Commit Graph

4934 Commits

Author SHA1 Message Date
diegosouzapw
914583d580 docs(a2a): add list-capabilities skill entry
Update Available Skills table from 5 to 6 skills.
Add list-capabilities skill with full columns: ID, description, tags, examples.
Add detail subsection explaining the markdown table artifact format,
rawUrl column, metadata.totalSkills, and link to AGENT-SKILLS.md.
2026-05-28 01:10:18 -03:00
diegosouzapw
2ee80c6702 docs(mcp): add omniroute_agent_skills_* tools + read:catalog scope
Add "Agent Skill Catalog Tools (3)" section after Skill Tools (4):
- omniroute_agent_skills_list (read:catalog)
- omniroute_agent_skills_get (read:catalog)
- omniroute_agent_skills_coverage (read:catalog)

Add read:catalog row to Authentication & Scopes table.
Update count in section intro (40 tools total, including 3 new catalog tools).
2026-05-28 01:10:03 -03:00
diegosouzapw
712b00346c docs(agent-skills): add AGENT-SKILLS.md + cross-link in SKILLS.md
Add docs/frameworks/AGENT-SKILLS.md (~190 lines):
- Overview of the 42-entry dynamic catalog (22 API + 20 CLI)
- Architecture map: catalog.ts, generator.ts, openapiParser.ts,
  cliRegistryParser.ts, schemas.ts, types.ts
- SKILL.md format with custom-block documentation
- REST API discovery reference table
- MCP tools table (omniroute_agent_skills_list/get/coverage)
- A2A list-capabilities invocation example
- Full 42-ID catalog tables (API + CLI)
- External agent consumption guide (REST/MCP/A2A/GitHub raw)
- Generator usage (dryRun/prune/onlyIds)
- Coverage API reference

Update docs/frameworks/SKILLS.md:
- Add "## Agent Skills vs Omni Skills" section at top with comparison table
- Link to AGENT-SKILLS.md
2026-05-28 01:09:47 -03:00
diegosouzapw
e7a1bf1c24 test(agent-skills): integration tests for discovery + content + MCP + A2A
Add tests/integration/agent-skills-discovery.test.ts (13 tests):
- Verifies every API_SKILL_IDS + CLI_SKILL_IDS has skills/<id>/SKILL.md on disk
- Validates frontmatter name + description present in each SKILL.md
- Validates body >= 100 chars per SKILL.md
- Verifies MCP omniroute_agent_skills_list handler returns 42 entries
- Verifies A2A list-capabilities returns 1 artifact containing all 42 IDs

Add tests/integration/agent-skills-content.test.ts (16 tests):
- Confirms all 42 catalog IDs have skills/{id}/ directory + SKILL.md
- Confirms 0 omniroute-* directories remain (post-prune)
- Confirms exactly 10 IDs have skill:custom-start/end blocks
  (omni-mcp, omni-compression, cli-providers, cli-eval, omni-agents-a2a,
   omni-combos-routing, omni-auth, omni-resilience, omni-inference, cli-serve)
- Confirms no unclosed custom blocks
2026-05-28 01:09:32 -03:00
diegosouzapw
02bc079ef9 feat(memory): add embedding layer — remote/static/transformers/cache (plan 21 F3)
Implements the multi-source embedding layer for the Memory Engine Redesign (plan 21).
Adds 5 production modules under src/lib/memory/embedding/:
- cache.ts: LRU+TTL in-memory cache (max=1000, TTL=5min, sha256 keyed)
- remote.ts: delegates to createEmbeddingResponse(), maps HTTP 401/403→no_key, 429→rate_limited, AbortError→timeout; all errors via sanitizeErrorMessage()
- staticPotion.ts: download-once potion-base-8M (JS-only WordPiece tokenizer + mean pooling, no WASM)
- transformersLocal.ts: lazy await import('@huggingface/transformers') singleton pipeline (Xenova/all-MiniLM-L6-v2, q8)
- index.ts: resolveEmbeddingSource (pure, sync), embed (cached dispatch), listEmbeddingProviders, invalidateEmbeddingCache

Also adds @huggingface/transformers and sqlite-vec to dependencies, and registers
@huggingface/transformers in next.config.mjs serverExternalPackages (D8/D25).

