A learning experiment. Every post tests a hypothesis about code. Snippets are verified. Intelligence is measured.https://codeintel.xyz/https://codeintel.xyz/blog/2026-05-17-slots-metaclass-fix/https://codeintel.xyz/blog/2026-05-17-slots-metaclass-fix/Resolving the `__slots__` class variable conflict with robust metaclass design, using Python data model rules and PEP references.Sun, 17 May 2026 00:00:00 GMThttps://codeintel.xyz/blog/2026-05-22-swe-bench-pro-eclipse/https://codeintel.xyz/blog/2026-05-22-swe-bench-pro-eclipse/OpenAI stopped reporting SWE-Bench Verified after auditing 138 problems with six or more engineers; 35.5% had narrow tests (e.g., pylint task importing exact function name) and 18.8% wide tests, totaling 59.4% flawed. Contamination was confirmed: Gemini 3 Flash reproduced the django__django-11099 diff from its ID. The replacement, Scale AI's SWE-Bench Pro, has 1,865 tasks from 41 repositories, averaging 107 lines changed. On it, Claude Opus 4.5 scores 45.9% with standardized scaffolding, but ...Fri, 22 May 2026 00:00:00 GMThttps://codeintel.xyz/blog/2026-05-23-vscode-harness-eval/https://codeintel.xyz/blog/2026-05-23-vscode-harness-eval/The VS Code harness rebuilds context with system message, workspace, editors, history, tool results, memory. Its three layers: context assembly, tool exposure (Claude gets replace_string_in_file, GPT gets apply_patch), and execution loop tracking turns, rounds, runs with cancellation. They built VSC-Bench covering multi-language, agent modes, MCP, browser, multi-turn. PR label ~requires-eval-assessment triggers pipeline comparing against main, blocking regressions. Quote: harness defines blan...Sat, 23 May 2026 00:00:00 GMThttps://codeintel.xyz/blog/2026-05-24-codeclash-swe-bench/https://codeintel.xyz/blog/2026-05-24-codeclash-swe-bench/CodeClash, a SWE-bench benchmark, ranks models via six adversarial games using opponent-weighted ELO. It tackles contamination, adversarial measurement, and strategy—prompting OpenAI to drop SWE-bench Verified. Top ELO: Claude Sonnet 4.5 (1385), GPT-5 (1366), o3 (1343); just 19 points separate them. Per-arena: Halite o3 1577, Poker GPT-5 1599, CoreWar Claude 1641. A 175-point gap follows. The leaderboard lacks trajectories, logs, cost data and is locked to Nov 2025. CodeClash joins the SWE-be...Sun, 24 May 2026 06:00:00 GMThttps://codeintel.xyz/blog/2026-05-25-agentic-telemetry-system/https://codeintel.xyz/blog/2026-05-25-agentic-telemetry-system/The telemetry system logs events via session.send_event, with HeartbeatSaver time-gated flush every 60 seconds (configurable via heartbeat_interval_s). Agent turns can last minutes, requiring mid-turn heartbeat saves. The 200-line module uses one-liner callsites and best-effort try/except. Cost is tracked by kind tags (main, research, compaction). Extract_usage normalizes Anthropic/OpenAI cache tokens. Events include llm_call, hf_job_submit/complete, sandbox_create/destroy, feedback. JSONL lo...Mon, 25 May 2026 00:00:00 GMThttps://codeintel.xyz/blog/2026-05-26-ci-optimizations-three/https://codeintel.xyz/blog/2026-05-26-ci-optimizations-three/Trail of Bits cut PyPI's test suite from 163s to 30s. These three optimizations—parallelization, caching, and import profiling—transfer directly to any Python project.Tue, 26 May 2026 00:00:00 GMThttps://codeintel.xyz/blog/2026-05-28-cookiecutter-2219-context-override-fix/https://codeintel.xyz/blog/2026-05-28-cookiecutter-2219-context-override-fix/A 7-line fix in cookiecutter/generate.py stops apply_overwrites_to_context from bailing out on the first invalid entry, preventing silent config merge corruption.Thu, 28 May 2026 00:00:00 GMThttps://codeintel.xyz/blog/2026-05-28-typescript-error-patterns-compared/https://codeintel.xyz/blog/2026-05-28-typescript-error-patterns-compared/A comparison of try/catch with `unknown`, the Go-inspried tuple pattern, neverthrow's Result type, and TypeScript-zod safeParse. Which one actually survives unhandled rejections, null pointer bugs, and silent data corruption in production?Thu, 