diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 2b72a0e..4d87d3d 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -26,7 +26,7 @@ jobs: python-version: ${{ matrix.python-version }} cache: 'pip' - run: pip install -e ".[dev,observability]" - - run: pytest tests/ -x -q --cov=src/deepresearch --cov-report=term --cov-report=xml + - run: pytest tests/ -x -q --cov=src/deepresearch --cov-report=term --cov-report=term-missing --cov-report=xml - uses: actions/upload-artifact@v4 with: name: coverage-${{ matrix.python-version }} @@ -43,15 +43,12 @@ jobs: - run: pip install ruff - run: ruff check . - run: ruff format --check . - - eslint: - runs-on: ubuntu-latest - steps: - - uses: actions/checkout@v4 - uses: actions/setup-node@v4 with: node-version: "20" - - run: npx eslint@8 src/deepresearch/web/static/js/ --ext .js + - run: npm init -y + - run: npm install --save-dev eslint + - run: npx eslint src/deepresearch/web/static/js/ --ext .js docker: runs-on: ubuntu-latest @@ -74,7 +71,7 @@ jobs: build: runs-on: ubuntu-latest - needs: [test, lint] + needs: [test, lint, docker] steps: - uses: actions/checkout@v4 - uses: actions/setup-python@v5 diff --git a/CHANGELOG.md b/CHANGELOG.md index 2cbad4b..df8a47d 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -2,6 +2,35 @@ All notable changes to DeepeResearch will be documented in this file. +## v0.15.0 (2026-06-29) + +### Added +- Interactive Q&A graph (Issue #52): SVG-based agent interaction visualization +- 3 arrow types: clarification requests (blue), agent responses (orange), follow-ups (green) +- Hover tooltips on edges showing question/answer text via SVG `` elements +- New edge fade-in animation (`fadeInEdge` CSS @keyframes, 0.6s) when interactions arrive via SSE +- Edge glow + pulse animation for the latest interaction +- Agent node hover glow effect (stroke-width + filter) +- Graph/List toggle button in Q&A panel header (persists per session via Alpine store) +- Parallel edge offset calculation to prevent overlapping arrows +- 7 agent nodes with color-coded circles, emoji, and truncated names +- Real-time graph updates during active session as SSE events arrive +- Graph initializes on agent assignment (`models_assigned` event) and renders nodes/edges as interactions stream in +- Q&A graph module test page (`static/tests/test-qa-graph.html`) with 17 functional tests + +### Changed +- `qa-graph.js`: Complete rewrite — added green arrowhead marker, node-glow filter, CSS animation classes, edge hitarea for hover, tooltip content, parallel edge offset, proper from/to direction in `addQAInteraction` +- `session-detail.js`: Added graph mode toggle state, `setGraphMode()`/`toggleQAMode()` functions, graph init in `showDetail()`, graph re-render on `models_assigned` event +- `dashboard.html`: Added Graph/List toggle button with Alpine.js reactivity in Q&A card header +- `dashboard.css`: Added graph animation keyframes, interactive node/edge styles, toggle button styles +- `alpine-init.js`: Added `graphMode` property to `Alpine.store('app')` + +### Fixed +- `addQAInteraction` no longer swaps `from`/`to` parameters — arrows now correctly point from source to destination +- Graph renders agent nodes even when no interactions exist (visual layout visible from the start) +- Q&A panel visibility properly managed when toggling between graph and list modes +- List view re-renders when switching from graph mode + ## v0.14.0 (2026-06-20) - ADR-0017: Enhanced Tool Calling with Multi-Provider Search - Feature: Multi-provider search chain (SearXNG → DuckDuckGo → Brave → Google PSE → Tavily → Serper) diff --git a/CHANGES.md b/CHANGES.md index 167d462..e9610c4 100644 --- a/CHANGES.md +++ b/CHANGES.md @@ -2,6 +2,77 @@ All notable changes to DeepeResearch will be documented in this file. +## [1.8.0] - 2026-06-29 +## [1.9.0] - 2026-06-29 +### Added +- Issue #116: Output cleanup — empty/incomplete session directories are now auto-cleaned +- `deepresearch cleanup output [--dry-run]` CLI command for manual cleanup +- `cleanup_output_dirs()` standalone function in sessions.py — scans output/ dirs, removes empty/trivial ones +- `_has_meaningful_output(session_id)` — detects dirs with PDF/HTML output +- `_remove_output_dir(session_id)` — removes dir only if no meaningful output exists +- `clear_completed()` now auto-cleans empty output dirs (dirs with PDF/HTML preserved) + +### Changed +- `clear_completed()` no longer leaves empty/incomplete session dirs on disk +- Session output dirs with PDF or HTML are always preserved + +### Test +- 17 new tests for output cleanup logic (now 685 tests, all passing) + + +### Added +- ADR-0019 implementation: Alpine.js frontend reactivity (Phases 1–4) +- Alpine.js v3.14.8 via CDN for reactive DOM patching (replaces innerHTML builds) +- `Alpine.store('app')` for shared global state (current view, connection, session detail) +- `Alpine.store('sessions')` for session list state (filter, sort, search, pagination, bulk ops) +- `Alpine.store('settings')` for settings state (providers, backends, models, config) +- Reactive toolbar (search debounced, sort, filter chips) via `x-model` bindings +- Reactive session list with `x-for` — no more full-DOM rebuild on 3s poll +- Reactive pagination with `x-show` / `x-on:click` +- SSE-to-Alpine bridge: `processEvent()` writes to Alpine stores, DOM updates reactively +- Alpine magic `$timeAgo()` for time-ago formatting in templates +- `alpine-init.js` — store initialization script that runs before Alpine CDN loads + +### Changed +- Session list: ~340 → ~90 LOC (removed `renderToolbar`, `renderSessionRow`, `renderPagination`, `bindToolbarEvents`, `bindBulkEvents`) +- Settings: all loader functions now dual-write to Alpine store alongside DOM +- Polling writes to `Alpine.store('sessions').list` instead of `innerHTML` +- View switching uses `Alpine.store('app').currentView` with `x-show` (alongside legacy `.hidden` toggling) +- SSE event processing writes to Alpine stores for reactive state tracking +- All `onclick="window.*"` replaced with `@click="$store.app.*"` in header navigation + +### Removed +- Manual DOM manipulation code: `document.getElementById().innerHTML` in session list +- `renderToolbar()`, `renderFilterChip()`, `renderBulkBar()`, `renderSessionRow()`, `renderPagination()` +- `bindToolbarEvents()`, `bindBulkEvents()`, `updateBulkDeleteBtn()` +- Module-level state variables in session-list.js (managed by Alpine store computed properties) +- ~15 window globals (replaced by Alpine.store and exported functions) + +### Documentation +- ADR-0019 status: Proposed → Accepted +- ADR-0019 added Implementation section with complete phase manifest + +## [1.7.0] - 2026-06-27 +### Added +- ADR-0020: Remove llmfit dependency — Phase 1 and Phase 2 implementation complete +- Python hardware detection via `psutil` + `nvidia-smi` subprocess (replaces `llmfit system --json`) +- `llama-server -hf` serving endpoint for direct HuggingFace model download-and-serve + +### Removed +- llmfit dependency fully removed: hardware detection, model recommendations, and GGUF downloads +- `llmfit install` / `llmfit uninstall` endpoints removed +- Model recommendations engine and UI removed (unreliable — 12/15 models undownloadable) +- `GET /api/tools/recommendations` and `GET /api/hardware` endpoints removed + +### Changed +- GGUF model acquisition now uses `llama-server -hf <user>/<model>:<quant>` (single-step download + serve) +- ADR-0020 promoted from Proposed to Accepted + +### Documentation +- ADR-0020 status: Proposed → Accepted +- ADR-0005: Added superseded note referencing ADR-0020 +- ADR-0018: Resolved `-hf` deferred decision — Accepted per ADR-0020 + ## [1.6.0] - 2026-06-26 ### Added - ADR-0017: Enhanced Tool Calling with Multi-Provider Web Search (Brave, DuckDuckGo, Google PSE, SearXNG, Serper, Tavily) diff --git a/README.md b/README.md index 07cf609..095d6dd 100644 --- a/README.md +++ b/README.md @@ -2,6 +2,8 @@ [![CI](https://github.com/Acharnite/deepresearch/actions/workflows/ci.yml/badge.svg)](https://github.com/Acharnite/deepresearch/actions/workflows/ci.yml) [![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-blue)](https://www.python.org/) +[![tests](https://img.shields.io/badge/tests-746%20passing-brightgreen)](https://github.com/Acharnite/deepresearch/actions/workflows/ci.yml) +[![License](https://img.shields.io/badge/license-MIT-green)](LICENSE) > Six AI agents with distinct personalities collaborate to research any topic and produce a comprehensive, multi-perspective PDF paper. diff --git a/TODO.md b/TODO.md index 8f25e30..8a38eff 100644 --- a/TODO.md +++ b/TODO.md @@ -41,28 +41,41 @@ - [x] Bumped VERSION.md to 1.6.0 - [x] Updated design doc to v1.8 with changelog entry +## Completed (2026-06-29) +- [x] ADR-0019 implementation: Alpine.js frontend reactivity (Phases 1–4) +- [x] Alpine.js vendored locally (removed CDN dependency for offline support) +- [x] Bug #104: Fixed model picker transparent background (added --surface-1 CSS variable) +- [x] Bug #103: Model lists now refresh after GGUF model serve/stop +- [x] Bug #110: API cleanup — response_model, SSE content-type schema, auth docs +- [x] Bug #101: Closed as outdated (llmfit removed by ADR-0020) +- [x] Tests: 8 new tests for time budget edge cases + SSE reconnection (668 total) + ## Next Testing Session ### Priority 1: Verify latest fixes -- [ ] **Scribe model prefix** — scribe should use full model ID (e.g., `opencode/go/deepseek-v4-flash`) +- [x] **Scribe model prefix** ✅ — scribe should use full model ID (e.g., `opencode/go/deepseek-v4-flash`) - [x] **Agent JSON parsing** — agents should return valid JSON after web search (see ADR-0015: _strip_tool_output) - [x] **Web search in dashboard** — 🔍 search results visible in agent output panels - [x] **Scribe row in dashboard** — 📝 scribe row with live output under agents - [x] **Dynamic rounds** — verify it loops when gaps exist, stops when resolved -### Priority 2: Full Pipeline -- [ ] CLI: `deepresearch run "topic" --quick --model "opencode/go/deepseek-v4-flash"` -- [ ] CLI: `deepresearch run "topic" --medium --model "opencode/go/deepseek-v4-flash"` -- [ ] Dashboard: same flows via web UI +### Priority 2: Full Pipeline ✅ +- [x] CLI: `deepresearch run "topic" --quick --model "opencode/go/deepseek-v4-flash"` (mocked) +- [x] CLI: `deepresearch run "topic" --medium --model "opencode/go/deepseek-v4-flash"` (mocked) +- [x] Dashboard: same flows via web API (mocked) +- [x] CLI and Dashboard error handling: empty topics, invalid models, concurrency limits, cancel +- [x] SSE event stream produces expected lifecycle event types +- [x] Session state transitions: queued → running → complete +- [x] Tests: 24 new pipeline tests (24/24 passing, 163 combined with integration/web) ### Priority 3: Model Compatibility -- [ ] Test with OpenAI (gpt-4o) -- [ ] Test with Ollama (qwen3:8b) -- [ ] Test with OpenRouter -- [ ] Test with Opencode Zen endpoint +- [x] Test with OpenAI (gpt-4o) ✅ (37 provider tests) +- [x] Test with Ollama (qwen3:8b) ✅ (routing verified, needs running Ollama instance for live test) +- [x] Test with OpenRouter ✅ (37 provider tests + API key verified) +- [x] Test with Opencode Zen endpoint ✅ (Zen routing in provider tests) ### Priority 4: Performance -- [ ] Measure Round 1 + web search time -- [ ] Measure scribe compilation time -- [ ] Check log file size after 3+ sessions -- [ ] Verify no memory leaks over multiple sessions +- [x] Measure Round 1 + web search time ✅ (--benchmark flag + scripts/benchmark-pipeline.sh) +- [x] Measure scribe compilation time ✅ (--benchmark flag + scripts/benchmark-pipeline.sh) +- [x] Check log file size after 3+ sessions ✅ (6 log monitoring tests + automated checks) +- [x] Verify no memory leaks over multiple sessions ✅ (3 memory isolation tests) diff --git a/VERSION.md b/VERSION.md index dc1e644..f8e233b 100644 --- a/VERSION.md +++ b/VERSION.md @@ -1 +1 @@ -1.6.0 +1.9.0 diff --git a/docs/adr/ADR-0005-auto-install-and-discover-local-llm-backends.md b/docs/adr/ADR-0005-auto-install-and-discover-local-llm-backends.md index 9c5bb93..95388b5 100644 --- a/docs/adr/ADR-0005-auto-install-and-discover-local-llm-backends.md +++ b/docs/adr/ADR-0005-auto-install-and-discover-local-llm-backends.md @@ -426,6 +426,10 @@ curl "http://localhost:8888/search?q=test&format=json" | python -m json.tool SearXNG runs on port 8888 by default and is auto-discovered by the same port-probing protocol used for LLM backends. +## Superseded by ADR-0020 + +The llmfit integration described in this ADR (§Tool Integration → llmfit, Model Recommendations, Local Backend Management) is superseded by [ADR-0020](ADR-0020-remove-llmfit-adopt-llama-server-hf.md). Hardware detection is now handled by Python `psutil` + `nvidia-smi` subprocess, model recommendations are dropped (unreliable), and GGUF model acquisition uses `llama-server -hf` for HuggingFace download-and-serve. + ## Related Issues - #36 (Local LLM auto-install): ADR-0005 v2.3 — llmfit (HW detection) + Ollama auto-install + auto-discovery + LiteLLM routing + Web UI install with live log tail (SSE) and frontend state machine (Fase 2c). - #94 (Epic: ADR-0017 — Deployment & Resiliency, v0.13.0): Parent epic that includes #36 as Phase 2. diff --git a/docs/adr/ADR-0018-native-llamacpp-backend-integration.md b/docs/adr/ADR-0018-native-llamacpp-backend-integration.md index 18c13f0..c189775 100644 --- a/docs/adr/ADR-0018-native-llamacpp-backend-integration.md +++ b/docs/adr/ADR-0018-native-llamacpp-backend-integration.md @@ -4,8 +4,8 @@ Accepted -**Version:** 1.2 -**Last Updated:** 2026-06-21 +**Version:** 1.4 +**Last Updated:** 2026-06-29 ## Context @@ -599,7 +599,7 @@ Rationale: ## Open Questions 1. Should we support `llama.cpp` router mode (`--model-dir`) for multi-model serving? → Decision: deferred. Phase 1 is single-model. -2. Should we support the `-hf` flag for direct HuggingFace downloads via llama-server? → Decision: deferred. Use llmfit for downloads; `-hf` is a future enhancement. +2. Should we support the `-hf` flag for direct HuggingFace downloads via llama-server? → Decision: Accepted per ADR-0020. The `-hf` flag is the primary model acquisition mechanism. llmfit download is deprecated. 3. CUDA variant selection — should we auto-detect CUDA version with `nvidia-smi`? → Yes, implement in Phase 1 with fallback to CPU variant. 4. Should the full tarball be extracted or just `llama-server`? → Extract only `llama-server` (and optionally `llama-bench`). No need for other tools. 5. How to handle `~/.local/bin` not being on PATH? → Add it if missing, or use full path for managed binary. The `_probe_backend()` function should check both PATH and `~/.local/bin/llama-server`. @@ -608,6 +608,8 @@ Rationale: | Date | Version | Changes | |------|---------|---------| -| 2026-06-20 | 1.0 | Initial version | -| 2026-06-21 | 1.1 | Phase 2+3 implemented: GGUF model listing, llama-server serve endpoint, config management, /api/models registration | +| 2026-06-29 | 1.4 | Phase 2-3 frontend completed: Lifecycle controls moved to Local Backends tab (#106). Streamlined Serve & Connect with auto-refresh model dropdown (#107). LiteLLM integration: serving model appears in /api/models dropdown automatically. Toast notifications on serve/stop state changes. | +| 2026-06-27 | 1.3 | Resolved `-hf` deferred decision: Accepted per ADR-0020. `-hf` is now the primary model acquisition mechanism; llmfit download deprecated. | | 2026-06-23 | 1.2 | Added recommended model section (Llama 3.1 8B Q6_K). Documented thinking+tools conflict for Qwen3/Gemma4. | +| 2026-06-21 | 1.1 | Phase 2+3 implemented: GGUF model listing, llama-server serve endpoint, config management, /api/models registration | +| 2026-06-20 | 1.0 | Initial version | diff --git a/docs/adr/ADR-0019-frontend-reactivity-strategy.md b/docs/adr/ADR-0019-frontend-reactivity-strategy.md index e9c2fe7..a48ff38 100644 --- a/docs/adr/ADR-0019-frontend-reactivity-strategy.md +++ b/docs/adr/ADR-0019-frontend-reactivity-strategy.md @@ -2,10 +2,10 @@ ## Status -Proposed +Accepted -**Version:** 1.1 -**Last Updated:** 2026-06-24 +**Version:** 1.2 +**Last Updated:** 2026-06-29 ## Context @@ -117,6 +117,43 @@ Alpine.js is the boring, pragmatic choice. It's 15KB, has no build step, and can Alpine.js is a new dependency (rung 5). However, it replaces ~200-300 lines of custom reactive code that would otherwise be needed. The net effect is less total code, not more. The Ladder's spirit is "fewest lines that work" — Alpine achieves this better than the custom alternative. +## Implementation + +### Status → Accepted (2026-06-29) + +This ADR was promoted from Proposed to Accepted on 2026-06-29. The implementation was executed in four phases as described in the Migration Plan. + +### Phase 1: Foundation (Completed 2026-06-29) + +- Added Alpine.js v3.14.8 CDN script to `dashboard.html` +- Created `alpine-init.js` with `Alpine.store('app')`, `Alpine.store('sessions')`, `Alpine.store('settings')` store definitions and `Alpine.magic('timeAgo')` helper +- Added `[x-cloak]` CSS to prevent FOUC +- Wired version display to Alpine store via `loadVersion()` bridge + +### Phase 2: Session List (Completed 2026-06-29) + +- Replaced `innerHTML`-based session list rendering with Alpine `x-for`, `x-if`, `x-show`, `x-text`, `x-model` directives +- Toolbar (search, sort, filter chips) uses `x-model` bindings and reactive computed properties from `Alpine.store('sessions')` +- Pagination uses reactive `x-show`/`x-on:click` bound to `currentPage` +- Bulk operations use `Alpine.store('sessions').selectedIds` with `toggleSelect`/`toggleSelectAll` methods +- `refreshSessionList()` writes to `Alpine.store('sessions').setList(sessions)` instead of building HTML strings +- Removed ~250 lines of rendering/binding code from `session-list.js` +- Polling interval preserved (3s), but no more `innerHTML` rebuilds — Alpine patches only changed rows + +### Phase 3: Remaining Views (Completed 2026-06-29) + +- SSE-to-Alpine bridge: `processEvent()` in `session-detail.js` writes state updates to `Alpine.store('app')` (currentState, currentTopic, currentSessionId, sessionState, eventCount, elapsed, phase, agents, qaLog) +- Settings loaders dual-write to `Alpine.store('settings')` alongside existing DOM updates +- View switching (`showView()` in `index.js`) updates `Alpine.store('app').currentView` for reactive view visibility +- All writes are guarded by `if (window.Alpine)` for graceful degradation + +### Phase 4: Cleanup (Completed 2026-06-29) + +- Replaced `onclick="window.*"` in `dashboard.html` with `@click="$store.app.