP-over-HTTP client) and `ffp_meetings` (digest store, batch worker, scheduler logic, idle detection); new config block `meetings`; new daemon actions `quill_status` / `quill_search_meetings` / `meeting_digest_get` / `meeting_digests_list` / `meeting_process` / `meeting_batch_run` / `meeting_batch_status` / `meeting_ask`. The Quill MCP URL is validated loopback-only; the meeting actions write a separate cache file under their own lock, so a long after-hours batch never blocks config saves or notifications.
+- **Action-item review board.** A weekly/monthly board on the Meetings tab aggregates the action items parsed from your meeting digests, each markable **accepted / rejected / pending** (status persisted in `data/meeting_action_status.jsonl`). New daemon actions `meeting_actions_list` / `meeting_action_set_status`.
+- **Weekly review.** A one-click roll-up of the week's processed meetings (highlights / themes / open items) generated on the local model from the cached digests — pick the week and Generate. New daemon action `meeting_week_summary`.
+- **Meeting hours on the Overview tab** — today / this-week meeting counts and hours, pulled from Quill (new daemon action `meeting_overview`).
+- **Digest quality flags + strict re-digest.** Each meeting digest is checked for low-substance / social-filler / too-short / trivial-meeting signals and flagged in the Meetings tab; a "Re-digest (strict)" button re-runs the summary with a stricter prompt. New daemon action `meeting_redigest`.
+
+### Fixed
+
+- Benchmark history no longer shows a blank row for an interrupted/empty run.
+- "Run batch now" persists the current Meetings settings (including the Enable toggle) before running, so it reflects the form rather than the last-saved config.
+- The Meetings results list is now scrollable and shows a meeting counter.
+- **Packaging now ships all runtime modules.** `ffp_meetings`, `ffp_notifications`, and `ffp_quill` were missing from `pyproject.toml` `py-modules` and the PyInstaller spec `hiddenimports`, so a wheel / frozen installer could omit them and crash on import even though source-tree tests passed. All three are now declared, and a new test (`test_packaging_modules`) asserts `py-modules` and the spec stay in sync with `scripts/*.py`.
+- The Telemetry time-of-day chart now renders only **active hours** — zero-activity hours are dropped instead of drawn as empty bars (and an empty history shows "No activity yet").
+
+### Internal
+
+- Removed the unused `ffp_tools.py` tool-calling prototype (no runtime caller).
+- Unified the config seed templates: the dev example (`config/`) and the shipped first-run seed (`setup/defaults/`) had drifted (the seed was missing the `llm` block) — they're now identical, enforced by `test_config_seeds`.
+- Docs refreshed for the current UI/build: README dashboard tabs (Chat + Meetings), the `open_chat` hotkey (`Ctrl+Alt+C`), a new "Supported surfaces" section (web chat only, installer-vs-source install, per-user autostart), and the installer README (3 exes, dropped retired `ffp-chat.exe` references).
 
 ## 2.0.0
 

README.md

@@ -4,7 +4,11 @@ Flowkey is a Windows desktop assistant that adds local-LLM hotkeys for grammar f
 
 Everything runs locally through [FastFlowLM](https://fastflowlm.com) (AMD Ryzen AI NPU) or, on machines without the NPU, through [Ollama](https://ollama.com) (CPU/GPU) as a secondary provider. No cloud service, analytics, or telemetry is used by the app.
 
-Current version: `2.0.0`
+Current version: `2.1.0`
+
+## What's new in 2.1
+
+- **Meetings, on your own time.** Connect the local [Quill](https://quillapp.com) note app to search your meetings and ask about them on the local model. Because asking about a full transcript costs real prefill time on the NPU, an **after-hours scheduler** pre-computes each meeting's digest (summary / goals / action items) during a configurable idle window (default 17:00–21:00) so daytime reads are instant. New **Meetings** tab + Config card; off by default.
 
