Commit Graph

39 Commits

Author SHA1 Message Date
Yahya Alhinai aaf1dc5ede fix(voice): throttle repeated pod alerts 2026-06-28 06:49:04 +00:00
Yahya Alhinai c1ac687dcf feat(voice): on-demand PodMan voice test + Hermes notify + TTS tuning
Snapshot of in-progress voice work, committed to unblock concurrent edits: speakInRoom + POST voice-test endpoint, Test PodMan voice button (PodView/api), Hermes notify action + scripts/hermes-notify.mjs, agent exits on LiveKit disconnect for auto-restart, TTS playback tuning (subscriber-ready delay, preroll/tail silence, fallback line, microphone source), verify script updates.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-28 06:45:37 +00:00
Yahya Alhinai 562bc1979a fix: stabilize livekit gemini voice playback 2026-06-28 05:59:21 +00:00
Yahya Alhinai 721fe2b8d9 feat: use gemini tts for livekit voice 2026-06-28 05:43:38 +00:00
Yahya Alhinai c771e1594c feat: show screen thumbnails in pod streams 2026-06-28 05:33:00 +00:00
sb-iam 95a9bde5ee Merge pull request #7 from karti-ai/feat/live-graph-glue
fix(graph): readable Team-memory graph (short labels, clean collision labels, file cap)
2026-06-27 22:17:02 -07:00
sb-iam a21a2895c4 fix(graph): readable labels + file cap (de-hairball the viz)
The deployed graph was an unreadable mess: full file paths centered on nodes
bled across columns, and collision labels showed garbage vision symbols
("infra/README.md### Running the git watcher").

- node labels are now the last two path segments (full path in summary)
- collision labels are just the file (drop the junk #symbol)
- cap file nodes to 9 (collision files prioritized)

demo-pod: 22 -> 20 clean nodes; no label bleed.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-27 22:14:42 -07:00
sb-iam 4427e18bb9 Merge pull request #6 from karti-ai/feat/live-graph-glue
feat(graph): live Team memory graph from real Mongo data
2026-06-27 22:02:05 -07:00
sb-iam 2006096cda feat(graph): demo-ready materializer + per-pod Team memory action
Materializer (live.ts) — cut demo-pod from 110 -> 22 nodes:
- cap to 8 recent collisions; collapse repeats by memorySignature
- collapse interventions to one (most recent) per collision
- filter junk 'files' (URLs, env vars, browser/app names, scratch/test) to
  real source paths only
- prune test-artifact engineers (a/b/verify/codex-check/-testrepo) + any node
  orphaned by that
- collisions referenced by accepted outcomes bypass the cap so the learned_from
  money path never drops; risk-paths metric counts distinct signatures

UI: per-pod 'Team memory' action on each PodCard's menu (replaces the header
button that always opened pods[0]).

Verified against live demo-pod data (joins connect); typechecks clean.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-27 21:35:14 -07:00
Ramis 4142876b23 feat: unlock voice audio + terse demo-style collision alerts
Voice generation, critical escalation, and audio publish all worked, but
participants heard nothing: browsers block autoplay of the agent's audio
track until a user gesture. Add the canonical LiveKit unlock — listen for
AudioPlaybackStatusChanged and show an "Enable sound" button that calls
room.startAudio() so PodMan's voice cues are actually heard.

Also make collision alerts short and direct instead of chatty AI prose:
  card:  "Conflict: ram + yahya both on README.md (unpushed). Seen before."
  voice: "Conflict. ram + yahya, both on README.md."

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AaCFWMkYQmTcuPsxaaACft
2026-06-27 21:08:41 -07:00
sb-iam 412d3f7df6 tune(graph): de-noise the live materializer
Verified materializePodGraph against real demo-pod data (joins all connect:
21/21 interventions->collisions, learned_from produced). Tuning:
- engineer nodes are case-insensitive (merges Shakthi/shakthi)
- git (engineer_states) now only CONFIRMS editing on files vision/collisions
  already surfaced, instead of adding the whole repo diff (killed a 29-file
  node explosion from a watcher running against the full podman repo)

Cut demo-pod from 110 -> 77 nodes; git file-edges 39 -> 6.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-27 21:03:57 -07:00
Yahya Alhinai 59f92f18df feat: add realtime pod activity streams 2026-06-28 03:50:56 +00:00
sb-iam 85ab8da598 feat(graph): live materializer + light shadcn theme (real-data glue)
- backend/src/graph/live.ts: materializePodGraph builds the graph from the real
  collections (pods, engineer_states, observations, collisions, interventions,
  outcomes) instead of the demo seed. Parses git-status paths, fuses git+vision,
  draws collides/warns/learned_from, computes live metrics + a column layout.
- store.ts: loadPodGraph now prefers live → seeded team_model.graph → demo.
- GraphView.tsx: light/shadcn theme (from the team-memory-theme work), composed
  from the ruixen primitives; node-shape encoding unchanged.
- docs/graph.md: live data→graph mapping + fallback order.