6 unit test files: cache (9), resolve (14), remote (10), static-potion (13), transformers (6), list-providers (8) — all 60 tests green.
2026-05-28 00:40:56 -03:00
diegosouzapw
4b0bda9b91 Merge F8 (MonitorTab) into refactor/pages-v3-19 2026-05-28 00:31:11 -03:00
diegosouzapw
cf88675917 Merge F7 (CompressionPreviewAccordion) into refactor/pages-v3-19 2026-05-28 00:31:10 -03:00
diegosouzapw
2e756b8789 Merge F6 (TestBenchAccordion) into refactor/pages-v3-19 2026-05-28 00:31:08 -03:00
diegosouzapw
c4853a4ce1 Merge F5 (StreamTransformerAccordion) into refactor/pages-v3-19 2026-05-28 00:30:51 -03:00
diegosouzapw
52b9192d83 Merge F4 (AdvancedSection/RawJsonPanel/PipelineView) into refactor/pages-v3-19 2026-05-28 00:30:50 -03:00
diegosouzapw
9a8554de9e Merge F3 (SimpleControls/ResultNarrated/TranslateTab) into refactor/pages-v3-19 2026-05-28 00:30:48 -03:00
diegosouzapw
0820ec453b feat(translator): add SimpleControls, ResultNarrated, TranslateTab (F3) 2026-05-28 00:29:35 -03:00
diegosouzapw
0c38ed57ec test(api): integration tests for agent-bridge routes (F5)
4 integration test files covering: happy paths for all 8 major routes,
LOCAL_ONLY classification assertion, Zod 400 paths, cert flow (status/trust/
download/regenerate), bypass CRUD (POST/GET/DELETE), mappings PUT→GET
round-trip. Every error path asserts no stack trace leakage (Hard Rule #12).
Total: 41 tests, 41 pass.
2026-05-28 00:24:48 -03:00
diegosouzapw
19c4ff9bb0 feat(api): agent-bridge state + server + agents + cert + bypass + upstream-ca routes (F5)
12 REST routes under /api/tools/agent-bridge/ covering all AgentBridge
backend surfaces: server lifecycle, per-agent state/DNS/mappings/detect,
cert status/download/regenerate, bypass pattern CRUD, upstream CA config.
All routes use Zod validation and route errors through sanitizeErrorMessage.

feat(authz): mark agent-bridge LOCAL_ONLY + SPAWN_CAPABLE (F5)

Adds /api/tools/agent-bridge/ to both LOCAL_ONLY_API_PREFIXES and
SPAWN_CAPABLE_PREFIXES in routeGuard.ts — satisfying Hard Rules #15 + #17.
2026-05-28 00:24:38 -03:00
diegosouzapw
3852656e8b feat(translator): add AdvancedSection, RawJsonPanel, PipelineView (F4) 2026-05-28 00:19:43 -03:00
diegosouzapw
3a535625b5 Merge F8 into parent: detail pages + move cards to cli-code/components (plan 14) 2026-05-28 00:18:37 -03:00
diegosouzapw
029a1f8e5b Merge F7 into parent: rename /agents → /acp-agents + concept/comparison cards (plan 14) 2026-05-28 00:18:37 -03:00
diegosouzapw
02d5dfb61f Merge F6 into parent: /dashboard/cli-agents page (plan 14) 2026-05-28 00:18:36 -03:00
diegosouzapw
5778043444 Merge F5 into parent: /dashboard/cli-code page (plan 14) 2026-05-28 00:18:35 -03:00
diegosouzapw
2d58519ca9 refactor(dashboard,cli): move cards to cli-code/components + add detail pages /cli-code/[id] + /cli-agents/[id] + ToolDetailClient orchestrator (plan 14 F8)
- git mv cli-tools/components → cli-code/components (history preserved, 15 renames)
- Add isExpanded=false + onToggle=()=>{} defaults to all 12 specialized cards
- Create cli-code/[id]/page.tsx: server component, guards category=code
- Create cli-agents/[id]/page.tsx: server component, guards category=agent
- Create cli-code/components/ToolDetailClient.tsx: orchestrator with isExpanded:true always (D23), header with back-link + vendor/category/baseUrl badges
- Delete cli-tools/CLIToolsPageClient.tsx + cli-tools/page.tsx (accordion-based orchestrator replaced)
- Tests: ToolDetailClient smoke (5), cli-code detail page (3), cli-agents detail page (3) — 11/11 passing
2026-05-28 00:15:04 -03:00
diegosouzapw
2cc0f5bb5b test(playground): cover hooks and streamMetrics 2026-05-27 23:59:47 -03:00
diegosouzapw
06210da48f feat(playground): add useToolsBuilder/useStructuredOutput hooks 2026-05-27 23:59:41 -03:00
diegosouzapw
a180725f56 feat(playground): add usePresets/useImprovePrompt hooks 2026-05-27 23:59:35 -03:00
diegosouzapw
c708b1f40c feat(playground): add useStreamMetrics hook 2026-05-27 23:59:30 -03:00
diegosouzapw
2f92399e23 feat(playground): add streamMetrics pure function 2026-05-27 23:59:23 -03:00
diegosouzapw
8b430bfcc9 merge(F9b): apply generator + prune (42 SKILL.md, 18 omniroute-* pruned) 2026-05-27 23:51:38 -03:00
diegosouzapw
f4571094c2 feat(skills): generate 42 SKILL.md (22 API + 20 CLI) + prune 18 omniroute-* orphans 2026-05-27 23:50:13 -03:00
diegosouzapw
591d99ca36 merge(F9a): preserve curated content from 18 old SKILL.md via markers + archive 2026-05-27 23:41:08 -03:00
diegosouzapw
2e1862192e feat(skills): preserve curated content from 18 old SKILL.md via custom-start/end markers + archive
Migrates 1560 lines of curated content from 18 omniroute-* skill files
into 10 new destination SKILL.md placeholders using the generator-safe
<!-- skill:custom-start --> ... <!-- skill:custom-end --> markers so
F9b --apply preserves them instead of overwriting.

