Commit Graph

3952 Commits

Author SHA1 Message Date
diegosouzapw
8c11acaa33 feat(quota): per-pool usage-log endpoint + card 2026-05-31 11:31:20 -03:00
diegosouzapw
18b615f5f0 feat(quota): show per-account upstream quota in the pool card
Adds a read-only AccountQuotaRow component that fetches cached quota data
from GET /api/usage/provider-limits (same endpoint as ProviderLimits.tsx)
and renders a compact per-connection quota summary (% remaining + reset
countdown) inside each PoolCard, below the dimensions section and before
the BurnRateChart. Fail-softs to "—" on error / empty / loading state.
2026-05-31 11:21:25 -03:00
diegosouzapw
d490a30b58 feat(quota): pool budget = per-account limit × account count (summed balde)
A pool with N same-type connections now has an effective budget of
perAccountLimit × N per dimension. Only the limit fed to fair-share
scales — consumption (pool-keyed shared bucket) is unchanged.
2026-05-31 11:09:25 -03:00
diegosouzapw
4157fbe7a9 feat(quota): balance + failover across same-provider accounts (N-step fill-first combo)
Replace the (connId × modelId) upsert loop in syncQuotaCombos with a
model-grouped build: one combo per model with ALL connections as steps
and strategy "fill-first", fixing the collision where a second same-provider
connection overwrote the first (last upsert won, only one account ever used).
2026-05-31 11:02:18 -03:00
diegosouzapw
2521c09119 feat(quota): one provider per pool (block mixed-type) — server guard + wizard filter
- Add assertSingleProvider() helper in quotaPools.ts: queries provider_connections
  with DISTINCT provider WHERE id IN (...), throws if >1 provider detected.
- Call guard early in createPool (when connectionIds.length > 1) and updatePool
  (when input.connectionIds.length > 1), before any DB writes.
- Add lockedProvider useMemo in PoolWizard.tsx: derived from first selected
  connection; availableConnections filtered to same provider once locked.
- Show wizardSingleProviderNote i18n hint in step 1 when lockedProvider is set.
- Add wizardSingleProviderNote to en.json + pt-BR.json (parity).
- New test: tests/unit/quota-pool-single-provider.test.ts (4 cases).
- Update tests/unit/quota-multiprovider.test.ts: all D2 tests now use two
  same-provider connections (both PROVIDER_A/openrouter) — the tests were
  exercising connection-plumbing (scope, enforce membership, combo fan-out),
  not mixed-provider behavior per se; updated to remain valid under Task 3 rule.
2026-05-31 10:53:02 -03:00
diegosouzapw
bbc4c575e0 feat(quota): explain key-enable + exclusive behavior in concept card 2026-05-31 10:41:22 -03:00
diegosouzapw
767fad3d5c feat(quota): 2-column responsive grid for pool cards 2026-05-31 10:38:18 -03:00
diegosouzapw
cf9a78ad32 fix(quota): unwrap pool usage response so quota-share page renders pools with allocations
GET /api/quota/pools/[id]/usage returns { usage: snapshot }, but usePoolUsage
stored the whole wrapper, leaving usage.dimensions undefined. StackedAllocationBar
then dereferenced usage.dimensions[dimensionIndex] (undefined[0]) and crashed the
entire quota-share page for any pool that has allocations. Unwrap data.usage in the
hook + defensively guard usage.dimensions?.[i] / dim.perKey ?? [] in the bar.
2026-05-31 08:39:05 -03:00
diegosouzapw
209d0b5ae4 test(build): expect app/peer-stamp.mjs in pack-artifact required paths 2026-05-31 07:00:08 -03:00
diegosouzapw
a9f1e7f5b4 fix(build): ship app/peer-stamp.mjs in npm pack (server-ws.mjs hard-dep)
server-ws.mjs imports ./peer-stamp.mjs but the npm-pack path didn't include it:
prepublish.ts didn't copy it and pack-artifact-policy pruned it (not in the
app/ allowlist). Without it the WS wrapper throws ERR_MODULE_NOT_FOUND on boot
and the peer-IP stamp (authz LOCAL_ONLY locality) never runs. Copy it in
prepublish + allowlist + mark required so a regression fails the pack.
