Commit graph

1729 commits

Author SHA1 Message Date
Bryan Helmkamp
971a6f2451 Remove AI slop from introducing-fabro blog post
Replace "leveraging" buzzword and "This is the key insight:" trope.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 21:38:14 -04:00
Bryan Helmkamp
493fe4b328 Hide Showcase from homepage navigation
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 21:34:18 -04:00
Bryan Helmkamp
18677fcae9 Update marketing site fonts to Razor Geometric treatment
Switch from Space Grotesk / DM Sans / JetBrains Mono to
Outfit / Lexend / Fira Code for a tighter, sharper aesthetic.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 21:22:14 -04:00
Bryan Helmkamp
c4b1dbe194 Rewrite "Introducing Fabro" blog post with founder voice
Expanded from a 1-min stub to a full introductory post with
problem framing, workflow graph example, model stylesheet syntax,
verification gates, checkpoint/resume, and install CTA.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 21:21:24 -04:00
Bryan Helmkamp
b6317a057a Hide Showcase from marketing site navigation
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 21:19:01 -04:00
Bryan Helmkamp
f3efcc931e Record GPT-5.4 20min timeout: 65.7% on SWE-Bench-Lite ($718.62)
Best resolve rate at 197/300 but 3.3x more expensive than Opus.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 20:55:59 -04:00
Bryan Helmkamp
ae4aa1e04c Showcase: render workflow graphs as SVGs, add nav, fix prompt
- Render DOT workflow definitions as visual SVG diagrams at build time
  using @viz-js/viz, replacing raw code blocks on show pages and
  placeholder first-letter thumbnails on index cards
- Collapse models/skills/languages into a compact metadata strip on
  show pages instead of separate boxed sections
- Fix prompt expand/collapse to use a single DOM element with max-height
  animation instead of duplicating the text in two swapped containers
- Add prev/next navigation links at the bottom of show pages
- Extract duplicated langIcons data into shared src/lib/langIcons.ts
- Use varied reveal animation types (reveal-scale, reveal-left)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 20:55:31 -04:00
Bryan Helmkamp
359306569a Update roadmap and standardize on Graphviz terminology
Roadmap: replace placeholder items with current shipped/building/planned
features. Use real dates for sorting instead of manual sortOrder. Fix
UTC timezone rendering for date display.

Terminology: replace all standalone "DOT" references with "Graphviz" or
"Graphviz DOT" across docs, marketing, README, AGENTS.md, and OpenAPI
spec. Changelogs left unchanged as historical records.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 20:01:33 -04:00
Bryan Helmkamp
b06eeb1859 Update /discord redirect to use invite link
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 19:50:29 -04:00
Bryan Helmkamp
48717239e7 Add Showcase section to marketing site
Gallery of workflow recipes with index grid and detail pages.
Three sample entries: PR Review Bot, Test Generator, Docs Sync.
Add Roadmap link to shared Nav component and homepage nav.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 19:11:05 -04:00
Bryan Helmkamp
0587fae2e5 Docs: add auto-merge config, auto-merge to GitHub features, turn-level retries
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 19:06:15 -04:00
Bryan Helmkamp
8586e54596 Add March 16 changelog and update March 15 with new entries
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 19:03:47 -04:00
Bryan Helmkamp
3bd2a43499 Roadmap: replace inline shipped descriptions with hover tooltip
Saves vertical space by showing only date + title in shipped rows,
with an info icon that reveals the description on hover.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 18:27:58 -04:00
Bryan Helmkamp
38ec5d2846 Add blog and redesign blog/roadmap pages
- Add blog collection (content config, prose styles, introducing-fabro post)
- Add Blog link to homepage nav and footer
- Make Layout description prop dynamic for per-page meta/OG tags
- Extract shared Nav, Footer, PageScripts components from duplicated markup
- Blog index: compact header, featured card for latest post, row list for older posts
- Blog post: clean reading surface (no grid/noise overlay), reading time, better header
- Roadmap: improved card contrast with tinted backgrounds, conditional section rendering

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 18:26:10 -04:00
Bryan Helmkamp
d8155a305c Reduce default patch generation concurrency to 75
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 16:05:24 -04:00
Bryan Helmkamp
0ea22dafe8 Handle assistant output replay on stream retries 2026-03-16 15:59:00 -04:00
Bryan Helmkamp
a1497aa19b Fix typos in docs: "appliction" and "an Fabro"
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 15:57:33 -04:00
Bryan Helmkamp
fb3b7bc9c7 Fix broken link and stale badge label in README
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 15:25:31 -04:00
Bryan Helmkamp
06603fc579 Add turn-level retry for stream-ended-without-Finish errors
When an LLM stream drops mid-response (e.g. under high concurrency with
OpenAI), retry the same turn up to 3 times instead of failing the entire
agent session. Conversation history is preserved across retries.

