--- title: "Foxl Blog" description: "Engineering deep-dives, incident reports, measured tradeoffs, and release notes from the team building Foxl." date_modified: "2026-07-24" canonical_url: "https://foxl.ai/blog" markdown_url: "https://foxl.ai/blog/index.md" rss_url: "https://foxl.ai/rss.xml" --- # Foxl Blog Engineering deep-dives, incident reports, measured tradeoffs, and release notes from the team building Foxl. - Canonical HTML: [https://foxl.ai/blog]() - RSS: [https://foxl.ai/rss.xml]() - Full Markdown corpus: [https://foxl.ai/blog/full.md]() - Articles: 28 ## [Foxl v0.4.22: Claude Opus 5 Is the New Default]() Release note | Published 2026-07-24 | Updated 2026-07-24 | 6 min read Claude Opus 5 is Anthropic's most intelligent model, and it ships as the default across Foxl Agent, Foxl Code, and Foxl Notes on day one - at the same price as Opus 4.8 and half of Fable 5. Auditing every model engine for the launch also turned up a Gemini CLI that returned empty replies to every request, aliases pointing at the wrong generation, and a pricing table in our own docs that was wrong by a factor of nine. [Markdown]() ## [Five Releases in One Day: The Engine Is Foxl Code Itself]() Deep dive | Published 2026-07-22 | Updated 2026-07-22 | 6 min read On July 22 Foxl shipped v0.4.15 through v0.4.19 - five production releases, each hitting six web surfaces, a notarized macOS build, and iOS TestFlight. This is the story of the loop that made that pace ordinary: Foxl Code working on the Foxl monorepo, with a human supplying taste and one-line bug reports, including a critical incident fixed the hour it was reported and an experiment shipped, disproven on hardware, and reverted the same day. [Markdown]() ## [Foxl v0.4.15: The Tabs That Vanished (and the Phone That Forgot)]() Release note | Published 2026-07-22 | Updated 2026-07-22 | 5 min read Skills, Channels, and custom MCP tools were all still in the app - just unreachable, orphaned by a moved tab bar. v0.4.15 restores them inside Settings, drops the gradient carousels, and fixes a family of mobile bugs that were all one iOS lifecycle fact in disguise: every launch is a cold start. [Markdown]() ## [Hearing the Whole Meeting: How an Empty AirPods Transcript Rewrote Two Releases]() Deep dive | Published 2026-07-21 | Updated 2026-07-21 | 11 min read One bug report - "I recorded a meeting with AirPods and the transcript came back empty" - led through a macOS permission that fails silently, an inaudible test tone, a GPL driver we chose not to bundle, a WebKit limitation with no escape hatch, a native Swift recorder, and a ten-item audit of what makes a phone app worth being an app. The story of v0.4.13 and v0.4.14. [Markdown]() ## [Foxl v0.4.12: The Quiet Fixes]() Release note | Published 2026-07-20 | Updated 2026-07-20 | 4 min read A batch of small things that were quietly wrong: a single tilde striking through your text, a background reply with no sign it was running, a stuttering mobile keyboard, and phone notifications tied to your desktop settings. Individually minor, together the gap between almost-right and careful. [Markdown]() ## [Foxl v0.4.10: A Mobile-First Redesign]() Release note | Published 2026-07-17 | Updated 2026-07-17 | 5 min read v0.4.10 rebuilds the phone experience around native conventions - a reveal-drawer sidebar, a settings sheet shared by all three products, swipe-to-manage chats, a keyboard the composer follows, and a glass message bar - and closes a set of production bugs around credits, error visibility, and dead tunnel connections. [Markdown]() ## [Designing Connection Ownership for Always-On AI Agents]() Incident | Published 2026-07-16 | Updated 2026-07-16 | 5 min read v0.4.7 fixed duplicate device sessions and fenced stale desktop sockets, then v0.4.8 and v0.4.9 exposed the missing distinction between liveness, connection-generation ownership, and in-flight request correlation. This is the full incident sequence and the contract that replaced it. [Markdown]() ## [Choosing a Source of Truth for Agent Conversations]() Incident | Published 2026-07-12 | Updated 2026-07-16 | 5 min read The UI ledger and the agent snapshot drifted through head trimming, synthetic cancel turns, and interrupted saves. The fix made user-visible SQLite history authoritative on normal cold restores and kept snapshots as derived history or fallback data. [Markdown]() ## [Your Meeting Was Transcribed Twice. Deleting Code Fixed It.]() Incident | Published 2026-07-12 | Updated 2026-07-16 | 6 min read Two independent transcription pipelines appended two rows for the same utterance when the microphone re-heard speaker output. Mixing both captures into one ASR stream removed the two-writer failure mode and let us delete the similarity filter. [Markdown]() ## [The Checksum Byte That Ate Your Long Answers]() Incident | Published 2026-06-26 | Updated 2026-07-16 | 5 min read Foxl replies were truncating mid-sentence on long answers. The cause was a single byte. Our relay decoded Amazon Bedrock's binary event-stream as if it were text and brace-scanned for JSON - so a CRC32 checksum byte equal to 0x22 (a double-quote) flipped the parser into string mode and silently swallowed the rest of the stream. A captured 32 KB stream dropped 70 of 119 events. Here is the binary-framing parser that fixed it, and the fixture test that keeps it fixed. [Markdown]() ## [Foxl v0.3.3: What "Day-One Support" Actually Shipped]() Release note | Published 2026-06-09 | Updated 2026-07-16 | 4 min read A corrected release record for Fable 5: what Foxl integrated on June 9, why provider suspension was a separate state, and how a later Bedrock profile change forced routing to move from global to