2026-05-31 06:58:35 -03:00
diegosouzapw
816ba12599 docs(authz): document OMNIROUTE_PEER_STAMP_TOKEN in .env.example + ENVIRONMENT.md
Satisfies the env/docs contract check (the per-process peer-stamp secret is
referenced in code; the auto-loader generates it, so it's documented as an
optional/auto var alongside OMNIROUTE_WS_BRIDGE_SECRET).
2026-05-31 01:36:54 -03:00
diegosouzapw
d07d3dcdaf fix(quota): orphan pool (no valid connection) must not contribute its slug to key scope
D2 moved poolSlug collection outside the connection loop, so a pool whose only
connection was deleted still leaked its slug into resolveQuotaKeyScope — that
slug has no quotaShared-* models behind it. Gate the slug on >=1 valid member
connection (restores Phase-A2 behavior for multi-connection pools).
2026-05-31 01:36:53 -03:00
diegosouzapw
009c928d0a fix(build): copy server-ws.mjs + peer-stamp + responses-ws-proxy into standalone output
Docker runs the Next standalone build (run-standalone.mjs), which now prefers
server-ws.mjs — but build-next-isolated.mjs only copied run-standalone.mjs, not
the WS wrapper or its deps, so Docker fell back to bare server.js with no peer
stamp (LOCAL_ONLY routes 403, CLI token broken — fail-closed but unusable).
Co-locate all three at the standalone root so the peer stamp runs in Docker too.
(The npm package path already ships them via prepublish.ts.)
2026-05-31 01:26:54 -03:00
diegosouzapw
729252008b fix(authz): close 2nd Host-spoof path (cliTokenAuth) + IPv6 loopback + Docker stamp
Adversarial review of the peer-IP fix surfaced: (1) CRITICAL — cliTokenAuth.ts
still derived loopback from new URL(request.url).hostname (the same spoofable
Host class), letting a remote caller with a stolen CLI token reach management
APIs via Host: 127.0.0.1; now it trusts the middleware-stamped locality verdict
(AUTHZ_HEADER_PEER_LOCALITY, a client-stripped trusted header). (2) HIGH —
isLoopbackHost mangled bare IPv6 (::1, ::ffff:127.0.0.1) via split(":")[0],
a fail-closed DoS on IPv6 deploys. (3) HIGH — the Docker entrypoint ran bare
server.js (no peer stamp); run-standalone.mjs now prefers server-ws.mjs.
2026-05-31 01:15:27 -03:00
diegosouzapw
0a09fa5a11 fix(authz): trust real TCP peer IP stamp over spoofable Host header for LOCAL_ONLY gate
The middleware runtime exposes no socket, so a prior fix derived LOCAL_ONLY
locality from the Host header — letting a remote caller send Host: 127.0.0.1
and reach spawn-capable routes (RCE class). The custom Node servers now stamp
the real socket.remoteAddress into a token-signed internal header; the policy
trusts only a stamp whose token matches this process's secret, and fails closed
otherwise. Preserves the owner-authorized loopback + private-LAN access without
trusting any client-controlled header.
