* feat(telemetry): add OTLP HTTP exporter and print TraceID
- Add HTTP/protobuf exporter support alongside existing gRPC exporter
- Route based on OTEL_EXPORTER_OTLP_PROTOCOL config (http/protobuf vs grpc)
- Print TraceID to stderr when telemetry is enabled for easier correlation
- Add corresponding unit tests
* feat(telemetry): add span coverage for LLM calls, tool execution, plan/filter phases
- Add StartLLMSpan / RecordLLMResult helpers (span.go), symmetric with
existing StartToolSpan / RecordToolResult
- Wrap LLM completion calls in llmloop.RunPerFile with llm.request spans
- Wrap all three tool execution paths in executeToolCall with
tool.execute.* spans (dynamic tools, code_comment sync/async, other tools)
- Add plan.execute span around executePlanPhase
- Add main.loop span around RunPerFile call in executeSubtask
- Add review_filter.execute span around executeReviewFilter, with
comments.before / comments.filtered attributes
- Record llm.error attribute on LLM failures for diagnosability
- Record review.repo / review.from / review.to / review.model on the
top-level review.run span
- Metrics (RecordLLMRequest / RecordToolCall) are preserved alongside
the new spans — they serve different purposes (aggregate dashboards
vs per-run diagnosis)
Verified end-to-end against Sunfire (OTLP HTTP gateway): full span tree
observed for review.run -> subtask.execute -> plan.execute/main.loop/
review_filter.execute -> llm.request/tool.execute.*
* fix(telemetry): address CR findings — span error handling, async span lifecycle, protocol robustness
- Add span.RecordError(err) to RecordLLMResult and RecordToolResult for
consistency with EndSpan
- Use OTel standard pattern (span.SetStatus + span.RecordError) in error
paths of review.run, plan.execute, main.loop, review_filter.execute
- Move async code_comment span end into pool.Submit callback so span
duration reflects actual execution time
- Unify time.Since(startTime) in code_comment error path to a single dur
- Remove http/json from supported OTLP protocols (not actually implemented)
- Add stderr warning when unknown OTLP protocol falls back to gRPC
* feat(telemetry): include trace_id in JSON output, restrict stderr to text format
- Add trace_id as top-level field in jsonOutput struct (omitempty)
- JSON format: trace_id in structured response for programmatic extraction
- Text format: TraceID printed to stderr for human debugging
- Telemetry disabled: trace_id field omitted entirely
* fix: address PR review findings
- loop.go: wrap async span lifecycle in defer to prevent leak on panic
- exporter.go: update parseOTLPEndpoint comment to reflect gRPC+HTTP usage
- scan_cmd.go: align traceID extraction and OTel error handling with review_cmd
- output.go/shared.go: propagate traceID to outputJSONNoFiles for consistency
- agent.go: move comments.filtered attribute before early return so 0 is
distinguishable from not-executed
* feat(telemetry): address PR review — http/json routing, LLM span coverage, trace_id tests
- Route http/json to HTTP exporter (Go OTel SDK HTTP transport only
supports protobuf serialization; users need HTTP transport, not JSON encoding)
- Add llm.request spans to executePlanPhase, executeReviewFilter, and
ReLocateComment with Usage nil-safety consistent with loop.go
- Add trace_id assertions to output helper tests and emitRunResult
end-to-end tests using real TracerProvider
* docs: add OTLP protocol selection and endpoint format to telemetry section
Sync across all 5 README language versions (en, zh-CN, ja-JP, ko-KR, ru-RU).
* fix: unify time.Since in async code_comment defer to single dur variable
* fix(tool): resolve file_read paths against git top-level in monorepos
ocr review from a monorepo subdirectory failed with "file not found" (#287):
git reports diff and `git show HEAD:<path>` paths relative to the repo root,
but RepoDir was scoped to the invocation subdirectory, producing a double
prefix. resolveWorkingDir now anchors RepoDir at `git rev-parse
--show-toplevel` on the review path (requireGit=true); scan keeps the CWD so
its `git ls-files` walk stays scoped.