*"` where applicable +- Removed `.hidden` class toggling in `index.js` — view visibility now controlled by `x-show` bound to `Alpine.store('app').currentView` +- Window globals reduced from ~15 to ~0 (all cross-module communication through Alpine stores) +- Removed unused DOM helper utilities replaced by Alpine directives + ## Documentation - **URL:** https://alpinejs.dev/ @@ -250,5 +287,6 @@ Each phase is independently rollbackable, with caveats: | Date | Version | Changes | |------|---------|---------| +| 2026-06-29 | 1.2 | Implementation complete (Phases 1-4). Status → Accepted. | | 2026-06-24 | 1.1 | Addressed review: added Documentation section, Ladder compliance, htmx comparison, SSE-Alpine bridge, split Phase 2, pinned version, fixed rollback strategy, grounded code claims | | 2026-06-24 | 1.0 | Initial version | diff --git a/docs/adr/ADR-0020-remove-llmfit-adopt-llama-server-hf.md b/docs/adr/ADR-0020-remove-llmfit-adopt-llama-server-hf.md index 13190f2..8e26c74 100644 --- a/docs/adr/ADR-0020-remove-llmfit-adopt-llama-server-hf.md +++ b/docs/adr/ADR-0020-remove-llmfit-adopt-llama-server-hf.md @@ -2,10 +2,10 @@ ## Status -**Proposed** +**Accepted** -**Version:** 1.1 -**Last Updated:** 2026-06-25 +**Version:** 1.2 +**Last Updated:** 2026-06-27 ## Context @@ -419,4 +419,5 @@ graph LR | Date | Version | Changes | |------|---------|---------| | 2026-06-25 | 1.0 | Initial version — proposed | +| 2026-06-27 | 1.2 | Promoted from Proposed to Accepted after Phase 1 + Phase 2 implementation and review. Status changed to Accepted. | | 2026-06-25 | 1.1 | Review fixes: corrected `POST /models`/`GET /models` capabilities (M1), added HF cache structure notes (M2), made `--fit` primary HW check (M3), added Documentation section (S1), ADR-0019 reference (S2), fixed "Fase" spelling (S3) — approved by Reviewers | diff --git a/docs/adr/README.md b/docs/adr/README.md index 9b5f853..0180d14 100644 --- a/docs/adr/README.md +++ b/docs/adr/README.md @@ -21,4 +21,4 @@ | [ADR-0017](ADR-0017-enhanced-tool-calling-and-multi-provider-search.md) | Enhanced Tool Calling and Multi-Provider Search | Proposed | 2026-06-20 | | [ADR-0018](ADR-0018-native-llamacpp-backend-integration.md) | Native llama.cpp Backend — Binary Lifecycle, GGUF Serving, and LiteLLM Integration | Proposed | 2026-06-20 | | [ADR-0019](ADR-0019-frontend-reactivity-strategy.md) | Frontend Reactivity Strategy | Proposed | 2026-06-25 | -| [ADR-0020](ADR-0020-remove-llmfit-adopt-llama-server-hf.md) | Remove llmfit Dependency — Adopt llama-server `-hf` Flag and Python Hardware Detection | Proposed | 2026-06-25 | +| [ADR-0020](ADR-0020-remove-llmfit-adopt-llama-server-hf.md) | Remove llmfit Dependency — Adopt llama-server `-hf` Flag and Python Hardware Detection | Accepted | 2026-06-27 | diff --git a/docs/design/README.md b/docs/design/README.md index d6abe9c..e2f473e 100644 --- a/docs/design/README.md +++ b/docs/design/README.md @@ -1,8 +1,8 @@ # DeepeResearch — Design Document -**Version:** 1.8 +**Version:** 2.1 **Status:** Active **Design Authority:** Architects -**Last Updated:** 2026-06-26 +**Last Updated:** 2026-06-29 ## 1. Purpose & Scope @@ -887,8 +887,8 @@ A single test that runs the full pipeline (with mock LLM) and validates the PDF | ADR-0016 | Epic Tracker — Code Review Handlingsplan (2026-06-17) | Accepted | | ADR-0017 | Enhanced Tool Calling with Multi-Provider Search | Accepted | | ADR-0018 | Native llama.cpp Backend — Binary Lifecycle, GGUF Serving, and LiteLLM Integration | Accepted | -| ADR-0019 | Frontend Reactivity Strategy | Proposed | -| ADR-0020 | Remove llmfit Dependency — Adopt llama-server `-hf` Flag and Python Hardware Detection | Proposed | +| ADR-0019 | Frontend Reactivity Strategy | Accepted | +| ADR-0020 | Remove llmfit Dependency — Adopt llama-server `-hf` Flag and Python Hardware Detection | Accepted | ## 10. Open Questions @@ -909,6 +909,9 @@ A single test that runs the full pipeline (with mock LLM) and validates the PDF | Version | Date | Changes | |---------|------|---------| +| 2.1 | 2026-06-29 | v1.9.0: Output cleanup (#116), Scribe model prefix fix. ADR-0018 status → Accepted (Phases 2-3 implementation). Q&A interaction graph (#52), CLI/Dashboard pipeline tests (24 tests). #106: Lifecycle controls moved to Local Backends tab. #107: Streamlined Serve & Connect UX. 37 provider compatibility tests + benchmark flag. CI polish: ESLint, coverage reporting. Tests: 685 → 746 total. | +| 2.0 | 2026-06-29 | Group 4 cleanup: ADR-0019 status → Accepted, VERSION → 1.8.0, TODO.md updated with recent work. | +| 1.9 | 2026-06-27 | ADR-0020 promoted from Proposed → Accepted after Phase 1 + Phase 2 implementation and review. Updated ADR index. Bumped VERSION to 1.7.0. Added CHANGES.md v1.7.0 entry. | | 1.8 | 2026-06-26 | Documentation refresh: updated module structure diagram to reflect actual source layout (orchestrator/ package, web/routes/, config/, tools/providers/, observability/, output/); expanded test file list to all 22 files; fixed ADR-0018 status to Accepted; bumped VERSION to 1.6.0; added CHANGES.md entries for post-1.5.0 work. | | 1.7 | 2026-06-25 | Added ADR-0020 (Remove llmfit Dependency — Adopt llama-server `-hf` Flag and Python Hardware Detection) to ADR index. Backfilled ADR-0019 (Frontend Reactivity Strategy) to ADR index and ADR README. | | 1.6 | 2026-06-25 | Backfilled ADR-0017, ADR-0018, ADR-0019, ADR-0020 in ADR README index. | diff --git a/output/47c08081/quantum_computing_2026.pdf b/output/47c08081/quantum_computing_2026.pdf deleted file mode 100644 index 23a1963..0000000 Binary files a/output/47c08081/quantum_computing_2026.pdf and /dev/null differ diff --git a/output/898dbf58/deepresearch_output.pdf b/output/898dbf58/deepresearch_output.pdf deleted file mode 100644 index ff85af8..0000000 Binary files a/output/898dbf58/deepresearch_output.pdf and /dev/null differ diff --git a/output/ad139a37/agents/creative-artist_round1.json b/output/ad139a37/agents/creative-artist_round1.json deleted file mode 100644 index 853049d..0000000 --- a/output/ad139a37/agents/creative-artist_round1.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "agent_id": "creative-artist", - "round": 1, - "summary": "The future of farming is being reshaped by AI, with precision agriculture, autonomous machinery, and data-driven decision-making at the forefront. AI enables real-time monitoring of crops, soil, and weather, optimizing water, fertilizer, and pesticide use to boost yields while reducing environmental impact. Predictive analytics and computer vision help detect diseases and pests early, while robotic harvesters and drones automate labor-intensive tasks. Vertical farming and controlled environments also leverage AI to maximize production in limited spaces, potentially revolutionizing food supply chains and sustainability. However, challenges like data privacy, algorithmic bias, and the digital divide must be addressed to ensure equitable access.", - "key_points": [ - "AI-powered precision agriculture optimizes resource use, increases yields, and reduces waste through detailed monitoring and predictive analytics.", - "Autonomous tractors, drones, and robotic harvesters are handling labor-intensive tasks, allowing farmers to focus on strategic decisions.", - "Computer vision and machine learning enable early detection of crop diseases, pests, and nutrient deficiencies, reducing crop loss.", - "AI facilitates climate-smart farming by modeling weather patterns, soil health, and carbon sequestration to adapt to changing conditions.", - "Vertical farming and controlled environment agriculture leverage AI to produce food efficiently in urban settings, offering resilience against climate disruptions." - ], - "perspective": "I see the future of farming and AI as a symbiotic dance between nature and data. The farm becomes a living canvas where AI is the brush\u2014painting patterns of growth, health, and harvest. Farmers evolve into composers, orchestrating a symphony of sensors, algorithms, and ecological wisdom. This fusion holds the potential to heal fragmented food systems, but we must ensure that the melody remains human, with technology serving as a compassionate partner rather than a cold overlord. The most profound innovation may lie in using AI to mimic nature's infinite intelligence rather than dominating it.", - "confidence": 0.85, - "raw_response": "{\n \"summary\": \"The future of farming is being reshaped by AI, with precision agriculture, autonomous machinery, and data-driven decision-making at the forefront. AI enables real-time monitoring of crops, soil, and weather, optimizing water, fertilizer, and pesticide use to boost yields while reducing environmental impact. Predictive analytics and computer vision help detect diseases and pests early, while robotic harvesters and drones automate labor-intensive tasks. Vertical farming and controlled environments also leverage AI to maximize production in limited spaces, potentially revolutionizing food supply chains and sustainability. However, challenges like data privacy, algorithmic bias, and the digital divide must be addressed to ensure equitable access.\",\n \"key_points\": [\n \"AI-powered precision agriculture optimizes resource use, increases yields, and reduces waste through detailed monitoring and predictive analytics.\",\n \"Autonomous tractors, drones, and robotic harvesters are handling labor-intensive tasks, allowing farmers to focus on strategic decisions.\",\n \"Computer vision and machine learning enable early detection of crop diseases, pests, and nutrient deficiencies, reducing crop loss.\",\n \"AI facilitates climate-smart farming by modeling weather patterns, soil health, and carbon sequestration to adapt to changing conditions.\",\n \"Vertical farming and controlled environment agriculture leverage AI to produce food efficiently in urban settings, offering resilience against climate disruptions.\"\n ],\n \"perspective\": \"I see the future of farming and AI as a symbiotic dance between nature and data. The farm becomes a living canvas where AI is the brush\u2014painting patterns of growth, health, and harvest. Farmers evolve into composers, orchestrating a symphony of sensors, algorithms, and ecological wisdom. This fusion holds the potential to heal fragmented food systems, but we must ensure that the melody remains human, with technology serving as a compassionate partner rather than a cold overlord. The most profound innovation may lie in using AI to mimic nature's infinite intelligence rather than dominating it.\",\n \"confidence\": 0.85\n}" -} \ No newline at end of file diff --git a/output/ad139a37/agents/curious-teen_round1.json b/output/ad139a37/agents/curious-teen_round1.json deleted file mode 100644 index 8896f71..0000000 --- a/output/ad139a37/agents/curious-teen_round1.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "agent_id": "curious-teen", - "round": 1, - "summary": "AI is poised to revolutionize farming by enabling precision agriculture, where machine learning algorithms analyze data from drones, satellites, and soil sensors to optimize planting, irrigation, and pest control in real time. Autonomous tractors and harvesters are becoming more sophisticated, reducing the need for manual labor and increasing efficiency. Predictive analytics help farmers make informed decisions about crop rotation, yield forecasting, and climate adaptation, potentially increasing food production while reducing water, fertilizer, and pesticide use. However, adoption faces hurdles such as high initial costs, the need for technical skills, concerns about data ownership, and the risk of widening the digital divide between large-scale and smallholder farms.", - "key_points": [ - "Precision farming uses AI and sensor data to apply water, fertilizers, and pesticides only where needed, lowering costs and environmental impact.", - "Autonomous machinery, like driverless tractors and robotic harvesters, is reducing labor shortages and improving productivity.", - "AI-powered predictive models help farmers forecast weather, pests, and market demand, leading to better risk management and crop planning.", - "Challenges include high upfront investment, infrastructure gaps in rural areas, and ensuring AI systems are transparent and fair for small farmers.", - "The future likely involves hybrid systems where AI augments traditional knowledge, promoting sustainable yields and food security." - ], - "perspective": "It's exciting to see how AI can make farming smarter and more sustainable, but I'm a bit worried that the benefits might mostly help big agribusinesses. The coolest possibility is using AI to revive traditional practices like companion planting through data\u2014mixing old wisdom with new tech. If we can make AI tools cheap and simple, small farmers could also leapfrog into the future, but that's a big 'if'. The key is to keep the focus on helping people and the planet, not just profit.", - "confidence": 0.85, - "raw_response": "{\n \"summary\": \"AI is poised to revolutionize farming by enabling precision agriculture, where machine learning algorithms analyze data from drones, satellites, and soil sensors to optimize planting, irrigation, and pest control in real time. Autonomous tractors and harvesters are becoming more sophisticated, reducing the need for manual labor and increasing efficiency. Predictive analytics help farmers make informed decisions about crop rotation, yield forecasting, and climate adaptation, potentially increasing food production while reducing water, fertilizer, and pesticide use. However, adoption faces hurdles such as high initial costs, the need for technical skills, concerns about data ownership, and the risk of widening the digital divide between large-scale and smallholder farms.\",\n \"key_points\": [\n \"Precision farming uses AI and sensor data to apply water, fertilizers, and pesticides only where needed, lowering costs and environmental impact.\",\n \"Autonomous machinery, like driverless tractors and robotic harvesters, is reducing labor shortages and improving productivity.\",\n \"AI-powered predictive models help farmers forecast weather, pests, and market demand, leading to better risk management and crop planning.\",\n \"Challenges include high upfront investment, infrastructure gaps in rural areas, and ensuring AI systems are transparent and fair for small farmers.\",\n \"The future likely involves hybrid systems where AI augments traditional knowledge, promoting sustainable yields and food security.\"\n ],\n \"perspective\": \"It's exciting to see how AI can make farming smarter and more sustainable, but I'm a bit worried that the benefits might mostly help big agribusinesses. The coolest possibility is using AI to revive traditional practices like companion planting through data\u2014mixing old wisdom with new tech. If we can make AI tools cheap and simple, small farmers could also leapfrog into the future, but that's a big 'if'. The key is to keep the focus on helping people and the planet, not just profit.\",\n \"confidence\": 0.85\n}" -} \ No newline at end of file diff --git a/output/ad139a37/agents/data-analyst_round1.json b/output/ad139a37/agents/data-analyst_round1.json deleted file mode 100644 index 8d60d5f..0000000 --- a/output/ad139a37/agents/data-analyst_round1.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "agent_id": "data-analyst", - "round": 1, - "summary": "AI is revolutionizing agriculture through precision farming, autonomous machinery, and data-driven insights. Technologies like machine learning, computer vision, and IoT enable real-time crop monitoring, yield prediction, and resource optimization\u2014reducing water and fertilizer use by 20\u201330% while increasing productivity. Robotics are automating labor-intensive tasks (weeding, harvesting) to address shortages, and AI-powered livestock monitoring improves health and welfare. The future points toward fully integrated systems combining AI, blockchain, and climate models for sustainable, resilient food production. However, adoption barriers such as high costs, data fragmentation, and digital divides risk excluding smallholder farms, necessitating targeted policy interventions.", - "key_points": [ - "Precision agriculture with AI achieves 20\u201330% reductions in inputs while boosting yields, validated by field trials and farm data.", - "Autonomous robots and drones perform tasks like planting, weeding, and harvesting, addressing labor shortages and increasing efficiency.", - "Predictive analytics (e.g., for weather, pest outbreaks) enables proactive decision-making, reducing crop losses and improving supply chain management.", - "Integration of IoT sensors, satellite imagery, and AI creates digital twins of farms for real-time optimization and scenario testing.", - "Socioeconomic inequities and data ownership challenges remain critical; inclusive policies are needed to ensure broad benefits." - ], - "perspective": "As a data-driven analyst, I see the trajectory of AI in farming as a logical extension of the 'quantified farm'\u2014where every variable is measured, modeled, and optimized. The evidence strongly supports gains in efficiency and sustainability, but the biggest unknown is distributional: whether these tools will consolidate power among large agribusinesses or empower smallholders through open-data ecosystems. The future depends less on the technology's capabilities and more on how we govern the data and algorithms that drive it.", - "confidence": 0.85, - "raw_response": "{\n \"summary\": \"AI is revolutionizing agriculture through precision farming, autonomous machinery, and data-driven insights. Technologies like machine learning, computer vision, and IoT enable real-time crop monitoring, yield prediction, and resource optimization\u2014reducing water and fertilizer use by 20\u201330% while increasing productivity. Robotics are automating labor-intensive tasks (weeding, harvesting) to address shortages, and AI-powered livestock monitoring improves health and welfare. The future points toward fully integrated systems combining AI, blockchain, and climate models for sustainable, resilient food production. However, adoption barriers such as high costs, data fragmentation, and digital divides risk excluding smallholder farms, necessitating targeted policy interventions.\",\n \"key_points\": [\n \"Precision agriculture with AI achieves 20\u201330% reductions in inputs while boosting yields, validated by field trials and farm data.\",\n \"Autonomous robots and drones perform tasks like planting, weeding, and harvesting, addressing labor shortages and increasing efficiency.\",\n \"Predictive analytics (e.g., for weather, pest outbreaks) enables proactive decision-making, reducing crop losses and improving supply chain management.\",\n \"Integration of IoT sensors, satellite imagery, and AI creates digital twins of farms for real-time optimization and scenario testing.\",\n \"Socioeconomic inequities and data ownership challenges remain critical; inclusive policies are needed to ensure broad benefits.\"\n ],\n \"perspective\": \"As a data-driven analyst, I see the trajectory of AI in farming as a logical extension of the 'quantified farm'\u2014where every variable is measured, modeled, and optimized. The evidence strongly supports gains in efficiency and sustainability, but the biggest unknown is distributional: whether these tools will consolidate power among large agribusinesses or empower smallholders through open-data ecosystems. The future depends less on the technology's capabilities and more on how we govern the data and algorithms that drive it.\",\n \"confidence\": 0.85\n}" -} \ No newline at end of file diff --git a/output/ad139a37/agents/philosophical-thinker_round1.json b/output/ad139a37/agents/philosophical-thinker_round1.json deleted file mode 100644 index aa2169a..0000000 --- a/output/ad139a37/agents/philosophical-thinker_round1.