2026-05-31 00:43:48 -03:00
diegosouzapw
b93cde7507 fix(quota): wire multi-provider icons into pool card (D3 dead-code gap) 2026-05-31 00:09:52 -03:00
diegosouzapw
acd517eb1e feat(quota): multi-connection pool wizard — select N providers, all models available (Phase D3)
- PoolCreateSchema: add optional connectionIds[] + .refine() that enforces primary membership
- PoolWizard: replace single-select dropdown with checkbox multi-select; first checked = primary (badge); step-2 adds helper note for additional connections; step-3 preview grouped by provider with +N more; POST body sends both connectionId and connectionIds
- PoolCard: optional providers[] prop renders a row of ProviderIcon (up to 3 + badge) instead of a single icon when pool has multiple connections
- i18n: 4 new keys added to both en.json and pt-BR.json (wizardConnectionsLabel, wizardPrimaryBadge, wizardAdditionalConnectionsNote, wizardPreviewMoreModels) — parity maintained (23 wizard keys each)
- Tests: quota-pool-wizard-multi.test.ts (21 tests) covering schema accept/reject, structural wizard assertions, and i18n parity
2026-05-30 23:03:21 -03:00
diegosouzapw
e5a624d0ec feat(quota): propagate N pool connections through scope, combos, enforce (Phase D2)
- quotaKey.ts (resolveQuotaKeyScope): iterate pool.connectionIds (fall back to
  [connectionId] for un-backfilled rows); each connection contributes its own
  connId + provider to the scope. poolSlugs logic unchanged (one slug per pool).
- quotaCombos.ts (syncQuotaCombos): replace single-connection resolvePoolProvider
  with resolvePoolForSync that returns all connectionIds; iterate each connId to
  build the desiredNames union across all providers; upsert combos pinned to the
  CORRECT per-connection connId; prune against the full union so only truly stale
  combos (no longer produced by any current connection) are deleted.
- enforce.ts (enforceQuotaShare + recordConsumption): both pool-matching loops
  changed from equality (p.connectionId === input.connectionId) to membership
  (p.connectionIds.includes) with fallback for un-backfilled rows. Fail-open
  (B16) and pool-level dimension key semantics are preserved unchanged.
- quotaPools.ts: no logic change needed — connectionIds already flows through
  getPool (D1); syncQuotaCombosGuarded passes poolId and syncQuotaCombos
  resolves the full QuotaPool internally.
- tests/unit/quota-multiprovider.test.ts: 6 new tests covering D2 (scope,
  enforce primary/secondary membership, combos 2-provider create + prune).
  All 22 tests pass (14 new + 8 existing enforce + pool-connections suites).
2026-05-30 22:44:50 -03:00
diegosouzapw
428947207f test(quota): align sidebar-costs-section to 4 items after C2 Plans retirement 2026-05-30 22:35:45 -03:00
diegosouzapw
69acd664d7 feat(quota): pool can span N connections — quota_pool_connections join table (Phase D1)
Adds migration 086 to create the `quota_pool_connections` join table with a backfill
that seeds every existing pool's single connection_id as its first member. Updates
QuotaPool type with `connectionIds: string[]`, wires createPool/updatePool/deletePool
to maintain the join table transactionally, and keeps `connection_id` as the primary
back-compat column synced to `connectionIds[0]`.
2026-05-30 22:32:02 -03:00
diegosouzapw
2300db6cc5 feat(quota): retire standalone Plans screen, unified into pool wizard (Phase C2)
Remove plans/ route and sidebar entry; PoolWizard Step 2 now covers plan-dimensions inline.
2026-05-30 22:15:27 -03:00
diegosouzapw
62de5a83b8 feat(quota): 3-step pool wizard unifying connection, plan and key allocation (Phase C1) 2026-05-30 22:08:41 -03:00
diegosouzapw
6a14c31280 feat(quota): reconcile key allowedQuotas when pool allocations saved as exclusive (Phase C3) 2026-05-30 21:56:05 -03:00
diegosouzapw
3742afcd64 feat(quota): /v1/models lists only quotaShared-* models for quota-exclusive keys (Phase B3) 2026-05-30 21:41:13 -03:00
diegosouzapw
78c5a30cf9 feat(quota): restrict quota-exclusive keys to their quotaShared-* models (Phase B4) 2026-05-30 21:35:41 -03:00
diegosouzapw
49f6092099 feat(quota): auto-sync quotaShared-* combos on pool allocation changes (Phase B2)
Mints one combo per model of the pool's provider when a quota pool is
created/updated/reallocated, and prunes stale quota combos on deletion.
