bb4b4df987
fix(stop+stability): stop button interrupts live generation; classifier, prompt + preview pane improvements
...
Stop button fix:
- Plumb AbortSignal end-to-end: callVibnChat → Gemini SDK (config.abortSignal) / OpenAI fetch → executeMcpTool (/api/mcp fetch)
- Treat abort as clean user stop (not fatal error); partial reply persisted with '(stopped by user)'
Classifier fix:
- Add timeout/gateway/5xx/connection-error vocabulary to diagnose intent
- Prevents 'I get a gateway timeout' from falling through to feature_build (40 rounds) and looping
Prompt / agent behaviour:
- Render verification is now scope-aware: small edits stop at green healthCheck; no browser_console/curl audit on healthy server
- Sanitize stale '### Phase Checkpoint' walls from loaded history so old threads stop biasing new turns
- Next.js dev command updated to --no-turbopack for container stability (per-route lazy compile caused cold-start 503s)
- New public page prompt: agent checks middleware allowlist in the same turn
- Scope discipline and QA-tool gating carried forward from prior session
Code cleanup:
- Remove duplicate AgentPhase declaration (TS2440)
- Remove dead checkpoint emit branch and orphan 'checkpoint' phase value
- Remove unused MAX_TOOL_ROUNDS constant
Preview pane (build status):
- 4-state machine: initial-load / building (with elapsed timer) / build-failed / not-running
- pollMs 0 → 5 000ms so dev-server recovery and build completion auto-update without refresh
- anatomy route + use-anatomy type: inFlightBuild gains createdAt for elapsed timer
2026-06-10 21:40:48 -07:00
d4b679bca0
feat(verification): acceptance-check layer + executor fix-loop; hide phase-checkpoint walls; guaranteed turn-end summary. Verification gated behind VIBN_VERIFICATION_ENABLED.
2026-06-10 19:43:36 -07:00
1dcebe0fa7
fix(governor): classify multi-word greetings ('hey there!', 'good morning') and short verb-less messages as conversational so they don't trigger the agent loop
2026-06-10 17:50:31 -07:00
756fe7b092
ux(chat): clean tool-pill results (no raw JSON, Failed/exit verbs); structured build-health status instead of 'didn't reach a clean stopping point'; label active toolbar mode
2026-06-10 17:44:19 -07:00
beb0bebe8f
fix(governor): stop misclassifying 'okay <request>' and investigative questions as conversational; raise status_check/diagnose tool budgets (fixes round_cap cut-offs)
2026-06-10 17:26:41 -07:00
6d2ab7bd33
feat(telemetry): emit per-turn governor summary (stop_reason, rounds, tool_results) for orchestration diagnostics
2026-06-10 17:07:43 -07:00
9b6dfcab73
chore(telemetry): correct Path Confusion loop breaker implementation
2026-06-10 12:16:42 -07:00
62d78e088f
chore(telemetry): resolve loop crash caused by Temporal Dead Zone hoisting and fix conversational budget mapping
2026-06-10 12:04:13 -07:00
92ad20946c
feat(orchestration): implement state-based loop governor with forced checkpoints, phase events, and robust tool signatures
2026-06-10 11:55:17 -07:00
8eb941f1d9
chore(telemetry): implement robust path-confusion stall guard, persist verify signatures correctly, and redact secrets from telemetry logs
2026-06-10 11:38:49 -07:00
0e579be136
chore(telemetry): loosen error normalization to preserve status codes and line numbers for accurate verification signatures
2026-06-10 11:12:29 -07:00
6cbe7c2515
chore(telemetry): resolve universal path normalizer logic and path-confusion tracking
2026-06-10 11:08:42 -07:00
b1ad4fb363
feat(telemetry): implement phase-based execution loop and adaptive tool budgets
2026-06-09 18:58:12 -07:00
ee8109c927
chore(telemetry): add path-confusion loop breaker and strict blank-preview diagnostic protocol
2026-06-09 16:27:09 -07:00
eca23d2266
chore(telemetry): replace fragile regex path normalization with bulletproof path.posix.resolve
2026-06-09 16:25:51 -07:00
7917ad2b37
chore(telemetry): remove hardcoded legacy getacquired slug from universal path normalizer
2026-06-09 16:21:12 -07:00
0ae3748ec4
chore(telemetry): implement universal path normalizer and omni-reaper to prevent preview sprawl
2026-06-09 16:11:31 -07:00
69f7e79266