The top-level lookup uses a stdout-only git helper so stderr notices can't
pollute the path, and fails loudly if --show-toplevel errors or is empty
(e.g. a bare repo) instead of silently reusing the subdirectory. Adds
regression tests for the subdir hoist, the scan-path scoping, git-show
resolution of root-relative paths, and the bare-repo failure.
* docs(rules): document repo-root rule.json resolution in monorepos
Since #287 anchored RepoDir at the git top-level, ocr review from a
monorepo subdirectory loads the repo-root .opencodereview/rule.json
rather than a subdir-local one. Call out this user-visible behavior at
loadProjectRule so the scope change isn't a surprise (review feedback).
Add two structured fields, category and severity, to every review finding
so CI integrations can sort, group, filter, or gate builds without
re-parsing natural-language comment text.
- Tool schema (tools.json): add category/severity as enum-constrained,
required properties of code_comment. severity is limited to
critical/high/medium/low (info dropped, since LLMs struggle to
distinguish low from info).
- System prompt (task_template.json) is intentionally left untouched to
avoid the review-quality regression observed on the benchmark suite;
the tool schema alone drives field population.
- JSON output: category/severity are flat siblings of content/start_line,
omitted entirely when empty (backward compatible).
- CLI output: render an inline [category - severity] badge before the
comment, colored by severity.
- Sync docs across all five README locales.
* fix(tui): persist official-tab models and refine saved secret hint
Persist user-added models to providers.<name>.models on the official tab.
When an API key or auth token is already saved, show a replace hint with a
prefix/suffix fingerprint (skipped for short keys), use a fixed mask placeholder,
and ensure typing or paste replaces the saved value instead of re-saving it.
* fix(tui): model add/delete UX and config wizard hardening
- Add model add/delete in config provider and config model (official + custom)
- Show d Delete only on model rows; green highlight when selected
- Improve Esc cancel text; track savedInSession to avoid misleading messages
- Reload config on save failure; read registry models fresh after reload
- Export llm.ModelListContains; fix config model persist using registry-only check
* fix(tui): defer provider config until confirm and harden API key UX
Only persist provider/model on wizard confirm; keep in-session picks via
sessionModelPick. Validate API key before quit, clear saved keys when emptied,
and improve official env-var hints and custom edit clear behavior.
* feat(tui): show active model suffix on official provider list
Align Official tab with Custom: display (model) next to the active preset
when cfg.Provider matches and a global model is configured.
* feat(mcp): add Model Context Protocol server support
Add MCP client and provider packages that allow integrating external
MCP tool servers into the review loop. Includes config commands for
managing MCP servers, stdio subprocess integration tests, and
comprehensive test coverage.
* refactor(mcp): rename loop variable in contentToText to avoid shadowing Client receiver
* fix(mcp): use platform-specific shell for setup command
The MCP server setup command was hardcoded to use `sh -c`, which
fails on Windows. Extract a `shellCommand` helper behind build tags
to use `cmd /c` on Windows and `sh -c` elsewhere.
* docs(mcp): add MCP server documentation to all README locales
The testdiff CLI was an early-stage tool for manually testing the
internal/diff package. It has no external references and its role is
fully covered by the existing unit tests in internal/diff/.
