Mentat

Mentat AI

Mentat AI

Mentat AI

Mentat AI

Mentat AI

Mentat AI

Mentat AI

Mentat AI

Mentat AI

Mentat AI

Glia wins Excellence Award for safer AI in banking

Glia, a customer service platform providing AI-powered interactions for the banking sector, has been named a winner in the Banking and Financial Services Category at the 2026 Artificial Intelligence Excellence Awards. The awards recognises achievements in a range of industries and use cases, spotlighting “companies and leaders moving AI beyond experimentation and into practical, accountable […] The post Glia wins Excellence Award for safer AI in banking appeared first on AI News.

When AI turns software development inside-out: 170% throughput at 80% headcount

Many people have tried AI tools and walked away unimpressed. I get it — many demos promise magic, but in practice, the results can feel underwhelming. That’s why I want to write this not as a futurist prediction, but from lived experience. Over the past six months, I turned my engineering organization AI-first. I’ve shared before about the system behind that transformation — how we built the workflows, the metrics, and the guardrails. Today, I want to zoom out from the mechanics and talk about what I’ve learned from that experience — about where our profession is heading when software development itself turns inside out. Before I do, a couple of numbers to illustrate the scale of change. Subjectively, it feels that we are moving twice as fast. Objectively, here’s how the throughput evolved. Our total engineering team headcount floated from 36 at the beginning of the year to 30. So you get ~170% throughput on ~80% headcount, which matches the subjective ~2x. Zooming in, I picked a couple of our senior engineers who started the year in a more traditional software engineering process and ended it in the AI-first way. [The dips correspond to vacations and off-sites]: Note that our PRs are tied to JIRA tickets, and the average scope of those tickets didn’t change much through the year, so it’s as good a proxy as the data can give us. Qualitatively, looking at the business value, I actually see even higher uplift. One reason is that, as we started last year, our quality assurance (QA) team couldn’t keep up with our engineers' velocity. As the company leader, I wasn’t happy with the quality of some of our early releases. As we progressed through the year, and tooled our AI workflows to include writing unit and end-to-end tests, our coverage improved, the number of bugs dropped, users became fans, and the business value of engineering work multiplied. From big design to rapid experimentation Before AI, we spent weeks perfecting user flows before writing code. It made sense

Teenage Engineering's PO-32 acoustic modem and synth implementation

IndexCache, a new sparse attention optimizer, delivers 1.82x faster inference on long-context AI models

Processing 200,000 tokens through a large language model is expensive and slow: the longer the context, the faster the costs spiral. Researchers at Tsinghua University and Z.ai have built a technique called IndexCache that cuts up to 75% of the redundant computation in sparse attention models, delivering up to 1.82x faster time-to-first-token and 1.48x faster generation throughput at that context length. The technique applies to models using the DeepSeek Sparse Attention architecture, including the latest DeepSeek and GLM families. It can help enterprises provide faster user experiences for production-scale, long-context models, a capability already proven in preliminary tests on the 744-billion-parameter GLM-5 model. The DSA bottleneck Large language models rely on the self-attention mechanism, a process where the model computes the relationship between every token in its context and all the preceding ones to predict the next token. However, self-attention has a severe limitation. Its computational complexity scales quadratically with sequence length. For applications requiring extended context windows (e.g., large document processing, multi-step agentic workflows, or long chain-of-thought reasoning), this quadratic scaling leads to sluggish inference speeds and significant compute and memory costs. Sparse attention offers a principled solution to this scaling problem. Instead of calculating the relationship between every token and all preceding ones, sparse attention optimizes the process by having each query select and attend to only the most relevant subset of tokens. DeepSeek Sparse Attention (DSA) is a highly efficient implementation of this concept, first introduced in DeepSeek-V3.2. To determine which tokens matter most, DSA introduces a lightweight "lightning indexer module" at every layer of the model. This indexer scores all preceding tokens and selects a small batch for the main core attention mechanism to process. By doing this, DSA slashes the heavy co