chore(telemetry): add path-confusion loop breaker and strict blank-preview diagnostic protocol
2026-06-09 16:10:45 -07:00
f1e1d1e753
chore(telemetry): verify signature comment and cleanup
2026-06-09 15:35:46 -07:00
5409d651b3
ux(chat): tune silent-loop status nudge threshold to 6 rounds and strip leaked tool trace payloads from UI
2026-06-09 15:02:34 -07:00
d5d5d6e8d4
chore(telemetry): align shell_exec and dev_server_start cwd to flattened workspace root
2026-06-09 14:59:42 -07:00
173eabd8bf
chore(telemetry): jack up MAX_TOOL_ROUNDS to 150 for ultimate custom app-building runway
2026-06-09 14:30:36 -07:00
65c8dcb6dc
chore(telemetry): jack up MAX_TOOL_ROUNDS to 150 for ultimate custom app-building runway
2026-06-09 14:18:44 -07:00
1301819501
chore(telemetry): raise MAX_TOOL_ROUNDS to 60 for complete engineering runway
2026-06-09 14:16:31 -07:00
341e40c8d5
chore(telemetry): align attached-file reader to flattened project root path
2026-06-09 13:38:32 -07:00
bb63755dcd
chore(telemetry): refactor stall detector to track real state progress and persist non-null verify signatures across edit rounds
2026-06-09 13:36:30 -07:00
5026cc64a3
chore(telemetry): flatten the project slug layer and remove cd path instructions from system prompt
2026-06-09 13:28:57 -07:00
649cf0279c
ux(mcp): resolve tool-pill red X contradiction inside Playwright browser crawler
2026-06-09 12:42:53 -07:00
9d32747e07
chore(telemetry): optimize state-based loop stall detector by tracking tool input signatures and clean up unused helper functions
2026-06-09 12:23:20 -07:00
4caf7755bf
chore(telemetry): implement state-based loop governor, 180s tool timeout, visual-qa path fix, and fs_write diff-guard
2026-06-09 12:05:15 -07:00
bf2b4f966a
chore(telemetry): add bulletproof mcp_token sanitization and read-only mode fallback in chat route
2026-06-09 10:47:32 -07:00
1f2fbd1115
chore(telemetry): fix agent loops, name mangling, dev server leaks, CWD alignment, and add daily session auditor
2026-06-08 16:09:58 -07:00
2e5a03f273
fix(agency): add force-dynamic to workspace api route to prevent aggressive next.js cache
2026-06-08 13:23:07 -07:00
d9057b922d
feat(auth): make Name field required on signup
2026-06-08 10:45:26 -07:00
c1d37184eb
feat(frontend): email+password auth, /signin + /signup pages, marketing consolidation, onboarding workspace naming + full data persistence
2026-06-06 20:28:38 -07:00
16a545a26a
feat: complete live-verified GTM onboarding flow & places autocomplete search proxies
2026-06-06 17:53:13 -07:00
28a959ea5a
fix(db): cast project_id to uuid in agent_sessions INSERT query
2026-05-30 12:40:14 -07:00
775c42e2fa
fix(auth): allow empty string appPath inside session-creation route
2026-05-29 19:23:06 -07:00
3cb079f6e4
feat(auth): enable requireWorkspacePrincipal on agent/sessions routes to support desktop API keys
2026-05-29 19:08:23 -07:00
a8b55b7d8f
feat(auth): enable requireWorkspacePrincipal on individual project GET/PATCH routes to support desktop API keys
2026-05-29 18:48:28 -07:00
7a3b964fb2
feat(auth): enable requireWorkspacePrincipal on projects GET route to support desktop API keys
2026-05-29 17:06:23 -07:00
2a8bc25804
feat: added desktop sso endpoints
2026-05-28 16:05:47 -07:00
2647919bd5
feat(refactor): live zed-style codebase files autocomplete and context attachment
2026-05-21 17:20:31 -07:00
50f65e337d
feat(refactor): premium zed-style chat UI, collapsible reasoning, and comprehensive strict type sweeps
2026-05-21 17:05:42 -07:00
8323108f96
feat(ai): configure Architect mode prompt with Spec Kit templates and enforce task completion rules in background runner
2026-05-19 19:40:23 -07:00
2b799e4907
feat(ai): automate end-to-end PRD, architecture, and task generation directly from Objective
2026-05-19 19:32:07 -07:00
1da2a0b166
fix(ai): bump roundSinceText cutoff to 30 to prevent panic loops
2026-05-19 15:26:15 -07:00
5309a72206
fix(api): delete legacy atlas and advisor agent endpoints
2026-05-19 15:09:59 -07:00
0a4b3af327
fix(ai): restore thinking animations for gemini streams
2026-05-19 14:53:24 -07:00
6a083ff261
fix(ai): bump loop-breaker limits from 16 to 30 to permit long autonomous workflows
2026-05-19 14:51:45 -07:00