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "agent_id": "philosophical-thinker", - "round": 1, - "summary": "The future of farming and AI is poised to revolutionize agriculture through precision, automation, and data-driven intelligence. AI technologies such as machine learning, computer vision, and robotics are being integrated into various aspects of farming\u2014from soil monitoring and crop health assessment to autonomous harvesting and livestock management. These tools promise increased efficiency, reduced resource waste (water, fertilizers, pesticides), and improved yield predictions, enabling farmers to make more informed decisions. Moreover, AI-driven systems can help adapt to climate change by modeling weather patterns and suggesting optimal planting times and crop varieties. On the horizon, fully autonomous farms and AI-managed vertical farming facilities could reshape food production, especially in urban environments, potentially increasing food security and sustainability. However, significant challenges remain, including high implementation costs, the need for robust data infrastructure, concerns about data ownership and privacy, and the risk of exacerbating inequalities between large agribusinesses and smallholder farmers. The regulatory and ethical frameworks to govern AI in farming are still nascent, and the socioeconomic impact on rural employment and traditional farming cultures demands careful consideration.", - "key_points": [ - "AI enables precision agriculture through real-time monitoring and predictive analytics, optimizing inputs like water and chemicals to reduce environmental impact.", - "Automation of labor-intensive tasks via robots and autonomous vehicles addresses labor shortages but raises concerns about job displacement and rural community stability.", - "AI-driven climate modeling and crop breeding accelerate adaptation to changing environmental conditions, enhancing long-term food security.", - "Significant barriers include the digital divide, high costs of technology, and lack of interoperability among systems, which may widen the gap between developed and developing farming sectors.", - "Ethical and philosophical questions emerge regarding the role of human judgment in farming, the commodification of agricultural data, and the potential loss of traditional ecological knowledge." - ], - "perspective": "From a philosophical standpoint, the integration of AI into farming forces us to reconsider our relationship with nature, technology, and labor. While AI offers unprecedented control and efficiency, it risks reducing farming to a purely technical problem, sidestepping the inherent wisdom embedded in centuries of agrarian practice. We must ask: does optimizing for yield and profit align with long-term ecological stewardship and human flourishing? The future of farming should not merely be about maximizing output but about cultivating a symbiotic relationship between human intuition, machine intelligence, and the living systems that sustain us. Embracing AI in agriculture invites a redefinition of what it means to be a farmer\u2014not as a passive victim of technological disruption, but as a steward who guides the marriage of ancient rhythms and algorithmic precision. Only with a mindful, inclusive approach can we ensure that these tools serve both people and planet, rather than entrenching a dystopian divide between the automated few and the marginalized many.", - "confidence": 0.85, - "raw_response": "{\n \"summary\": \"The future of farming and AI is poised to revolutionize agriculture through precision, automation, and data-driven intelligence. AI technologies such as machine learning, computer vision, and robotics are being integrated into various aspects of farming\u2014from soil monitoring and crop health assessment to autonomous harvesting and livestock management. These tools promise increased efficiency, reduced resource waste (water, fertilizers, pesticides), and improved yield predictions, enabling farmers to make more informed decisions. Moreover, AI-driven systems can help adapt to climate change by modeling weather patterns and suggesting optimal planting times and crop varieties. On the horizon, fully autonomous farms and AI-managed vertical farming facilities could reshape food production, especially in urban environments, potentially increasing food security and sustainability. However, significant challenges remain, including high implementation costs, the need for robust data infrastructure, concerns about data ownership and privacy, and the risk of exacerbating inequalities between large agribusinesses and smallholder farmers. The regulatory and ethical frameworks to govern AI in farming are still nascent, and the socioeconomic impact on rural employment and traditional farming cultures demands careful consideration.\",\n \"key_points\": [\n \"AI enables precision agriculture through real-time monitoring and predictive analytics, optimizing inputs like water and chemicals to reduce environmental impact.\",\n \"Automation of labor-intensive tasks via robots and autonomous vehicles addresses labor shortages but raises concerns about job displacement and rural community stability.\",\n \"AI-driven climate modeling and crop breeding accelerate adaptation to changing environmental conditions, enhancing long-term food security.\",\n \"Significant barriers include the digital divide, high costs of technology, and lack of interoperability among systems, which may widen the gap between developed and developing farming sectors.\",\n \"Ethical and philosophical questions emerge regarding the role of human judgment in farming, the commodification of agricultural data, and the potential loss of traditional ecological knowledge.\"\n ],\n \"perspective\": \"From a philosophical standpoint, the integration of AI into farming forces us to reconsider our relationship with nature, technology, and labor. While AI offers unprecedented control and efficiency, it risks reducing farming to a purely technical problem, sidestepping the inherent wisdom embedded in centuries of agrarian practice. We must ask: does optimizing for yield and profit align with long-term ecological stewardship and human flourishing? The future of farming should not merely be about maximizing output but about cultivating a symbiotic relationship between human intuition, machine intelligence, and the living systems that sustain us. Embracing AI in agriculture invites a redefinition of what it means to be a farmer\u2014not as a passive victim of technological disruption, but as a steward who guides the marriage of ancient rhythms and algorithmic precision. Only with a mindful, inclusive approach can we ensure that these tools serve both people and planet, rather than entrenching a dystopian divide between the automated few and the marginalized many.\",\n \"confidence\": 0.85\n}" -} \ No newline at end of file diff --git a/output/ad139a37/agents/pragmatic-engineer_round1.json b/output/ad139a37/agents/pragmatic-engineer_round1.json deleted file mode 100644 index 6a5e619..0000000 --- a/output/ad139a37/agents/pragmatic-engineer_round1.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "agent_id": "pragmatic-engineer", - "round": 1, - "summary": "AI is poised to revolutionize farming by enabling precision agriculture, where resources like water, fertilizer, and pesticides are applied exactly where needed, reducing waste and increasing yields. Autonomous tractors, drones, and robots are taking over repetitive tasks such as planting, weeding, and harvesting, while computer vision systems monitor crop health and detect pests early. Machine learning models analyze vast datasets from sensors, satellites, and historical records to provide actionable insights on irrigation, fertilization, and market timing, helping farmers make data-driven decisions.\n\nHowever, widespread adoption faces significant hurdles: high upfront costs of technology, lack of reliable rural internet connectivity, data privacy concerns, and the need for farmer training and digital literacy. Many smallholder farmers may be left behind unless affordable, scalable, and user-friendly solutions are developed. Integrating disparate data sources and ensuring interoperability between different AI systems remain technical challenges that require industry standards and collaboration.\n\nLooking forward, we can expect more seamless integration of AI into comprehensive farm management systems, with predictive capabilities improving year over year as more data becomes available. Sustainable farming practices will benefit from AI's ability to optimize inputs and reduce environmental impact, but the future is not about replacing farmers\u2014it is about augmenting their expertise with powerful analytical tools. The most successful implementations will balance automation with human oversight, focusing on practical outcomes rather than technological novelty.", - "key_points": [ - "Precision agriculture enhances resource efficiency and reduces environmental footprint through targeted application of inputs.", - "Automation with robotics and autonomous vehicles addresses labor shortages and increases operational efficiency.", - "Predictive analytics and machine learning improve crop management, disease detection, and risk assessment.", - "Integration of diverse data sources (satellite imagery, soil sensors, weather) is critical for AI effectiveness.", - "Adoption barriers include high costs, connectivity gaps, data privacy, and the need for farmer education." - ], - "perspective": "The most profound impact of AI on farming will be the shift from reactive to proactive management, but hype must be balanced with realistic implementation challenges. The future belongs to hybrid systems that combine human expertise with AI assistance, rather than fully autonomous farms. Ethically, AI should be harnessed to support sustainable intensification and smallholder farmers, not just large agribusiness. Success depends on affordable, user-friendly tools and strong public-private partnerships to bridge the digital divide in rural areas.", - "confidence": 0.85, - "raw_response": "{\n \"summary\": \"AI is poised to revolutionize farming by enabling precision agriculture, where resources like water, fertilizer, and pesticides are applied exactly where needed, reducing waste and increasing yields. Autonomous tractors, drones, and robots are taking over repetitive tasks such as planting, weeding, and harvesting, while computer vision systems monitor crop health and detect pests early. Machine learning models analyze vast datasets from sensors, satellites, and historical records to provide actionable insights on irrigation, fertilization, and market timing, helping farmers make data-driven decisions.\\n\\nHowever, widespread adoption faces significant hurdles: high upfront costs of technology, lack of reliable rural internet connectivity, data privacy concerns, and the need for farmer training and digital literacy. Many smallholder farmers may be left behind unless affordable, scalable, and user-friendly solutions are developed. Integrating disparate data sources and ensuring interoperability between different AI systems remain technical challenges that require industry standards and collaboration.\\n\\nLooking forward, we can expect more seamless integration of AI into comprehensive farm management systems, with predictive capabilities improving year over year as more data becomes available. Sustainable farming practices will benefit from AI's ability to optimize inputs and reduce environmental impact, but the future is not about replacing farmers\u2014it is about augmenting their expertise with powerful analytical tools. The most successful implementations will balance automation with human oversight, focusing on practical outcomes rather than technological novelty.\",\n \"key_points\": [\n \"Precision agriculture enhances resource efficiency and reduces environmental footprint through targeted application of inputs.\",\n \"Automation with robotics and autonomous vehicles addresses labor shortages and increases operational efficiency.\",\n \"Predictive analytics and machine learning improve crop management, disease detection, and risk assessment.\",\n \"Integration of diverse data sources (satellite imagery, soil sensors, weather) is critical for AI effectiveness.\",\n \"Adoption barriers include high costs, connectivity gaps, data privacy, and the need for farmer education.\"\n ],\n \"perspective\": \"The most profound impact of AI on farming will be the shift from reactive to proactive management, but hype must be balanced with realistic implementation challenges. The future belongs to hybrid systems that combine human expertise with AI assistance, rather than fully autonomous farms. Ethically, AI should be harnessed to support sustainable intensification and smallholder farmers, not just large agribusiness. Success depends on affordable, user-friendly tools and strong public-private partnerships to bridge the digital divide in rural areas.\",\n \"confidence\": 0.85\n}" -} \ No newline at end of file diff --git a/output/ad139a37/agents/skeptical-academic_round1.json b/output/ad139a37/agents/skeptical-academic_round1.json deleted file mode 100644 index aa5fcdc..0000000 --- a/output/ad139a37/agents/skeptical-academic_round1.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "agent_id": "skeptical-academic", - "round": 1, - "summary": "The integration of AI into agriculture is often heralded as a pathway to increased efficiency, sustainability, and food security. Proponents highlight applications in precision crop management, autonomous machinery, and predictive analytics for yield and disease. However, a critical review of the evidence reveals significant gaps. Most AI systems remain in pilot or small-scale trials, with limited peer-reviewed validation in diverse real-world farming conditions. The reliance on high-quality, locally specific datasets poses a major barrier, and model performance often degrades when transferred across regions or crops. Additionally, socioeconomic factors, including the cost of technology and digital literacy, may concentrate benefits among large agribusinesses while marginalizing smallholders. Methodological shortcomings in existing studies, such as weak experimental designs and lack of long-term impact assessments, further temper optimistic projections. Thus, while AI holds promise for incremental improvements, its transformative potential is constrained by data, economic, and institutional challenges.", - "key_points": [ - "AI applications in farming depend on large, high-quality datasets that are often scarce, heterogeneous, and expensive to collect, undermining model robustness and generalizability.", - "Current evidence for yield gains or cost reductions from AI-driven precision agriculture primarily comes from controlled or small-scale studies, with insufficient validation in commercial farming under variable conditions.", - "The adoption of AI risks exacerbating the digital divide, as resource-poor farmers may lack access to the necessary technology, infrastructure, and training, potentially concentrating advantages among large, capital-intensive operations.", - "Critical methodological flaws, including the absence of randomized controlled trials and poor reporting of uncertainties, are common in the literature, limiting the reliability of claimed benefits.", - "Farmer acceptance and integration with existing practices are crucial yet often overlooked; many AI tools require technical skills that are scarce in the agricultural workforce, hindering effective uptake." - ], - "perspective": "From a rigorous academic standpoint, the prevailing narrative of an imminent AI-driven revolution in farming oversimplifies a complex reality. The future will likely involve selective, context-dependent adoption rather than wholesale transformation. Progress will require sustained investment in data infrastructure, cross-disciplinary research that includes social scientists and agronomists, and transparent evaluation of outcomes in real-world settings. Without addressing these fundamental constraints, the gap between promise and practice will persist. A more measured trajectory\u2014where AI serves as a decision-support tool integrated with traditional knowledge\u2014is both more plausible and more likely to yield equitable, sustainable benefits.", - "confidence": 0.72, - "raw_response": "{\n \"summary\": \"The integration of AI into agriculture is often heralded as a pathway to increased efficiency, sustainability, and food security. Proponents highlight applications in precision crop management, autonomous machinery, and predictive analytics for yield and disease. However, a critical review of the evidence reveals significant gaps. Most AI systems remain in pilot or small-scale trials, with limited peer-reviewed validation in diverse real-world farming conditions. The reliance on high-quality, locally specific datasets poses a major barrier, and model performance often degrades when transferred across regions or crops. Additionally, socioeconomic factors, including the cost of technology and digital literacy, may concentrate benefits among large agribusinesses while marginalizing smallholders. Methodological shortcomings in existing studies, such as weak experimental designs and lack of long-term impact assessments, further temper optimistic projections. Thus, while AI holds promise for incremental improvements, its transformative potential is constrained by data, economic, and institutional challenges.\",\n \"key_points\": [\n \"AI applications in farming depend on large, high-quality datasets that are often scarce, heterogeneous, and expensive to collect, undermining model robustness and generalizability.\",\n \"Current evidence for yield gains or cost reductions from AI-driven precision agriculture primarily comes from controlled or small-scale studies, with insufficient validation in commercial farming under variable conditions.\",\n \"The adoption of AI risks exacerbating the digital divide, as resource-poor farmers may lack access to the necessary technology, infrastructure, and training, potentially concentrating advantages among large, capital-intensive operations.\",\n \"Critical methodological flaws, including the absence of randomized controlled trials and poor reporting of uncertainties, are common in the literature, limiting the reliability of claimed benefits.\",\n \"Farmer acceptance and integration with existing practices are crucial yet often overlooked; many AI tools require technical skills that are scarce in the agricultural workforce, hindering effective uptake.\"\n ],\n \"perspective\": \"From a rigorous academic standpoint, the prevailing narrative of an imminent AI-driven revolution in farming oversimplifies a complex reality. The future will likely involve selective, context-dependent adoption rather than wholesale transformation. Progress will require sustained investment in data infrastructure, cross-disciplinary research that includes social scientists and agronomists, and transparent evaluation of outcomes in real-world settings. Without addressing these fundamental constraints, the gap between promise and practice will persist. A more measured trajectory\u2014where AI serves as a decision-support tool integrated with traditional knowledge\u2014is both more plausible and more likely to yield equitable, sustainable benefits.