Show HN: Forkrun – NUMA-aware shell parallelizer (50×–400× faster than parallel)

forkrun is the culmination of a 10-year-long journey focused on &quot;how to make shell parallelization fast&quot;. What started as a standard &quot;fork jobs in a loop&quot; has turned into a lock-free, CAS-retry-loop-free, SIMD-accelerated, self-tuning, NUMA aware shell-based stream parallelization engine that is (mostly) a drop-in replacement for xargs -P and GNU parallel.<p>On my 14-core&#x2F;28-thread i9-7940x, forkrun achieves:<p>* 200,000+ batch dispatches&#x2F;sec (vs ~500 for GNU Parallel)<p>* ~95–99% CPU utilization across all 28 logical cores, even when the workload is non-existant (bash no-ops &#x2F; `:`) (vs ~6% for GNU Parallel). These benchmarks are intentionally worst-case (near-zero work per task) because they measure the capability of the parallelization framework itself, not how much work an external tool can do.<p>* Typically 50×–400× faster on real high-frequency low-latency workloads (vs GNU Parallel)<p>A few of the techniques that make this possible:<p>* Born-local NUMA: stdin is splice()&#x27;d into a shared memfd, then pages are placed on the target NUMA node via set_mempolicy(MPOL_BIND) before any worker touches them, making the memfd NUMA-spliced. Each numa node only claims work that is <i>already</i> born-local on its node. Stealing from other nodes is permitted under some conditions when no local work exists.<p>* SIMD scanning: per-node indexers&#x2F;scanners use AVX2&#x2F;NEON to find line boundaries (delimiters) at speeds approaching memory bandwidth, and publish byte-offsets and line-counts into per-node lock-free rings.<p>* Lock-free claiming: workers claim batches with a single atomic_fetch_add — no locks, no CAS retry loops; contention is reduced to a single atomic on one cache line.<p>* Memory management: a background thread uses fallocate(PUNCH_HOLE) to reclaim space without breaking the logical offset system.<p>…and that’s just the surface. The implementation uses many additional systems-level techniques (phase-aware tail handling, adaptive batching, early-flush detection, etc.) to eliminate overhead, increase throughput and reduce latency at every stage.<p>In its fastest (-b) mode (fixed-size batches, minimal processing), it can exceed 1B lines&#x2F;sec.<p>forkrun ships as a single bash file with an embedded, self-extracting C extension — no Perl, no Python, no install, full native support for parallelizing arbitrary shell functions. The binary is built in public GitHub Actions so you can trace it back to CI (see the GitHub &quot;Blame&quot; on the line containing the base64 embeddings). Trying it is literally two commands:<p><pre><code> . frun.bash frun shell_func_or_cmd &lt; inputs </code></pre> For benchmarking scripts and results, see the BENCHMARKS dir in the GitHub repo<p>For an architecture deep-dive, see the DOCS dir in the GitHub repo<p>Happy to answer questions.

Show HN: Threadprocs – executables sharing one address space (0-copy pointers)

This project launches multiple independent programs into a single shared virtual address space, while still behaving like separate processes (independent binaries, globals, and lifetimes). When threadprocs share their address space, pointers are valid across them with no code changes for well-behaved Linux binaries.<p>Unlike threads, each threadproc is a standalone and semi-isolated process. Unlike dlopen-based plugin systems, threadprocs run traditional executables with a `main()` function. Unlike POSIX processes, pointers remain valid across threadprocs because they share the same address space.<p>This means that idiomatic pointer-based data structures like `std::string` or `std::unordered_map` can be passed between threadprocs and accessed directly (with the usual data race considerations).<p>This accomplishes a programming model somewhere between pthreads and multi-process shared memory IPC.<p>The implementation relies on directing ASLR and virtual address layout at load time and implementing a user-space analogue of `exec()`, as well as careful manipulation of threadproc file descriptors, signals, etc. It is implemented entirely in unprivileged user space code: &lt;<a href="https:&#x2F;&#x2F;github.com&#x2F;jer-irl&#x2F;threadprocs&#x2F;blob&#x2F;main&#x2F;docs&#x2F;02-implementation.md" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;jer-irl&#x2F;threadprocs&#x2F;blob&#x2F;main&#x2F;docs&#x2F;02-imp...</a>&gt;.<p>There is a simple demo demonstrating “cross-threadproc” memory dereferencing at &lt;<a href="https:&#x2F;&#x2F;github.com&#x2F;jer-irl&#x2F;threadprocs&#x2F;tree&#x2F;main?tab=readme-ov-file#demo" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;jer-irl&#x2F;threadprocs&#x2F;tree&#x2F;main?tab=readme-...</a>&gt;, including a high-level diagram.<p>This is relevant to systems of multiple processes with shared memory (often ring buffers or flat tables). These designs often require serialization or copying, and tend away from idiomatic C++ or Rust data structures. Pointer-based data structures cannot be passed directly.<p>There are significant limitations and edge cases, and it’s not clear this is a practical model, but the project explores a way to relax traditional process memory boundaries while still structuring a system as independently launched components.