 ## What's new in 2.0
 
@@ -98,7 +102,7 @@ Launch the app with AutoHotkey v2:
 | `explain:` + `Ctrl+Shift+G` | Explain code, regex, SQL, or technical text |
 | `tone:` + `Ctrl+Shift+G` | Rewrite in the selected tone preset |
 | `<custom>:` + `Ctrl+Shift+G` | Any mode you define in Dashboard → Config → Custom modes (e.g. `translate:`) |
-| `Ctrl+Shift+T` | Open chat (each tab has a "My notes" toggle that grounds replies in your notes vault) |
+| `Ctrl+Alt+C` | Open chat (the Chat tab has a "My notes" toggle that grounds replies in your notes vault) |
 | `Ctrl+Shift+A` | Ask in chat with selected text |
 | `Ctrl+Alt+N` | Capture a note |
 
@@ -108,12 +112,20 @@ Prefix tip: put the keyword on the first line of your selection — `prompt: rou
 
 The dashboard is a web page served by the local daemon — open it from the tray menu ("Dashboard") or browse to `http://127.0.0.1:52650/`. It is loopback-only and works in any browser.
 
-- **Tabs:** Overview, History, Telemetry, Notes, Benchmark, Config.
+- **Tabs:** Overview, Chat, Telemetry, History, Notes, Meetings, Config.
 - **Theme:** auto-follows your OS day/night setting; the topbar button cycles auto → light → dark.
 - **Custom modes:** Config → Custom modes lets you add your own `prefix:` commands (id + system prompt). Changes apply to the running app within a second.
 - **Models:** pull models with live progress — pick a suggestion or type any name (on Ollama, anything from the [library](https://ollama.com/library) works); set active, remove. Suggestions are hardware-aware: detected RAM/VRAM caps the model size (e.g. 32 GB RAM → ~4B on the NPU; 8 GB VRAM → ~9B on the GPU), oversized models are hidden, and free-typing one asks before pulling.
 - **Benchmark:** works on both providers — `flm bench` on FastFlowLM (~10–20 min, NPU), timed generations with native metrics on Ollama (~1–3 min, server keeps running).
 - **Notes:** browse or search your vault; History shows recent runs (text is stored only if history storage is enabled).
+- **Meetings:** connect the local [Quill](https://quillapp.com) app to search meetings, read AI digests (pre-computed after-hours), review action items (accept / reject), and generate a weekly review. Off by default — enable in Config → Meetings.
+- **Notifications:** per-event toggles, dedupe window, Do-Not-Disturb, and quiet hours; every toast (shown or muted) is logged to the Telemetry feed.
+
+## Supported surfaces
+
+- **Chat is web-only.** Chat lives in the dashboard's **Chat** tab (`Ctrl+Alt+C` or tray → "Open Chat"). The old standalone modal chat popup is retired — there is no separate chat window.
+- **Two install paths.** The signed **Inno Setup installer** (`Flowkey-Setup-<version>.exe`, per-machine, admin) *or* a **source install** (`INSTALL.cmd`, runs from an unzipped folder — no build, no signing). Both are supported; pick one.
+- **Autostart is per-user.** "Launch Flowkey when I sign in" is a single per-user `HKCU\…\Run` entry the daemon manages from Dashboard → Config — that toggle is the source of truth. The installer doesn't add machine-wide autostart.
 