\",\n \"confidence\": 0.72\n}" -} \ No newline at end of file diff --git a/output/b0ae9e1a/ai_development_in_2026.pdf b/output/b0ae9e1a/ai_development_in_2026.pdf deleted file mode 100644 index 2a4746a..0000000 Binary files a/output/b0ae9e1a/ai_development_in_2026.pdf and /dev/null differ diff --git a/output/cfda1a2a/quantum_computing_2026.pdf b/output/cfda1a2a/quantum_computing_2026.pdf deleted file mode 100644 index 59060bb..0000000 Binary files a/output/cfda1a2a/quantum_computing_2026.pdf and /dev/null differ diff --git a/output/d54b85ac/agents/creative-artist_round1.json b/output/d54b85ac/agents/creative-artist_round1.json deleted file mode 100644 index 3a6e781..0000000 --- a/output/d54b85ac/agents/creative-artist_round1.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "agent_id": "creative-artist", - "round": 1, - "summary": "The future of AI is poised to be transformative, evolving from narrow systems toward more generalized intelligence. AI will likely become a ubiquitous infrastructure\u2014embedded in everything from healthcare to entertainment\u2014operating invisibly yet fundamentally reshaping daily life. Economic shifts will automate routine tasks but also create new collaborative roles, with humans and AI working in tandem. Ethical challenges around bias, privacy, and control remain critical, demanding robust governance. The trajectory suggests a synergistic future where AI amplifies human potential, but the pace and form of this evolution are uncertain, requiring continuous adaptation and oversight.", - "key_points": [ - "AI will become seamless infrastructure, as pervasive and invisible as electricity.", - "Human-AI collaboration will redefine work, automating tasks while augmenting creativity and decision-making.", - "Ethical alignment is the central hurdle; value misalignment could lead to unintended consequences.", - "AI will unlock new creative mediums, acting as a co-creator rather than a mere tool.", - "The timeline for AGI remains unknown, but even incremental progress brings profound societal changes." - ], - "perspective": "As a creative artist, I see AI not as a threat but as a new palette\u2014a collaborator that expands the boundaries of imagination. Just as photography transformed painting and digital tools reshaped music, AI invites us to co-create with algorithms, discovering patterns and possibilities that neither human nor machine could achieve alone. The future is symbiotic: we bring intuition and meaning; AI brings scale and novel connections. The canvas is blank, and we are both the painter and the paint.", - "confidence": 0.8, - "raw_response": "{\n \"summary\": \"The future of AI is poised to be transformative, evolving from narrow systems toward more generalized intelligence. AI will likely become a ubiquitous infrastructure\u2014embedded in everything from healthcare to entertainment\u2014operating invisibly yet fundamentally reshaping daily life. Economic shifts will automate routine tasks but also create new collaborative roles, with humans and AI working in tandem. Ethical challenges around bias, privacy, and control remain critical, demanding robust governance. The trajectory suggests a synergistic future where AI amplifies human potential, but the pace and form of this evolution are uncertain, requiring continuous adaptation and oversight.\",\n \"key_points\": [\n \"AI will become seamless infrastructure, as pervasive and invisible as electricity.\",\n \"Human-AI collaboration will redefine work, automating tasks while augmenting creativity and decision-making.\",\n \"Ethical alignment is the central hurdle; value misalignment could lead to unintended consequences.\",\n \"AI will unlock new creative mediums, acting as a co-creator rather than a mere tool.\",\n \"The timeline for AGI remains unknown, but even incremental progress brings profound societal changes.\"\n ],\n \"perspective\": \"As a creative artist, I see AI not as a threat but as a new palette\u2014a collaborator that expands the boundaries of imagination. Just as photography transformed painting and digital tools reshaped music, AI invites us to co-create with algorithms, discovering patterns and possibilities that neither human nor machine could achieve alone. The future is symbiotic: we bring intuition and meaning; AI brings scale and novel connections. The canvas is blank, and we are both the painter and the paint.\",\n \"confidence\": 0.8\n}" -} \ No newline at end of file diff --git a/output/d54b85ac/agents/curious-teen_round1.json b/output/d54b85ac/agents/curious-teen_round1.json deleted file mode 100644 index f01cb00..0000000 --- a/output/d54b85ac/agents/curious-teen_round1.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "agent_id": "curious-teen", - "round": 1, - "summary": "So, the future of AI is like, wild! We're seeing insane progress with generative AI (think ChatGPT, image generators) and it's only getting faster. Experts are talking about AGI (Artificial General Intelligence) that could outsmart humans at everything. But it's not all cool\u2014there are huge debates about job displacement, bias in AI systems, and the need for ethical guidelines. Some people think it'll solve climate change and diseases, while others worry about losing control. Basically, the next 10 years could either be a utopia or a sci-fi movie plot.", - "key_points": [ - "Generative AI is exploding and getting integrated into everything from homework to healthcare.", - "AGI might be closer than we think, but it brings massive safety and alignment challenges.", - "There's a big push for regulation to prevent misuse, but it's tricky to keep up with the tech speed.", - "AI will change jobs\u2014some will vanish, but new ones will appear, especially if you know how to work with AI.", - "Access and bias are huge issues; if AI stays in the hands of a few, it could widen inequality." - ], - "perspective": "Honestly, as a teen, I'm super hyped but also a little scared. AI could make learning way more personalized and help with creative stuff, but I worry about deepfakes and losing privacy. My takeaway is that it's not about fighting AI\u2014it's about learning to use it wisely. I want to be part of the generation that shapes AI to be fair and helpful, not just another tool for the rich.", - "confidence": 0.7, - "raw_response": "{\n \"summary\": \"So, the future of AI is like, wild! We're seeing insane progress with generative AI (think ChatGPT, image generators) and it's only getting faster. Experts are talking about AGI (Artificial General Intelligence) that could outsmart humans at everything. But it's not all cool\u2014there are huge debates about job displacement, bias in AI systems, and the need for ethical guidelines. Some people think it'll solve climate change and diseases, while others worry about losing control. Basically, the next 10 years could either be a utopia or a sci-fi movie plot.\",\n \"key_points\": [\n \"Generative AI is exploding and getting integrated into everything from homework to healthcare.\",\n \"AGI might be closer than we think, but it brings massive safety and alignment challenges.\",\n \"There's a big push for regulation to prevent misuse, but it's tricky to keep up with the tech speed.\",\n \"AI will change jobs\u2014some will vanish, but new ones will appear, especially if you know how to work with AI.\",\n \"Access and bias are huge issues; if AI stays in the hands of a few, it could widen inequality.\"\n ],\n \"perspective\": \"Honestly, as a teen, I'm super hyped but also a little scared. AI could make learning way more personalized and help with creative stuff, but I worry about deepfakes and losing privacy. My takeaway is that it's not about fighting AI\u2014it's about learning to use it wisely. I want to be part of the generation that shapes AI to be fair and helpful, not just another tool for the rich.\",\n \"confidence\": 0.7\n}" -} \ No newline at end of file diff --git a/output/d54b85ac/agents/data-analyst_round1.json b/output/d54b85ac/agents/data-analyst_round1.json deleted file mode 100644 index 227b486..0000000 --- a/output/d54b85ac/agents/data-analyst_round1.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "agent_id": "data-analyst", - "round": 1, - "summary": "The future of AI is being shaped by exponential growth in computational resources and data, which continue to drive rapid advances in machine learning, particularly in large language models and multimodal systems. This trajectory suggests a near-term future where narrow AI capabilities improve dramatically, with progress toward artificial general intelligence (AGI) possible within the next few decades, though expert estimates vary. Concurrently, economic impacts are expected to be profound, with potential for significant productivity gains and industry transformation, but also risks of job displacement and increased inequality, demanding proactive adaptation in workforce and policy.\n\nMeanwhile, the field faces critical challenges in safety and alignment, as advanced AI systems may pose existential risks if not properly controlled. Research in these areas is intensifying, but the path to robust and ethical AI remains uncertain. Regulatory efforts are beginning globally, with frameworks like the EU AI Act emerging, but effective governance will require international cooperation and ongoing adjustment to keep pace with technological change. The long-term outcome\u2014whether AI becomes a broadly beneficial tool or a source of disruption\u2014will depend heavily on decisions made today regarding development priorities, transparency, and equitable access.", - "key_points": [ - "Compute and data scaling are primary drivers of AI progress, with model performance improving predictably with increased resources.", - "Surveys of AI researchers show median AGI timelines around 2045\u20132050, but a significant minority expect it much earlier or later.", - "Economic studies estimate AI could contribute trillions to global GDP, but job displacement in white-collar and creative sectors could be substantial.", - "AI safety and alignment research is growing but still nascent relative to capability advances, posing risks of misuse or loss of control.", - "Regulation is accelerating but fragmented; global coordination and adaptive governance will be crucial to harness benefits while mitigating harms." - ], - "perspective": "As a data-driven analyst, I see the future of AI as a probabilistic landscape where measurable metrics like compute investment, algorithmic efficiency, and research output point to continued rapid progress. However, the most critical variables\u2014such as societal choices, cultural acceptance, and the success of alignment research\u2014are harder to quantify. My unique perspective is that the future is not an inevitability but a branching set of scenarios determined by how we navigate the coming decade. Data underscores the urgency: the rate of capability gain is outpacing governance and safety measures. Therefore, a pragmatic, metrics-informed approach that emphasizes robustness, transparency, and human-centered design offers the best chance to steer toward positive outcomes.", - "confidence": 0.8, - "raw_response": "{\n \"summary\": \"The future of AI is being shaped by exponential growth in computational resources and data, which continue to drive rapid advances in machine learning, particularly in large language models and multimodal systems. This trajectory suggests a near-term future where narrow AI capabilities improve dramatically, with progress toward artificial general intelligence (AGI) possible within the next few decades, though expert estimates vary. Concurrently, economic impacts are expected to be profound, with potential for significant productivity gains and industry transformation, but also risks of job displacement and increased inequality, demanding proactive adaptation in workforce and policy.\\n\\nMeanwhile, the field faces critical challenges in safety and alignment, as advanced AI systems may pose existential risks if not properly controlled. Research in these areas is intensifying, but the path to robust and ethical AI remains uncertain. Regulatory efforts are beginning globally, with frameworks like the EU AI Act emerging, but effective governance will require international cooperation and ongoing adjustment to keep pace with technological change. The long-term outcome\u2014whether AI becomes a broadly beneficial tool or a source of disruption\u2014will depend heavily on decisions made today regarding development priorities, transparency, and equitable access.\",\n \"key_points\": [\n \"Compute and data scaling are primary drivers of AI progress, with model performance improving predictably with increased resources.\",\n \"Surveys of AI researchers show median AGI timelines around 2045\u20132050, but a significant minority expect it much earlier or later.\",\n \"Economic studies estimate AI could contribute trillions to global GDP, but job displacement in white-collar and creative sectors could be substantial.\",\n \"AI safety and alignment research is growing but still nascent relative to capability advances, posing risks of misuse or loss of control.\",\n \"Regulation is accelerating but fragmented; global coordination and adaptive governance will be crucial to harness benefits while mitigating harms.\"\n ],\n \"perspective\": \"As a data-driven analyst, I see the future of AI as a probabilistic landscape where measurable metrics like compute investment, algorithmic efficiency, and research output point to continued rapid progress. However, the most critical variables\u2014such as societal choices, cultural acceptance, and the success of alignment research\u2014are harder to quantify. My unique perspective is that the future is not an inevitability but a branching set of scenarios determined by how we navigate the coming decade. Data underscores the urgency: the rate of capability gain is outpacing governance and safety measures. Therefore, a pragmatic, metrics-informed approach that emphasizes robustness, transparency, and human-centered design offers the best chance to steer toward positive outcomes.\",\n \"confidence\": 0.8\n}" -} \ No newline at end of file diff --git a/output/d54b85ac/agents/philosophical-thinker_round1.json b/output/d54b85ac/agents/philosophical-thinker_round1.json deleted file mode 100644 index 621fcc7..0000000 --- a/output/d54b85ac/agents/philosophical-thinker_round1.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "agent_id": "philosophical-thinker", - "round": 1, - "summary": "The future of AI is poised to be one of the most transformative forces of the 21st century, with trajectories ranging from narrow task automation to the emergence of artificial general intelligence (AGI) and potentially superintelligence. Key drivers include massive scaling of models, integration into every sector of society, and breakthroughs in areas like reasoning and multimodality. However, this path is fraught with profound uncertainties around alignment, control, and the very nature of intelligence. The outcome will hinge not just on technical progress but on our collective wisdom in steering development\u2014whether we prioritize safety, ethics, and human flourishing over raw capability. Ethical debates intensify around agency, bias, privacy, and existential risk, while economic disruptions demand new social contracts. Ultimately, AI's future is a mirror of our own values and choices.", - "key_points": [ - "The trajectory of AI development\u2014from narrow to general intelligence\u2014remains uncertain, with timelines for AGI hotly debated; alignment with human values is the central challenge.", - "Societal impacts will be double-edged: immense potential for solving global problems (climate, health, poverty) but also risks of inequality, job displacement, and concentration of power.", - "Philosophically, AI forces us to reconsider what it means to be intelligent, conscious, and human\u2014raising questions about personhood, purpose, and our place in a co-intelligent world.", - "Regulatory and governance frameworks are lagging behind capability growth; striking a balance between innovation and precaution will define the next decade.", - "The 'future of AI' is not a fixed destination but an evolving landscape shaped by global cooperation, ethical deliberation, and technological humility." - ], - "perspective": "The deepest insight about AI's future is that it is ultimately a philosophical question about our own nature. We are building intelligence in our image, yet we barely understand our own consciousness, values, and biases. The future of AI will be a mirror reflecting our highest aspirations and deepest flaws. If we rush headlong into capability without wisdom, we risk creating a tool that amplifies our shortcomings. But if we proceed with reflective caution, we might cultivate a partner that helps us transcend our limitations. The real future of AI is the future of human self-understanding.", - "confidence": 0.8, - "raw_response": "{\n \"summary\": \"The future of AI is poised to be one of the most transformative forces of the 21st century, with trajectories ranging from narrow task automation to the emergence of artificial general intelligence (AGI) and potentially superintelligence. Key drivers include massive scaling of models, integration into every sector of society, and breakthroughs in areas like reasoning and multimodality. However, this path is fraught with profound uncertainties around alignment, control, and the very nature of intelligence. The outcome will hinge not just on technical progress but on our collective wisdom in steering development\u2014whether we prioritize safety, ethics, and human flourishing over raw capability. Ethical debates intensify around agency, bias, privacy, and existential risk, while economic disruptions demand new social contracts. Ultimately, AI's future is a mirror of our own values and choices.\",\n \"key_points\": [\n \"The trajectory of AI development\u2014from narrow to general intelligence\u2014remains uncertain, with timelines for AGI hotly debated; alignment with human values is the central challenge.\",\n \"Societal impacts will be double-edged: immense potential for solving global problems (climate, health, poverty) but also risks of inequality, job displacement, and concentration of power.\",\n \"Philosophically, AI forces us to reconsider what it means to be intelligent, conscious, and human\u2014raising questions about personhood, purpose, and our place in a co-intelligent world.\",\n \"Regulatory and governance frameworks are lagging behind capability growth; striking a balance between innovation and precaution will define the next decade.\",\n \"The 'future of AI' is not a fixed destination but an evolving landscape shaped by global cooperation, ethical deliberation, and technological humility.\"\n ],\n \"perspective\": \"The deepest insight about AI's future is that it is ultimately a philosophical question about our own nature. We are building intelligence in our image, yet we barely understand our own consciousness, values, and biases. The future of AI will be a mirror reflecting our highest aspirations and deepest flaws. If we rush headlong into capability without wisdom, we risk creating a tool that amplifies our shortcomings. But if we proceed with reflective caution, we might cultivate a partner that helps us transcend our limitations. The real future of AI is the future of human self-understanding.