Sovereign AI Infrastructure: Scaling Enterprise Agents from 8GB RAM to Global Clusters with Fararoni.

The Era of Local Execution AI deployment has shifted from cloud experimentation to the...

The Great AI Fragmentation: How Anthropic Broke OpenAI's Monopoly

Anthropic surged from 4% to 20% enterprise market share in 12 months. OpenAI's dominance collapsed. Here's what actually changed in the AI market in 2

Image Augmentation in Practice — Lessons from 10 Years of Training CV Models and Building Albumentations

TL;DR Image augmentation is usually explained as “flip, rotate, color jitter”. In practice it...

feat: Sandbox integration test — real binary lifecycle + stress testing (#37)

## Summary Implements comprehensive GitHub Actions sandbox testing workflow that validates real daemon binary lifecycle, catching deployment bugs that in-process tests cannot detect. ## Changes - **Complete Sandbox Workflow**: Tests actual `pi-daemon` binary in CI environment - **Comprehensive Coverage**: Smoke tests, concurrency, stress testing, crash recovery - **Real-world Validation**: PID files, port binding, signal handling, memory behavior - **Future-Ready**: Enhancement issues created for persistence, supervisor, scheduler testing ## Test Phases Implemented ### 🔍 Phase 1: Smoke Testing - **Binary Startup**: Release build starts as real daemon process - **Endpoint Validation**: Health, status, agent CRUD, webchat, OpenAI API - **PID Management**: daemon.json creation, tracking, cleanup verification - **Basic Functionality**: All core features work in real deployment scenario ### ⚡ Phase 2: Concurrency & Load Testing - **HTTP Load**: 50 concurrent requests to `/api/status` endpoint - **Agent Stress**: 20 concurrent agent registrations with verification - **WebSocket Load**: 5 concurrent WebSocket connections within per-IP limits - **Memory Monitoring**: RSS usage tracking with 200MB warning threshold ### 💪 Phase 3: Stress & Recovery Testing - **Sustained Load**: 30-second continuous request generation with memory growth monitoring - **Crash Recovery**: Kill -9 simulation → restart verification → full functionality restored - **Memory Validation**: Growth monitoring with warnings if >50MB increase during load ### 🛑 Phase 4: Graceful Shutdown Testing - **API Shutdown**: `POST /api/shutdown` endpoint triggers graceful exit - **Process Cleanup**: PID file removal, port release verification - **CLI Validation**: Commands handle daemon state correctly when stopped ## Critical Gaps Addressed | What In-Process Tests Miss | Real Deployment Bug Example | Sandbox Test Coverage | |---------------------------|----------------------------|---------------------| | Binary actually starts | Compiles but panics on launch | ✅ Real daemon startup | | PID file lifecycle | Written but not cleaned up | ✅ File