* feat: improve config provider TUI interaction
- Support wrap-around navigation in provider, custom provider, and model lists
(up at first item jumps to last, down at last item jumps to first)
- Add d key to delete custom models in model selection step with confirmation prompt
- Add protocol selection (anthropic/openai) to manual configuration flow
and respect UseAnthropic setting in saved config
- Preserve manual protocol selection when re-entering the form
- Fix manual form input fields losing focus after returning from next step
- Use safe slice removal in removeFromSlice to avoid backing array corruption
* fix: address code review feedback
- Restore Blur() calls in handleManualFormEnter to prevent visual focus artifacts
when transitioning between manual form steps
- Add empty-providers guard in handleUp/handleDown to avoid negative index
- Consolidate redundant protocolIdx checks into single if/else in viewManualTab
and viewCustomProviderForm for clarity
* fix: persist custom model deletions and support masked auth token editing
- Track deleted custom models in TUI and apply them on exit
(both confirm and cancel paths) to keep config.json in sync
- Clear custom provider's active Model field when that model is deleted,
preventing stale "model" reference in the provider list label
- Add masked display for manual config Auth Token to allow easy re-entry,
matching the official provider flow (any key clears and starts fresh)
* test: update manual form tests for masked auth token behavior
Update TestProviderTUI_ManualFormPrefilledValues,
TestProviderTUI_ManualFormEscRestoresOriginalValues, and
TestProviderTUI_ManualFormPrefilledWhenProviderSet to assert
the new masked display state (manualTokenMasked + manualTokenOriginal)
instead of the raw token value.
* feat: refine config provider TUI flows and session persistence
Custom provider interactions:
- Simplify create/edit form to Name → Protocol → URL → API Key → Auth Header
- After create or edit save, jump straight into the model list for that provider
- Support comma-separated model names in the custom model input
- Show masked API key in edit form; empty Auth Header defaults to (Authorization)
- Populate edit form from existingCfg to avoid stale list data after in-session saves
Model selection and highlight:
- Green highlight follows the persisted active model, not the cursor position
- Prefer provider entry.model over global cfg.model when resolving active model
- Deleting a non-active model keeps the current green highlight unchanged
Delete and navigation:
- Delete custom providers (d) and custom models (d) with confirmation prompts
- Persist create/edit/model-select/add/delete changes to disk during the session
- Fix custom provider deletion not surviving Esc exe-entry
Tests:
- Add coverage for model highlight, delete-model behavior, and create→model-list flow
- Update manual/custom form tests for masked token and session save behavior
* refactor: address provider TUI code review feedback
- Remove dead helper removeFromSlice (superseded by removeModels)
- Move misplaced doc comment to applyEditCustomProviderSave
- Drop redundant applyProviderDeletions post-TUI call so provider
deletions rely solely on the in-session save
- Fix brace/indent drift in updateDeleteModelConfirm and cache the
model list instead of recomputing m.models() twice
* feat: refine provider TUI flows and manual config form
Custom provider flow:
- Default protocol to anthropic on the new-provider form
- Single-name model input; reject duplicates with inline error and
preserve the typed value so the user can edit instead of re-typing
- Drop the global green highlight; cursor/blue is the only selection cue
Manual configuration form:
- Add Auth Header step (URL → Protocol → Model → Auth Token → Auth Header)
and persist it to Llm.AuthHeader on confirm
- Reorder so Auth Header is always entered last
- Make Auth Token required; empty Enter stays on the field
- Show every field's label on every render, even when empty, matching
the custom-provider form style
Tests:
- Cover custom model input add / duplicate paths
- Cover manual form prefill of Llm.AuthHeader
- Cover that deleting a non-active model keeps the active model intact
* Improve provider TUI validation, persistence, and code clarity.
Address code review feedback: align custom Auth Header validation with manual mode; fix savedInSession after model deletion; refactor applyEditCustomProviderSave to return error; remove dead applyModelDeletions/deletedModels; document ExtraBody shallow-copy limit. Also fix manual/custom form UX (token skip on edit, k key input, formError scoping, switch indentation).
* Fix provider/model TUI list ordering and add test coverage.
Address review and UX feedback: remove model list sorting in provider and config model TUIs; preserve Models list order when selecting active model (ensureModelInList); add test for duplicate rename on custom provider edit. Includes prior review fixes for savedInSession, applyEditCustomProviderSave error return, and dead code removal.
* Normalize AuthHeader at apply layer and simplify UseAnthropic assignment.
Call NormalizeAuthHeader in applyManualConfig and applyCustomProviderConfig before save; simplify UseAnthropic assignment in manual config; add unit tests.
* Address review: lowercase error strings and newProviderTUI signature.
Use lowercase "failed to save" errors; replace variadic configPath with string and remove configPathFromArgs; pass "" in tests when no path; gofmt provider_tui.go.