Previously this killed the whole stage and restarted from scratch.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 15:16:35 -04:00
Bryan Helmkamp
dfcece9a0d Record Opus 4.6 20min timeout: 58.0% on SWE-Bench-Lite ($218.65)
100% patch rate, 0 timeouts. Only +1 instance over Sonnet at 4x the cost.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 14:43:20 -04:00
Bryan Helmkamp
d13972e195 Update install instructions to show Claude Code, Codex, and Bash methods
Match the marketing website's tabbed install widget across README, docs
quick-start, and CLAUDE.md. Add marketing site build/deploy commands.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 14:03:53 -04:00
Bryan Helmkamp
26d0a6a562 Add tabbed install widget (Claude/Codex/Bash) with copy buttons, show hero screenshot on load
Replace single curl command with a tabbed install widget defaulting to Claude,
with Codex and Bash alternatives. Each tab has a copy-to-clipboard button.
Remove scroll-reveal animation from hero screenshot so it's visible immediately.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 13:56:42 -04:00
Bryan Helmkamp
165742d7fa Record Sonnet 4.6 20min timeout: 57.7% on SWE-Bench-Lite ($55.22)
20min timeout vs 10min: 173 vs 167 resolved (+6), patch rate 99% vs 94%.
Also fixes: revert to v4 snapshots, concurrency default to 100, preflight
uses actual 4 CPU per sandbox.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 13:36:26 -04:00
Bryan Helmkamp
0cc02c294d Move install files to apps/marketing/public, symlink from repo root
Vercel deploys only the apps/marketing/ subtree, so the real files
need to live there. Repo root now symlinks into marketing/public.
Also add .vercel to gitignore.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 13:23:58 -04:00
Bryan Helmkamp
5fad662651 Temporarily hide Roadmap from nav while content is being written
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 12:51:55 -04:00
Bryan Helmkamp
4d93fa55df Improve marketing site mobile layout: reduce hero top spacing and hide curl command
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 12:46:22 -04:00
Bryan Helmkamp
0db08b937c Fix snapshot CPU mismatch: use v4 snapshots (4 CPU), reduce concurrency to 100
Daytona bakes CPU/memory at snapshot creation time. v4 snapshots have
4 CPU / 8 GB. Preflight now checks against 4 CPU per sandbox.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 12:44:14 -04:00
Bryan Helmkamp
241be62cde Reduce default concurrency to 150, increase default timeout to 20min
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 12:32:18 -04:00
Bryan Helmkamp
5d2f4c0828 Add llms.txt and additional meta tags for marketing site
- Add llms.txt with structured overview of Fabro docs for LLM consumption
- Add canonical link, application-name, apple-mobile-web-app-title
- Add twitter:image dimensions
- Make og:url dynamic per page

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 12:30:16 -04:00
Bryan Helmkamp
7b452a0783 Add OG image and meta tags for link sharing, remove comma from tagline
- Add 1200x630 branded OG image matching Mintlify docs card style
- Add Open Graph and Twitter Card meta tags to Layout.astro
- Save og-image-template.html for easy regeneration
- Remove comma from "open source, dark software factory" everywhere

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 12:24:58 -04:00
Bryan Helmkamp
582fe2b0c4 Fix marketing site mobile layout: responsive nav and content overflow
Nav links, icons, and CTA button overflowed the viewport on mobile.
Text in Workflow-as-Code and Multi-model sections was clipped because
wide SVG/pre children caused CSS grid blowout (min-width: auto default).

- Add hamburger menu for mobile nav on both pages (hidden md:, toggle JS)
- Add overflow-x-hidden to html/body/main to prevent horizontal scroll
- Add .grid > * { min-width: 0 } to prevent grid children from expanding
  beyond their container

