2 Commits
Author SHA1 Message Date
Aleksander DygońandClaude Opus 5.5 03c2ff34c2 Remove code comments and add the no-comments rule (#12604)
* Remove code comments and add the no-comments rule

Remove the comments from first-party code and configuration files:
TS/JS, JSX, CSS, SQL migrations, Swift, Kotlin, Gradle, shell,
Docker, systemd, Nix, YAML, TOML, JSONC and GritQL.

Keep only what a tool reads: license headers, shebangs, compiler
and lint directives, JSDoc types in plain .js files, generated file
headers, GritQL scope lines, the install-server.sh help text and the
openbot-boat-pre-stop marker. Vendored code, fixtures and released
schemas keep their comments.

Add the rule to AGENTS.md, and change the docs that asked for
comments. Add two i18n keys that only comments named to
RELEASED_SOURCE_KEYS.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Keep comments that are data in strings

The benchmark task files in opencode-free-models-bench.ts tell the
model what each function must do. The sample file and HTML page in
the two stories are display content. Put their comments back.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Keep released migrations and mobile native inputs unchanged

check:migrations compares each released migration with v0.73.0 byte
for byte, so restore src/backend/migrations. A change to a native
build input of apps/mobile makes a new runtime version, so restore
those files and the extra fingerprint sources.

List these files and the comment markers that a tool reads in
AGENTS.md. Remove the last requests for comments in
src/renderer/AGENTS.md.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-19 12:19:28 +01:00
Aleksander DygońandClaude Opus 5.5 168cb1198d Keep an OpenCode answer whole when reasoning streams between its tokens (#3361)
* Keep an ACP answer whole when reasoning streams between its tokens (#3351)

A thought chunk closed the open answer as commentary. A model that streams
its reasoning between the tokens of one answer (seen on a custom OpenCode
endpoint) had its answer cut mid-word into commentary items, so words showed
with a space inside them, such as "B aca". A thought no longer closes the
answer. A tool call or the end of the turn still sets its phase.

Add scripts/opencode-token-stream-e2e.ts: it runs the real OpenCode CLI and
driver against a fake OpenAI-compatible endpoint that streams sub-word
tokens, with and without reasoning between them.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Limit the whole-answer rule to OpenCode and keep the harness retry path

Review findings on #3361:
- The harness error report (#1471) needed #appendThought to end the partial
  answer. That branch now ends it itself, so the retried answer replaces it.
- A thought keeps the answer open only for the OpenCode flavor
  (thoughtsInsideAnswer). Other ACP agents keep the old step boundary, so the
  Antigravity failure check on the answer text is not changed.
- Add a fake OpenCode agent and opencode-thought-interleave-e2e to the
  provider fakes CI job. It covers interleaved thoughts and the harness retry.
- The token stream control case now checks the answer text.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 09:48:48 +01:00