* feat: add tool_calls field to JSON output for tool usage statistics
Track per-tool invocation counts in llmloop.Runner and expose them
through the ResultProvider interface so both review and scan modes
report tool call statistics in --format json output.
* fix: correct tool_calls counting and ensure stable JSON schema
Move recordToolCall after lookupTool nil check so only actually-executed
tool calls are counted. Always emit tool_calls field in JSON output for
a consistent schema, initializing by_tool to empty map when nil.
* fix: remove omitempty from tool_calls to ensure stable JSON schema
Drop omitempty from the tool_calls struct tag and initialize ToolCalls
in outputJSONNoFiles so the field is always present in JSON output
regardless of execution path.
* feat: add ocr scan for full-file code review
Introduce a new top-level subcommand `ocr scan` (alias `s`) that reviews
whole files instead of git diffs. Use cases include reviewing unfamiliar
codebases, pre-migration audits, and ad-hoc per-directory reviews.
Architecture splits scan and diff review at the package level so the two
pipelines can evolve independently:
- internal/scan/ new package: file enumeration via `git ls-files`,
full-scan agent, FULL_SCAN_TASK rendering, preview
- internal/llmloop/ new package: shared LLM tool-use loop, three-zone
memory compression, CommentWorkerPool, AgentWarning.
Both internal/agent and internal/scan delegate to
llmloop.Runner; agent and scan never import each other
- internal/agent/ slimmed: LLM loop / compression / token aggregation
moved to llmloop; review-only orchestration remains
- internal/model/ new ScanItem (full-file payload) + Preview /
PreviewEntry / ExcludeReason shared by both modes
- internal/diff/ new gitignore.go exporting helpers reused by scan
- cmd/opencodereview/ new scan_cmd.go; shared.go consolidates startup
(loadCommonContext / loadLLMRuntime), output
(emitRunResult, ResultProvider) and stdout silencing
(quietHandle); review_cmd.go follows the same shape
Template additions:
- FULL_SCAN_TASK: dedicated prompt with Tool-call discipline guidance to
reduce gratuitous tool calls per file
- FULL_SCAN_MAX_TOOL_REQUEST_TIMES (default 60): scan-only per-file budget,
raised over diff's 30 to fit multi-finding files; --max-tools still
composes (only raise, never lower)
In scan mode, file_read_diff is filtered out of MainToolDefs since it has
no useful semantics without a diff.
Tests cover provider enumeration (with temp git repo), template rendering,
filter passes, dependency budget, flag validation, and excludeToolDef.
* feat(scan): v2 — exclude / non-git / split template / plan / batch / dedup / project-summary
Address design-review feedback by evolving `ocr scan` along seven axes
while keeping `ocr review` behavior unchanged:
1. File size cap is now configurable (ScanTemplate.MaxFileSizeBytes,
default 2 MiB; previously a hard-coded 5 MiB). The cap exists only to
bound memory reading; the real review-feasibility gate is the per-file
token budget downstream.
2. Drop the `--all` flag. Bare `ocr scan` now scans the whole repo;
`--path` narrows. Less ceremony, fewer redundant flags.
3. New `--exclude` flag on both review and scan. Comma-separated
gitignore-style patterns; merged with rule.json's exclude layer via
the new shared.applyCLIExcludes helper.
4. Scan supports non-git directories. internal/scan.Provider chooses
between `git ls-files` (full .gitignore semantics) and a
filepath.WalkDir fallback (root .gitignore + ExcludedDirs blocklist)
per isGitRepo probe. loadCommonContext takes a requireGit bool; review
keeps the hard requirement, scan relaxes it.
5. Scan configuration lives in its own file. internal/config/template:
- new ScanTemplate type with LoadScanDefault/ApplyLanguage/Validate
- new embedded scan_template.json
- Template loses the FULL_SCAN_* fields (review template unaffected)
scan.Agent.Args.Template now holds a ScanTemplate; toLoopTemplate
adapts it for llmloop.Runner.