 ## Project Layout
 

SPEC.md

@@ -0,0 +1,106 @@
+# Flowkey SPEC
+
+Caveman-encoded (compression, not amputation). Paths / ids / action names / numbers / endpoints verbatim.
+
+## §G goals
+
+- G1: local LLM hotkey assistant, Windows. ⊥ cloud, ⊥ analytics, ⊥ telemetry off-machine.
+- G2: run on AMD NPU (FastFlowLM) | any CPU/GPU (Ollama). provider ? → auto-fallback to other.
+- G3: web dashboard = single home for chat, notes, meetings, config, benchmark, notifications.
+- G4: heavy LLM cost (prefill) → pre-compute after-hours, read cached.
+
+## §C context / stack
+
+- front: AHK v2 — `scripts/grammarFix.ahk` + `scripts/lib/*` + `scripts/ui/*`
+- daemon: Python stdlib — `scripts/ffp_daemon.py` @ `http://127.0.0.1:52650` (single-instance = bound port)
+- LLM: FastFlowLM NPU @ `:52625` | Ollama @ `:11434`, OpenAI-compat `POST /v1/chat/completions`
+- dashboard: daemon-served `scripts/ui/web/{index.html,app.js,styles.css}`, CSP `default-src 'self'`
+- paths: `scripts/paths.py` → USER_ROOT/{config,data,logs}; `_version.py` = version src of truth
+- version: current `2.1.0` (held `release/v2.1.0`); public `2.0.0`; repo `agr77one/Fastflow`
+- run tree = `flowkey-pub2` (worktree, branch `live`=origin/main). old `FastFlowPrompt_Local_Setup`=1.5.0 stale.
+
+## §I interfaces
+
+- cfg blocks: `enabled`, `llm`, `providers.{fastflowlm,ollama}`, `server`, `routing`, `notes`, `chat`, `modes`, `dictionary`, `notifications`, `meetings`, `hotkeys`
+- api: `POST /action/<name>` ! header `X-FFP-API: 1` → 200 `{ok,result,error,elapsed_ms}`
+- api: `GET /` → dashboard; `GET /healthz` → `{ok,version,api,actions}`
+- action: `config_snapshot` → full cfg; `apply_config_patch {patch}` → merge (whitelist `filter_config_patch`)
+- action: `notify_gate {title,message}` → `{show,reason,category}` (logs); `notifications_log {limit}` → rows
+- action: `quill_status` → `{reachable,enabled,server,server_version}`
+- action: `quill_search_meetings {query,limit}` → `{meetings:[{id,title,date,duration,participants,url}]}`
+- action: `meeting_overview` → `{enabled,reachable,today:{count,minutes},week:{count,minutes}}`
+- action: `meeting_process {meeting_id,title,date,url}` → digest rec (writes `meeting_digests.jsonl`)
+- action: `meeting_batch_run {max_per_run?}` → `{ok,processed,queued,errors}`; `meeting_batch_status` → status
+- action: `meeting_digest_get {meeting_id}` → `{found,digest_md,...}`; `meeting_digests_list` → `{digests,count}`
+- action: `meeting_ask {meeting_id,question}` → `{ok,answer,source,seconds}`
+- action: `meeting_actions_list {range:week|month}` → `{range,items:[{id,text,owner,status,...}],counts}`
+- action: `meeting_action_set_status {id,status:pending|accepted|rejected}` → `{ok}`
+- action: `meeting_week_summary {week_offset}` → `{ok,week_label,meeting_count,summary}`
+- mcp: Quill @ `http://127.0.0.1:19532/mcp` — Streamable-HTTP, SSE `data:`, `Mcp-Session-Id` header; init→notifications/initialized→tools/call
+- cmd: `flm serve <model> --pmode turbo --host 127.0.0.1 --port 52625`
+- data: `data/{meeting_digests,meeting_action_status,notifications,chat_threads}.jsonl`
+- autostart: HKCU Run `FastFlowPrompt` → bundled `AutoHotkey64.exe` + `grammarFix.ahk`; `FlowkeyGitSync` → `sync.ps1`
+- sched: Windows task `FlowkeyGitSync` daily 12:00 → `sync.ps1` (ff-only pull, guarded)
+- ACTIONS count = 73
+
+## §V invariants
+
+- V1: ∀ `POST /action` → header `X-FFP-API` = API_VERSION `1` | 403
+- V2: ∀ req Host ∉ {`127.0.0.1`,`localhost`} → 403 (DNS-rebind defense)
+- V3: config patch → only keys ∈ `filter_config_patch` whitelist; rest dropped
+- V4: flm/llm/`meetings.mcp_url` ! loopback http/https | reject (SSRF guard)
+- V5: dashboard DOM → createElement/textContent only; ⊥ innerHTML; ⊥ native alert/confirm/prompt → use `confirmDialog`
+- V6: history text redacted by default (`history_store_text` false)
+- V7: notes ops ! contained via `_vault_subpath`; `../` → reject
+- V8: notify → daemon `notify_gate` decides+logs; AHK `Notify_Impl` fail-OPEN if daemon unreachable