creation/removal | | Port binding issues | Works on random ports, fails on 4200 | ✅ Standard port binding | | Signal handling | Ctrl+C cleanup, SIGTERM shutdown | ✅ Kill signals + cleanup | | Concurrent behavior | Race conditions under load | ✅ 50+ concurrent operations | | Memory leaks | Only visible after sustained use | ✅ Memory growth monitoring | | Config from disk | Tests use in-memory config | ✅ Real TOML file loading | | WebSocket limits | Per-IP connection enforcement | ✅ Connection limit testing | ## Future Enhancements Created ### Issue #77: P2.6 Persistence Testing (Phase 2+) - Data survival across restarts (agents, sessions, usage) - Database integrity after ungraceful shutdown - **Blocked by:** #13 (SQLite memory substrate) ### Issue #78: P3.4 Supervisor Stress Testing (Phase 3+) - Heartbeat timeout detection under load - Auto-restart functionality validation - **Blocked by:** #17 (Supervisor implementation) ### Issue #79: P3.5 Scheduler Validation (Phase 3+) - Cron job execution timing accuracy - Job management under concurrent load - **Blocked by:** #16 (Cron scheduler engine) ## Workflow Configuration ### Trigger Conditions - **Pull Requests** to main branch - **Path Filter**: Only when `crates/**`, `Cargo.toml`, `Cargo.lock` change - **Skip**: Documentation-only changes (no unnecessary CI overhead) ### Environment Setup - **Ubuntu Latest**: Standard CI environment - **Release Build**: Tests production binary (optimized, no debug symbols) - **Dependencies**: jq for JSON parsing, websocat for WebSocket testing - **Timeout**: 10 minutes prevents hung processes from blocking CI ### Error Handling & Reporting - **Actionable Errors**: Clear failure messages with context - **Resource Monitoring**: Memory usage warnings and alerts - **Cleanup**: Guaranteed daemon process cleanup even on test failures - **Debugging**: Process PID tracking and status validation ## Test Execution Flow ```bash # 1. Build release binary cargo build --release # 2. Start daemon in background ./target/release/pi-daemon start --foreground & # 3. Wait for health endpoint (30s timeout) curl -sf http://127.0.0.1:4200/api/health # 4. Run comprehensive test suite # - API endpoint validation # - Agent CRUD lifecycle # - Webchat content verification # - OpenAI compatibility testing # - Concurrent load testing # - Memory usage monitoring # - Crash recovery simulation # - Graceful shutdown validation # 5. Cleanup and summary pkill pi-daemon && rm daemon.json ``` ## Benefits - ✅ **Deployment Confidence**: Catches real-world integration issues - ✅ **Performance Validation**: Memory and concurrency behavior under load - ✅ **Recovery Testing**: Ensures robustness against crashes and restarts - ✅ **Signal Handling**: Validates production process management - ✅ **Resource Management**: Prevents port confli