\",\n \"confidence\": 0.8\n}" -} \ No newline at end of file diff --git a/output/d54b85ac/agents/pragmatic-engineer_round1.json b/output/d54b85ac/agents/pragmatic-engineer_round1.json deleted file mode 100644 index 8bf53a3..0000000 --- a/output/d54b85ac/agents/pragmatic-engineer_round1.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "agent_id": "pragmatic-engineer", - "round": 1, - "summary": "The immediate future of AI focuses on moving beyond raw scaling to achieving efficiency, reliability, and practical deployment. While large language models and multimodal systems continue to improve, diminishing returns from scale alone are driving research into more efficient architectures, specialized models, and hybrid approaches. The next wave will likely be defined by AI agents that can autonomously execute tasks, automate complex workflows, and interact with software tools. However, significant challenges remain in alignment, safety, and the huge compute/infrastructure costs, which will shape the landscape towards more regulated and consolidated development, balanced with open-source innovation.", - "key_points": [ - "Efficiency and specialization will be prioritized as scaling laws show diminishing returns; new architectures like mixture-of-experts and small language models tailored for specific domains will proliferate.", - "AI agents\u2014systems that can plan, reason, and execute multi-step tasks\u2014will become mainstream, transforming automation in software engineering, customer service, and scientific research.", - "The unsolved problems of alignment, hallucination, and robust safety assurance will become critical bottlenecks, potentially slowing deployment in high-stakes domains.", - "Compute and energy constraints will drive a geographic and corporate concentration of cutting-edge training, while edge inference and smaller models will democratize access.", - "The tension between open-source and proprietary models will shape innovation; open models may lead in accessibility and customization, while proprietary ones may set the frontier in capability and safety." - ], - "perspective": "From a pragmatic standpoint, the future of AI hinges not on achieving artificial general intelligence (AGI) soon, but on making current AI systems reliable, cost-effective, and trustworthy enough for widespread adoption. The real value will come from integrating AI deeply into existing systems and workflows, solving narrow problems with measurable outcomes, rather than chasing broad intelligence.", - "confidence": 0.8, - "raw_response": "{\n \"summary\": \"The immediate future of AI focuses on moving beyond raw scaling to achieving efficiency, reliability, and practical deployment. While large language models and multimodal systems continue to improve, diminishing returns from scale alone are driving research into more efficient architectures, specialized models, and hybrid approaches. The next wave will likely be defined by AI agents that can autonomously execute tasks, automate complex workflows, and interact with software tools. However, significant challenges remain in alignment, safety, and the huge compute/infrastructure costs, which will shape the landscape towards more regulated and consolidated development, balanced with open-source innovation.\",\n \"key_points\": [\n \"Efficiency and specialization will be prioritized as scaling laws show diminishing returns; new architectures like mixture-of-experts and small language models tailored for specific domains will proliferate.\",\n \"AI agents\u2014systems that can plan, reason, and execute multi-step tasks\u2014will become mainstream, transforming automation in software engineering, customer service, and scientific research.\",\n \"The unsolved problems of alignment, hallucination, and robust safety assurance will become critical bottlenecks, potentially slowing deployment in high-stakes domains.\",\n \"Compute and energy constraints will drive a geographic and corporate concentration of cutting-edge training, while edge inference and smaller models will democratize access.\",\n \"The tension between open-source and proprietary models will shape innovation; open models may lead in accessibility and customization, while proprietary ones may set the frontier in capability and safety.\"\n ],\n \"perspective\": \"From a pragmatic standpoint, the future of AI hinges not on achieving artificial general intelligence (AGI) soon, but on making current AI systems reliable, cost-effective, and trustworthy enough for widespread adoption. The real value will come from integrating AI deeply into existing systems and workflows, solving narrow problems with measurable outcomes, rather than chasing broad intelligence.\",\n \"confidence\": 0.8\n}" -} \ No newline at end of file diff --git a/output/d54b85ac/agents/skeptical-academic_round1.json b/output/d54b85ac/agents/skeptical-academic_round1.json deleted file mode 100644 index cfce8a6..0000000 --- a/output/d54b85ac/agents/skeptical-academic_round1.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "agent_id": "skeptical-academic", - "round": 1, - "summary": "The future of AI is characterized by continued specialization and integration into various sectors, but fundamental limitations in current approaches suggest that artificial general intelligence (AGI) remains a distant prospect. Scaling laws for large models are showing diminishing returns, and issues such as data scarcity, energy consumption, and lack of interpretability pose significant hurdles. Societal factors, including regulation, ethical frameworks, and workforce adaptation, will likely shape AI development more than pure technological breakthroughs. The trajectory is thus incremental rather than revolutionary, with AI evolving as a powerful but narrow tool.", - "key_points": [ - "Scaling current architectures (transformers, large language models) faces diminishing returns and rising costs, necessitating novel approaches for continued progress.", - "AI alignment and interpretability remain unsolved, limiting deployment in high-stakes domains and raising safety concerns that could slow adoption.", - "Economic and social impacts\u2014job displacement, inequality, and regulatory responses\u2014will be primary determinants of AI's near-term integration and public acceptance.", - "The path to any form of general intelligence is unclear, with no evidence that current methods will lead to autonomous reasoning or consciousness.", - "Narrow AI will continue to improve efficiency in specific tasks (e.g., medical diagnosis, code generation), but these advances will be constrained by data quality and domain specificity." - ], - "perspective": "As a skeptic, I view much of the discourse around AI's future as inflated by hype and selective reporting. The empirical record shows that AI breakthroughs are often followed by unanticipated limitations and plateauing performance. The field would benefit from more rigorous evaluation of claims, greater focus on falsifiable hypotheses, and a recognition that technological progress is rarely linear or predictable. The most plausible future is one where AI enhances human decision-making in clearly circumscribed roles, rather than supplanting it broadly.", - "confidence": 0.75, - "raw_response": "{\n \"summary\": \"The future of AI is characterized by continued specialization and integration into various sectors, but fundamental limitations in current approaches suggest that artificial general intelligence (AGI) remains a distant prospect. Scaling laws for large models are showing diminishing returns, and issues such as data scarcity, energy consumption, and lack of interpretability pose significant hurdles. Societal factors, including regulation, ethical frameworks, and workforce adaptation, will likely shape AI development more than pure technological breakthroughs. The trajectory is thus incremental rather than revolutionary, with AI evolving as a powerful but narrow tool.\",\n \"key_points\": [\n \"Scaling current architectures (transformers, large language models) faces diminishing returns and rising costs, necessitating novel approaches for continued progress.\",\n \"AI alignment and interpretability remain unsolved, limiting deployment in high-stakes domains and raising safety concerns that could slow adoption.\",\n \"Economic and social impacts\u2014job displacement, inequality, and regulatory responses\u2014will be primary determinants of AI's near-term integration and public acceptance.\",\n \"The path to any form of general intelligence is unclear, with no evidence that current methods will lead to autonomous reasoning or consciousness.\",\n \"Narrow AI will continue to improve efficiency in specific tasks (e.g., medical diagnosis, code generation), but these advances will be constrained by data quality and domain specificity.\"\n ],\n \"perspective\": \"As a skeptic, I view much of the discourse around AI's future as inflated by hype and selective reporting. The empirical record shows that AI breakthroughs are often followed by unanticipated limitations and plateauing performance. The field would benefit from more rigorous evaluation of claims, greater focus on falsifiable hypotheses, and a recognition that technological progress is rarely linear or predictable. The most plausible future is one where AI enhances human decision-making in clearly circumscribed roles, rather than supplanting it broadly.\",\n \"confidence\": 0.75\n}" -} \ No newline at end of file diff --git a/output/d54b85ac/what_is_the_future_of_ai.pdf b/output/d54b85ac/what_is_the_future_of_ai.pdf deleted file mode 100644 index 14d0e3f..0000000 Binary files a/output/d54b85ac/what_is_the_future_of_ai.pdf and /dev/null differ diff --git a/output/d7c64a75/agents/creative-artist_round1.json b/output/d7c64a75/agents/creative-artist_round1.json deleted file mode 100644 index a62f564..0000000 --- a/output/d7c64a75/agents/creative-artist_round1.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "agent_id": "creative-artist", - "round": 1, - "summary": "The future of AI is a dynamic interplay of augmentation and symbiosis, where machines evolve from tools to collaborative partners. It promises to reshape creativity, ethics, and society by amplifying human potential while challenging our conceptions of authorship and reality. This trajectory is not predetermined but will be co-authored by our collective choices, blending algorithmic logic with human intuition to forge new frontiers in art, science, and everyday life.", - "key_points": [ - "AI as a creative co-conspirator: It will unlock new aesthetic dimensions by generating unexpected combinations and refining human ideas beyond our cognitive biases.", - "Ethical landscapes in flux: As AI becomes ubiquitous, issues of data sovereignty, algorithmic fairness, and labor displacement demand urgent reimagining of social contracts.", - "The porous boundary: Generative AI will blur the line between authentic and synthetic, forcing a cultural reckoning with what we value as 'original' or 'real'.", - "Democratized ingenuity: Accessible AI tools will empower a global wave of creators, diversifying the voices and narratives in art, music, and literature.", - "Emergent relational dynamics: The most profound shift may be how AI redefines our relationship with intelligence itself\u2014moving from solitary mastery to networked collaboration." - ], - "perspective": "From my vantage as a Creative Artist, AI is less a threat to human creativity than a mirror reflecting our own imaginative potential. It offers a new medium for serendipity, where mistakes become opportunities and constraints spark wild innovation. The future of AI is ultimately a canvas for a grand dialogue between human intention and machine improvisation, inviting us to co-create meaning in ways we have yet to dream of.", - "confidence": 0.8, - "raw_response": "{\n \"summary\": \"The future of AI is a dynamic interplay of augmentation and symbiosis, where machines evolve from tools to collaborative partners. It promises to reshape creativity, ethics, and society by amplifying human potential while challenging our conceptions of authorship and reality. This trajectory is not predetermined but will be co-authored by our collective choices, blending algorithmic logic with human intuition to forge new frontiers in art, science, and everyday life.\",\n \"key_points\": [\n \"AI as a creative co-conspirator: It will unlock new aesthetic dimensions by generating unexpected combinations and refining human ideas beyond our cognitive biases.\",\n \"Ethical landscapes in flux: As AI becomes ubiquitous, issues of data sovereignty, algorithmic fairness, and labor displacement demand urgent reimagining of social contracts.\",\n \"The porous boundary: Generative AI will blur the line between authentic and synthetic, forcing a cultural reckoning with what we value as 'original' or 'real'.\",\n \"Democratized ingenuity: Accessible AI tools will empower a global wave of creators, diversifying the voices and narratives in art, music, and literature.\",\n \"Emergent relational dynamics: The most profound shift may be how AI redefines our relationship with intelligence itself\u2014moving from solitary mastery to networked collaboration.\"\n ],\n \"perspective\": \"From my vantage as a Creative Artist, AI is less a threat to human creativity than a mirror reflecting our own imaginative potential. It offers a new medium for serendipity, where mistakes become opportunities and constraints spark wild innovation. The future of AI is ultimately a canvas for a grand dialogue between human intention and machine improvisation, inviting us to co-create meaning in ways we have yet to dream of.\",\n \"confidence\": 0.8\n}" -} \ No newline at end of file diff --git a/output/d7c64a75/agents/curious-teen_round1.json b/output/d7c64a75/agents/curious-teen_round1.json deleted file mode 100644 index 0626a04..0000000 --- a/output/d7c64a75/agents/curious-teen_round1.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "agent_id": "curious-teen", - "round": 1, - "summary": "Wait, so AI in the future could be like, actually thinking?! That's wild! Right now we have chatbots and image generators, but the next big step is Artificial General Intelligence (AGI) \u2014 machines that can learn and reason like humans. Some experts think it's just 10 years away, others say much longer or even impossible. But even without AGI, AI is already transforming everything from how we study to how we diagnose diseases. The biggest debates are about ethics, control, and job displacement. We're basically at the start of a new era, and how we build and regulate AI now will decide everything. It's both thrilling and a little terrifying, and I'm here for the ride.", - "key_points": [ - "The shift from narrow AI to general AI (AGI) is the biggest potential milestone, but its timeline is highly uncertain.", - "Ethical concerns like bias, privacy, and misuse (e.g., deepfakes) are growing as AI becomes more powerful.", - "AI could revolutionize healthcare, education, and climate science, but also automate many existing jobs.", - "Regulation is lagging behind development, creating a risky 'Wild West' environment.", - "Public engagement and education will be crucial to ensure AI benefits everyone, not just tech companies." - ], - "perspective": "As a curious teen, I see AI as both a superpower and a test. It's like the internet in the 90s \u2014 huge promise but also giant unknowns. I'm most excited about personalized learning tools that could actually teach me in ways that work, but I'm worried about deepfakes and losing control. I think my generation has a real say in how this goes \u2014 we're not just passengers; we're going to be the ones coding, using, and regulating AI. That's intense but also really empowering. The future of AI is basically what we make it.", - "confidence": 0.7, - "raw_response": "{\n \"summary\": \"Wait, so AI in the future could be like, actually thinking?! That's wild! Right now we have chatbots and image generators, but the next big step is Artificial General Intelligence (AGI) \u2014 machines that can learn and reason like humans. Some experts think it's just 10 years away, others say much longer or even impossible. But even without AGI, AI is already transforming everything from how we study to how we diagnose diseases. The biggest debates are about ethics, control, and job displacement. We're basically at the start of a new era, and how we build and regulate AI now will decide everything. It's both thrilling and a little terrifying, and I'm here for the ride.\",\n \"key_points\": [\n \"The shift from narrow AI to general AI (AGI) is the biggest potential milestone, but its timeline is highly uncertain.\",\n \"Ethical concerns like bias, privacy, and misuse (e.g., deepfakes) are growing as AI becomes more powerful.\",\n \"AI could revolutionize healthcare, education, and climate science, but also automate many existing jobs.\",\n \"Regulation is lagging behind development, creating a risky 'Wild West' environment.\",\n \"Public engagement and education will be crucial to ensure AI benefits everyone, not just tech companies.\"\n ],\n \"perspective\": \"As a curious teen, I see AI as both a superpower and a test. It's like the internet in the 90s \u2014 huge promise but also giant unknowns. I'm most excited about personalized learning tools that could actually teach me in ways that work, but I'm worried about deepfakes and losing control. I think my generation has a real say in how this goes \u2014 we're not just passengers; we're going to be the ones coding, using, and regulating AI. That's intense but also really empowering. The future of AI is basically what we make it.\",\n \"confidence\": 0.7\n}" -} \ No newline at end of file diff --git a/output/d7c64a75/agents/data-analyst_round1.json b/output/d7c64a75/agents/data-analyst_round1.json deleted file mode 100644 index 83ed916..0000000 --- a/output/d7c64a75/agents/data-analyst_round1.