Ben f5f61fb48c blog: Four More Coding Agents That Remember Your Project (#4042) ...

* blog: Four New Coding Agents, and Four Ways to Fail Silently

Covers coding-agents 0.5.0, which adds pi, Qwen Code, DeepAgents Dcode and
opencode 2, bringing the package to 16 harnesses.

The angle is that three of the four integrations, wired the obvious way,
failed without producing an error:

- opencode 2 rewrote the plugin contract, and handing either host the
  other's export loads a plugin that registers nothing and reports no
  error. Both CLIs also read the same config file, which v1 rejects
  outright if it contains v2's plugins key.
- Qwen Code speaks Claude Code's hook protocol field for field, but its
  timeouts are milliseconds, so the usual values register 30ms hooks. It
  looks fine in testing because orphaned processes still finish.
- Dcode's last_assistant_message is a Python repr, so encrypted reasoning
  payload was retained as the assistant turn and re-appended every turn.
- pi and Prime Agent shared one package.json key, so the host it did not
  name loaded the other's bundle under the wrong harness.

Screenshots are the install output and the three new hosts at startup.
Captions describe what each frame actually shows and do not claim to show
memory injection, which these captures do not.

Cover is c03: the four harness marks converging on one memory core.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AE4NCnCKXUzNDF3N9FaQja

* blog: reframe around the agents, not the integration work

The first draft read as a bug-fix changelog: four sections, each about a
trap we hit wiring a host. That is inward-facing, and it buries what a
reader actually wants to know.

Rewritten around three things:

- How a coding agent works, and what it loses on every session reset. The
  mechanical part is rederivable from the code; the last mile is a
  decision that was never in the code at all.
- What memory adds to that loop: cold seed at session start, recall per
  prompt, native tools during, write-back at the end.
- Sixteen agents sharing one bank per repository, so switching agents
  costs nothing. This is the strongest point in the release and the first
  draft did not make it at all.

Each new agent now gets described for what it is rather than for how it
broke. Qwen Code's QWEN.md convention and Dcode's headless mode are used
to make the memory argument concrete, which also gives the screenshots
something to support.

The integration difficulties are kept as one short closing aside with a
single example, rather than the spine of the post.

Title changed to match. Adds a comparison table for the four agents.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AE4NCnCKXUzNDF3N9FaQja

---------

Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-09-02 14:54:39 -04:00

19 KiB

916x463px

Raw Permalink History