6. New scan phases — each nil-able in the template and toggleable via a
CLI flag, so users can revert to v1 behavior trivially:
* PLAN_TASK (--no-plan): per-file pre-pass that outputs a JSON
summary + checkpoints, embedded into MAIN_TASK as {{plan_guidance}}.
formatPlanGuidance renders to markdown; malformed JSON falls back
to raw text. PLAN_TASK failure never blocks the main loop.
* BATCH_STRATEGY (--batch): files are grouped before dispatch.
"none" preserves v1, "by-language" (default) groups by extension,
"by-directory" groups by first-level subdir. BatchSize caps natural
groups so a single language with 500 files doesn't form one giant
batch. Batches are processed sequentially; files within a batch
remain concurrent up to MaxConcurrency.
* DEDUP_TASK (--no-dedup): per-batch postprocess that asks the LLM
to cluster near-duplicate comments. Output is a `groups` JSON;
every input id must appear exactly once or the result is rejected
and originals are kept (safety: never silently lose comments).
CommentCollector grows Snapshot/Since/ReplaceSince for this.
* PROJECT_SUMMARY_TASK (--no-summary): once-per-run cross-file
summary appended to text output and surfaced as `project_summary`
in JSON output. ResultProvider grows ProjectSummary(); agent.Agent
returns "" (review mode has no project summary).
All four new LLM steps record token usage via runner.RecordUsage so
aggregate counters stay accurate.
7. Tests cover the new pure code paths:
- batch_test.go: 3 strategies, BatchSize cap, language-key edge cases
- dedup_test.go: groups parser, malformed shapes, fence stripping,
payload field selection
- agent_test.go: formatPlanGuidance variants, buildSummaryCommentsList
truncation, maybeRunPlan skip paths
- provider_test.go: non-git directory walker fallback
- template_test.go: ScanTemplate loads / ApplyLanguage / review
template no longer contains scan fields
The seven phases can be reverted independently by toggling flags or
clearing the corresponding optional template fields; nothing forces the
new behavior on existing review users.
* fix(scan): three real bugs surfaced by SCAN_PLAN_TASK self-review
A v2 end-to-end test (ocr scan --path internal/scan/preview.go) had the
PLAN_TASK phase flag three concrete bugs in the scan package itself.
This commit fixes them and adds regression tests.
1. Preview() mutated a.items as a side-effect.
Both Preview and Run wrote to a.items. Calling Preview before Run
silently primed Run with the preview's enumeration instead of
triggering a fresh listFiles. Preview is documented as a read-only
dry-run; uphold that. Local variable now; a.items stays nil after
Preview returns.
2. Preview.result.Entries was nil when there were no items.
With no items at all the loop never ran, so Entries remained nil and
JSON marshalling produced "files":null. Pre-allocate to a non-nil
empty slice so the JSON contract stays "files":[] regardless.
3. Provider.Enumerate and listFilesViaWalk never checked ctx.Done().
On a large repo a cancelled context would still complete the full
walk before the caller saw an error (every iteration costs a stat or
ReadFile syscall). Add the check at the top of each iteration in
both the git-ls-files path and the walker fallback path; the walker
returns ctx.Err() so filepath.WalkDir propagates the cancellation.
Three new regression tests pin the contracts:
- TestPreview_DoesNotMutateAgentItems
- TestPreview_EmptyResultEntriesIsNonNilSlice
- TestProvider_Enumerate_RespectsContextCancellation
* feat(scan): cost estimate + token budget cap; fix file_find on non-git dirs
Two cost-control features and one robustness fix, all surfaced by running
the scanner against a real ~870K-token repository.
Cost estimate (internal/scan/estimate.go):
- Before dispatch, Run prints an order-of-magnitude projection of token
usage (input/output/total), derived from per-file content size × an
assumed round count, plus the optional plan/dedup/summary phases.
- Deliberately reports tokens only, not dollars — pricing varies per
provider/model and a precise figure would mislead. Actual usage is still
reported from the API after the run.