Typechecks clean. Not yet runtime-verified end-to-end (Atlas creds rotated again).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-27 20:44:50 -07:00
Ramis e474fef228 fix: detect same-file collisions reliably via basename + git overlap
Live observations showed two engineers both dirty on README.md but zero
collisions firing. Two root causes:

1. normalize() only lowercased and prepended src/, so the same file at
   different path depths ("agent.ts" vs "backend/src/agent.ts") never
   matched. Replace with lowercased-basename matching.
2. Git ground truth (engineer_states.changedFiles) was only used to set
   the unpushed flag, never to match the file. The strongest signal was
   wasted.

Detector now fuses vision currentFile AND git changedFiles into one
file->engineers map, so a collision fires when two people share a dirty
file even if both screens aren't on it at the same instant.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AaCFWMkYQmTcuPsxaaACft
2026-06-27 20:44:44 -07:00
Yahya Alhinai dd99050be8 fix: prevent agent frame backpressure 2026-06-28 03:42:08 +00:00
Yahya Alhinai d9e6e8cef4 fix: harden agent worker crash handling 2026-06-28 03:38:50 +00:00
Ramis 745f0032f7 fix: make MongoDB mandatory, fail loud instead of degrading
Reverse the best-effort error swallowing. MongoDB is core to PodMan's
continual-learning story and must always be used, so a broken memory
layer must surface immediately rather than silently masquerade as
working (which is how observations stayed at 0 unnoticed).

- agent verifies Mongo via initMemory() at boot; bad creds / unreachable
  Atlas now fail loudly before joining the room, not mid-demo
- server exits on Mongo init failure instead of warning and limping on
- getGitStates and onScreenFrame no longer swallow Mongo errors
- memory persist() logs the failure and rethrows instead of warning

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AaCFWMkYQmTcuPsxaaACft
2026-06-27 20:34:27 -07:00
Ramis 6a6fbca9e0 fix: stop agent crashing on Mongo errors during live loop
A Mongo auth/connection failure in getGitStates escaped uncaught and
killed the agent process on the first screen frame, so collision
detection never ran. Make git-state fusion best-effort (degrade to
vision-only) and wrap the whole onScreenFrame loop so no per-frame
Gemini/GitHub/Mongo error can crash the long-running agent.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AaCFWMkYQmTcuPsxaaACft
2026-06-27 20:31:38 -07:00
Yahya Alhinai 7497318cde test: strengthen deployment verification 2026-06-28 02:54:29 +00:00
Yahya Alhinai 39a06499af feat: add local vector recall fallback 2026-06-28 02:27:45 +00:00
Yahya Alhinai 4253921532 Add Hermes operations management layer 2026-06-28 02:17:23 +00:00
Yahya Alhinai 89893110f1 feat: activate gemini voice tts path 2026-06-28 02:11:02 +00:00
sb-iam 4ff17415b6 Merge origin/main into feat/graph-data-viz
Resolve App.tsx header conflict: keep main's "Privacy-limited" badge AND the
"Team memory" graph button (both in the header action group). server.ts and
backend/package.json auto-merged cleanly — main's closeMemory/shutdown and the
graph:seed script are both preserved.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-27 18:54:10 -07:00
Yahya Alhinai c818d5081e feat: harden podman deployment orchestration 2026-06-28 01:44:26 +00:00
sb-iam eedfa935b1 Merge origin/main into feat/graph-data-viz
Resolve conflicts:
- backend/src/server.ts: keep main's getPresence + closeRoom (room auto-cleanup)
  and add the graph imports/routes (additive).
- frontend/src/App.tsx: take main's shadcn command-center UI and re-integrate
  GraphView — import, graphPodId state, an early-return render branch, and a
  shadcn "Team memory" button next to Refresh.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-27 18:41:56 -07:00
sb-iam 32bff6a3ab fix(graph): address review — reachFrom direct edges + node a11y
- reachFrom now returns the direct outbound edges PLUS the recursive
  $graphLookup reaches, de-duped by edge id, with maxDepth to bound cycles.
  It was dropping edges straight off the start node. [review P2]
- GraphView SVG nodes are keyboard-accessible: role/tabIndex/aria-label +
  Enter/Space handler alongside onClick. [review P3]

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-27 18:14:48 -07:00
sb-iam 546aeeed70 feat(graph): continual-learning graph data model + dark-Bauhaus viz
Adds the team_model graph layer (the "it learned" view) and its visualization,
per docs/graph.md. Demo-backed first; built on origin/main conventions.