feat: Quota-aware trial scheduling based on /usage subscription limits

## Problem The performance harness burns significant tokens per trial (300K-1.8M each). With subscription-based Claude Code, daily and weekly quotas are real constraints. Currently there is zero awareness of quota state when recommending or executing benchmark runs — the orchestrator will happily suggest 7 trials that consume 5M+ tokens without knowing the user is at 80% of their daily limit with no reset for 5 days. ## Desired Behavior The harness (and the orchestrator recommending runs) should be **quota-aware**: 1. **Before recommending trials**, estimate the token cost based on historical averages per task 2. **Query `/usage`** (or equivalent subscription API) to get: - Current daily usage vs daily limit - Current weekly usage vs weekly limit - Reset timing (when does daily reset? when does weekly reset?) 3. **Apply scheduling intelligence**: - If daily resets tomorrow and we're at 60% → run all trials now - If weekly doesn't reset for 5 days and we're at 70% → suggest deferring or running fewer trials - If we're at 90% daily but resets in 2 hours → suggest waiting 4. **Surface quota impact** in run recommendations: ``` Proposed: 7 trials, est. ~5M tokens Current quota: 12M/20M daily (60%), resets in 14h Weekly: 45M/100M (45%), resets in 3d Recommendation: Safe to proceed — daily headroom sufficient ``` ## Implementation Considerations - `/usage` data structure needs investigation — what does the subscription API expose? - Historical token-per-task averages can be computed from existing results - The 70% threshold is a starting point — should be configurable - Weekly quota is the binding constraint when reset is far away - Daily quota matters more when reset is imminent - The orchestrator (not just the runner CLI) should have this awareness — it's the one suggesting "let's run 18 trials" ## Not In Scope (first pass) - Automatic pause/resume of running trials (too complex for v1) - Real-time token tracking during a trial (stream parsing is post-hoc) - Multi-user quota coordination ## Acceptance Criteria - [ ] Runner CLI shows estimated token cost before execution - [ ] Quota state queried and displayed before trial recommendations - [ ] Scheduling advice based on quota headroom + reset timing - [ ] Configurable threshold (default 70% of remaining quota) - [ ] Works with current subscription model (daily + weekly limits)