Token budget cap (--max-tokens-budget / ScanTemplate.MaxTokensBudget):
- Caps total token usage for one scan. The gate is checked per file inside
dispatchBatch, right before acquiring a concurrency slot: if tokens
already spent plus a look-ahead estimate of the next file would exceed
the budget, that file and all remaining files are skipped and a
token_budget_reached warning is recorded.
- An earlier batch-level gate was too coarse: with the default by-language
batching, a Go-heavy repo puts most files in one batch, so the gate only
fired between batches and overran the budget ~2.4×. The per-file gate
bounds overrun to roughly one in-flight file per worker (~1.3× at
concurrency=1 in testing).
- 0 = unlimited (unchanged default behavior).
Phase-gate helpers (planEnabled/dedupEnabled/summaryEnabled) consolidate
the "template defines it AND --no-* flag not set" checks so the cost
estimate and the dispatch path agree on which phases will actually run.
file_find non-git fallback (internal/tool/file_find.go):
- `git ls-files` exits 128 in a non-git directory, which spammed failures
when scanning plain directories (scan already supports non-git repos via
the provider's walker, but the file_find tool did not). Now falls back
to filepath.WalkDir honoring the root .gitignore and the default
excluded-dir blocklist when git fails and no specific ref is requested.
Tests:
- estimate_test.go: humanTokens formatting, per-file vs aggregate estimate
consistency, phase scaling, phase-gate tri-state.
- budget_test.go: fake LLM client drives the gate deterministically —
verifies dispatch stops before exceeding budget and that 0 = unlimited.
- file_find_test.go: non-git directory fallback finds files, honors
.gitignore / blocklist, and returns the not-found sentinel correctly.
* docs(readme): document ocr scan subcommand and flags
ocr scan existed but was undiscoverable from the README. Add it to the
intro blurb, Quick Start, the Commands table, Examples, and a dedicated
flags table (path / exclude / preview / max-tokens-budget / no-plan /
no-dedup / no-summary / batch / format / concurrency / rule / repo).
Note non-git support and the pre-run cost estimate. Also backfill the
--exclude flag in the ocr review flags table (added during the v1.3 merge
but never documented).
Flag names and defaults verified against `ocr scan -h`.
* fix(scan): code_search works in non-git directories via git grep --no-index
code_search relied on `git grep`, which exits 128 in a non-git directory —
so `ocr scan` on a plain directory (already supported by file enumeration and
file_find) silently returned errors instead of search results. Detect that
failure and retry with `git grep --no-index --exclude-standard`, which searches
the working tree directly while still honoring .gitignore. Reuses all existing
grep flag/parsing logic; ref-based search still requires a real repo.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(scan): preserve context on compression failure; fix NUL parsing in gitLs
Address three real bugs from the PR #93 automated review that regressed when
compression moved into internal/llmloop:
- Sync compression failure / empty summary now return the original messages
instead of truncating to the frozen zone, which discarded the whole
per-file conversation context.
- Async compression now abandons the job on error instead of applying a
truncated snapshot, and re-applies messages appended while it ran
(snapshotLen), so concurrent tool results are no longer lost.
- scan Provider.gitLs uses cmd.Output() instead of CombinedOutput() so
stderr can't corrupt the NUL-delimited (-z) filename parsing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add ability to delete custom providers from configuration
Implements GitHub issue #136.
CLI: add 'ocr config unset custom_providers.<name>' command to delete
a custom provider from config. If the deleted provider is the active
one, clears 'provider' and 'model' fields and prompts the user.
TUI: press 'd' on Custom tab to delete a provider with y/n confirmation.
Shows warning when deleting the active provider. Deletions are persisted
even if the user cancels provider selection afterward.