Mappings:
- omniroute → omni-auth (direct)
- omniroute-chat + image + tts + stt + embeddings + web-search + web-fetch → omni-inference (aggregated, 7 sections)
- omniroute-mcp → omni-mcp (direct)
- omniroute-a2a → omni-agents-a2a (direct)
- omniroute-routing → omni-combos-routing (direct)
- omniroute-compression → omni-compression (direct)
- omniroute-monitoring → omni-resilience (direct)
- omniroute-cli + omniroute-cli-admin → cli-serve (aggregated, 2 sections)
- omniroute-cli-providers → cli-providers (direct)
- omniroute-cli-eval → cli-eval (direct)
- omniroute-cli-cloud → archived only (no direct equivalent)

Archive: all 18 originals copied to
_tasks/features-v3.8.6/refactorpages/_orchestration/15-pruned-archive/
2026-05-27 23:39:44 -03:00
diegosouzapw
bb312062ea merge(F2): db migrations + memoryVec + localDb re-export 2026-05-27 23:26:22 -03:00
diegosouzapw
d12ce14168 merge(F1): shared foundation (types + schemas) 2026-05-27 23:26:20 -03:00
diegosouzapw
6ba76aa500 test(memory): add edge-case test for getMemoryVecMeta when sentinel row is absent 2026-05-27 23:22:48 -03:00
diegosouzapw
371a7d8dbc feat(dashboard,cli): add /dashboard/cli-agents page for autonomous CLI agents (plan 14 F6) 2026-05-27 23:18:50 -03:00
diegosouzapw
b9f93a5c07 feat(memory): add migration 073, memoryVec CRUD module, and localDb re-export (plan 21 F2)
- 073_memory_vec.sql: creates memory_vec_meta singleton table (active_dim,
  embedding_signature, last_reset_at, vec_loaded) and adds needs_reindex column
  to memories table with a partial index; idempotent via CREATE IF NOT EXISTS +
  INSERT OR IGNORE + migration runner's duplicate-column-name guard
- src/lib/db/memoryVec.ts: implements 6 CRUD functions per §3.8 contract
  (getMemoryVecMeta, setMemoryVecMeta, markMemoryNeedsReindex,
  markAllMemoriesNeedReindex, getMemoryReindexQueue, countMemoryReindexPending)
- src/lib/localDb.ts: adds re-export block for the 6 functions (Hard Rule #2)
- .env.example: documents 7 new MEMORY_* env vars per §3.9
- tests/unit/memory-vec-meta.test.ts: 7 tests (meta get/set, migration idempotency)
- tests/unit/memory-needs-reindex.test.ts: 12 tests (mark/unmark, markAll, queue)
2026-05-27 23:16:05 -03:00
diegosouzapw
5dd75be1b9 test(batch): add integration tests + sanitization asserts + coverage gap fillers (F9)
- Add tests/unit/batches-f9-helpers.test.ts (19 tests, top-level for c8 coverage gate)
  covering uncovered branches: alias-match pricing, blank CSV rows, body.input/prompt paths,
  non-object JSON lines, invalid Anthropic params, body-is-array validation
- Add tests/unit/dashboard/batch/concept-cards.test.tsx (16 tests)
  covering BatchConceptCard + FilesConceptCard: render, toggle, localStorage hydration, sanitization
- Add tests/unit/dashboard/batch/list-regression.test.tsx (15 tests)
  covering BatchListTab + FilesListTab: render N items, Remove-completed flow,
  status/purpose filter, loading/empty states, sanitization
- Add tests/unit/dashboard/batch/sanitization.test.tsx (8 tests)
  covering NewBatchWizard + UploadFileModal + useBatchActions: each error path
  asserts zero stack-trace/path leakage into the UI (D14 / Hard Rule #12)
- Fix bug in validateJsonl.ts: body=array was not caught as invalid
  (typeof array === "object" is true — add Array.isArray guard, 1-line fix)

