* feat(seahorse): implement short-term memory engine of seahorse
Add pkg/seahorse/ module implementing a SQLite-backed DAG-based summary
hierarchy for context management, ported from lossless-claw's LCM design:
- types.go + short_constants.go: core types (Message, Summary, Conversation,
ContextItem) and configuration constants (fanout, token targets, thresholds)
- migration.go: idempotent DB schema with FTS5 trigram tokenizer for CJK
- store.go: full SQLite CRUD (conversations, messages, summaries DAG,
context_items with ordinal gap numbering, FTS5 search)
- short_engine.go: Engine lifecycle (NewEngine, Ingest, Assemble, Compact),
session pattern filtering (ignore/stateless glob→regex compilation),
per-session mutex via sync.Map
- short_assembler.go: budget-aware context assembly with fresh tail protection
(32 messages), oldest-first eviction, summary XML formatting, RebuildContextItems
- short_compaction.go: leaf compaction (messages→summary) and condensed
compaction (summaries→higher-level summary), 3-level LLM escalation,
CompactUntilUnder for emergency overflow
- short_retrieval.go: lookupByID, FTS5/LIKE search, recursive expand with
token cap
- context_seahorse.go: agent.ContextManager adapter, registered as "seahorse",
provider↔seahorse message type conversion (ToolCalls, tool_result)
* fix(seahorse): correct 3 adapter bugs in context management
- TokenCount: use full message (Content+ToolCalls+Media) instead of Content-only
- Empty Content: rebuild Content from tool_result Parts when stored empty
- Duplicate summaries: summaries only in Summary field, not in History messages
- Grep: fix SearchResult.Snippet→Content for summaries
- Schema: fix FTS5 SQL uses VIRTUAL TABLE not TEMP TABLE
- TestFTS5SQLConstants: verify FTS5 SQL syntax correctness
- Test: fix flaky TestCompactLeaf
* fix(agent): ingest steering messages into seahorse SQLite
Steering messages were only persisted to session JSONL but not ingested
into seahorse SQLite, causing them to be missing from context assembly.
Added `ts.ingestMessage(turnCtx, al, pm)` call in the steering message
injection block alongside the existing JSONL persistence.
Test: TestSeahorseSteeringMessageIngested verifies steering messages
appear in seahorse SQLite DB after being processed.
* fix(seahorse): address 3 blocking bugs from code review
- Fix resequenceContextItemsTx scan error handling (store.go:850)
Changed `return err` to `return scanErr` to properly propagate scan errors
instead of returning nil (which silently corrupts data)
- Fix sql.NullString for INTEGER column (store.go:847)
Changed `mid` from sql.NullString to sql.NullInt64 since message_id
is INTEGER in schema. Removed unnecessary strconv.ParseInt call.
- Fix compactCondensed fallback deleting non-candidate items
Added ReplaceContextItemsWithSummary method for per-item deletion
when candidates are not contiguous in ordinal space.
Optimized to use range deletion when candidates are consecutive.
* fix(seahorse): pass Budget to Compact for correct condensed threshold
Issue #4 from PR review: When Budget was not passed to seahorse.Compact,
it defaulted to `tokensBefore * 0.75`, making `tokensBefore > budget`
always true and causing condensed compaction to trigger unnecessarily.
Changes:
- context_seahorse.go: Forward Budget from CompactRequest to CompactInput
- loop.go: Pass Budget (ContextWindow) in all 3 Compact calls
- Add test verifying condensed is skipped when tokens < threshold
- Fix lint issues in store.go and store_test.go
* fix(seahorse): add mutex for assembler lazy initialization
Issue #5 from PR review: The check-then-create pattern for e.assembler
was a data race when multiple goroutines called Assemble() concurrently:
if e.assembler == nil {
e.assembler = &Assembler{...}
}
Changes:
- Add assemblerMu sync.Mutex to Engine struct
- Add initAssemblerOnce() using double-checked locking (same pattern as initCompactionOnce)
- Add TestAssemblerLazyInitRace to verify thread-safety
* fix(seahorse): handle non-consecutive depths in selectShallowestCondensationCandidate
Issue #8 from PR review: the loop iterated depth 0, 1, 2... assuming
consecutive keys, but break when key was missing caused deeper depths
to never be checked.
Fix: collect all existing depth keys, sort, then iterate in order.
