Add --reverse to git log in getCommitLog so commits are returned
oldest-first. Previously, git log defaulted to newest-first, causing
the loop in uploadCommits to overwrite state with the oldest commit.
The next run then queried git log <oldest>..HEAD, re-fetching all
already-uploaded commits and triggering infinite duplicate uploads.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Set User-Agent to csc/${version} in both auth() and authWithFallback()
Signed-off-by: 林凯90331 <90331@sangfor.com>
Co-authored-by: CoStrict <zgsm@sangfor.com.cn>
- Add UUID type import and type guard in force-snip command
- Add null/undefined checks in snipCompact, snipProjection, and sessionStorage
- Improve optional chaining in SnipTool for safer property access
- Prevent potential runtime errors from invalid UUID values
Co-Authored-By: claude-sonnet-4-6 <noreply@anthropic.com>
Change isEnabled() logic so raw dump is on by default unless
explicitly disabled via CSC_DISABLE_RAW_DUMP=1 or
COSTRICT_DISABLE_RAW_DUMP=1.
Signed-off-by: 林凯90331 <90331@sangfor.com>
Co-authored-by: CoStrict <zgsm@sangfor.com.cn>
Add session messages and repo info caching to avoid repeated JSONL
parsing and git subprocess spawning across tasks.
Share state across all tasks in a single batch to minimize file lock
contention and JSON parse overhead.
Convert queue operations from sync to async to prevent event loop
blocking in the main process.
Restore inline batch worker fallback when external spawn fails,
and increase worker interval from 30s to 2min to reduce CPU impact.
Add 5s debounce per session+messageID to prevent duplicate enqueues.
Improve binary mode spawn reliability by falling back to node runtime
when bun is not available.
Signed-off-by: 林凯90331 <90331@sangfor.com>
Co-authored-by: CoStrict <zgsm@sangfor.com.cn>
Implement the raw dump data reporting module for uploading conversation,
summary, and commit data to the CoStrict endpoint.
Key features:
- Local dump mode for debugging without network
- PID-based file locking to prevent state corruption with multiple csc instances
- 5-minute deduplication window for summary uploads
- Auto-detect sender (user/agent) and conditional user_input
- Repository fields (repo_addr, repo_branch, work_dir) in conversation
- Anonymous interface fallback when auth fails
- Filter commits to current user and limit fetch range
- Skip empty intermediate conversation turns
- Fix worker spawning for build and binary modes
- Remove git diff HEAD fallback to avoid unrelated working tree changes
Signed-off-by: 林凯90331 <90331@sangfor.com>
Co-authored-by: CoStrict <zgsm@sangfor.com.cn>
Invert the enablement logic so raw dump is disabled unless
CSC_DISABLE_RAW_DUMP or COSTRICT_DISABLE_RAW_DUMP is explicitly
set to 0 or false.
Signed-off-by: 林凯90331 <90331@sangfor.com>
Co-authored-by: CoStrict <zgsm@sangfor.com.cn>
- Add in-process isRunning flag to block reentrant runBatch (file lock
fails when pid === process.pid)
- Replace setInterval + double immediate trigger with self-scheduling
setTimeout that only fires after previous batch awaits
- Move clearQueue() to right after readQueue() so any unexpected
concurrent runBatch sees an empty queue and exits immediately
- Cache repoInfo and workingTreeDiff in processTask, pass into all three
upload functions to halve git invocations per task
- Add 30s AbortController timeout on postJson fetch so the worker no
longer hangs indefinitely on unresponsive networks
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Replace per-turn detached workers with a file-backed queue consumed by
a single long-running batch worker (30s interval, 0-10s jitter).
- queue.ts, batchWorker.ts: file queue with pid-based lock for worker
singleton; tasks deduped by sessionID:messageID before processing
- worker.ts: retry with backoff (5s, 10s) for 429 and network errors;
update commit state per upload so partial failures resume cleanly;
export auth, loadSessionMessages, getSessionDirectory and upload*
helpers for batchWorker reuse
- git.ts: cap commit log at 50 entries within last 7 days; pause 500ms
every 10 commits to spread load
- worker.ts: resolve session jsonl via ~/.claude/projects/{normalized}
with fallbacks, scanning for the file containing the target session
- logger.ts: file + stderr logger gated by CSC_RAW_DUMP_DEBUG, default
silent
- sessionDataUploader.ts: implement createSessionTurnUploader to pick
the last assistant message; query.ts fires uploadSessionTurn after
query_api_streaming_end (non-blocking)
Signed-off-by: 林凯90331 <90331@sangfor.com>
Co-authored-by: CoStrict <zgsm@sangfor.com.cn>
Introduce a framework-decoupled raw-dump module that uploads conversation, summary, and commits data to the CoStrict server in a non-blocking detached worker process.
- Add src/services/rawDump/ with index, types, state, spawn, git, worker, and README
- Implement reportTurn and reportSession entry points with in-memory dedup and env-based disable switch (CSC_DISABLE_RAW_DUMP / COSTRICT_DISABLE_RAW_DUMP)
- Replace sessionDataUploader stub with uploadSessionTurn that delegates to reportTurn
Signed-off-by: 林凯90331 <90331@sangfor.com>
Co-authored-by: CoStrict <zgsm@sangfor.com.cn>
When ANTHROPIC_BASE_URL points to a non-Anthropic endpoint (e.g.
DeepSeek), the JSON-formatted user_id containing {, ", : characters
fails validation against ^[a-zA-Z0-9_-]+$. Send only the hex device_id
for third-party providers.
Add ImageLimits type and plumb optional limits through the chain:
callMCPTool/callMCPToolWithUrlElicitationRetry -> processMCPResult ->
transformMCPResult -> transformResultContent -> maybeResizeAndDownsampleImageBuffer.
When provided, limits override the module-level defaults
(IMAGE_TARGET_RAW_SIZE, IMAGE_MAX_WIDTH, IMAGE_MAX_HEIGHT,
API_IMAGE_MAX_BASE64_SIZE) inside maybeResizeAndDownsampleImageBuffer.
When undefined, behavior is unchanged for current callers.
Add _meta preservation in the text-block case of transformResultContent
(only when the caller opts in via includeMeta=true). transformMCPResult
passes includeMeta=true on the tool-result path; the prompt-handler call
site keeps the default false, preserving prior behavior.
Add skipLargeOutput early-return in processMCPResult after the IDE check:
when the caller passes skipLargeOutput=true and the content has no images,
the function returns content directly without large-output handling.
Add unwrap-to-text in processMCPResult for the persisted-content path:
when the large-string format gate is enabled
(MCP_TRUNCATION_PROMPT_OVERRIDE env var, or
tengu_mcp_subagent_prompt Statsig gate), and the content is a single
bare text block (no annotations, no _meta), unwrap to raw text and
switch the format description to 'Plain text'. Default-off; gate-off
behavior is unchanged.
Verified structurally against the 2.1.128 binary: function signatures,
the IDE check, gate logic, _meta-unwrap pattern, and imageLimits
plumbing match this implementation.
The buildDiffableContent and buildPrevDiffableContent fields were closures
capturing full system prompt and tool schema arrays (~300KB each). With 10
map entries × 2 closures, this held ~6MB of GC-unreachable memory.
Since recordPromptState already serializes the same data for hashing,
pre-computing the diffable content string has negligible marginal cost.