us. [Markdown]() ## [Building Foxl Mobile from a Shared React Codebase]() Deep dive | Published 2026-06-08 | Updated 2026-07-16 | 7 min read Foxl v0.3.0 reused a shared React source tree across hosted web, Electron, and a Capacitor iOS host, with runtime-specific builds and platform integration. The hard parts were keyboard docking and safe-area ownership without offsetting touch targets. [Markdown]() ## [Foxl v0.2.51: Notes Integration and the Recording Gates]() Release note | Published 2026-06-07 | Updated 2026-07-16 | 5 min read The Notes shell integration first landed in v0.2.50. v0.2.51 kept it, fixed GPT-5.x routing, and began a microphone repair that required four production gates and was complete only in v0.2.53. [Markdown]() ## [Designing Durable Coding Agents with Reconciliation Loops]() Deep dive | Published 2026-05-19 | Updated 2026-07-16 | 10 min read Foxl Code treats autonomy as a reconciliation loop over approved plans, task state, isolated runtimes, budget-scoped credentials, durable lifecycle events, and eventually consistent GitHub effects. [Markdown]() ## [Making foxl.ai Crawlable with Next.js Static Export]() Deep dive | Published 2026-05-13 | Updated 2026-07-16 | 6 min read For two months, Google couldn't index our landing page. The fix: swap Vite CSR for Next.js static export. Here's what we learned about Cloudflare Workers constraints, JSON-LD sitelinks, and why "we'll add SSR later" is a trap. [Markdown]() ## [Foxl v0.2.27: Trimming the Sidebar, the Skill Library, and the Tray]() Release note | Published 2026-05-09 | Updated 2026-07-16 | 5 min read Integrations became third-party only, the default skill set was reduced, and redundant built-in tools moved behind the general execution path. The release also simplified the tray and exposed credit usage in the account surface. [Markdown]() ## [Foxl v0.2.23: Notifications That Actually Do Something]() Release note | Published 2026-05-04 | Updated 2026-07-16 | 4 min read Action buttons on every banner, resource metadata carried through the existing body-click route, and an intermediate macOS "Install Now" repair. Remaining native failures were fixed in v0.2.29-v0.2.30. [Markdown]() ## [Foxl v0.2.21: Strands SDK 1.0 and Express 5]() Release note | Published 2026-04-30 | Updated 2026-07-16 | 3 min read Upgraded to Strands SDK v1.0.0 stable with concurrent tool execution and cancellation hooks, plus Express 5 migration for async error handling and modern routing. [Markdown]() ## [Foxl v0.2.19: gpt-image-2 on Your ChatGPT Subscription]() Release note | Published 2026-04-24 | Updated 2026-07-16 | 4 min read This release added image generation through ChatGPT OAuth, corrected GPT model routing, and updated the agent SDK. Later notes clarify provider-controlled eligibility, quotas, and model changes. [Markdown]() ## [Foxl v0.2.16: Claude Code OAuth, Reborn as a Compatibility Layer]() Deep dive | Published 2026-04-21 | Updated 2026-07-16 | 3 min read Live probes showed that system-prompt and tool-name shapes changed observed Claude subscription routing. Foxl shipped a compatibility layer, then documented the limits of treating provider behavior as a stable contract. [Markdown]() ## [Foxl v0.2.11: The Feed - Proactive, Quietly]() Release note | Published 2026-04-18 | Updated 2026-07-16 | 4 min read Foxl v0.2.11 added an opt-in For You feed powered by a background agent. When enabled, its default cadence was hourly; most items landed quietly and only urgent ones requested notifications. [Markdown]() ## [Foxl v0.2.13: Pixel Office Redesign, Deep-Linkable Notifications]() Release note | Published 2026-04-18 | Updated 2026-07-16 | 5 min read A cozy Pixel Office redesign with 2.5D sprites, real-time pet-position persistence, agent-completion notifications that deep-link to the finished agent, and Claude Code OAuth on Windows fixed for real. [Markdown]() ## [Building Desktop OAuth for Outlook and Slack]() Deep dive | Published 2026-04-17 | Updated 2026-07-16 | 8 min read PKCE for Microsoft, relay-proxied secret for Slack, loopback callback servers, and skill-gated tool registration. The engineering behind 37 new agent actions. [Markdown]() ## [Foxl v0.2.5: Claude Opus 4.7 Day-One Support]() Release note | Published 2026-04-16 | Updated 2026-07-16 | 2 min read At its April 16 launch, Foxl v0.2.5 added Claude Opus 4.7 on Bedrock as the default model and expert-routing target, with adaptive thinking and Opus 4.6 retained for existing selections. [Markdown]() ## [Foxl v0.2.2: New Models, Faster]() Release note | Published 2026-04-15 | Updated 2026-07-16 | 3 min read Non-Claude AI models on Bedrock, a dedicated browser profile that remembers your logins, message editing with attachments, and a one-click system report. [Markdown]() ## [Running an Always-On AI Agent on Real Desktops]() Deep dive | Published 2026-04-15 | Updated 2026-07-16 | 11 min read Laptops sleep. Browsers fight over profiles. Cron jobs fire on Saturdays. Everything we learned shipping an AI agent that lives on your actual machine. [Markdown]() ## [Foxl v0.2.0: DB-Backed Agents, Smarter Scheduling]() Release note | Published 2026-04-12 | Updated 2026-07-16 | 3 min read SQLite-backed auto-continuation prevents duplicate agents, cron scheduler gets weekday support, and the sidebar shows real-time agent timers. [Markdown]() ## [Designing a Local-First Trust Boundary for AI Agents]() Deep dive | Published 2026-03-18 | Updated 2026-07-16 | 11 min read Local-first is a boundary, not a claim that no byte leaves the machine. Foxl keeps tools, files, credentials, and durable conversation state local while sending only the selected model context through the provider path you configure. [Markdown]()