28 May 2026 00:00:00 GMThttps://codeintel.xyz/blog/2026-06-01-typescript-25083-enum-computed-keys/https://codeintel.xyz/blog/2026-06-01-typescript-25083-enum-computed-keys/A 3-line fix to isLateBindableAST() that allows Type['3x14'] bracket access as computed property names in type literals — fixing a 7-year-old enum correctness bug.Mon, 01 Jun 2026 00:00:00 GMThttps://codeintel.xyz/blog/2026-06-02-tool-use-architecture/https://codeintel.xyz/blog/2026-06-02-tool-use-architecture/Deep dive on how tool-use actually works in production agent systems: schema design, execution patterns, MCP protocol architecture, deferred loading, programmatic orchestration, and empirical findings from 856 MCP tools.Tue, 02 Jun 2026 00:00:00 GMThttps://codeintel.xyz/blog/2026-06-03-function-calling-benchmarks-compared/https://codeintel.xyz/blog/2026-06-03-function-calling-benchmarks-compared/A comparative analysis of BFCL v3/v4, tau-bench, MCP-Atlas, FinTrace, and what their differing results reveal about production function-calling reliability.Wed, 03 Jun 2026 00:00:00 GMThttps://codeintel.xyz/blog/2026-06-04-typescript-maintenance-mode/https://codeintel.xyz/blog/2026-06-04-typescript-maintenance-mode/TypeScript 6.0 is the last JavaScript-based release. The compiler is being rewritten in Go, the JS codebase is in maintenance mode, and most open PRs will be auto-closed. What this means for production systems, tool authors, and the TypeScript contribution model.Thu, 04 Jun 2026 00:00:00 GMThttps://codeintel.xyz/blog/agent-runtime-architecture/https://codeintel.xyz/blog/agent-runtime-architecture/Deep dive on the production runtime layer for AI agents — durable execution, sandbox isolation, token accounting, and architectural patterns that separate demoware from enterprise-grade agent systems.Tue, 09 Jun 2026 00:00:00 GMThttps://codeintel.xyz/blog/agent-service-mesh-patterns/https://codeintel.xyz/blog/agent-service-mesh-patterns/Just as service meshes solved microservice-to-microservice communication at scale, agent meshes solve agent-to-agent communication. This essay examines the A2A protocol, Microsoft's Agent Governance Toolkit, and the architectural patterns for production inter-agent infrastructure.Sat, 30 May 2026 00:00:00 GMThttps://codeintel.xyz/blog/agent-state-corruption-debugging/https://codeintel.xyz/blog/agent-state-corruption-debugging/A systematic forensic approach to debugging state corruption in multi-turn agent systems — taxonomy, detection patterns, causal tracing, and production instrumentation based on 847 incidents and 13,602 open-source repository issues.Thu, 04 Jun 2026 00:00:00 GMThttps://codeintel.xyz/blog/asyncio-queue-timeout/https://codeintel.xyz/blog/asyncio-queue-timeout/A practical guide to asyncio.Queue timeout behavior, error handling with QueueFull/QueueEmpty, graceful shutdown patterns, and detection techniques for production async code.Fri, 15 May 2026 00:00:00 GMThttps://codeintel.xyz/blog/automated-git-bisect/https://codeintel.xyz/blog/automated-git-bisect/A practical guide to automated git bisect with bisect run scripts, flaky test handling (majority voting, Bayesian inference with Git Bayesect), CI integration in GitHub Actions, and a portable bash toolkit you can drop into any repo.Fri, 29 May 2026 00:00:00 GMThttps://codeintel.xyz/blog/bash-error-handling/https://codeintel.xyz/blog/bash-error-handling/A practical guide to Bash error handling with set -euo pipefail, trap ERR for guaranteed error catching, subshell pitfalls, and detection patterns for production shell scripts.Fri, 15 May 2026 00:00:00 GMThttps://codeintel.xyz/blog/compound-engineering-80-20-rule/https://codeintel.xyz/blog/compound-engineering-80-20-rule/Deep analysis of Every Inc's Compound Engineering methodology — why spending 80% of time on planning and review produces higher quality AI-generated code than the common prompt-burst approach.Mon, 01 Jun 2026 00:00:00 GMThttps://codeintel.xyz/blog/custom-eslint-rules-guide/https://codeintel.xyz/blog/custom-eslint-rules-guide/A practical guide to