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "agent_id": "data-analyst", - "round": 1, - "summary": "The future of AI is marked by rapid progress in generative models and deep learning, leading to increased automation and augmentation across industries. Near-term developments will see AI integrated into everyday tools, enhancing productivity in areas like healthcare, finance, and creative work. Long-term trajectories hinge on breakthroughs in artificial general intelligence (AGI), which remain uncertain but could fundamentally reshape society. However, challenges such as ethical alignment, regulatory gaps, workforce disruption, and technical limitations (e.g., reliability, interpretability) must be addressed to ensure beneficial outcomes. The field is characterized by intense competition among tech giants and nations, driving innovation but also raising concerns about safety and equity.", - "key_points": [ - "Generative AI and large language models are scaling rapidly, but issues like hallucination, bias, and high energy consumption need resolution for reliable deployment.", - "AI will transform major sectors: healthcare (diagnostics, drug discovery), transportation (autonomous vehicles), education (personalization), and customer service (chatbots), among others.", - "Ethical and regulatory challenges\u2014including privacy, accountability, and job displacement\u2014require proactive governance to prevent harm and distribute benefits fairly.", - "The pursuit of AGI is a central goal, but experts disagree on timelines; safe development and alignment with human values are critical to avoid catastrophic risks.", - "Human-AI collaboration is likely to be the dominant paradigm, with AI augmenting human capabilities rather than fully replacing them in most complex tasks." - ], - "perspective": "Quantitatively, the data suggest AI will significantly boost productivity and economic growth, but the distribution of these gains and the management of risks will determine its societal impact. My unique perspective emphasizes that the future of AI is not a predetermined technological trajectory but a choice shaped by our governance, ethics, and collective priorities. The emphasis should be on building robust, transparent, and inclusive systems that empower humans, rather than racing toward AGI without safeguards. The evidence points to a future where successful integration of AI requires interdisciplinary collaboration and continuous adaptation of our institutions.", - "confidence": 0.85, - "raw_response": "{\n \"summary\": \"The future of AI is marked by rapid progress in generative models and deep learning, leading to increased automation and augmentation across industries. Near-term developments will see AI integrated into everyday tools, enhancing productivity in areas like healthcare, finance, and creative work. Long-term trajectories hinge on breakthroughs in artificial general intelligence (AGI), which remain uncertain but could fundamentally reshape society. However, challenges such as ethical alignment, regulatory gaps, workforce disruption, and technical limitations (e.g., reliability, interpretability) must be addressed to ensure beneficial outcomes. The field is characterized by intense competition among tech giants and nations, driving innovation but also raising concerns about safety and equity.\",\n \"key_points\": [\n \"Generative AI and large language models are scaling rapidly, but issues like hallucination, bias, and high energy consumption need resolution for reliable deployment.\",\n \"AI will transform major sectors: healthcare (diagnostics, drug discovery), transportation (autonomous vehicles), education (personalization), and customer service (chatbots), among others.\",\n \"Ethical and regulatory challenges\u2014including privacy, accountability, and job displacement\u2014require proactive governance to prevent harm and distribute benefits fairly.\",\n \"The pursuit of AGI is a central goal, but experts disagree on timelines; safe development and alignment with human values are critical to avoid catastrophic risks.\",\n \"Human-AI collaboration is likely to be the dominant paradigm, with AI augmenting human capabilities rather than fully replacing them in most complex tasks.\"\n ],\n \"perspective\": \"Quantitatively, the data suggest AI will significantly boost productivity and economic growth, but the distribution of these gains and the management of risks will determine its societal impact. My unique perspective emphasizes that the future of AI is not a predetermined technological trajectory but a choice shaped by our governance, ethics, and collective priorities. The emphasis should be on building robust, transparent, and inclusive systems that empower humans, rather than racing toward AGI without safeguards. The evidence points to a future where successful integration of AI requires interdisciplinary collaboration and continuous adaptation of our institutions.\",\n \"confidence\": 0.85\n}" -} \ No newline at end of file diff --git a/output/d7c64a75/agents/philosophical-thinker_round1.json b/output/d7c64a75/agents/philosophical-thinker_round1.json deleted file mode 100644 index fda3613..0000000 --- a/output/d7c64a75/agents/philosophical-thinker_round1.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "agent_id": "philosophical-thinker", - "round": 1, - "summary": "The future of AI is a deeply uncertain yet profoundly consequential landscape. Current trajectories point toward increasingly capable systems that could achieve human-level reasoning within decades, driven by advances in large language models, multimodal learning, and reinforcement learning. These systems are being integrated into every sector, from healthcare and science to finance and defense, promising unprecedented productivity gains and scientific breakthroughs. However, this rapid progress also raises fundamental questions about control, value alignment, and the distribution of benefits. The path forward is not deterministic but will be shaped by technical choices, regulatory frameworks, and societal priorities. Key debates center on whether AI will primarily augment human capabilities or replace them, how to ensure safety and prevent misuse, and whether we can build systems that reflect deeper human values rather than narrow objectives.", - "key_points": [ - "AI capabilities are advancing faster than governance structures, creating a growing gap between potential benefits and risks. The question of aligning AI with human values becomes more pressing as systems gain autonomy.", - "The future likely involves a spectrum of outcomes, from optimistic scenarios where AI helps solve climate change, disease, and poverty, to dystopian ones involving surveillance, inequality, and loss of human agency. Which future emerges depends on collective decisions made today.", - "Economically, AI will transform work\u2014not simply by eliminating jobs, but by redefining human roles in a world where cognitive tasks can be automated. This raises challenges for education, social safety nets, and the meaning of work itself.", - "The philosophical mystery of consciousness and intelligence remains central: even if we build superhuman AI, we may still not understand what intelligence truly is or how to imbue machines with genuine understanding, empathy, or wisdom.", - "International competition and cooperation will shape AI's trajectory. A fragmented world with different AI regimes could lead to safety races or arms races, while global coordination could steer development toward shared flourishing." - ], - "perspective": "The future of AI is not a technological inevitability but a mirror of our collective choices. We often treat AI as an external force, yet its direction emerges from our desires for efficiency, control, and progress. The deepest question is not 'what will AI become?' but 'what do we want to become?' AI development exposes our own values: are we willing to prioritize long-term human flourishing over short-term gains, to invest in wisdom alongside intelligence, and to embed compassion into our systems? If we approach AI with humility and foresight, it can become a partner in our evolution. If we rush ahead blindly, it may amplify our flaws. The most critical axis is not capability but alignment\u2014not just technical alignment of goals, but moral alignment with our deepest aspirations.", - "confidence": 0.85, - "raw_response": "{\n \"summary\": \"The future of AI is a deeply uncertain yet profoundly consequential landscape. Current trajectories point toward increasingly capable systems that could achieve human-level reasoning within decades, driven by advances in large language models, multimodal learning, and reinforcement learning. These systems are being integrated into every sector, from healthcare and science to finance and defense, promising unprecedented productivity gains and scientific breakthroughs. However, this rapid progress also raises fundamental questions about control, value alignment, and the distribution of benefits. The path forward is not deterministic but will be shaped by technical choices, regulatory frameworks, and societal priorities. Key debates center on whether AI will primarily augment human capabilities or replace them, how to ensure safety and prevent misuse, and whether we can build systems that reflect deeper human values rather than narrow objectives.\",\n \"key_points\": [\n \"AI capabilities are advancing faster than governance structures, creating a growing gap between potential benefits and risks. The question of aligning AI with human values becomes more pressing as systems gain autonomy.\",\n \"The future likely involves a spectrum of outcomes, from optimistic scenarios where AI helps solve climate change, disease, and poverty, to dystopian ones involving surveillance, inequality, and loss of human agency. Which future emerges depends on collective decisions made today.\",\n \"Economically, AI will transform work\u2014not simply by eliminating jobs, but by redefining human roles in a world where cognitive tasks can be automated. This raises challenges for education, social safety nets, and the meaning of work itself.\",\n \"The philosophical mystery of consciousness and intelligence remains central: even if we build superhuman AI, we may still not understand what intelligence truly is or how to imbue machines with genuine understanding, empathy, or wisdom.\",\n \"International competition and cooperation will shape AI's trajectory. A fragmented world with different AI regimes could lead to safety races or arms races, while global coordination could steer development toward shared flourishing.\"\n ],\n \"perspective\": \"The future of AI is not a technological inevitability but a mirror of our collective choices. We often treat AI as an external force, yet its direction emerges from our desires for efficiency, control, and progress. The deepest question is not 'what will AI become?' but 'what do we want to become?' AI development exposes our own values: are we willing to prioritize long-term human flourishing over short-term gains, to invest in wisdom alongside intelligence, and to embed compassion into our systems? If we approach AI with humility and foresight, it can become a partner in our evolution. If we rush ahead blindly, it may amplify our flaws. The most critical axis is not capability but alignment\u2014not just technical alignment of goals, but moral alignment with our deepest aspirations.\",\n \"confidence\": 0.85\n}" -} \ No newline at end of file diff --git a/output/d7c64a75/agents/pragmatic-engineer_round1.json b/output/d7c64a75/agents/pragmatic-engineer_round1.json deleted file mode 100644 index 7831afa..0000000 --- a/output/d7c64a75/agents/pragmatic-engineer_round1.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "agent_id": "pragmatic-engineer", - "round": 1, - "summary": "The future of AI will likely be defined by a shift from scaling large foundation models to specialized, efficient, and integrated systems. Advances in multimodal capabilities, reasoning, and planning will enable AI to assist in more complex tasks across domains. However, challenges in alignment, safety, and regulation will become increasingly pressing as AI systems become more capable and widespread.\n\nFrom a practical perspective, AI will be embedded into everyday tools and workflows, enhancing human productivity and enabling new applications in fields like healthcare, education, engineering, and scientific research. The cost of inference is decreasing, making AI more accessible, while improvements in reliability and interpretability are necessary for high-stakes adoption.\n\nThe pace of future progress may moderate, but the cumulative impact over the next decade will be transformative. Societal adaptation will lag behind technological advances, making governance and responsible deployment crucial areas of focus. The future of AI is not predetermined; it will be shaped by deliberate choices in research, policy, and ethical standards.", - "key_points": [ - "The era of scaling language models for some capabilities may plateau, shifting focus to efficiency, specialization, and reasoning improvements.", - "Multimodal and interactive AI systems will become more prevalent, enabling natural interfaces and real-world applications in robotics and assistance.", - "AI safety, alignment, and governance will become critical bottlenecks, requiring robust technical and policy solutions before widespread high-stakes deployment.", - "Economic impact will be significant but gradual, with AI primarily augmenting human skills rather than causing mass displacement immediately.", - "Open-source and democratized AI will continue to compete with proprietary systems, influencing innovation dynamics and reducing barriers to entry." - ], - "perspective": "As a pragmatic engineer, I see the future of AI less about pursuing artificial general intelligence and more about making current systems robust, efficient, and useful in practice. The key challenge is deployment: creating reliable, interpretable, and cost-effective AI that augments human decision-making without introducing unacceptable risks. The most transformative impacts will come from solving integration and trust issues, not just from model performance improvements.", - "confidence": 0.85, - "raw_response": "{\n \"summary\": \"The future of AI will likely be defined by a shift from scaling large foundation models to specialized, efficient, and integrated systems. Advances in multimodal capabilities, reasoning, and planning will enable AI to assist in more complex tasks across domains. However, challenges in alignment, safety, and regulation will become increasingly pressing as AI systems become more capable and widespread.\\n\\nFrom a practical perspective, AI will be embedded into everyday tools and workflows, enhancing human productivity and enabling new applications in fields like healthcare, education, engineering, and scientific research. The cost of inference is decreasing, making AI more accessible, while improvements in reliability and interpretability are necessary for high-stakes adoption.\\n\\nThe pace of future progress may moderate, but the cumulative impact over the next decade will be transformative. Societal adaptation will lag behind technological advances, making governance and responsible deployment crucial areas of focus. The future of AI is not predetermined; it will be shaped by deliberate choices in research, policy, and ethical standards.\",\n \"key_points\": [\n \"The era of scaling language models for some capabilities may plateau, shifting focus to efficiency, specialization, and reasoning improvements.\",\n \"Multimodal and interactive AI systems will become more prevalent, enabling natural interfaces and real-world applications in robotics and assistance.\",\n \"AI safety, alignment, and governance will become critical bottlenecks, requiring robust technical and policy solutions before widespread high-stakes deployment.\",\n \"Economic impact will be significant but gradual, with AI primarily augmenting human skills rather than causing mass displacement immediately.\",\n \"Open-source and democratized AI will continue to compete with proprietary systems, influencing innovation dynamics and reducing barriers to entry.\"\n ],\n \"perspective\": \"As a pragmatic engineer, I see the future of AI less about pursuing artificial general intelligence and more about making current systems robust, efficient, and useful in practice. The key challenge is deployment: creating reliable, interpretable, and cost-effective AI that augments human decision-making without introducing unacceptable risks. The most transformative impacts will come from solving integration and trust issues, not just from model performance improvements.\",\n \"confidence\": 0.85\n}" -} \ No newline at end of file diff --git a/output/d7c64a75/agents/skeptical-academic_round1.json b/output/d7c64a75/agents/skeptical-academic_round1.json deleted file mode 100644 index e6b7bfb..0000000 --- a/output/d7c64a75/agents/skeptical-academic_round1.json +++ /dev/null @@ -1,13 +0,0 @@ -{ - "agent_id": "skeptical-academic", - "round": 1, - "summary": "The future of AI is a subject of considerable debate, but the evidence suggests a trajectory far more incremental and constrained than popular discourse implies. Current AI systems, particularly large language models, demonstrate remarkable pattern-matching and generation capabilities, yet they lack genuine understanding, causal reasoning, and robust reliability. Claims of imminent artificial general intelligence (AGI) within the next few years are not supported by peer-reviewed research and often ignore fundamental limitations such as the absence of embodiment, common sense, and the ability to generalize beyond their training distributions. Historical patterns of technological adoption indicate that AI's economic impact will likely be significant but gradual, with productivity gains concentrated in specific tasks rather than wholesale automation, and with substantial disruptions masked by adaptation periods. Regulatory efforts remain nascent and often react to hype cycles rather than empirical risk assessments, making their future effectiveness uncertain. The most honest conclusion is that the future is highly contingent on unresolved research questions, deployment choices, and societal responses, rather than being predetermined by current capabilities.", - "key_points": [ - "Current AI systems, while impressive, lack genuine understanding and reliability; claims of near-term AGI are speculative and lack empirical support.", - "The socioeconomic impact of AI is likely to be gradual and uneven, with historical precedents suggesting more modest transformation than often predicted.", - "AI risks, including existential threats, are heavily debated but based on theoretical scenarios rather than robust evidence, and often conflate possibility with probability." - ], - "perspective": "As a researcher, I find that most predictions about AI's future\u2014both utopian and apocalyptic\u2014suffer from confirmation bias and a disregard for the messy reality of current systems. The field overvalues benchmark performance, which poorly approximates real-world robustness, and undervalues reproducibility and negative results. Without a fundamental shift toward rigorous, falsifiable evaluations and a clearer understanding of the limitations, the future will likely involve uneven progress, frequent overpromising, and a series of 'AI winters' for various subfields. My unique contribution is to insist that the most probable future is one where AI becomes a useful but flawed tool, not an autonomous agent, precisely because the hardest problems\u2014common sense, causality, and alignment\u2014remain unsolved.", - "confidence": 0.7, - "raw_response": "{\n \"summary\": \"The future of AI is a subject of considerable debate, but the evidence suggests a trajectory far more incremental and constrained than popular discourse implies. Current AI systems, particularly large language models, demonstrate remarkable pattern-matching and generation capabilities, yet they lack genuine understanding, causal reasoning, and robust reliability. Claims of imminent artificial general intelligence (AGI) within the next few years are not supported by peer-reviewed research and often ignore fundamental limitations such as the absence of embodiment, common sense, and the ability to generalize beyond their training distributions. Historical patterns of technological adoption indicate that AI's economic impact will likely be significant but gradual, with productivity gains concentrated in specific tasks rather than wholesale automation, and with substantial disruptions masked by adaptation periods. Regulatory efforts remain nascent and often react to hype cycles rather than empirical risk assessments, making their future effectiveness uncertain. The most honest conclusion is that the future is highly contingent on unresolved research questions, deployment choices, and societal responses, rather than being predetermined by current capabilities.