- shared: PodGraph / node / edge / metric types + GraphNodeDoc / GraphEdgeDoc
- backend/src/graph: demo graph data; Mongo store (loadPodGraph w/ demo
  fallback, seedGraph, reachFrom via $graphLookup); graph:seed script
- backend/src/server.ts: additive GET /api/pods/:id/graph + /graph/reach/:node
- frontend: dark-Bauhaus GraphView + fetch helper, reachable from a
  "Team memory" toggle in App.tsx
- docs/graph.md: spec (data model, $graphLookup, API, demo-first plan)

Demo-backed: the route serves a grounded demo graph when team_model has no
graph yet; graph:seed writes team_model + graph_nodes/graph_edges so the
$graphLookup traversal is real. Swap loadPodGraph to live team_model later.

Known follow-ups before merge: branch is based on 65a0791; origin/main is now
at 1294b84, so this needs a rebase + App.tsx conflict resolution (teammate
rewrote App.tsx with live room view / one-click join).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-27 18:14:48 -07:00
Kartikeya 891d4b12bd feat(livekit): close the room when a pod is deleted
DELETE /api/pods/:id now also calls closeRoom (RoomServiceClient.deleteRoom)
to end the live LiveKit room and disconnect anyone connected. PodView listens
for RoomEvent.Disconnected and returns the user to the pod list, so a deleted
pod cleanly kicks everyone out instead of stranding them in a dead room.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-27 17:22:07 -07:00
Kartikeya e29fabc3f1 fix(livekit): stable identity + room auto-cleanup
Use the member name as the LiveKit identity (was random per join) so a
refresh/rejoin replaces the existing session instead of leaving a ghost
participant in the room. Set roomConfig on the token (emptyTimeout 60s,
departureTimeout 20s) so empty rooms and departed participants clean up
promptly. Pods map 1:1 to a deterministic room name, so joins reuse the
same room rather than spawning new ones.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-27 17:13:32 -07:00
Yahya Alhinai b1b0761973 chore: format repo and fix lint config 2026-06-28 00:09:48 +00:00
Ramis a853ef7709 feat: fuse engineer_states git truth into collision detector
Add getGitStates(podId) to db.ts — queries the engineer_states collection
written by scripts/podman-agent.mjs and returns a map keyed by engineer name.

In PodMan.onScreenFrame(), fuse before detectCollisions(): if an engineer has
changedFiles in engineer_states, force hasUnpushedChanges=true on their context.
This overrides Gemini vision's unreliable pixel-based guess with deterministic
local git state — preventing the money-moment collision from silently not firing.

Key assumption: LiveKit participant identity matches the --name arg used when
running the git watcher (e.g. identity "alice" → --name alice).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AaCFWMkYQmTcuPsxaaACft
2026-06-27 16:53:13 -07:00
Kartikeya 0f3b55a4f9 feat: one-click join + live pod presence
Join UX: click a member's name to join directly, or type a name and "Join"
(adds to roster + joins) — removes the redundant dropdown step. "Add" still
adds to the roster without joining.

