Extract utility functions (stripEmptyPlanBlock, stripMarkdownFences,
buildMessageXML, copyMessages, countMessagesTokens, reviewModeString,
detectGitBranch) into util.go and all compression logic into compression.go
to improve readability (agent.go: 1489 → 1114 lines).
Fix pre-existing compression bugs from commit 14adf6f:
- Return unmodified messages on compression failure instead of truncating
to frozen zone (which discarded all conversation context)
- Check error in async compression goroutine to avoid applying failed results
- Track snapshot length to append post-snapshot messages when applying async
compression, preventing silent message loss
- Strip old <previous_review_summary> before appending new one to prevent
cumulative frozen zone bloat across multiple compressions
- Guard pendingJob cleanup to only clear when it matches the completed job,
preventing accidental clearing of a newly scheduled job
- Add context.Context and 5s timeout to detectGitBranch
- Deep copy ToolCalls in copyMessages to match session/history.go
- Reuse finalCount in addNextMessage to avoid redundant token counting
Move all LLM prompt content from inline JSON strings in task_template.json
to individual Markdown files under prompts/, following the same embed.FS
pattern used by internal/config/rules/. This improves maintainability by
enabling native syntax highlighting, cleaner diffs, and separation of
prompt content from runtime configuration.
Also removes two dead config fields (TOOL_REQUEST_WAIT_TIME_MS,
MAX_SUBTASK_EXECUTION_TIME_MINUTES) that had no runtime consumers.
Add benchmark comparison data (metrics table, key conclusion, and
screenshot) to EN, ZH-CN, JA-JP, KO-KR, and RU-RU READMEs.
Non-Chinese languages use the English screenshot.
Update Claude Code benchmark results for Claude-4.8-Opus and GLM-5.1,
refresh token cost ratio (1/5 → 1/9) and F1 score (26.1% → 25.1%) to
reflect latest data. Add clickable sort headers for F1/Precision/Recall
columns with visual indicators. Centralize hardcoded stats into i18n
and use semantic i18n keys for benchmark subtitle.
Add preset provider list (Anthropic, OpenAI, DashScope, DeepSeek, Z.AI)
and custom endpoint support details to the multi-model protocol feature
description in both en.ts and zh.ts.
The main npm package included all 6 platform binaries (~243MB) because
.npmignore did not exclude the opencodereview-* artifacts downloaded
during CI. Adding a files whitelist reduces the package from ~243MB
to ~1.4MB.
Session directories were created with 0755 (rwxr-xr-x) and session
files with 0644 (rw-r--r--), making them readable by any local user
on shared systems such as multi-user servers and CI runners.
Session JSONL files contain full LLM request and response data,
including the complete source code diff, file contents read by the
file_read tool, and the model's analysis — all sensitive material.
Change MkdirAll mode from 0755 to 0700 and OpenFile mode from 0644
to 0600, restricting access to the file owner only. This matches the
0600 permission already used for the config file (which holds the API
key) in cmd/opencodereview/provider_cmd.go.
Fixes#144
Internal npm registry (anpm) only allows specific scopes like @ali,
not @alibaba-group. Derive scope from OCR_PKG_NAME and apply it to
platform subpackage names during publish. Also make platform.js read
package names from optionalDependencies dynamically instead of relying
solely on the hardcoded scope.
Ship Go binaries inside per-platform npm packages (@alibaba-group/ocr-{os}-{arch})
so npm install resolves the correct binary via optionalDependencies + os/cpu fields.
This removes the need for a postinstall download from GitHub Releases, which is
extremely slow for users behind restricted networks (e.g. China mainland).
The postinstall download is retained as a fallback for --no-optional installs.
ApplyLanguage was only called when the config file existed, so without
~/.opencodereview/config.json no language instruction was injected and
the LLM picked its own language. Now ApplyLanguage is called
unconditionally, defaulting to English via resolveLang("").
Update all README translations to reflect the corrected default
(English) and clarify that any language name is accepted.
Previously, checksum failures in install.js were silently downgraded to
warnings, allowing unverified binaries to be installed. Similarly,
update.js accepted HTTP registries and skipped verification when no
matching platform entry was found.
Now both scripts treat checksum verification as mandatory when configured:
all failure paths (download error, compute error, mismatch, missing
platform entry) abort the operation and clean up downloaded files.
update.js also drops the http module and silently skips version checks
for non-HTTPS registries.
Align README.ru-RU.md with the English README updates from 72aad2c:
add interactive provider/model setup (Option A), restructure config
options into A/B/C, and add new commands to the reference table.
Strip C0/C1 control characters and DEL from model/diff-derived strings
before printing to the terminal, preventing OSC 52 clipboard hijack,
screen erasure spoofing, and other ANSI injection attacks (CWE-150).
JSON output is unaffected as encoding/json already escapes control chars.
- Replace hardcoded fmt.Printf width specifiers with text/tabwriter
- Column widths now adapt to actual content, preventing overflow
- Eliminates risk of misaligned columns when provider names exceed preset width
Remove the duplicate kimi provider entry introduced by overlapping PRs
(#130 and #134). Keep the Kimi Moonshot API entry with MOONSHOT_API_KEY.
Set LC_ALL=C in Makefile test target to ensure git outputs English
messages regardless of system locale.
When a file was renamed on the target branch, ocr review emitted
'[ocr] WARNING: cannot read file <old path> at ref <to>: exit status 128'.
Two compounding bugs:
1. The parser required 'a/'/'b/' prefixes when matching '--- /dev/null' /
'+++ /dev/null', but git emits these lines without prefixes, so
IsNew/IsDeleted were never set and deleted files fell through to a
doomed 'git show ref:<old path>'.
2. 'rename from' / 'rename to' extended headers were never parsed, and
git diff/show call sites did not force rename detection, so renames
degraded to delete+add whenever the user had diff.renames=false.
Fixes:
- Parse 'rename from'/'rename to', 'new file mode', 'deleted file mode'
and unprefixed /dev/null markers in ParseDiffText.
- Pass --find-renames to all git diff/show invocations so rename
detection no longer depends on user config.
- Add IsRenamed to model.Diff (json: is_renamed) and prefer it in
diffStatus.
- Add parser unit tests and a range-mode rename regression test.
Fixes#99
The cpAuth text input width was 40, which truncated the 51-character
placeholder "optional, leave empty for default (Authorization)".
Increased to 55 so the full text is visible.
* ci: use self-hosted runners with container images for build and deploy workflows
- deploy-pages: switch to self-hosted runner with node:20 container, remove redundant setup-node
- release: use self-hosted runner with golang:1.26.4 container for build job, remove redundant setup-go
- release: use self-hosted runner with ubuntu:24.04 container for release job
- release: use self-hosted runner with node:20 container for npm-publish job, remove redundant setup-node
- release: add jq installation step for version injection in npm-publish
* ci: fix dubious ownership in self-hosted container jobs
- Add git safe.directory trust step after checkout in release.yml build and npm-publish jobs
- Add git safe.directory trust step after checkout in deploy-pages.yml build job
- Switch deploy-pages deploy job from ubuntu-latest to self-hosted with node:20 container
Add README.ru-RU.md and CONTRIBUTING.ru-RU.md following the existing
localization pattern (zh-CN, ja-JP, ko-KR), and add the Русский link to
the language switcher line in all README and CONTRIBUTING variants.
Also add the previously missing 한국어 link to the CONTRIBUTING.zh-CN.md
and CONTRIBUTING.ja-JP.md switchers.
Closes#100