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 12:23:35 -04:00
Bryan Helmkamp
adf6594b97 Add Daytona CPU preflight check before starting eval runs
Checks running sandboxes against the 500 CPU org limit with 20% buffer.
Exits with a suggested --max-workers value if capacity is insufficient.
Default concurrency set to 200 (safe with 2 CPU per sandbox).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 12:20:36 -04:00
Bryan Helmkamp
d6041b9c18 Migrate roadmap data to Astro content collections
Replace inline arrays with a `roadmap` collection using glob loader
and Zod schema. Each item is a YAML file in src/content/roadmap/ with
title, description, status, date, and sortOrder fields.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 12:17:31 -04:00
Bryan Helmkamp
b86851c51a Add REPL Handoff example workflow to docs
Documents the pattern of planning interactively in Claude Code and
delegating implementation to Fabro via the /fabro-implement slash
command, with multi-model simplification and verification gates.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 12:13:05 -04:00
Bryan Helmkamp
4c86c87c78 Add /roadmap page to marketing site with timeline layout
Shipped/Building/Next sections with sample content, vertical timeline,
scroll reveal animations, and matching dark factory aesthetic. Linked
from top nav and footer on both pages.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 12:04:48 -04:00
Bryan Helmkamp
830bd2cefe Update marketing site: copyright to Qlty Software Inc. and allow ngrok hosts
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 11:58:29 -04:00
Bryan Helmkamp
942054c43a Record timeout and sandbox resources in scoreboard metadata
Adds --timeout, --sandbox-cpu, --sandbox-memory flags to record_results.py.
Re-recorded both existing runs with the new fields.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 11:24:56 -04:00
Bryan Helmkamp
5eccf9701b Record Sonnet 4.6 baseline: 55.7% on SWE-Bench-Lite ($39.78)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 11:23:23 -04:00
Bryan Helmkamp
06ce28bcea Add install.md for AI agent-driven installation
Self-contained installation instructions following the install.md spec.
Decoupled from install.sh — handles platform detection, binary download,
PATH setup in shell dotfiles, and verification independently. Prompts
the user to run `fabro install` interactively to complete setup.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 11:07:21 -04:00
Bryan Helmkamp
939fd58a49 Skip shell config modification in non-interactive mode
Prevents install.sh from silently writing to dotfiles (.zshrc, .bashrc,
config.fish) when run non-interactively (e.g. by an AI coding agent).
In non-interactive mode, it now prints the manual PATH export instead.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 11:01:42 -04:00
Bryan Helmkamp
2cf15d0a8d Add status.py for quick progress checks on generation and eval runs
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 10:59:49 -04:00
Bryan Helmkamp
777358e8d6 Add Discord and Changelog links to marketing site nav and footer
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 10:56:10 -04:00
Bryan Helmkamp
7f95d5f518 Switch display font from Barlow Condensed to Space Grotesk
Replace aggressive uppercase/wide-tracking headings with sentence-case
tight-tracking for a more natural, geometric-techy feel.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 10:50:53 -04:00
Bryan Helmkamp
6403ab029a Redesign marketing site with industrial-refined visual identity
Replace Sora with Barlow Condensed uppercase headings, add cross-hatch grid
and noise atmosphere, swap emoji for custom SVG line-art icons, add scroll
animation variants (reveal-left/right/scale), animated trace bars and workflow
graph draw-in, convert images to WebP with picture fallbacks, expand footer
to 3-column layout, and consolidate sections from 12 to 8.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 10:48:52 -04:00
Bryan Helmkamp
e26286d966 Add best-effort Daytona sandbox cleanup on timeout and disable PR creation
On timeout, finds the orphaned sandbox via fabro ps --label and deletes
it. Non-fatal if cleanup fails. Also adds [pull_request] enabled=false
to generated workflow.toml configs to prevent eval runs from opening PRs.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 10:42:47 -04:00
Bryan Helmkamp
cd786bb875 Add install.sh serving and /discord, /docs redirects to marketing site
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 10:33:25 -04:00
Bryan Helmkamp
b491542e95 Make SWE-bench patch generation and evaluation resumable
On restart, reads existing output JSONL files to find completed instance
IDs, skips them, and appends new results. Final summary recomputes from
the full results file so it reflects all runs combined.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 10:33:06 -04:00
Bryan Helmkamp
2924968a8a Add screenshots, workflow diagram, lightbox, and fix logotype viewBox
- Add runs-board.png below hero as product showcase
- Add plan-implement.svg workflow diagram in Workflow-as-Code section
  above the DOT code block, with dark-mode contrast fix
- Replace verification 2x2 card grid with run-detail.png screenshot
- Add click-to-expand lightbox for all three visual assets
- Fix logotype SVG viewBox (0 0 1455 → 0 0 1500) across all 5 files
  to prevent "O" in FABRO from being clipped
- Increase Docs link contrast in nav (text-ice-100, font-medium)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 10:09:57 -04:00
Bryan Helmkamp
c2a89a5898 Add SWE-bench eval README with setup, usage, and monitoring instructions
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 09:59:03 -04:00
Bryan Helmkamp
0431ad1a05 Add scoreboard system and record Haiku 4.5 baseline: 54.0% on SWE-Bench-Lite
record_results.py combines generation + eval results into a git-tracked
scoreboard. Per run: README, meta.json, instances.jsonl. Auto-generates
leaderboard.json ranked by resolve rate.

Haiku 4.5 baseline: 162/300 (54.0%), $26.13 total ($0.087/instance).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 09:56:43 -04:00