Local src/lib/batches/ coverage: 100% stmts / 93.7% branches / 100% funcs / 100% lines.
Global coverage gate: 75.96% stmts / 71.97% branches / 75.52% funcs (all above 75/75/75/70).
2026-05-27 23:14:17 -03:00
diegosouzapw
79797cd450 refactor(dashboard,acp): rename /dashboard/agents → /dashboard/acp-agents + use shared concept/comparison cards (plan 14 F7)
- git mv agents/ → acp-agents/ (preserves history)
- useTranslations("agents") → useTranslations("acpAgents")
- Replace inline architecture/comparison cards with <CliConceptCard currentType="acp" /> + <CliComparisonCard currentType="acp" />
- Update all cross-links from /dashboard/cli-tools → /dashboard/cli-code
- Update cliToolsRedirectCta/openCliTools keys → cliCodeRedirectCta
- Update sidebarVisibility: id "agents" → "acp-agents", href "/dashboard/agents" → "/dashboard/acp-agents", i18nKey "agents" → "acpAgents"
- Update HIDEABLE_SIDEBAR_ITEM_IDS and DEVELOPER_SHOWN preset: "agents" → "acp-agents"
- Add tests/unit/ui/AcpAgentsPage.test.tsx (6 vitest tests: smoke, namespace, concept card, comparison card, cross-link, agent grid)
2026-05-27 23:11:58 -03:00
diegosouzapw
ca6413917a test(playground): integration tests for improve-prompt and presets
49 integration tests covering:
- improve-prompt: happy paths (system+prompt, only system, only prompt), auth
  enforcement, upstream error sanitization, malformed body, missing fields
- presets CRUD: full lifecycle (POST→GET list→GET id→PUT partial→DELETE→404),
  params JSON round-trip, UUID validation, null system handling
- presets Zod: all invalid bodies → 400, system > 50000 chars boundary,
  UUID format validation across GET/PUT/DELETE
All error assertions verify no stack trace leakage (Hard Rule #12).
2026-05-27 23:08:09 -03:00
diegosouzapw
c36ba1f864 feat(playground): add improve-prompt route
POST /api/playground/improve-prompt: validates body via ImprovePromptRequestSchema,
calls /v1/chat/completions internally with the user-chosen model (D8), parses
improved content via parseImprovedContent, returns { improvedSystem?, improvedPrompt?,
tokensIn, tokensOut }. Auth optional (REQUIRE_API_KEY gate). All errors route
through buildErrorBody/sanitizeErrorMessage (Hard Rule #12).
2026-05-27 23:07:57 -03:00
diegosouzapw
cb6a8c1641 merge(F4): Inspector core into Group A parent 2026-05-27 23:06:49 -03:00
diegosouzapw
6a5304b79a merge(F3): MITM handlers + targets + server.cjs hook into Group A parent 2026-05-27 23:06:49 -03:00
diegosouzapw
d380883a6e test(search): integration coverage for providers catalog
- 14 tests covering all status transitions (configured/missing/rate_limited)
- Validates 12 search + 3 fetch = 15 provider total count
- Asserts kind field correctness per provider type
- Tests back-compat data array with legacy {id,object,created,name,search_types} shape
- Tests perplexity-search credential fallback to perplexity
- Validates response against SearchProviderCatalogResponseSchema (Zod)
- Tests 401 behavior when auth is required
2026-05-27 23:05:48 -03:00
diegosouzapw
afd68eec71 feat(search): extend /api/search/providers with fetch providers + status
- Adds 3 fetch providers (firecrawl, jina-reader, tavily-search) to the catalog
  with kind='fetch', costPerQuery, freeMonthlyQuota, and fetchFormats metadata
- Replaces raw SQL credential lookup with getProviderCredentials() + isAllRateLimited
