Glean 拾遗
中 EN
Submit a link
Daily · timeline

A few picks a day.

Sat, Nov 14, 2026 3picks
← 11-13
Calendar ▾
2026 · 11
MoTuWeThFrSaSu ······123456789101112131415161718192021222324252627282930
has picks today
06:00

Graph Engineering: Building a CI Triage Agent Graph

Graph Engineering：把单一循环拆成多智能体编排图

A how-to for replacing a single agent loop with a graph of specialists: nodes each own one verb and a scoped context, edges are deterministic routing code, a shared state file carries history across runs, and a gate decides done or not done. The worked example is a GitHub Actions failure triage system, with copy-ready agent definitions for a classifier and a bug fixer, edge rules that keep hard constraints out of prompts, a STATE.md layout, and a test-gate prompt. Autonomy is staged from manual /goal to scheduled /loop to cloud Routines. The author concedes most teams should not build one yet, and names comprehension debt as the cost of a graph that ships code nobody reads.

x.com · 27 min · Agent Orchestration · Claude Code · Graph Engineering · Multi-Agent · Verification Loop
06:00

Two Agents, One Record: Git-Style Branches Instead of Row Locks

Agent 并发写同一份记忆会静默丢更新，Omnigraph 用 Git 分支模型接管冲突

Two agents doing read-modify-write on shared memory lose updates silently: because an agent writes back the whole record it read, a stale save can reset a field another agent just changed, and both report success. The post walks through the three usual fixes—single writer, row locks or optimistic version checks, last-write-wins—and argues all fall short for multi-step tasks spanning several records, since none produces a reviewable diff or an audit trail. It then demos Omnigraph, an MIT-licensed graph database in Rust with a Git-style model: each agent commits to its own branch, merges compare against the merge base, and a stale branch is rejected with divergent_update instead of publishing. The walkthrough uses Claude Code and Codex, covering @key stable IDs, --snapshot reads of old commits, and a Cedar policy with per-agent tokens returning HTTP 403 for writes to main. Useful for anyone building multi-agent shared state, though the headline's 1,000-agent scale is never shown—the demo is one developer and two agents.

x.com · 11 min · Agent Infrastructure · Agent-Memory · Multi-Agent · Version Control
06:00

The Harness Is the Machine: Seven Invariants for Agent Engineering

Harness 才是机器：Agent 工程的七条不变式

The essay argues that agent failures come from the environment around the model, not from prompts. It lays out seven harness invariants: bound the contract before the first token, feed the context window only AST symbol slices, quarantine writes in ephemeral git worktrees, persist state to disk as receipt.md, gate merges on compiler and test exit codes rather than model claims, strip credentials and network egress, and emit a machine-readable audit receipt per run. It cites a before/after on a multi-file refactor (18% completion bare, 89% with a harness), plus a .claude/rules YAML example, a pre-verify.sh sensor hook, and a receipt template. Useful for engineers wiring coding agents into CI, though the headline numbers are unsourced, the model version names are fictional, and the post ends with promotion.

x.com · 14 min · Agent Engineering · Agent Harness · Agent Workflows · Coding Agents · Git Worktree