* fix(seahorse): wrap DeleteMessagesAfterID and appendContextItems in transactions
- DeleteMessagesAfterID: wrap all DELETE operations in a transaction for
atomicity, remove redundant manual FTS delete (handled by trigger)
- appendContextItems: use transaction to fix read-then-write race condition
- Add GetMaxOrdinalTx and resolveItemTokenCountTx for transaction-scoped queries
- Remove unused resolveItemTokenCount function
Fixes PR review issues 6 and 7.
* fix(seahorse): derive readable content from Parts and cap CompactUntilUnder iterations
- Derive readable content from MessageParts in AddMessageWithParts so
FTS5 indexing and summary formatting can access tool call information
- formatMessagesForSummary and truncateSummary now fall back to Parts
when Content is empty, fixing blank summaries for Part-based messages
- Add MaxCompactIterations (20) to prevent CompactUntilUnder infinite
loops; exceeded iterations are logged as warnings
* feat(mcp): store oversized text results as artifacts
* feat(mcp): fix doc
* fix(mcp): preserve raw MCP payload in text artifacts
* fix(mcp): avoid leaking large text when artifact persistence fails
* chore(mcp): clarify inline text limit and cover artifact edge cases
* feat: add VK channel support
- Add VK channel implementation using vksdk
- Support text messages and media attachments
- Implement Long Poll API for real-time messaging
- Add group chat support with trigger prefixes
- Add user whitelist (allow_from) configuration
- Add VK channel documentation
Files:
- pkg/channels/vk/: VK channel implementation
- pkg/config/config.go: Add VKConfig structure
- pkg/channels/manager.go: Register VK channel
- pkg/gateway/gateway.go: Import VK channel package
- docs/channels/vk/: Usage documentation
* test: add unit tests for VK channel
- Test channel initialization with various configurations
- Test allow_from whitelist functionality
- Test group trigger configuration
- Test max message length (4000 chars)
- Test message splitting logic
- Test attachment processing
All tests passing ✓
* fix: resolve linting issues in VK channel
- Format VKConfig struct tags to comply with golines
- Remove unused mu sync.Mutex field
- Remove unused stripPrefix method
All tests passing ✓
* style: format VKConfig with golines
- Align struct tags to match project style
- Match formatting with other channel configs (Telegram, etc.)
- Fix golines linting error
* style: fix struct tag formatting in config.go
* docs: update VK channel docs to use secure token storage
* feat(vk): add voice capabilities support
- Implement VoiceCapabilities() method for VK channel
- Add audio_message attachment handling in processAttachments
- Add comprehensive tests for voice capabilities
- Support both ASR (speech-to-text) and TTS (text-to-speech)
* docs: add VK channel to documentation and update voice support
- Add VK channel to README.md and README.zh.md channel lists
- Update VK channel documentation with voice message support
- Document ASR and TTS capabilities for VK channel
- Add voice transcription configuration reference
* refactor(web): load channel configs without exposing secret values
- add a dedicated channel config API that returns sanitized config plus
configured secret metadata
- update channel config pages and forms to use secret presence for
placeholders, validation, reset, and save behavior
- refresh the channel settings layout and clean up related i18n copy
- add backend tests for the new channel config endpoint
* fix(config): restore missing strings import
* feat(provider): add Venice AI support and update related documentation
* revert(asr): restore asr files to previous commit
* feat(config): add Venice API base URL and local LM Studio configuration
* fix(config): update Venice API base URL to correct endpoint
* feat(updater): add web self-update endpoint and updater package
* feat(selfupgrade): when url empty, using GetTestReleaseAPIURL for test .
* feat(selfupgrade): only GetTestReleaseAPIURL .
* feat(upgrade): cli $0 update work well!
* fix(ci): fix ci err
* fix(test): fix ci test
* fix(ci): fix ci lint fmt err
* test(updater): add test for updater
* fix(ci): fix ci lint var copy err
* fix(ci): retry ci
* updater: require checksum verification, prefer API digest, verify SHA256, fix zip extraction, update tests
* fix(lint): lint fixed
* fix(lint): lint fixed2
* updater: stream download and verify sha256; add http client timeout and progress
Avoid double-download by streaming asset into temp file while computing SHA256 and verifying against checksum; replace http.Get with shared httpClient (2m timeout) to prevent hangs; add simple stderr progress display; remove unused helpers.