2026-05-30 21:23:08 -03:00
diegosouzapw
6214ea6768 feat(quota): add quotaShared-* virtual model naming helpers (Phase B1) 2026-05-30 21:12:30 -03:00
diegosouzapw
a921300a53 feat(quota): force quota-exclusive keys onto pool connection in account selection (Phase A4) 2026-05-30 21:00:36 -03:00
diegosouzapw
8316c618b2 feat(quota): enforce quota-exclusive keys by pool provider (Phase A3)
Keys with non-empty allowedQuotas may only use models whose provider belongs
to their pools' provider set; anything outside → 403 QUOTA_ONLY.
Normal allowedModels/allowedCombos checks are bypassed for quota-exclusive keys.
2026-05-30 20:53:35 -03:00
diegosouzapw
c29d6ed7a4 feat(quota): add resolveQuotaKeyScope helper (Phase A2)
Introduces src/lib/quota/quotaKey.ts with resolveQuotaKeyScope(), a
pure async helper that maps an API key's allowedQuotas pool-ID list to
the concrete connectionIds and provider slugs it is permitted to use.
Covers empty/null/undefined input, missing pools, orphaned connectionIds,
and multi-pool deduplication. No behaviour change to existing code paths.
2026-05-30 20:40:33 -03:00
diegosouzapw
51b586c2af feat(quota): add allowed_quotas allow-list field to api_keys (Phase A1) 2026-05-30 18:58:23 -03:00
diegosouzapw
6b0e89fb42 fix(authz): derive LOCAL_ONLY locality from Host header (middleware has no socket IP)
The authz pipeline runs in the Next middleware runtime (proxy.ts -> runAuthzPipeline)
where ctx.request is a NextRequest with no .socket/.ip. requestPeerAddress therefore
returned null, so isLoopbackRequest was ALWAYS false and every LOCAL_ONLY path 403'd
even from loopback (Services/MCP/Traffic-Inspector were unusable). Read the Host
header instead — exactly what isLoopbackHost/isPrivateLanHost were built to parse —
which restores loopback and, combined with isPrivateLanHost, enables the
owner-authorized private-LAN access. Spawn-capable endpoints still require
manage-scope auth after this gate.
2026-05-30 18:20:39 -03:00
diegosouzapw
270c2eb925 fix(i18n): add missing settings proxy tab labels (proxyGlobalConfigTab/proxyPoolTab/freePoolTab/proxyDocumentationTab) 2026-05-30 17:51:34 -03:00
diegosouzapw
5a61ae9a98 feat(authz): allow LOCAL_ONLY paths from private-LAN peer IPs (owner-authorized)
Services + Traffic-Inspector (LOCAL_ONLY, spawn-capable) returned 403 when the
dashboard was reached via the LAN IP (192.168.0.x) instead of loopback. Add
isPrivateLanHost (RFC1918 IPv4 + IPv6 ULA/link-local) and widen ONLY the
local-only PATH gate to accept private-LAN socket peer IPs — based on the real
socket peer address (not the spoofable Host header), so public-internet clients
present public IPs and stay blocked. The CLI-token gate stays strictly loopback;
paths remain LOCAL_ONLY-classified (Hard Rules 15/17 unchanged). Enforcement-layer
carve-out for a LAN-deployed instance, authorized by the operator.
2026-05-30 17:26:10 -03:00
diegosouzapw
6095842ef0 fix(quota-share): guard usage.dimensions to stop "reading 'length'" ISE
The pool usage snapshot can come back without a dimensions array (e.g. when the
plan resolves to empty for catalog-only providers). PoolCard.computeStatus and
hasDimensions read usage.dimensions.length directly, crashing the whole page
("Cannot read properties of undefined (reading 'length')"). Normalize to [] in
PoolCard and in usePoolsUsageAggregate (dimensions/perKey).