- Add runConfigUnset() with key validation and active-provider handling
- Add 'unset' case to parseConfigArgs() and printConfigUsage()
- Add delete confirmation state machine to providerTUIModel
- Add applyProviderDeletions() helper in provider_cmd.go
- Add 10 new tests covering CLI parsing, deletion logic, and TUI flows
- Update README with unset command documentation
* fix: address PR review feedback
- Add defensive bounds check for deleteTargetIdx before deletion
- Use explicit slice copy to avoid retaining references (memory leak)
- Update subCmd comment to reflect 'set' and 'unset' values
* refactor: extract shared deleteCustomProvider and improve test coverage
Address PR review feedback from lizhengfeng101:
- Extract deleteCustomProvider() as a pure function shared by both
runConfigUnset (CLI) and applyProviderDeletions (TUI)
- Extract unsetCustomProvider() accepting configPath for testability
- Add existence check in applyProviderDeletions (skip non-existent providers)
- Rewrite 3 tests to call actual functions instead of inlining logic
- Remove unused strings import from config_cmd_test.go
* style: use [ocr] WARNING prefix for active provider deletion messages
Align with project convention (output.go, flags.go): warnings use
'[ocr] WARNING' prefix and write to stderr instead of stdout.
* fix: address second round of PR review feedback
- Fix test state pollution in TestUnsetInvalidKey: use t.Run sub-tests
with independent config files per case (#7)
- Log warning instead of silently swallowing errors in
applyProviderDeletions (#9)
- Add comment explaining existingCfg snapshot assumption in
viewCustomTab (#10)
- Simplify runConfigUnset error message to single line for consistency
with project style (#11)
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.
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
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.
Previously --max-tools only took effect when greater than the template
default (30), making it impossible to reduce iterations for large diffs.
Now any non-zero value overrides the default, clamped to a floor of 10
with a stderr warning when the input is below the minimum.
Export NormalizeAuthHeader from the llm package and remove the duplicate
normalizeConfigAuthHeader in config_cmd.go. Invalid auth_header values
now return an error at configuration time instead of being silently
accepted and causing opaque 401s at runtime.
Subtask errors are already printed in real-time when they occur in agent.go.
The final outputTextWithWarnings was printing them again after comments were displayed.
Introduce gitcmd.Runner with channel-based semaphore to cap concurrent
git subprocesses (default 16, configurable via --max-git-procs). Route
all tool-layer and diff-layer git calls through the shared runner.
Also fix diff.Provider.runGit lacking context.Context — now the full
chain (GetDiff → MergeBase → ParseDiffText → finalizeDiff) propagates
the caller's context for proper cancellation and timeout support.
Registry was a plain map alias and DiffMap a shared map[string]string,
both relying on implicit write-before-read ordering with no compile-time
safety. Refactor Registry into an encapsulated struct with Freeze() that
panics on post-freeze writes, and wrap DiffMap as an immutable value type
with defensive copy on construction. Move DiffMap injection to before
filterDiffs to preserve the original behavior of exposing all file diffs.
Add cache_control ephemeral breakpoints on system prompt and tool
definitions to activate Anthropic prompt caching for multi-turn
agent loops. Fix token double-counting by removing the redundant
totalTokensUsed accumulator and computing it from sub-items. Surface
cache read/write statistics in both text and JSON summary output.
When using --audience agent --format json, the text summary line was
printed before the JSON body, causing parse failures for integrations.
Move summary data into the JSON "summary" field and skip PrintTraceSummary
in JSON mode.
Unify the config folder name to `.opencodereview` across all runtime paths,
tests, docs, and i18n strings. Also make defaultConfigPath() return an error
instead of silently falling back to a current-directory file when $HOME is
unresolvable.
Allow users to configure include/exclude glob patterns in
.open-code-review/rule.json (global or project-level) to control
which files are reviewed. Exclude has highest priority, include
penetrates default path exclusions but not the extension allowlist.
Only one layer takes effect following --rule > project > global priority.
Consolidate review rules into a composedResolver that supports four layers
(--rule flag > project .open-code-review/rule.json > global ~/rule.json >
embedded system default), each with first-match-wins fall-through semantics.
When all subtask LLM calls fail (e.g. invalid API key), dispatchSubtasks
now returns an error instead of empty comments with nil error. Partial
failures are recorded as subtask_error warnings so output functions can
distinguish "no issues found" from "review failed".