Add example usage for Costory billing datasources in documentation

- Included Terraform example for Anthropic billing datasource. - Added Terraform example for Cursor billing datasource. - Defined required variables and provider configuration for both datasources.

[AI Agent] Master Tracking: Complete AI Agent Implementation

## 🎯 Goal Track the complete implementation of autonomous Python AI Agent for CoffeeOrderSystem. --- ## 📋 Implementation Steps ### Phase 1: Infrastructure (Week 1) - [ ] **Step 1:** Setup Python AI Agent Service infrastructure #133 - Python service with FastAPI - Docker integration - Basic health checks - Makefile commands ### Phase 2: AI Integration (Week 1-2) - [ ] **Step 2:** Implement Cognee integration with semantic code search #134 - CogneeService with RAG search - Architecture context gathering - Entity file discovery - Integration tests - [ ] **Step 3:** Implement PlannerAgent with LangChain #135 - TaskPlan models - LangChain planning chain - Prompt templates - Plan generation and posting ### Phase 3: Code Generation (Week 2-3) - [ ] **Step 4:** Implement DevAgent for code generation #136 - GitHub file operations - Code generation prompts - Create/modify/delete operations - Branch management - [ ] **Step 5:** Implement PRAgent and workflow orchestration #137 - PR creation with rich descriptions - Workflow orchestrator - Background task processing - Complete end-to-end flow ### Phase 4: Advanced Features (Week 3-4) - [ ] **Step 6:** Add learning/memory system - Store successful patterns in Cognee - Learn from PR reviews - Avoid failed patterns - Improve over time - [ ] **Step 7:** Add GitHub webhook listener - Auto-trigger on issue label - Real-time processing - Queue management - Concurrent task handling --- ## 🎯 Success Criteria ### MVP (Minimum Viable Product) - ✅ Agent creates plans for issues - ✅ Agent generates compilable code - ✅ Agent creates PRs with descriptions - ✅ Works for simple tasks (add field, update config) - ✅ Error handling with GitHub notifications ### Production Ready - ☐ Handles complex multi-layer changes - ☐ Learns from successful PRs - ☐ Automatic triggering via webhooks - ☐ Rate limiting and queue management - ☐ Comprehensive test coverage (>80%) - ☐ Monitoring and metrics --- ## 📊 Architecture Overview ``` ┌────────────────────────────────────┐ │ GitHub Issues (labeled: ai-agent) │ └───────────────┬────────────────────┘ │ ↓ (webhook or manual trigger) ┌───────────────┼────────────────────┐ │ WorkflowOrchestrator │ └───────────────┬────────────────────┘ │ ┌────────┼────────┐ │ │ │ ↓ ↓ ↓ PlannerAgent DevAgent PRAgent │ │ │ │ │ │ ┌───┼───┐ │ ┌───┼───┐ │ │ │ │ │ │ │ ↓ ↓ ↓ ↓ ↓ ↓ ↓ Cognee LLM GitHub GitHub (RAG) (GPT-4) (API) ``` ### Component Responsibilities **PlannerAgent:** - Analyzes GitHub issue - Searches codebase via Cognee - Creates structured TaskPlan - Posts plan as issue comment **DevAgent:** - Generates code via LLM - Creates/modifies/deletes files - Commits to feature branch - Preserves code style **PRAgent:** - Creates pull request - Writes comprehensive PR description - Links to original issue - Adds testing checklist **WorkflowOrchestrator:** - Coordinates all agents - Handles errors - Posts progress updates - Manages background execution --- ## 📦 Tech Stack ### Core - **Python 3.11+** - Agent runtime - **FastAPI** - Web framework - **LangChain** - LLM orchestration - **OpenAI GPT-4** - Code generation - **PyGithub** - GitHub API client ### AI/ML - **Cognee** - RAG and semantic search - **OpenAI Embeddings** - Vector search - **LangChain Chains** - Prompt management ### Infrastructure - **Docker** - Containerization - **PostgreSQL** - Shared with .NET API - **uvicorn** - ASGI server --- ## 📝 Usage Example ### 1. Create Issue ```markdown Title: Add loyalty points to Customer Labels: ai-agent, enhancement Description: Add LoyaltyPoints field (int, default 0) to Customer entity. Requirements: - Update Domain/Entities/Customer.cs - Update Application/DTOs/CustomerDto.cs - Create EF Core migration - Add unit tests ``` ### 2. Trigger Agent ```bash make agent-process # Enter issue number: 138 ``` ### 3. Monitor Progress Issue comments show: ``` 🤖 AI Agent Started Phase 1/3: Analyzing task... 🤖 Execution Plan Summary: Add LoyaltyPoints field to Customer entity Steps: 1. MODIFY Domain/Entities/Customer.cs 2. MODIFY Application/DTOs/CustomerDto.cs 3. CREATE Migration file 4. CREATE Test file 🛠️ Phase 2/3: Generating code (4 files)... ✅ Step 1/4: modify Customer.cs ✅ Step 2/4: modify CustomerDto.cs ... 📦 Phase 3/3: Creating pull request... 🤖 Pull Request Created: #139 Branch: ai-agent/issue-138 Ready for review! ``` ### 4. Review PR PR includes: - Closes #138 - Comprehensive description - File changes summary - Testing checklist - Risk assessment ### 5. Merge Agent learns from successful merge for future tasks. --- ## 🧪 Testing Strategy ### Unit Tests - Agent logic (plan parsing, code generation) - Service mocks (GitHub, Cognee) - P