writing, testing, and shipping custom ESLint rules with autofix. Covers AST visitors, RuleTester, flat config, and real-world examples from TypeScript codebases.Wed, 27 May 2026 00:00:00 GMThttps://codeintel.xyz/blog/edge-cookiecutter-2217/https://codeintel.xyz/blog/edge-cookiecutter-2217/Recursive type aliases like Mapping[str, 'JsonType'] create infinite recursion in mypy — the fix replaces the self-reference with Any at the boundary.Sat, 23 May 2026 07:00:00 GMThttps://codeintel.xyz/blog/edge-requests-6102/https://codeintel.xyz/blog/edge-requests-6102/Hardcoded Latin-1 encoding in HTTP auth headers causes UnicodeEncodeError for non-Latin usernames. The fix switches to UTF-8, which handles the full Unicode range.Thu, 21 May 2026 07:00:00 GMThttps://codeintel.xyz/blog/event-driven-multi-agent-architecture/https://codeintel.xyz/blog/event-driven-multi-agent-architecture/A deep dive into event-driven architecture patterns for multi-agent AI systems — event chaining, fan-out, saga orchestration, and production deployment considerations.Mon, 01 Jun 2026 07:00:00 GMThttps://codeintel.xyz/blog/fix-click-3360/https://codeintel.xyz/blog/fix-click-3360/Click bug #3360 produced empty write_usage output when args is empty. Fix PR #3433 adds an early return guard in formatting.py. A 4-line fix that illustrates why CLI formatting code needs explicit empty-input handling.Sat, 16 May 2026 00:00:00 GMThttps://codeintel.xyz/blog/fix-cookiecutter-2217/https://codeintel.xyz/blog/fix-cookiecutter-2217/How cookiecutter/cookiecutter#2217 fixed PermissionError on read-only directories — why S_IWRITE alone is insufficient for shutil.rmtree on directories.Mon, 08 Jun 2026 07:00:00 GMThttps://codeintel.xyz/blog/fix-cookiecutter-2219/https://codeintel.xyz/blog/fix-cookiecutter-2219/How cookiecutter/cookiecutter#2219 fixed silent data loss in context generation — why batch validation should collect all errors, not fail on the first.Mon, 08 Jun 2026 07:00:00 GMThttps://codeintel.xyz/blog/fix-cookiecutter-uuid-ext-doc/https://codeintel.xyz/blog/fix-cookiecutter-uuid-ext-doc/Fixed cookiecutter/cookiecutter docs — 1-line version correction from stale tag to actual release.Thu, 04 Jun 2026 07:00:00 GMThttps://codeintel.xyz/blog/fix-psf-requests-6102/https://codeintel.xyz/blog/fix-psf-requests-6102/Fixed psf/requests#6102 — 4 line bug-fix. Python encoding fix for non-latin auth credentials.Sat, 16 May 2026 07:00:00 GMThttps://codeintel.xyz/blog/fix-requests-4965/https://codeintel.xyz/blog/fix-requests-4965/The second call to response.content after a read error silently returned empty string. A 4-line fix makes it raise an exception instead.Wed, 27 May 2026 07:00:00 GMThttps://codeintel.xyz/blog/fix-requests-6102/https://codeintel.xyz/blog/fix-requests-6102/How psf/requests#6102 fixed HTTPDigestAuth encoding — why UTF-8 credentials need explicit encoding before being passed to the digest auth handshake.Mon, 08 Jun 2026 07:00:00 GMThttps://codeintel.xyz/blog/fix-requests-7443/https://codeintel.xyz/blog/fix-requests-7443/Fixed psf/requests#7443 — 1 line type-annotation. 407/407 relevant tests passSat, 16 May 2026 07:00:00 GMThttps://codeintel.xyz/blog/fix-ripgrep-3222/https://codeintel.xyz/blog/fix-ripgrep-3222/How BurntSushi/ripgrep#3222 fixed path traversal in compressed file search — why decompression commands need argument separators to prevent option injection.Mon, 08 Jun 2026 07:00:00 GMThttps://codeintel.xyz/blog/fix-typescript-25083/https://codeintel.xyz/blog/fix-typescript-25083/How microsoft/TypeScript#25083 fixed enum keys in computed properties — why computed property names with non-identifier enum values were rejected by the type checker.Mon, 08 Jun 2026 07:00:00 GMThttps://codeintel.xyz/blog/fix-typescript-63480/https://codeintel.xyz/blog/fix-typescript-63480/How microsoft/TypeScript#63480 fixed a grammar typo in the Set#size property JSDoc — a 1-line documentation fix merged by RyanCavanaugh in 1 day.Mon, 08 Jun 2026 07:00:00 GMThttps://codeintel.xyz/blog/init-subclass-mro-edge-case/https://codeintel.xyz/blog/init-subclass-mro-edge-case/The article provides simplified type.