+- V9: notify category `errors` (critical) → bypass DND & quiet_hours; still logged; still honors per-cat disable
+- V10: notify master `enabled`=false → mute all incl errors
+- V11: scheduler run ⟺ `should_run_batch` = meetings.enabled & in-window & (idle ? idle≥threshold)
+- V12: after-hours batch idempotent → skip meeting ∃ cached digest
+- V13: `meeting_*` actions ∉ `_WRITE_ACTIONS` → self-lock (`_io_lock`/`_batch_lock`), separate files ∴ long batch ⊥ block config/notify writes
+- V14: NPU prefill ∝ context (~17s @ ~7k tok) ∴ pre-compute digests after-hours; ask grounds on cached digest
+- V15: action-item id = `sha1(meeting_id|norm(text))[:16]` → stable across re-list ∴ status persists
+- V16: week = Monday 00:00 local; month = 1st 00:00 local
+- V17: builtin mode prompts locked from patching (only `tone.preset` patchable)
+- V18: version ∀ ∈ {`_version.py`,`pyproject.toml`,`installer/installer.iss`,`README.md`} equal; CI smoke fails on drift
+- V19: `main` branch-protected (ruleset 17344133) → land via PR + ruleset toggle; ⊥ direct push
+- V20: change gates ! pass: `ruff check scripts tests`, `pytest`, `node --check scripts/ui/web/app.js`, AHK parse-check (PowerShell `/ErrorStdOut`)
+- V21: local data (config/data/logs/vendor/certs) ∈ `.gitignore` ∴ pull moves code only, never user data
+- V22: `sync.ps1` ∃ uncommitted tracked changes → skip pull (⊥ clobber un-pushed WIP)
+
+## §T tasks
+
+```
+id|status|task|cites
+T1|x|web dashboard = home (chat/notes/config/bench/notifications/meetings)|V5
+T2|x|Ollama provider + auto-fallback + hw-aware model sizing|G2
+T3|x|notifications gate+log+panel (`ffp_notifications`)|V8,V9,V10
+T4|x|Quill meetings + after-hours digest scheduler (`ffp_quill`,`ffp_meetings`)|V11,V12,V14
+T5|x|overview meeting hours + action-item board + weekly review|V15,V16
+T6|x|git autosync: `sync.ps1` + daily task + autostart→flowkey-pub2|V21,V22
+T7|~|2.1.0 release held on `release/v2.1.0` → land after user test|V18,V19
+T8|.|installer clean-VM smoke test|—
+T9|.|[AUDIT] dead-code: unused daemon helper + 2 AHK wrappers + stale chat-popup config key + obsolete settings ref in test fixture + deprecated install shims|—
+T10|.|[AUDIT-P1] autostart: unify 3 divergent Run keys (daemon/src-installer/pkg-installer) → single HKCU entry; fix UI autostart status reporting|V20
+T11|.|[AUDIT] old open_chat default `^+t` still appears in first-run + web config fallback → replace with `^!c`|B5
+T12|.|[AUDIT] first-run seed thinner than DEFAULT_CONFIG schema → add seed-vs-schema drift guard (compare keys on first-run copy)|—
+T13|.|[AUDIT] installer bootstrap wrapper hardcodes old installer filename → derive from `_version.py`|V18
+T14|.|[AUDIT] quality-gate gaps: installer policy drift, autostart reg-name drift, bootstrap output name, README/dashboard tab count|V20
+T15|.|[DOCS] dashboard docs: 7 tabs listed, live = 8 (add Benchmark)|—
+T16|.|[DOCS] autostart docs conflict: main says no machine-wide entry; installer docs+impl still describe it → align on HKCU-only|—
+T17|.|[DOCS] installer layout: build script says flattened, installer.md still shows nested layout|—
+T18|.|[DOCS] provider roadmap marks selector/status UX incomplete → update to reflect it exists|—
+T19|.|[DOCS] first-run wizard text: "chat popup" + retired hotkey → update to current|B5
+T20|.|[DOCS] daemon log location stale in docs → update to current path|—
+```
+
+## §B bugs
+
+```
+id|date|cause|fix
+B1|2026-06|"Run batch now" ran vs last-saved cfg not form → "disabled"|autosave meetings patch before `meeting_batch_run`
+B2|2026-06|bench history blank row from 0-point result file|skip `rows==[]` in `ffp_benchmark.history`
+B3|2026-06|autostart → stale tree / empty `flowkey-public`|repoint HKCU Run → flowkey-pub2 + bundled AHK
+B4|2026-06|install launch: AHK called `.py`, shipped only `.exe`|flatten bundle to {app} + AHK→exe bridge (PR #19)
+B5|2026-06|`Ctrl+Shift+T` open_chat collided w/ browser reopen-tab|default → `^!c`; tray label = configured hotkey
+```