  respecting SEARCH_CREDENTIAL_FALLBACKS (e.g. perplexity-search → perplexity)
- Status field: 'configured' | 'missing' | 'rate_limited' per provider
- Validates response against SearchProviderCatalogResponseSchema (defensive, non-blocking)
- Back-compat: legacy `data` array preserved alongside new `providers` array
- Errors routed through buildErrorBody (Hard Rule #12)
2026-05-27 23:05:40 -03:00
diegosouzapw
4cf36ccdce feat(dashboard,cli): add /dashboard/cli-code page with smart status grid + concept/comparison cards (plan 14 F5)
- Server component page.tsx (minimal, passes machineId)
- CliCodePageClient: filters CLI_TOOLS by category=code+baseUrlSupport!=none (19 tools D15)
- Renders CliConceptCard + CliComparisonCard at top, header bar with search/detection/baseUrl
  filters, refresh button, empty-state amber banner when no active providers, 2-col grid
- useToolBatchStatuses (F4) for batch detection; CardSkeleton while loading
- Client-side filtering by name/vendor/description, detection status, baseUrl type
- Cardinality guard: console.warn if count != EXPECTED_CODE_COUNT (non-blocking)
- Test: 11 cases covering smoke, 19 cards, search filter, detection/loading skeleton,
  empty state, concept/comparison cards, refresh refetch, detailHref pattern
2026-05-27 23:05:21 -03:00
diegosouzapw
6236b604ec feat(memory): add shared foundation types, Zod schemas, and roundtrip tests (plan 21 F1)
- src/lib/memory/embedding/types.ts — EmbeddingSource, EmbeddingProviderListing, EmbeddingResolution, EmbeddingResult, EmbeddingError (verbatim §3.1)
- src/shared/schemas/memory.ts — 7 Zod schemas (MemorySettingsExtended, MemoryUpdatePut, RetrievePreview, MemoryReindex, MemorySummarize, EmbeddingProviderListing, MemoryEngineStatus, RetrievePreviewResult) + z.infer types (verbatim §3.2)
- src/shared/schemas/qdrant.ts — 4 Zod schemas (QdrantSettings, QdrantSettingsUpdate, QdrantSearch, QdrantHealthResult) + z.infer types (verbatim §3.3)
- tests/unit/memory-schemas-roundtrip.test.ts — 34 assertions (≥22 required); all pass
2026-05-27 22:54:18 -03:00
diegosouzapw
9343451ca8 docs(agents): atualiza fluxos de release e triagem
Expande os workflows de release para incluir auditoria de segurança,
CHANGELOG completo por commits, quality gate obrigatório, homologação em
VPS local, publicação oficial, deploy em Akamai e validação de artefatos.

Reorganiza a triagem de features com arquivos permanentes por bucket,
suporte a itens em andamento, regra de reclaim após 15 dias e novo
tratamento para ideias viáveis catalogadas.

Corrige a orientação de revisão de discussões para usar a ordem
cronológica real dos comentários e respostas ao identificar a última
atividade.
2026-05-27 22:52:23 -03:00
diegosouzapw
0a4a7fabce feat(batch): add action footer to BatchDetailModal (cancel/download/retry) + tests (F7) 2026-05-27 22:51:31 -03:00
diegosouzapw
e77544876e Merge branch 'feat/playground-search-db-F2' into feat/playground-api-F3 2026-05-27 22:44:18 -03:00
diegosouzapw
5847c3b50e Merge F4 into parent: shared CLI UI components + useToolBatchStatuses hook (plan 14) 2026-05-27 22:43:21 -03:00
diegosouzapw
b30a36fcf1 Merge F3 into parent: settings handlers for new custom configType tools (plan 14) 2026-05-27 22:43:21 -03:00
diegosouzapw
78c846d219 Merge F2 into parent: batch endpoint /all-statuses + cache + DRY refactor (plan 14) 2026-05-27 22:43:20 -03:00