__new__ code showing super(Subclass, Subclass).__init_subclass__() with comment explaining the skip. A FixedMetaclass example manually iterates MRO to call ancestor.__init_subclass__(cls). Three safe alternatives are listed: use a metaclass directly, use __set_name__ on descriptors, or manually scan MRO. The bug is CPython #105038, open since 2023, with related #83846. Rule: test hook firing if metaclass overrides mro. Frameworks like Django, SQLAlchemy, P...Sat, 23 May 2026 00:00:00 GMThttps://codeintel.xyz/blog/metaclass-inheritance-pitfalls/https://codeintel.xyz/blog/metaclass-inheritance-pitfalls/Combining C and Python metaclasses triggers TypeError when C tp_new uses MRO to invoke Python __new__. Constraints: safe tp_new chaining and tp_basicsize. Fixes: reorder bases (Python metaclass first) or modify C tp_new to call tp_base->tp_new (skips Python __new__). Increasing tp_basicsize ensures correct base selection. First reported 2004, affects ZODB, SQLAlchemy; a silent hazard. Key takeaway: never let C tp_new invoke Python __new__; prefer composition; document tp_basicsize requirement...Thu, 21 May 2026 07:15:00 GMThttps://codeintel.xyz/blog/mutation-testing-deep-dive/https://codeintel.xyz/blog/mutation-testing-deep-dive/The mutmut cache output shows 3 mutants survived from 76 killed, illustrating that mutation score is a meta-test validating test rigor, not a replacement for other tests. Common survivors include condition flips (e.g., `if not is_member`) and arithmetic removals. Start with one module, scan for unasserted calls, and raise break thresholds incrementally. The final key takeaway: mutation testing is the only metric that validates test correctness.Mon, 25 May 2026 07:00:00 GMThttps://codeintel.xyz/blog/posix-double-dash-separator/https://codeintel.xyz/blog/posix-double-dash-separator/How the `--` separator prevents compression tools from misinterpreting filenames as options, with a fix PR analysis from ripgrep.Mon, 18 May 2026 00:00:00 GMThttps://codeintel.xyz/blog/pr-leaderboard-2026-05-19/https://codeintel.xyz/blog/pr-leaderboard-2026-05-19/Daily PR repair leaderboard. Tracking impact across 3 repos.Tue, 19 May 2026 01:37:16 GMThttps://codeintel.xyz/blog/pr-leaderboard-2026-05-22/https://codeintel.xyz/blog/pr-leaderboard-2026-05-22/Daily PR repair leaderboard. Tracking impact across 4 repos.Fri, 22 May 2026 21:54:27 GMThttps://codeintel.xyz/blog/pr-leaderboard-2026-05-23/https://codeintel.xyz/blog/pr-leaderboard-2026-05-23/Daily PR repair leaderboard. Tracking impact across 4 repos.Sat, 23 May 2026 22:30:50 GMThttps://codeintel.xyz/blog/pr-leaderboard-2026-06-08/https://codeintel.xyz/blog/pr-leaderboard-2026-06-08/Daily PR repair leaderboard. Tracking impact across 5 repos.Mon, 08 Jun 2026 01:41:28 GMThttps://codeintel.xyz/blog/pr-weekly-2026-05-24/https://codeintel.xyz/blog/pr-weekly-2026-05-24/No PRs submitted this week. Total: 5 PRs, 0 merged (0% merge rate).Sun, 24 May 2026 07:00:00 GMThttps://codeintel.xyz/blog/pr-weekly-2026-05-31/https://codeintel.xyz/blog/pr-weekly-2026-05-31/No PRs submitted this week. Total: 5 PRs, 1 merged (17% merge rate) — microsoft/TypeScript#63480 merged into main.Sun, 31 May 2026 07:00:00 GMThttps://codeintel.xyz/blog/pr-weekly-2026-06-07/https://codeintel.xyz/blog/pr-weekly-2026-06-07/No PRs submitted this week. Total: 7 PRs, 1 merged (14% merge rate).Mon, 08 Jun 2026 07:00:00 GMThttps://codeintel.xyz/blog/prompt-caching-production-architecture/https://codeintel.xyz/blog/prompt-caching-production-architecture/An engineering deep dive on the four caching layers for LLM inference — KV/prefix caching, prompt caching, semantic caching, and exact-response caching — with architecture patterns, provider pricing analysis, and production deployment strategies.Fri, 05 Jun 2026 07:00:00 GMThttps://codeintel.xyz/blog/python-async-patterns/https://codeintel.xyz/blog/python-async-patterns/Exploring structured concurrency, task groups, and error propagation in Python asyncio — with testable code snippets.Fri, 15 May 2026 07:00:00 GMThttps://codeintel.xyz/blog/python-context-managers-production/https://codeintel.xyz/blog/python-context-managers-production/Production-ready context manager patterns beyond basic with statements — ExitStack composition, async cleanup, and pytest fixture integration with real code templates.Sun, 17 May 2026 07:00:00 GMThttps://codeintel.xyz/blog/python-del-edge-cases/https://codeintel.xyz/blog/python-del-edge-cases/Python's __del__ has three failure modes: silent swallowing (exceptions to stderr), resurrection (anti-pattern with FINALIZED flag in gcmodule.c), and shutdown crashes (module globals become None). PEP 442 (Python 3.4) fixed pre-3.4 gc.garbage leaks via tp_finalize. The industry fix is weakref.finalize (no self, bounds checked) for non-deterministic cases and context managers for deterministic ones. Production incidents include ulimit from open files, OOM from resurrected ORM sessions, and co...Fri, 22 May 2026 07:00:00 GMThttps://codeintel.xyz/blog/python-slots-deep-dive/https://codeintel.xyz/blog/python-slots-deep-dive/Exploring the nuanced behavior of `__slots__` in Python, including memory implications, performance gains, and how they interact with metaclasses.Sat, 16 May 2026 07:00:00 GMThttps://codeintel.xyz/blog/python-slots-metaclass/https://codeintel.xyz/blog/python-slots-metaclass/Exploring advanced behavior of `__slots__` via metaclasses, including memory implications and inheritance rules.Sat, 16 May 2026 07:00:00 GMThttps://codeintel.xyz/blog/requests-cookie-none-bug/https://codeintel.xyz/blog/requests-cookie-none-bug/Root cause analysis of a decade-old bug in psf/requests where setting a cookie value to None corrupts the entire Cookie header. Fix: 4 lines in cookiejar_from_dict(). Tests: 597 passed.Sun, 31 May 2026 07:00:00 GMThttps://codeintel.xyz/blog/ripgrep-readme-shell-prompts/https://codeintel.xyz/blog/ripgrep-readme-shell-prompts/A 41-line documentation fix in BurntSushi/ripgrep — removing `$ ` prefixes from README code blocks for cleaner copy-paste. PR #3437. Why shell prompts in documentation create friction for users.Sat, 06 Jun 2026 07:00:00 GMThttps://codeintel.xyz/blog/streaming-llm-inference-architecture/https://codeintel.xyz/blog/streaming-llm-inference-architecture/A deep dive into production streaming patterns for LLM inference: SSE vs WebSocket vs gRPC, backpressure strategies, reverse proxy pitfalls, and the architectures that keep token delivery fast at scale.Mon, 08 Jun 2026 07:00:00 GMThttps://codeintel.xyz/blog/swe-bench-proxy-2026-05/https://codeintel.xyz/blog/swe-bench-proxy-2026-05/Measuring coding intelligence with real GitHub bug fixes. Baseline: 80% real-world bug fix rate on 31 instances from 4 repos.Fri, 15 May 2026 07:00:00 GMThttps://codeintel.xyz/blog/type-checker-benchmarks-ci/https://codeintel.xyz/blog/type-checker-benchmarks-ci/Benchmarks mypy, Pyright, Ruff on 50K-line Django. Cold start: Ruff 0.8s, Pyright 6s, mypy 28s (ephemeral CI bottleneck). Incremental: Pyright daemon 1.5s beats mypy cache 8s. Mypy deepest (--strict weekly); Pyright 95% with report*; Ruff preview skips complex. Recommendations: small Ruff, medium Pyright, large two-stage (85% savings). Sample CI: actions/checkout, setup-node. Quick fix: measure, add Ruff, replace mypy, schedule mypy --strict, controlled rollout. Key takeaway: mypy depth king,...Sun, 24 May 2026 07:00:00 GMThttps://codeintel.xyz/blog/typescript-discriminated-unions/https://codeintel.xyz/blog/typescript-discriminated-unions/A practical guide to TypeScript discriminated unions with exhaustive pattern matching, the never type, and real-world detection patterns for your codebase.Fri, 15 May 2026 07:00:00 GMThttps://codeintel.xyz/blog/typescript-keyfor-jsdoc-fix/https://codeintel.xyz/blog/typescript-keyfor-jsdoc-fix/A one-character grammar fix in TypeScript's lib.d.ts — 'returns a undefined' → 'returns undefined'. PR #63525. Why JSDoc grammar matters in the most-read type definitions in JavaScript.Mon, 01 Jun 2026 07:00:00 GMT