Presence: new GET /api/presence (LiveKit RoomServiceClient) reports who's
connected per pod. The pod list polls it and shows a "N in room" badge plus a
green dot on members currently connected, so people can see active pods and jump in.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-27 16:46:47 -07:00
Kartikeya 7ff750ad5e harden: address adversarial review of Pods CRUD
Backend: atomic create with insert-retry-on-duplicate-key (removes slug
TOCTOU race + wrong 400s), resilient per-index creation so a unique-index
failure can't silently drop the constraint or block seeding, idempotent
race-safe seeding via $setOnInsert, type validation + size caps on all pod
fields/members, removeMember no-ops without a write, /api/outcome guarded.
Frontend: per-pod busy state (one mutation no longer disables every card),
joined pod derived from the list (can't go stale), create keeps inputs on error.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-27 16:02:40 -07:00
Kartikeya 5a03ad4d6b feat: Mongo-backed Pods with full CRUD + member management
Pods are persisted in MongoDB and CRUD'd via /api/pods (list/create/get/
update/delete + add/remove member). Shared Pod reshaped to a persisted entity
(members: string[], description, timestamps) + PodInput. Backend seeds Demo/
Frontend/Backend Pods on first run (Squad -> Pod rename). Frontend replaces
hardcoded teams with live data: PodCard (member chips add/remove, inline edit,
delete, join) + CreatePodForm; App fetches+mutates via API. Removes teams.ts/
TeamCard; gitignores test artifacts.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-27 15:49:05 -07:00
Kartikeya 3fc19194f2 feat(backend): persist memory to MongoDB
Replace the in-memory store with a real MongoDB-backed store. Adds memory/db.ts
(client singleton, typed collections, startup ping + indexes) and rewrites
record{Observation,Collision,Intervention,Outcome} to insert into Mongo
(best-effort — failures log, don't crash). Server connects on startup and
exposes GET /api/memory/stats for verification.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-27 15:34:59 -07:00
Kartikeya 6bf359f4d4 fix: restore CORS + align frontend with /api/token endpoint
The canonical-architecture rewrite dropped app.use(cors()) and moved the
token route to POST /api/token ({room,identity,name}), but the frontend
still called the old /pods/:id/token — causing "Failed to fetch" in the
browser. Re-add CORS and update fetchPodToken to the new contract.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-27 14:53:26 -07:00
Kartikeya da5b2622b2 Integrate canonical architecture: two-process backend + LiveKit agent
Promote all 12 staged canonical files from docs/generated/files/ to their
live paths, creating the full PodMan architecture:

Backend:
- server.ts: HTTP service (token mint, sync-PR, outcome recording, /health, WS relay)
- agent.ts: worker joining LiveKit room, grabbing screenshare frames at ~1fps
- agent/podman.ts: orchestrator loop (vision -> collision detection -> intervention)
- env.ts: flat env var accessors replacing nested stub
- vision/gemini.ts: JPEG -> Gemini vision -> EngineerContext (real implementation)
- collision/detector.ts: fused vision+GitHub collision detection (the moat)
- github/client.ts: Octokit wrapper with caching + sync PR creation
- memory/store.ts: extended with recordObservation/recordCollision/recordIntervention/recordOutcome helpers
- memory/vectors.ts: stub for Voyage+Atlas vector recall (Loop A)
- memory/policy.ts: stub for intervention policy gate (Loop B)
- voice/live.ts: stub for Gemini Live TTS voice output

Shared:
- messages.ts: LiveKit data-channel wire protocol (DataMessage, InterventionOutcome, TeamModel, LocalGitReport)
- index.ts: re-exports messages module

Frontend:
- livekit/useScreenPublish.ts: hook for joining pod and publishing screenshare
- livekit/useInterventions.ts: hook for receiving collision cards and responding
- lib/api.ts: fetchToken + postOutcome HTTP helpers

Database:
- database/init.ts: MongoDB Atlas collections + indexes + vector search index

Infra:
- infra/.do/app.yaml: DO App Platform spec (static_site + service + worker)

Retire stubs superseded by canonical decomposition:
- backend/src/index.ts (replaced by server.ts)
- backend/src/intervention/engine.ts (logic now in agent/podman.ts)
- backend/src/livekit/token.ts (token minting now in server.ts)

Install missing dependencies: @livekit/rtc-node, sharp, mongodb, ws, @types/ws

Type error fixes:
- vision/gemini.ts: use MediaResolution.MEDIA_RESOLUTION_LOW enum value (not string literal)
- agent/podman.ts: wrap SuggestedActionKind into { kind: action } SuggestedAction object

All packages pass pnpm -r typecheck and pnpm -r build.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-27 14:27:14 -07:00
Kartikeya 6559ad3944 feat(backend): scaffold PodMan agent pipeline + token server
Express server with /health and a LiveKit token endpoint. Module skeletons
for the full loop: vision (Gemini), GitHub fusion, collision detector (pure,
testable), intervention engine, and continual-learning memory store. Approve
native build scripts (esbuild/genai/protobufjs) at the workspace root.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-27 14:16:58 -07:00
Kartikeya 1bb15724c6 Initial monorepo scaffold
Set up top-level structure (backend, frontend, database, infra, shared,
docs) with .gitkeep placeholders, root README, and .gitignore.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-27 14:00:20 -07:00