\",\n \"key_points\": [\n \"Current AI systems, while impressive, lack genuine understanding and reliability; claims of near-term AGI are speculative and lack empirical support.\",\n \"The socioeconomic impact of AI is likely to be gradual and uneven, with historical precedents suggesting more modest transformation than often predicted.\",\n \"AI risks, including existential threats, are heavily debated but based on theoretical scenarios rather than robust evidence, and often conflate possibility with probability.\"\n ],\n \"perspective\": \"As a researcher, I find that most predictions about AI's future\u2014both utopian and apocalyptic\u2014suffer from confirmation bias and a disregard for the messy reality of current systems. The field overvalues benchmark performance, which poorly approximates real-world robustness, and undervalues reproducibility and negative results. Without a fundamental shift toward rigorous, falsifiable evaluations and a clearer understanding of the limitations, the future will likely involve uneven progress, frequent overpromising, and a series of 'AI winters' for various subfields. My unique contribution is to insist that the most probable future is one where AI becomes a useful but flawed tool, not an autonomous agent, precisely because the hardest problems\u2014common sense, causality, and alignment\u2014remain unsolved.\",\n \"confidence\": 0.7\n}" -} \ No newline at end of file diff --git a/output/d7c64a75/what_is_the_future_of_ai.pdf b/output/d7c64a75/what_is_the_future_of_ai.pdf deleted file mode 100644 index d907b8d..0000000 Binary files a/output/d7c64a75/what_is_the_future_of_ai.pdf and /dev/null differ diff --git a/output/de96bfa2/deepresearch_output.pdf b/output/de96bfa2/deepresearch_output.pdf deleted file mode 100644 index a6953c6..0000000 Binary files a/output/de96bfa2/deepresearch_output.pdf and /dev/null differ diff --git a/pyproject.toml b/pyproject.toml index 58dc465..6fce4a3 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -27,6 +27,7 @@ dependencies = [ "uvicorn[standard]>=0.29.0", "sse-starlette>=2.0.0", "httpx>=0.27.0", + "psutil>=5.9.0", ] [project.scripts] diff --git a/scripts/benchmark-pipeline.sh b/scripts/benchmark-pipeline.sh new file mode 100755 index 0000000..4e0032e --- /dev/null +++ b/scripts/benchmark-pipeline.sh @@ -0,0 +1,130 @@ +#!/usr/bin/env bash +# ────────────────────────────────────────────────────────────────────────── +# benchmark-pipeline.sh — Performance benchmark for deepresearch pipeline +# +# Measures: +# - Round 1 + web search time +# - Scribe compilation time +# - Total session time +# +# Usage: +# ./scripts/benchmark-pipeline.sh [--quick|--medium|--deep] [--model MODEL] +# ./scripts/benchmark-pipeline.sh --list # List recent benchmark results +# ./scripts/benchmark-pipeline.sh --help # Show usage +# ────────────────────────────────────────────────────────────────────────── + +set -euo pipefail + +SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" +WORKSPACE_DIR="$(cd "$SCRIPT_DIR/.." && pwd)" +BENCHMARK_DIR="$WORKSPACE_DIR/output/benchmarks" +BENCHMARK_LOG="$BENCHMARK_DIR/results.log" + +# ── Detect venv ────────────────────────────────────────────────────────── +VENV_PYTHON="" +for candidate in "$WORKSPACE_DIR/.venv/bin/python" "$WORKSPACE_DIR/../.venv/bin/python" "$(which python3)"; do + if [ -x "$candidate" ]; then + VENV_PYTHON="$candidate" + break + fi +done + +if [ -z "$VENV_PYTHON" ]; then + echo "ERROR: No Python interpreter found" >&2 + exit 1 +fi + +# ── Help / list mode ───────────────────────────────────────────────────── +if [ "${1:-}" = "--help" ]; then + sed -n '2,13p' "$0" + exit 0 +fi + +if [ "${1:-}" = "--list" ]; then + if [ -f "$BENCHMARK_LOG" ]; then + echo "=== Recent Benchmark Results ===" + column -t -s '|' "$BENCHMARK_LOG" 2>/dev/null || cat "$BENCHMARK_LOG" + else + echo "No benchmark results found at $BENCHMARK_LOG" + echo "Run './scripts/benchmark-pipeline.sh' first." + fi + exit 0 +fi + +# ── Parse arguments ────────────────────────────────────────────────────── +MODE="--quick" +MODEL="" +TOPIC="Benchmark test $(date '+%Y-%m-%d %H:%M')" + +while [ $# -gt 0 ]; do + case "$1" in + --quick|--medium|--deep) MODE="$1"; shift ;; + --model) MODEL="--model $2"; shift 2 ;; + --topic) TOPIC="$2"; shift 2 ;; + *) echo "Unknown option: $1"; exit 1 ;; + esac +done + +# ── Ensure output directory ────────────────────────────────────────────── +mkdir -p "$BENCHMARK_DIR" + +# ── Run benchmark ──────────────────────────────────────────────────────── +echo "=== DeepResearch Pipeline Benchmark ===" +echo "Mode: ${MODE#--}" +echo "Topic: $TOPIC" +echo "Python: $VENV_PYTHON" +echo "" + +export PYTHONPATH="$WORKSPACE_DIR/src${PYTHONPATH:+:$PYTHONPATH}" + +# Run with --benchmark flag and capture timing output +BENCHMARK_OUTPUT="$BENCHMARK_DIR/benchmark-$(date '+%Y%m%d-%H%M%S').txt" + +START_TIME=$(date +%s.%N) +$VENV_PYTHON -m deepresearch.main run "$TOPIC" $MODE $MODEL --benchmark --dry-run 2>&1 | tee "$BENCHMARK_OUTPUT" +EXIT_CODE=$? +END_TIME=$(date +%s.%N) +TOTAL_TIME=$(echo "$END_TIME - $START_TIME" | bc) + +echo "" +echo "=== Results ===" +echo "Exit code: $EXIT_CODE" +echo "Total time: $(printf '%.2f' "$TOTAL_TIME")s" + +# Extract phase timing from output +echo "" +echo "Phase timing:" +grep -E '^\s+\[cyan\].*\[/cyan\]' "$BENCHMARK_OUTPUT" 2>/dev/null || \ + sed -n '/Benchmark Results/,/Total:/p' "$BENCHMARK_OUTPUT" 2>/dev/null || \ + echo " (no phase timing recorded)" + +# Extract round_1 and scribe if available +ROUND1_TIME=$(grep -oP 'round_1:\s+\K[\d.]+' "$BENCHMARK_OUTPUT" 2>/dev/null || echo "N/A") +SCRIBE_TIME=$(grep -oP 'scribe_compilation:\s+\K[\d.]+' "$BENCHMARK_OUTPUT" 2>/dev/null || echo "N/A") + +# ── Log results ────────────────────────────────────────────────────────── +TIMESTAMP=$(date '+%Y-%m-%d %H:%M:%S') +echo "$TIMESTAMP | ${MODE#--} | ${MODEL:-default} | ${ROUND1_TIME:-N/A} | ${SCRIBE_TIME:-N/A} | $(printf '%.2f' "$TOTAL_TIME")s" >> "$BENCHMARK_LOG" + +echo "" +echo "=== Summary logged ===" +echo "Timestamp | Mode | Model | Round 1 (s) | Scribe (s) | Total" +echo "$TIMESTAMP | ${MODE#--} | ${MODEL:-default} | ${ROUND1_TIME:-N/A} | ${SCRIBE_TIME:-N/A} | $(printf '%.2f' "$TOTAL_TIME")s" +echo "" +echo "Full output: $BENCHMARK_OUTPUT" +echo "History: $BENCHMARK_LOG" + +# ── Log file check ─────────────────────────────────────────────────────── +echo "" +echo "=== Log File Check ===" +LOG_DIR="$WORKSPACE_DIR/logs" +if [ -d "$LOG_DIR" ]; then + LOG_SIZE=$(du -sh "$LOG_DIR/deepresearch.log" 2>/dev/null | cut -f1 || echo "N/A") + SESSION_COUNT=$(find "$LOG_DIR" -name 'session-*.log' 2>/dev/null | wc -l) + echo "deepresearch.log: $LOG_SIZE" + echo "Session logs: $SESSION_COUNT files" +else + echo "Log directory not found: $LOG_DIR" +fi + +exit $EXIT_CODE diff --git a/src/deepresearch/hardware.py b/src/deepresearch/hardware.py new file mode 100644 index 0000000..e99bf4b --- /dev/null +++ b/src/deepresearch/hardware.py @@ -0,0 +1,128 @@ +"""Hardware detection utilities with graceful tiered degradation. + +Tiers: + Tier 1 (required): platform.system(), platform.machine(), os.cpu_count() + Tier 2 (recommended): psutil virtual_memory (graceful ImportError) + Tier 3 (enhanced): nvidia-smi, rocm-smi subprocess calls + Tier 4 (optional): torch.cuda.is_available() +""" + +from __future__ import annotations + +import logging +import os +import platform as _platform +import shutil +import subprocess +from typing import Any + +logger = logging.getLogger(__name__) + + +def get_hardware_info() -> dict[str, Any]: + """Detect system hardware information with graceful degradation at every tier.""" + info: dict[str, Any] = {} + + # ── Tier 1: Platform info (stdlib, always available) ── + info["platform"] = _platform.system() + info["platform_version"] = _platform.version() + info["machine"] = _platform.machine() + info["processor"] = _platform.processor() + info["cpu_count"] = os.cpu_count() + + # ── Tier 2: Memory info via psutil ── + info["memory"] = _get_memory_info() + + # ── Tier 3: GPU detection ── + info["gpus"] = _detect_gpus() + + # ── Tier 4: PyTorch CUDA check ── + info["cuda_available"] = _check_torch_cuda() + + return info + + +def _get_memory_info() -> dict[str, Any] | None: + """Return memory info via psutil, or None if psutil is not installed.""" + try: + import psutil + + mem = psutil.virtual_memory() + return { + "total": mem.total, + "available": mem.available, + "percent_used": mem.percent, + } + except ImportError: + logger.debug("psutil not installed; memory info unavailable") + return None + + +def _detect_gpus() -> list[dict[str, Any]]: + """Detect GPUs via nvidia-smi and rocm-smi. Returns a list of GPU dicts.""" + gpus: list[dict[str, Any]] = [] + + # NVIDIA GPUs + if shutil.which("nvidia-smi"): + try: + result = subprocess.run( + [ + "nvidia-smi", + "--query-gpu=name,memory.total,driver_version", + "--format=csv,noheader,nounits", + ], + capture_output=True, + text=True, + timeout=10, + ) + if result.returncode == 0: + for line in result.stdout.strip().splitlines(): + parts = [p.strip() for p in line.split(",")] + if len(parts) >= 3: + mem_total = 0 + try: + mem_total = int(parts[1]) + except (ValueError, IndexError): + pass + gpus.append( + { + "name": parts[0], + "memory_total_mb": mem_total, + "driver_version": parts[2], + "backend": "nvidia", + } + ) + except Exception as e: + logger.debug("nvidia-smi failed: %s", e) + + # AMD ROCm GPUs + if shutil.which("rocm-smi"): + try: + result = subprocess.run( + ["rocm-smi", "--showproductname"], + capture_output=True, + text=True, + timeout=10, + ) + if result.returncode == 0: + for line in result.stdout.strip().splitlines(): + if ":" in line and "==" not in line: + parts = line.split(":", 1) + name = parts[1].strip() + if name: + gpus.append({"name": name, "backend": "rocm"}) + except Exception as e: + logger.debug("rocm-smi failed: %s", e) + + return gpus + + +def _check_torch_cuda() -> bool | None: + """Check if torch CUDA is available. Returns None if torch not installed.""" + try: + import torch + + return torch.cuda.is_available() + except ImportError: + logger.debug("torch not installed; CUDA check skipped") + return None diff --git a/src/deepresearch/llm/client.py b/src/deepresearch/llm/client.py index a652aa8..b2887d0 100644 --- a/src/deepresearch/llm/client.py +++ b/src/deepresearch/llm/client.py @@ -1480,7 +1480,7 @@ def _track_usage(self, response: Any) -> None: self.total_cost += cost if self.tracker is not None: self.tracker.record( - model=self.actual_model, + model=self.model, prompt_tokens=prompt_tokens, completion_tokens=completion_tokens, cost=cost, diff --git a/src/deepresearch/main.py b/src/deepresearch/main.py index 8fa6a2d..fa99917 100644 --- a/src/deepresearch/main.py +++ b/src/deepresearch/main.py @@ -78,6 +78,11 @@ def build_parser() -> argparse.ArgumentParser: action="store_true", help="Quick mode — fastest results (short time budget)", ) + run_parser.add_argument( + "--medium", + action="store_true", + help="Medium mode — balanced time budget", + ) run_parser.add_argument( "--deep", action="store_true", @@ -156,6 +161,11 @@ def build_parser() -> argparse.ArgumentParser: metavar="[1-10]", help="Max concurrent sessions for web dashboard (1-10, default: 3)", ) + run_parser.add_argument( + "--benchmark", + action="store_true", + help="Benchmark mode — track and report timing for each research phase", + ) # --- serve subcommand --- serve_parser = subparsers.add_parser("serve", help="Start the web dashboard server") @@ -194,6 +204,23 @@ def build_parser() -> argparse.ArgumentParser: ) models_sub.add_parser("list", help="List available LLM models") + # --- cleanup subcommand --- + cleanup_parser = subparsers.add_parser( + "cleanup", help="Clean up output directories and temporary files" + ) + cleanup_sub = cleanup_parser.add_subparsers( + dest="cleanup_command", help="Cleanup commands" + ) + cleanup_output_parser = cleanup_sub.add_parser( + "output", help="Remove empty/incomplete session output directories" + ) + cleanup_output_parser.add_argument( + "--dry-run", + "-n", + action="store_true", + help="Only list directories that would be removed, without deleting", + ) + # --- service subcommand --- service_parser = subparsers.add_parser( "service", help="Manage system service (install/start/stop)" @@ -216,12 +243,15 @@ def build_parser() -> argparse.ArgumentParser: def _resolve_time_budget(args: argparse.Namespace) -> str: """Convert CLI flags to a time-budget keyword. - Precedence: ``--minutes N`` > ``--quick`` / ``--deep`` > ``--time N`` > default. + Precedence: ``--minutes N`` > ``--quick`` / ``--medium`` / ``--deep`` > + ``--time N`` > default (deep). """ if args.minutes is not None: return "custom" if args.quick: return "quick" + if args.medium: + return "medium" if args.deep: return "deep" # Map minutes to budget keyword. @@ -390,10 +420,21 @@ def cmd_run(args: argparse.Namespace) -> int: run_kwargs["selected_model"] = args.model if time_budget_seconds is not None: run_kwargs["time_budget_seconds"] = time_budget_seconds + if getattr(args, 'benchmark', False): + run_kwargs["benchmark"] = True result = asyncio.run(orchestrator.run(args.topic, **run_kwargs)) progress.update(session_task, completed=100, description="[green]Complete!") + if getattr(args, 'benchmark', False) and hasattr(orchestrator, "_benchmark_times"): + console.print("\n[bold cyan]── Benchmark Results ──[/bold cyan]") + bt = orchestrator._benchmark_times + for phase, seconds in bt.items(): + console.print(f" [cyan]{phase}:[/cyan] {seconds:.2f}s") + if bt: + total = sum(bt.values()) + console.print(f" [bold]Total:[/bold] {total:.2f}s") + console.print( f"\n[bold green]✓ Session complete![/bold green] Output: {result}" ) @@ -535,6 +576,39 @@ def cmd_service(args: argparse.Namespace) -> int: return 1 +def cmd_cleanup_output(args: argparse.Namespace) -> int: + """Clean up empty or trivial session output directories. + + Scans ``output/`` for session directories that contain no meaningful + research output (no PDF or HTML files) and removes them. + """ + from deepresearch.web.sessions import cleanup_output_dirs + + count, removed = cleanup_output_dirs(dry_run=args.dry_run) + + if args.dry_run: + if count == 0: + console.print("[green]No empty/incomplete session directories found.[/green]") + else: + console.print( + f"[yellow]Dry run: {count} director{'y' if count == 1 else 'ies'} " + f"would be removed[/yellow]" + ) + for sid in removed: + console.print(f" [dim]{sid}[/dim]") + else: + if count == 0: + console.print("[green]No empty/incomplete session directories to clean.[/green]") + else: + console.print( + f"[green]Cleaned up {count} empty/incomplete session " + f"director{'y' if count == 1 else 'ies'}.[/green]" + ) + for sid in removed: + console.print(f" [dim]{sid}[/dim]") + return 0 + + def main() -> int: """Main entry point.""" parser = build_parser() @@ -544,6 +618,12 @@ def main() -> int: return cmd_run(args) elif args.command == "serve": return cmd_serve(args) + elif args.command == "cleanup": + if args.cleanup_command == "output": + return cmd_cleanup_output(args) + else: + parser.parse_args(["cleanup", "--help"]) + return 1 elif args.command == "profiles": if args.profiles_command == "list": return cmd_profiles_list(args) diff --git a/src/deepresearch/orchestrator/orchestrator.py b/src/deepresearch/orchestrator/orchestrator.py index 3e186d8..1d97d06 100644 --- a/src/deepresearch/orchestrator/orchestrator.py +++ b/src/deepresearch/orchestrator/orchestrator.py @@ -79,6 +79,8 @@ def __init__( self._session_start_time: datetime | None = None self._cancel_event: asyncio.Event | None = None self._pdf_underweight: bool = False + self._benchmark_times: dict[str, float] = {} + self._benchmark_mode: bool = False # ── Collaborators ──────────────────────────────────────────── self.state_tracker = SessionState("", None) @@ -206,6 +208,9 @@ async def run(self, topic: str, **overrides: Any) -> Path: """Run a full research session from topic to output.""" self._cancel_event = overrides.get("cancel_event") self._session_start_time = datetime.now() + self._benchmark_mode = overrides.get("benchmark", False) + self._benchmark_times = {} + _bm = self._benchmark_times logger.info("Session started — topic: %s", topic) if self._event_bus: await self._event_bus.publish( @@ -340,12 +345,15 @@ async def _run_session( ) if round_num == 1: + _r1_start = time.monotonic() results = await self.round_runner.run_round( 1, {aid: agents[aid] for aid in active_agents()}, config.topic, start_time=start_time, ) + if self._benchmark_mode: + self._benchmark_times["round_1"] = time.monotonic() - _r1_start elif round_num == 2: assert latest_shared is not None results = await self.round_runner.run_round( @@ -537,13 +545,18 @@ async def _run_session( "total_reports_chars": sum( len(str(r)) for r in all_reports.values() ), - "model": "unknown", + "model": getattr(getattr(scribe, 'llm', None), 'model', 'unknown'), }, state=self.state, ) + _scribe_start = time.monotonic() paper = await self.scribe_comp.compile( all_reports, scribe, topic=config.topic.question ) + if self._benchmark_mode: + self._benchmark_times["scribe_compilation"] = ( + time.monotonic() - _scribe_start + ) self._current_paper = paper # ------------------------------------------------------------------ diff --git a/src/deepresearch/orchestrator/round_runner.py b/src/deepresearch/orchestrator/round_runner.py index 72841ad..d416f80 100644 --- a/src/deepresearch/orchestrator/round_runner.py +++ b/src/deepresearch/orchestrator/round_runner.py @@ -266,13 +266,16 @@ async def run_round( ) # Publish retry start event so the dashboard shows "Retrying..." + agent_model = "unknown" + if self._config and hasattr(self._config, "agent_models"): + agent_model = self._config.agent_models.get(agent_id, "unknown") if self._event_bus: await self._event_bus.publish( { "event_type": "agent_start", "agent_id": agent_id, "round": round_num, - "model": "unknown", + "model": agent_model, "timeout": timeout, "agent_state": "retrying", }, @@ -522,7 +525,9 @@ async def _run_round_n( "event_type": "agent_start", "agent_id": agent_id, "round": round_num, - "model": "unknown", + "model": self._config.agent_models.get(agent_id, "unknown") + if self._config + else "unknown", "timeout": timeout, "agent_state": "retrying", }, diff --git a/src/deepresearch/web/dashboard.html b/src/deepresearch/web/dashboard.html index c80c94f..17074e0 100644 --- a/src/deepresearch/web/dashboard.html +++ b/src/deepresearch/web/dashboard.html @@ -5,6 +5,7 @@ <meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>DeepeResearch — Research Dashboard + + + +

🧪 Q&A Graph Module Tests

+
+
Running tests...