installer/README.md

@@ -7,7 +7,7 @@ Everything needed to turn this project into a signed Windows installer that non-
 ```
 installer/
 ├── build.ps1              ← end-to-end orchestrator (run this)
-├── fastflowprompt.spec    ← PyInstaller spec (4 exes, onedir, MERGE-dedup)
+├── fastflowprompt.spec    ← PyInstaller spec (3 exes, onedir, MERGE-dedup)
 ├── installer.iss          ← Inno Setup 6.x script (per-machine, admin)
 ├── sign.ps1               ← cert generation + signtool wrapper
 ├── certs/                 ← .pfx and .cer (gitignored)
@@ -66,12 +66,12 @@ SmartScreen on first launch.
 
 Steps the script runs:
 
-1. Read `scripts\_version.py` → derive version (e.g. `2.0.0`)
+1. Read `scripts\_version.py` → derive version (e.g. `2.1.0`)
 2. Generate `file_version_info.txt` for the Win32 VERSIONINFO resource
 3. Download `vendor\ahk\AutoHotkey64.exe` if missing (`-BundleAhk`)
 4. Download `vendor\flm\flm-setup.exe` if missing (`-BundleFlm`)
 5. Run `pyinstaller --clean --noconfirm fastflowprompt.spec` → `dist\FastFlowPrompt\`
-6. Run `iscc installer.iss` → `out\Flowkey-Setup-2.0.0.exe`
+6. Run `iscc installer.iss` → `out\Flowkey-Setup-2.1.0.exe`
 7. Run `sign.ps1` against the output (`-Sign`)
 
 Debug flags:
@@ -93,7 +93,7 @@ Debug flags:
 
 ## What the uninstaller does
 
-1. Kills `ffp-daemon.exe`, `ffp-chat.exe`, and the AHK process running
+1. Kills `ffp-daemon.exe` and the AHK process running
    `grammarFix.ahk` so file removal doesn't fail on in-use binaries.
 2. Chain-uninstalls FastFlowLM via its `QuietUninstallString` — but only if
    we set the `.flm_installed_by_us` marker. Users who already had FLM keep
@@ -128,7 +128,6 @@ C:\Program Files\FastFlowPrompt\           (read-only, admin-installed)
 ├── Flowkey\                        PyInstaller bundle
 │   ├── ffp-daemon.exe
 │   ├── ffp-grammar-fix.exe
-│   ├── ffp-chat.exe
 │   ├── ffp-first-run.exe
 │   ├── _internal\
 │   └── setup\defaults\

installer/fastflowprompt.spec

@@ -1,5 +1,5 @@
 # -*- mode: python ; coding: utf-8 -*-
-"""PyInstaller spec for Flowkey v1.5.0.
+"""PyInstaller spec for Flowkey (version resolved from scripts/_version.py).
 
 Build:
 
@@ -53,20 +53,22 @@ HIDDEN_IMPORTS = [
     "ffp_benchmark",
     "ffp_chat",
     "ffp_config",
+    "ffp_daemon",
     "ffp_flm_server",
     "ffp_hardware",
     "ffp_llm_client",
+    "ffp_meetings",
+    "ffp_notifications",
     "ffp_notify",
     "ffp_provider_runtime",
     "ffp_provider_status",
     "ffp_pull",
+    "ffp_quill",
     "ffp_telemetry",
-    "ffp_tools",
     "ffp_updater",
     "loopback_http",
     "paths",
     "grammar_fix",
-    "ffp_daemon",
     "first_run",
     "install",
     "notes",

installer/installer.iss

@@ -41,7 +41,7 @@
 #define AppURL        "https://github.com/agr77one/Fastflow"
 #define AppExeName    "Flowkey.exe"  ; symbolic — actual launchers below
 ; Keep in lockstep with scripts\_version.py.
-#define AppVersion    "2.0.0"
+#define AppVersion    "2.1.0"
 
 [Setup]
 AppId={{8A4F1E6C-9B3D-4E62-9F7A-FASTFLOW140}}

installer/sign.ps1

@@ -52,7 +52,7 @@
 .EXAMPLE
     # Sign the installer
     $env:FFP_SIGN_PFX_PASSWORD = "ChangeMe!"
-    .\sign.ps1 -FilePath ..\out\Flowkey-Setup-2.0.0.exe
+    .\sign.ps1 -FilePath ..\out\Flowkey-Setup-2.1.0.exe
 #>
 
 [CmdletBinding(DefaultParameterSetName = "Sign")]