Weekly Rules Review: 2026-03-09

## Weekly Rules Documentation Review - 2026-03-09 ### Overall Health Assessment The rules documentation is in **good shape overall**. All 11 rule files are relevant, and the vast majority of file paths and code patterns they reference still exist in the codebase. Two files need minor updates, and one has a moderate accuracy issue. --- ### Audit Results #### AGENTS.md **Status**: Keep **Reasoning**: Core agent guide is accurate and well-structured. The rules index table, project setup instructions, pre-commit checks, and general guidance are all current. References to `npm run ts`, `tsgo`, TanStack Router, and Base UI are correct. --- #### rules/electron-ipc.md **Status**: Keep **Reasoning**: High-value, comprehensive guide. All referenced file paths exist (`src/ipc/contracts/core.ts`, `src/ipc/types/*.ts`, `src/ipc/handlers/base.ts`, `src/lib/queryKeys.ts`). The `pendingStreamChatIds` pattern still exists in `useStreamChat.ts`. The `writeSettings` shallow merge warning is still relevant (confirmed by recent fix in commit ef4ec84 preventing stale settings reads). --- #### rules/local-agent-tools.md **Status**: Keep **Reasoning**: Concise and accurate. `modifiesState` flag is actively used across many tool files. `buildAgentToolSet` exists in `tool_definitions.ts`. `handleLocalAgentStream` exists in `local_agent_handler.ts` with `readOnly`/`planModeOnly` guards confirmed. `todo_persistence.ts` exists. `fs.promises` guidance remains relevant for Electron main process. --- #### rules/e2e-testing.md **Status**: Needs Update **Reasoning**: Mostly accurate and high-value, but has two inaccuracies in helper method references. **Issues Found**: - Lines 64-75: References `po.clearChatInput()` and `po.openChatHistoryMenu()` as methods on PageObject directly, but they actually live on the `chatActions` sub-component: `po.chatActions.clearChatInput()` and `po.chatActions.openChatHistoryMenu()`. This contradicts the sub-component pattern documented earlier in the same file (lines 29-43). **Suggested Changes**: - Update the Lexical editor section examples to use `po.chatActions.clearChatInput()` and `po.chatActions.openChatHistoryMenu()` instead of `po.clearChatInput()` and `po.openChatHistoryMenu()` --- #### rules/git-workflow.md **Status**: Keep **Reasoning**: Comprehensive and high-value. Contains many hard-won learnings about fork workflows, `gh pr create` edge cases, GitHub API workarounds, and rebase conflict resolution patterns. The `GITHUB_TOKEN` workflow chaining limitation and the `--input` pattern for special characters are particularly valuable. Recent commits (51fc07e - GitHub App tokens) confirm this area is actively evolving. **Note**: This is the longest rules file (123 lines). Some of the very specific rebase conflict tips (React component wrapper conflicts, refactoring conflicts) may be overly situational, but they're low-cost to keep. --- #### rules/base-ui-components.md **Status**: Keep **Reasoning**: All referenced component files exist (`context-menu.tsx`, `tooltip.tsx`, `accordion.tsx`). `@base-ui/react` is in the project dependencies. The TooltipTrigger `render` prop guidance and Accordion API differences from Radix are high-value patterns that prevent common mistakes. --- #### rules/database-drizzle.md **Status**: Keep **Reasoning**: Short and high-value. `drizzle/meta/_journal.json` exists. Migration conflict resolution guidance is important for rebase workflows. --- #### rules/typescript-strict-mode.md **Status**: Keep **Reasoning**: All references verified. `tsconfig.app.json` confirms ES2020 target with `lib: ["ES2020"]`. The `tsgo` installation note (Go binary, not npm package) and `response.json()` returning `unknown` are valuable gotchas. Node.js >= 24 requirement is noted. --- #### rules/openai-reasoning-models.md **Status**: Needs Update **Reasoning**: The core concept is still valid - orphaned reasoning parts are still filtered in `src/ipc/utils/ai_messages_utils.ts`. However, the specific function name referenced is outdated. **Issues Found**: - References `filterOrphanedReasoningParts()` as a named function, but this logic was refactored into the `cleanMessage()` function (inline filtering within that function). The named export no longer exists. **Suggested Changes**: - Update the reference from `filterOrphanedReasoningParts()` to describe the filtering logic within `cleanMessage()` in `src/ipc/utils/ai_messages_utils.ts` --- #### rules/adding-settings.md **Status**: Keep **Reasoning**: All file paths verified: `UserSettingsSchema` in `src/lib/schemas.ts`, `DEFAULT_SETTINGS` in `src/main/settings.ts`, `SETTING_IDS` in `src/lib/settingsSearchIndex.ts`, `AutoApproveSwitch.tsx` as template. Recent commit d6ab829 (add max tool call steps setting) confirms this pattern is actively used. --- #### rules/chat-message-indicators.md **Status**: Keep **Reasoning**: Short (12 lines), low token cost. `dyad-status` tag implementation confirmed in