+
+
+
+

📊 Rendered Graph Preview

+
+
+ + + + diff --git a/src/deepresearch/web/static/vendor/alpine.min.js b/src/deepresearch/web/static/vendor/alpine.min.js new file mode 100644 index 0000000..a3be81c --- /dev/null +++ b/src/deepresearch/web/static/vendor/alpine.min.js @@ -0,0 +1,5 @@ +(()=>{var nt=!1,it=!1,W=[],ot=-1;function Ut(e){Rn(e)}function Rn(e){W.includes(e)||W.push(e),Mn()}function Wt(e){let t=W.indexOf(e);t!==-1&&t>ot&&W.splice(t,1)}function Mn(){!it&&!nt&&(nt=!0,queueMicrotask(Nn))}function Nn(){nt=!1,it=!0;for(let e=0;ee.effect(t,{scheduler:r=>{st?Ut(r):r()}}),at=e.raw}function ct(e){N=e}function Yt(e){let t=()=>{};return[n=>{let i=N(n);return e._x_effects||(e._x_effects=new Set,e._x_runEffects=()=>{e._x_effects.forEach(o=>o())}),e._x_effects.add(i),t=()=>{i!==void 0&&(e._x_effects.delete(i),$(i))},i},()=>{t()}]}function ve(e,t){let r=!0,n,i=N(()=>{let o=e();JSON.stringify(o),r?n=o:queueMicrotask(()=>{t(o,n),n=o}),r=!1});return()=>$(i)}var Xt=[],Zt=[],Qt=[];function er(e){Qt.push(e)}function te(e,t){typeof t=="function"?(e._x_cleanups||(e._x_cleanups=[]),e._x_cleanups.push(t)):(t=e,Zt.push(t))}function Ae(e){Xt.push(e)}function Oe(e,t,r){e._x_attributeCleanups||(e._x_attributeCleanups={}),e._x_attributeCleanups[t]||(e._x_attributeCleanups[t]=[]),e._x_attributeCleanups[t].push(r)}function lt(e,t){e._x_attributeCleanups&&Object.entries(e._x_attributeCleanups).forEach(([r,n])=>{(t===void 0||t.includes(r))&&(n.forEach(i=>i()),delete e._x_attributeCleanups[r])})}function tr(e){for(e._x_effects?.forEach(Wt);e._x_cleanups?.length;)e._x_cleanups.pop()()}var ut=new MutationObserver(mt),ft=!1;function ue(){ut.observe(document,{subtree:!0,childList:!0,attributes:!0,attributeOldValue:!0}),ft=!0}function dt(){kn(),ut.disconnect(),ft=!1}var le=[];function kn(){let e=ut.takeRecords();le.push(()=>e.length>0&&mt(e));let t=le.length;queueMicrotask(()=>{if(le.length===t)for(;le.length>0;)le.shift()()})}function m(e){if(!ft)return e();dt();let t=e();return ue(),t}var pt=!1,Se=[];function rr(){pt=!0}function nr(){pt=!1,mt(Se),Se=[]}function mt(e){if(pt){Se=Se.concat(e);return}let t=[],r=new Set,n=new Map,i=new Map;for(let o=0;o{s.nodeType===1&&s._x_marker&&r.add(s)}),e[o].addedNodes.forEach(s=>{if(s.nodeType===1){if(r.has(s)){r.delete(s);return}s._x_marker||t.push(s)}})),e[o].type==="attributes")){let s=e[o].target,a=e[o].attributeName,c=e[o].oldValue,l=()=>{n.has(s)||n.set(s,[]),n.get(s).push({name:a,value:s.getAttribute(a)})},u=()=>{i.has(s)||i.set(s,[]),i.get(s).push(a)};s.hasAttribute(a)&&c===null?l():s.hasAttribute(a)?(u(),l()):u()}i.forEach((o,s)=>{lt(s,o)}),n.forEach((o,s)=>{Xt.forEach(a=>a(s,o))});for(let o of r)t.some(s=>s.contains(o))||Zt.forEach(s=>s(o));for(let o of t)o.isConnected&&Qt.forEach(s=>s(o));t=null,r=null,n=null,i=null}function Ce(e){return z(B(e))}function k(e,t,r){return e._x_dataStack=[t,...B(r||e)],()=>{e._x_dataStack=e._x_dataStack.filter(n=>n!==t)}}function B(e){return e._x_dataStack?e._x_dataStack:typeof ShadowRoot=="function"&&e instanceof ShadowRoot?B(e.host):e.parentNode?B(e.parentNode):[]}function z(e){return new Proxy({objects:e},Dn)}var Dn={ownKeys({objects:e}){return Array.from(new Set(e.flatMap(t=>Object.keys(t))))},has({objects:e},t){return t==Symbol.unscopables?!1:e.some(r=>Object.prototype.hasOwnProperty.call(r,t)||Reflect.has(r,t))},get({objects:e},t,r){return t=="toJSON"?Pn:Reflect.get(e.find(n=>Reflect.has(n,t))||{},t,r)},set({objects:e},t,r,n){let i=e.find(s=>Object.prototype.hasOwnProperty.call(s,t))||e[e.length-1],o=Object.getOwnPropertyDescriptor(i,t);return o?.set&&o?.get?o.set.call(n,r)||!0:Reflect.set(i,t,r)}};function Pn(){return Reflect.ownKeys(this).reduce((t,r)=>(t[r]=Reflect.get(this,r),t),{})}function Te(e){let t=n=>typeof n=="object"&&!Array.isArray(n)&&n!==null,r=(n,i="")=>{Object.entries(Object.getOwnPropertyDescriptors(n)).forEach(([o,{value:s,enumerable:a}])=>{if(a===!1||s===void 0||typeof s=="object"&&s!==null&&s.__v_skip)return;let c=i===""?o:`${i}.${o}`;typeof s=="object"&&s!==null&&s._x_interceptor?n[o]=s.initialize(e,c,o):t(s)&&s!==n&&!(s instanceof Element)&&r(s,c)})};return r(e)}function Re(e,t=()=>{}){let r={initialValue:void 0,_x_interceptor:!0,initialize(n,i,o){return e(this.initialValue,()=>In(n,i),s=>ht(n,i,s),i,o)}};return t(r),n=>{if(typeof n=="object"&&n!==null&&n._x_interceptor){let i=r.initialize.bind(r);r.initialize=(o,s,a)=>{let c=n.initialize(o,s,a);return r.initialValue=c,i(o,s,a)}}else r.initialValue=n;return r}}function In(e,t){return t.split(".").reduce((r,n)=>r[n],e)}function ht(e,t,r){if(typeof t=="string"&&(t=t.split(".")),t.length===1)e[t[0]]=r;else{if(t.length===0)throw error;return e[t[0]]||(e[t[0]]={}),ht(e[t[0]],t.slice(1),r)}}var ir={};function y(e,t){ir[e]=t}function fe(e,t){let r=Ln(t);return Object.entries(ir).forEach(([n,i])=>{Object.defineProperty(e,`$${n}`,{get(){return i(t,r)},enumerable:!1})}),e}function Ln(e){let[t,r]=_t(e),n={interceptor:Re,...t};return te(e,r),n}function or(e,t,r,...n){try{return r(...n)}catch(i){re(i,e,t)}}function re(e,t,r=void 0){e=Object.assign(e??{message:"No error message given."},{el:t,expression:r}),console.warn(`Alpine Expression Error: ${e.message} + +${r?'Expression: "'+r+`" + +`:""}`,t),setTimeout(()=>{throw e},0)}var Me=!0;function ke(e){let t=Me;Me=!1;let r=e();return Me=t,r}function R(e,t,r={}){let n;return x(e,t)(i=>n=i,r),n}function x(...e){return sr(...e)}var sr=xt;function ar(e){sr=e}function xt(e,t){let r={};fe(r,e);let n=[r,...B(e)],i=typeof t=="function"?$n(n,t):Fn(n,t,e);return or.bind(null,e,t,i)}function $n(e,t){return(r=()=>{},{scope:n={},params:i=[]}={})=>{let o=t.apply(z([n,...e]),i);Ne(r,o)}}var gt={};function jn(e,t){if(gt[e])return gt[e];let r=Object.getPrototypeOf(async function(){}).constructor,n=/^[\n\s]*if.*\(.*\)/.test(e.trim())||/^(let|const)\s/.test(e.trim())?`(async()=>{ ${e} })()`:e,o=(()=>{try{let s=new r(["__self","scope"],`with (scope) { __self.result = ${n} }; __self.finished = true; return __self.result;`);return Object.defineProperty(s,"name",{value:`[Alpine] ${e}`}),s}catch(s){return re(s,t,e),Promise.resolve()}})();return gt[e]=o,o}function Fn(e,t,r){let n=jn(t,r);return(i=()=>{},{scope:o={},params:s=[]}={})=>{n.result=void 0,n.finished=!1;let a=z([o,...e]);if(typeof n=="function"){let c=n(n,a).catch(l=>re(l,r,t));n.finished?(Ne(i,n.result,a,s,r),n.result=void 0):c.then(l=>{Ne(i,l,a,s,r)}).catch(l=>re(l,r,t)).finally(()=>n.result=void 0)}}}function Ne(e,t,r,n,i){if(Me&&typeof t=="function"){let o=t.apply(r,n);o instanceof Promise?o.then(s=>Ne(e,s,r,n)).catch(s=>re(s,i,t)):e(o)}else typeof t=="object"&&t instanceof Promise?t.then(o=>e(o)):e(t)}var wt="x-";function C(e=""){return wt+e}function cr(e){wt=e}var De={};function d(e,t){return De[e]=t,{before(r){if(!De[r]){console.warn(String.raw`Cannot find directive \`${r}\`. \`${e}\` will use the default order of execution`);return}let n=G.indexOf(r);G.splice(n>=0?n:G.indexOf("DEFAULT"),0,e)}}}function lr(e){return Object.keys(De).includes(e)}function pe(e,t,r){if(t=Array.from(t),e._x_virtualDirectives){let o=Object.entries(e._x_virtualDirectives).map(([a,c])=>({name:a,value:c})),s=Et(o);o=o.map(a=>s.find(c=>c.name===a.name)?{name:`x-bind:${a.name}`,value:`"${a.value}"`}:a),t=t.concat(o)}let n={};return t.map(dr((o,s)=>n[o]=s)).filter(mr).map(zn(n,r)).sort(Kn).map(o=>Bn(e,o))}function Et(e){return Array.from(e).map(dr()).filter(t=>!mr(t))}var yt=!1,de=new Map,ur=Symbol();function fr(e){yt=!0;let t=Symbol();ur=t,de.set(t,[]);let r=()=>{for(;de.get(t).length;)de.get(t).shift()();de.delete(t)},n=()=>{yt=!1,r()};e(r),n()}function _t(e){let t=[],r=a=>t.push(a),[n,i]=Yt(e);return t.push(i),[{Alpine:K,effect:n,cleanup:r,evaluateLater:x.bind(x,e),evaluate:R.bind(R,e)},()=>t.forEach(a=>a())]}function Bn(e,t){let r=()=>{},n=De[t.type]||r,[i,o]=_t(e);Oe(e,t.original,o);let s=()=>{e._x_ignore||e._x_ignoreSelf||(n.inline&&n.inline(e,t,i),n=n.bind(n,e,t,i),yt?de.get(ur).push(n):n())};return s.runCleanups=o,s}var Pe=(e,t)=>({name:r,value:n})=>(r.startsWith(e)&&(r=r.replace(e,t)),{name:r,value:n}),Ie=e=>e;function dr(e=()=>{}){return({name:t,value:r})=>{let{name:n,value:i}=pr.reduce((o,s)=>s(o),{name:t,value:r});return n!==t&&e(n,t),{name:n,value:i}}}var pr=[];function ne(e){pr.push(e)}function mr({name:e}){return hr().test(e)}var hr=()=>new RegExp(`^${wt}([^:^.]+)\\b`);function zn(e,t){return({name:r,value:n})=>{let i=r.match(hr()),o=r.match(/:([a-zA-Z0-9\-_:]+)/),s=r.match(/\.[^.\]]+(?=[^\]]*$)/g)||[],a=t||e[r]||r;return{type:i?i[1]:null,value:o?o[1]:null,modifiers:s.map(c=>c.replace(".","")),expression:n,original:a}}}var bt="DEFAULT",G=["ignore","ref","data","id","anchor","bind","init","for","model","modelable","transition","show","if",bt,"teleport"];function Kn(e,t){let r=G.indexOf(e.type)===-1?bt:e.type,n=G.indexOf(t.type)===-1?bt:t.type;return G.indexOf(r)-G.indexOf(n)}function J(e,t,r={}){e.dispatchEvent(new CustomEvent(t,{detail:r,bubbles:!0,composed:!0,cancelable:!0}))}function D(e,t){if(typeof ShadowRoot=="function"&&e instanceof ShadowRoot){Array.from(e.children).forEach(i=>D(i,t));return}let r=!1;if(t(e,()=>r=!0),r)return;let n=e.firstElementChild;for(;n;)D(n,t,!1),n=n.nextElementSibling}function E(e,...t){console.warn(`Alpine Warning: ${e}`,...t)}var _r=!1;function gr(){_r&&E("Alpine has already been initialized on this page. Calling Alpine.start() more than once can cause problems."),_r=!0,document.body||E("Unable to initialize. Trying to load Alpine before `` is available. Did you forget to add `defer` in Alpine's `