2026-05-30 16:52:09 -03:00
diegosouzapw
f1d0416d72 feat(search-tools): Compare shows full results in side-by-side columns (Layout A)
- Capture full search results (title/url/snippet) per provider, not just URLs.
- Render one column per selected provider: metrics header + result list
  (title link, snippet, url), horizontal scroll for N providers.
- Mark results whose URL appears across providers with a star (overlap).
- Remove the 4-provider cap (MAX_PROVIDERS); add Select all / Clear; compare
  every configured provider. Raise max_results 5 -> 10.
2026-05-30 14:57:31 -03:00
diegosouzapw
36c276a6d7 feat(playground): Compare freeze fix, Chat provider/model selects, Build wizard (Phase 4)
- Chat (StudioConfigPane): add Provider + Model selects reusing the translator
  hooks; order Endpoint -> Provider -> Model; ConfigState gains optional provider.
- Compare (CompareTab): add a user-prompt input and include it in the request
  body; throttle per-column stream updates via requestAnimationFrame to stop the
  UI freeze (was setColumns per chunk x N columns with an empty user message).
- Build (BuildTab + build/BuildWizard): redesign as a guided 3-step wizard
  (What to test -> Configure -> Run) reusing ToolsBuilder/StructuredOutputEditor;
  all run/tool-call handlers preserved.
- i18n: playground.build.* (18 keys) in en + pt-BR.
2026-05-30 12:54:58 -03:00
diegosouzapw
8eacd78be4 feat(memory): health auto-check, enable toggle, sqlite-vec hint (Phase 3)
- MemoriesTab: auto-run health check on mount + poll every 30s (was manual-only).
- page: add enable/disable memory toggle (role=switch) via useMemorySettings.save({ enabled }).
- MemoryEngineStatus: show "npm install sqlite-vec" hint when vector store backend is "none".
- i18n: memory.memoryEnabled + memory.engine.vectorStoreInstallHint (en + pt-BR).
2026-05-30 12:45:27 -03:00
diegosouzapw
a03d7b40d7 fix(audit): translate event types and A2A task states (Phase 2)
- Add compliance.eventTypes (36 labels) to en.json + pt-BR.json.
- ComplianceTab: render translated label via t.has/t fallback instead of raw entry.action.
- A2aAuditTab: render translated task state via a2aState* keys instead of raw task.state.
- Memory type/strategy dropdowns needed no i18n change — keys already exist; the
  Phase 1 Select fix makes them render.
2026-05-30 12:38:23 -03:00
diegosouzapw
a59a90e6a1 fix(dashboard): v3.8.8 screen quick wins (Phase 1)
- search-tools: export modal no longer opens by default / stuck — guard on
  exportOpen and drop the invalid isOpen prop the modal never read.
- logs: remove duplicate proxy/console tabs + SegmentedControl (dedicated
  /dashboard/logs/proxy and /console pages already exist in the menu).
- memory: order tabs Memories -> Engine -> Playground.
- ui(Select): render children and suppress the placeholder/options branch when
  children are provided — fixes the "empty" memory type/strategy dropdowns
  (children were being shadowed by the component's own option list).
- test: source-level regression guards for all four.
2026-05-30 12:31:08 -03:00
diegosouzapw
cad06d85a6 fix(agent-bridge): strip non-serializable handler before Server→Client boundary
The /dashboard/tools/agent-bridge page (Server Component) passed ALL_TARGETS
directly to AgentBridgePageClient (a Client Component). Each MitmTarget carries
a `handler: () => Promise<...>` function, which Next.js forbids across the
Server/Client boundary, raising at SSR time:
  "Functions cannot be passed directly to Client Components ..."
This broke the whole page ("erro ao carregar").

