openclaw - The LGTM (Page 13)

The LGTM

Home
Agentic Coding
Claude Code
Codex

Sign in Subscribe

openclaw

A collection of 263 posts

MCP Cross-Agent Invocation Still Needs a Real User Role

MCP Cross-Agent Invocation Still Needs a Real User Role

OpenClaw’s MCP bridge has a small role bug with a large architectural smell: messages_send can put text into another session’s history, but it cannot reliably wake the receiving agent because it hardcodes the message as role: "assistant". In human terms, the message gets filed as

24 May 2026 5 min read

OpenClaw v2026.5.22 Is a Gateway Startup Release Wearing a Changelog Costume

OpenClaw v2026.5.22 Is a Gateway Startup Release Wearing a Changelog Costume

OpenClaw v2026.5.22 reads like a feature dump until you squint at the pieces that keep repeating: cache this, lazy-load that, stop dragging every plugin and handler tree into the startup path. The headline is not meeting notes, Grok search auth reuse, or another channel knob. The headline is

24 May 2026 5 min read

OpenClaw’s Heartbeat Fleet Problem Is a Scheduler Design Smell, Not Just an Ops Complaint

“Every 30 minutes” sounds harmless until fifteen agents hear it as “all at once.” That is the scheduler smell documented in OpenClaw issue #85885. An operator running a 15-agent OpenClaw deployment reports that agents configured with default heartbeat: {} fire on the same cadence, producing synchronized gateway load spikes. The attempted

23 May 2026 4 min read

OpenClaw Stops Letting Aborted Subagents Pretend They Succeeded

A child agent that aborts did not “complete with no message.” It failed. The parent deserves to know. That is the plain-language contract behind OpenClaw PR #85860, which fixes a multi-agent lifecycle bug where a subagent ending with stopReason: "aborted" could still be normalized into an OK completion

23 May 2026 3 min read

OpenClaw’s Cost Reporter Learned the Difference Between Free and Unknown

The most dangerous number in an agent platform is not a large bill. It is a confident zero. That is the bug OpenClaw PR #85882 is trying to fix. The patch changes openclaw gateway usage-cost so token-burning turns from models with unknown or all-zero pricing metadata are no longer reported

23 May 2026 3 min read

OpenClaw’s Process Supervisor Fix Is Boring in Exactly the Way Production Agents Need

Agent platforms love to talk about autonomy. Then a timeout arrives, and you find out whether the runtime behaves like an operator or like someone yanked the power cord. OpenClaw PR #85865 is squarely in the unglamorous category of fixes that production systems need. It changes process-supervisor cancellation from a

23 May 2026 3 min read

Control UI Token Pairing Shows the Cost of Security Fixes That Break Local Trust Paths

Control UI Token Pairing Shows the Cost of Security Fixes That Break Local Trust Paths

Security hardening is easy to applaud until it breaks the control surface people need to run the system. OpenClaw PR #85459 is a good example of that uncomfortable middle ground. It restores local Control UI and WebChat browser-origin pairing when the client has a valid gateway token, after a previous

22 May 2026 4 min read

OpenClaw Coalesces Provider Auth Rewarms Because Channel Latency Is a Runtime Bug

OpenClaw Coalesces Provider Auth Rewarms Because Channel Latency Is a Runtime Bug

Provider authentication rewarm sounds like the sort of phrase that belongs in a log line nobody reads. Then Telegram reactions start taking one to two minutes after a message, and suddenly backend housekeeping is the product. OpenClaw PR #85487 is a small gateway patch with a useful lesson: channel latency

22 May 2026 4 min read

Codex Compaction Recovery Turns a Stuck Preflight Into a Bounded Restart

Codex Compaction Recovery Turns a Stuck Preflight Into a Bounded Restart

Codex compaction is not a feature most users think about until it starts breaking the part they do care about: the next answer. That is why OpenClaw PR #85500 is more interesting than its small diff suggests. It turns a stuck native compaction preflight from an ambient runtime failure into

22 May 2026 4 min read

Telegram Delivery Bugs Are a Reminder That Agent Replies Are Not Just Chat History

The bug in OpenClaw PR #85361 is easy to undersell as a Telegram annoyance. A direct message came in, the assistant generated an answer, the transcript stored it, and Telegram never received it. Annoying, yes. But the real lesson is larger: in agent systems, “the model answered” and “the user

22 May 2026 4 min read

Codex Replay Recovery Shows Why Agent Sessions Need Poisoned-State Escape Hatches

The most interesting phrase in OpenClaw PR #85362 is not invalid_encrypted_content. That is just the error string. The interesting phrase is “replay-invalid session state,” because it names the actual disease instead of the symptom. Long-running coding agents accumulate state the way old services accumulate cron jobs: transcripts, provider

22 May 2026 4 min read

Local Embeddings Should Not Be Able to Take Down the Agent Runtime

Local Embeddings Should Not Be Able to Take Down the Agent Runtime

The local-agent story usually gets told as a hardware shopping guide. How much RAM do you need? Which quant fits? Is Metal fast enough? Can your Mac Studio run the embedding model without sounding like a leaf blower? Useful questions. Incomplete questions. The more important production question is whether the

22 May 2026 3 min read

← Newer Posts Page 13 of 22 Older Posts →

The LGTM © 2026

Sign up

Powered by Ghost