Weekly Report Mar 2 -- Mar 9, 2026

# Weekly Report: Mar 2 -- Mar 9, 2026 ## Quick Stats | Metric | Count | |--------|-------| | Merged PRs | 47 | | Open PRs | 24 (11 draft) | | Open issues | 61 | | New issues this week | 33 | | Issues closed this week | 6 | | CI runs on main | 30 | ## Highlights An exceptionally active week with 47 merged PRs. Key themes: - **Realm migration**: Keycloak master-to-kagenti realm migration landed (#764), with follow-up fixes (#851, #863) - **Platform hardening**: Podman support (#861), Docker Hub rate limit fixes (#844), PostgreSQL mount fix (#852) - **CI/CD improvements**: OpenSSF Scorecard 7.1->8+ (#807), stale workflow permissions (#859), HyperShift cluster auto-cleanup (#854) - **New capabilities**: CLI/TUI for Kagenti (#835), Istio trace export to OTel (#795), RHOAI 3.x integration (#809) - **Dependency updates**: 8 Dependabot PRs (Docker actions major bumps, CodeQL, Trivy) - **Authorization epic**: 7 new issues (#787-#794) laying out a comprehensive authorization and policy framework - **Agent sandbox epic**: New epic (#820) for platform-owned sandboxed agent runtime ## Issue Analysis ### Epics (active initiatives) | # | Title | Owner | Status | |---|-------|-------|--------| | #862 | AgentRuntime CR — CR-triggered injection | @cwiklik | New, design phase | | #820 | Platform-Owned Sandboxed Agent Runtime | @Ladas | Active, PR #758 in progress | | #828 | Migrate installer from Ansible/Helm to Operator | @pdettori | New, planning | | #787 | Authorization, Policies, and Access Management | @mrsabath | New, 6 sub-issues filed | | #841 | Org-wide orchestration: CI, tests, security | @Ladas | Active, PRs #866-#868 open | | #767 | Migrate from Keycloak master realm | @mrsabath | Mostly done (#764 merged), close candidate | | #619 | Tracing observability PoC | @evaline-ju | Active (#795 merged) | | #621 | OpenSSF Scorecard to 10/10 | @Ladas | Active (#807 merged, now 8+) | | #523 | Refactor APIs for Compositional Architecture | @pdettori | Active, PR #770 open | | #518 | OpenShift AI deployment issues | @Ladas | Active (#809 merged) | | #309 | Full Coverage E2E Testing | @cooktheryan | Ongoing | | #440 | Multi-Team Deployment on RHOAI | @Ladas | Ongoing | | #439 | Namespace-Based Token Usage Quotas | @Ladas | Ongoing | | #614 | Feedback review community meeting | @Ladas | Stale (>30d no update) | | #623 | Identify Emerging Agentic Deployment Patterns | @kellyaa | Stale | | #612 | Agent Attestation Framework | @mrsabath | Stale, PR #613 still draft | ### Security-Adjacent Issues | # | Title | Status | Recommendation | |---|-------|--------|----------------| | #822 | Keycloak configmap should be secret | Open | High priority — credentials in configmap | | #106 | Replace hardcoded secret with SPIRE identity | Open | Long-standing, PR #769 in draft | | #333 | SPIFFE ID missing checks | Open | Stale, needs triage | | #267 | Replace hard-coded Client Secret File path | Open | Good first issue, needs assignee | ### Bug Reports | # | Title | Still affects main? | PR exists? | Recommendation | |---|-------|---------------------|------------|----------------| | #856 | Warnings during Kagenti install | Likely yes | No | Triage — install warnings | | #855 | Can't checkout source on Windows | Yes (skill naming) | PR #869 | In progress | | #829 | Deleting A2A agent doesn't delete HTTPRoute | Likely yes | No | Needs fix | | #826 | No way to log out of Kagenti | Yes | No | UX bug, needs fix | | #825 | Build failures lead to stuck state | Likely yes | No | Needs investigation | | #738 | UI drops spire label on 2nd deploy | Likely yes | No | Stale (>30d) | | #486 | Installer issues (Postgres/Phoenix) | Partially (#852 fixed PG) | Partial | Re-verify Phoenix | | #781 | kagenti-deps fails on OCP 4.19 | Unknown | No | Stale, needs triage | | #606 | Unsupported Helm version | Unknown | No | Stale, needs triage | | #655 | Duplicated resources between repos | Unknown | No | Stale, needs triage | ### Issues Closed This Week (good velocity) | # | Title | Fix PR | |---|-------|--------| | #833 | UI login fails after realm migration | #834 | | #831 | --preload fails when images cached | #832 | | #819 | Remove deprecated Component CRD refs | #818 | | #813 | Import env vars references bad URL | #821 | | #810 | Import env vars silently fails on dup | #821 | | #804 | OAuth secret job SSL error on OCP | #805 | ### Feature Requests | # | Title | Priority | Recommendation | |---|-------|----------|----------------| | #858 | Use new URL for fetching Agent Cards | Medium | Good first issue | | #836 | AuthBridge sidecar opt-out controls in UI | Medium | Tied to #862 epic | | #824 | Help text for UI fields | Low | Good UX improvement | | #823 | Examples as suggestions in UI | Low | Nice-to-have | | #817 | Auto-add issues/PRs to project board | Medium | PR #870 open | | #814 | Mechanism to update agent via K8s | Medium | Operator feature | | #786 | Register MCP servers from UI | Medium | UI feature | | #783 | Agent card signing/verifica