Fix: introduce MitmTargetView = Omit<MitmTarget, "handler"> and pass a
sanitized array (ALL_TARGETS.map(({ handler, ...rest }) => rest)). The UI never
invokes handler, so behavior is unchanged. Adds a regression test asserting the
sanitized targets are function-free and JSON-serializable.
2026-05-30 11:06:38 -03:00
diegosouzapw
468354f8ff clean 2026-05-30 10:06:02 -03:00
diegosouzapw
37890ba007 chore: remove audit logs tab from logs page
Remove the AuditLogTab from the dashboard logs page now that audit logs
live under the dedicated /dashboard/audit route. Update integration wiring
expectations and add metadata frontmatter to studio framework docs.
2026-05-30 09:11:17 -03:00
Diego Rodrigues de Sa e Souza
9515375114 Merge pull request #2869 from diegosouzapw/refactor/pages-v3-C-playground-search-tools
feat(playground,search-tools): Playground Studio + Search Tools Studio (planos 17+18)
2026-05-30 04:30:57 -03:00
diegosouzapw
18641c9d87 fix(docs): document 2 PLAYGROUND_* env vars in ENVIRONMENT.md (env-doc-sync drift) 2026-05-30 04:30:25 -03:00
diegosouzapw
ac0e9d5272 Merge release/v3.8.8 into refactor/pages-v3-C (Playground + Search Tools Studio — plans 17+18)
Conflicts: migration 076_playground_presets->084; localDb/.env union; REPOSITORY_MAP dedup; package.json keep base (version 3.8.7, coverage --functions 40); .source regenerated (+3 docs); deps cli-table3/wtfnode/@types/bun/uuid (npm install).

i18n pt-BR: 19 collisions — 18 playground keys -> HEAD pt-BR translations (base had untranslated EN: Send->Enviar, Cancel->Cancelar etc), costsSection -> base Custos. Rule: prefer side != en.json (translated).

openapi: --theirs base + 3 playground/search paths + 2 schemas + 1 tag (js-yaml surgical insert; union-blind breaks YAML). No open-sse, typecheck:core 0 errors.
2026-05-30 04:19:49 -03:00
Diego Rodrigues de Sa e Souza
b7242579f4 Merge pull request #2873 from diegosouzapw/refactor/pages-v3-21-memory-engine-redesign
feat(memory): memory engine redesign — sqlite-vec + hybrid RRF + Studio UI (plan 21)
2026-05-30 04:13:23 -03:00
diegosouzapw
dd8f7aa6a1 Merge release/v3.8.8 into refactor/pages-v3-21 (Memory engine redesign — sqlite-vec + RRF + Studio)
Conflicts: migration 073_memory_vec->083; localDb/.env/REPOSITORY_MAP union; request.ts->base; i18n auto-merged; .source regenerated (+3 docs).

openapi: --theirs base + surgically inserted 14 memory paths + 4 schemas + Memory tag via js-yaml extract (union-blind broke YAML structure). +938 lines, base formatting preserved, gen-openapi validates.

deps: @huggingface/transformers + sqlite-vec added (package.json); npm install ran, lock regenerated. chatCore auto-merged (memory + quota hooks coexist, transform OK). typecheck:core 0 errors.
2026-05-30 04:04:20 -03:00
Diego Rodrigues de Sa e Souza
6253f31166 Merge pull request #2849 from diegosouzapw/refactor/pages-v3-20-batch-files-functional-redesign
feat(batch): functional & explanatory redesign for /batch + /batch/files
2026-05-30 03:51:35 -03:00
diegosouzapw
f4605828b1 Merge release/v3.8.8 into refactor/pages-v3-20 (Batch files functional redesign)
Conflicts: CLAUDE.md base; i18n en/pt-BR deep-merge — 3 apiManager keys resolved to base pt-BR translations (HEAD had stale EN), costsSection=Custos; .source --theirs+regenerated. 40 other locales auto-merged. No migrations/open-sse. Batch redesign confirmed complete in prior code review.
2026-05-30 03:42:04 -03:00