* feat: add load_image tool for local file vision
* fix: address load_image PR review feedback
- Exclude load_image from sub-agent tools via Unregister after Clone,
since RunToolLoop does not call resolveMediaRefs
- Add ToolRegistry.Unregister() method
- Fix scope collision: use channel:chatID instead of filename
- Add channel/chatID context resolution matching send_file pattern
- Add comment explaining iteration > 1 guard on resolveMediaRefs
- Remove emoji from ForUser for consistency with send_file
- Add load_image_test.go
* feat: enable load_image for subagents via MediaResolver in RunToolLoop
Instead of removing load_image from sub-agent tools (28f69e71), inject a
MediaResolver into the legacy RunToolLoop fallback path so media:// refs
are resolved to base64 before each LLM call — matching the main agent
loop behavior.
- Add MediaResolver field to ToolLoopConfig and call it on iteration > 1
- Add SubagentManager.SetMediaResolver() and wire it through runTask
- Remove ToolRegistry.Unregister() (no longer needed)
- Restore load_image in sub-agent tool set (revert Clone+Unregister)
- Add TestSubagentManager_SetMediaResolver_StoresResolver
* refactor(load_image): remove prompt parameter from tool schema
* test(tools): add success-path test for LoadImageTool
Add TestLoadImage_SuccessPath that creates a real PNG file with valid
magic bytes, calls Execute with WithToolContext, and verifies:
- result.IsError == false
- ToolResult.Media contains a media:// ref
- ToolResult.ForLLM contains the [image: marker
- media ref is resolvable in the store
Add explanatory comment in loop.go for why Media and ArtifactTags
coexist on non-ResponseHandled tool results (e.g. load_image).
* fix: preallocate slice in tests and add ResponseHandled guard in toolloop
Fix prealloc linter failure in load_image_test.go.
Prevent double-resolving media by checking ResponseHandled in toolloop.go.
* Register TTS tool if provider is available
---------
Co-authored-by: Reusu <admin@yumao.name>
Co-authored-by: 美電球 <hoshina@evaz.org>
Addresses reviewer concerns regarding silent message loss by narrowing the
error swallowing logic in EditMessage:
- Excludes context.DeadlineExceeded and context.Canceled from being swallowed,
ensuring local timeouts before transmission still trigger a fallback send.
- Adds an explicit check for the 'message is not modified' error to safely
identify edits that have already landed on Telegram's servers.
- Narrowly targets confirmed post-connect dropouts (e.g., connection reset)
instead of broad network-ish string matching.
- Fixes the missing isPostConnectError definition and required errors import.
- centralize gateway log level resolution and normalization
- propagate debug flags to spawned launcher and gateway processes
- add a log level selector to the logs page
- cover the new behavior with backend and config tests
Treat SystemParts as an alternative representation of message Content
rather than an additive one. This prevents systematic overestimation
of system message tokens which could trigger premature context
pruning or summarization.
- Picks the maximum of Content vs. SystemParts to stay conservative.
- Adds a per-part overhead (20 chars) to account for JSON metadata.
- Streamlines the ReasoningContent counting logic.
Fixes a deficiency where structured blocks for cache-aware adapters
caused overestimated budgets or hidden overflows.
* feat(provider): add lmstudio vendor and local no-key behavior
* refactor(provider): consolidate protocol metadata and local tests
* fix(provider): sync lmstudio probing and model normalization
* test(web): format lmstudio model status cases for golines
reItalic (_text_) ran after reLink converted [text](url) to <a href>,
injecting <i> tags into URLs containing underscores (e.g. Google Flights
URL-safe base64 in the tfs param). Telegram silently dropped such malformed
<a> tags, causing only 1 of 3 links to appear in messages.
Fix: extract markdown links into placeholders before any formatting runs,
restore them as <a href> last — same pattern used for code blocks.
* feat(channels): Channel.Send and MediaSender.SendMedia return delivered message IDs
Change Channel.Send signature from (ctx, msg) error to (ctx, msg) ([]string, error)
and MediaSender.SendMedia similarly, so callers can capture platform message IDs
for threading, reactions, and history annotation.
Adapters that return real IDs: Telegram (per-chunk MessageID), Discord (Message.ID),
Slack Send (ts), QQ (sentMsg.ID), Matrix (EventID). Slack SendMedia returns nil
because UploadFileV2 does not expose the posted message timestamp in its response.
All other adapters return nil IDs.
preSend and sendWithRetry in manager.go updated to propagate ([]string, bool).
README examples updated for both English and Chinese docs.
* style: apply golangci-lint fixes (golines)
* docs: fix Send migration guide — restore old error-only signature in before/after example
- Add `reaction` tool that reacts to a message (defaults to current inbound message via context)
- Extend `message` tool with optional `reply_to_message_id` parameter
- Introduce `WithToolInboundContext` to inject inbound message IDs into tool execution context
- Surface `MessageID` and `ReplyToMessageID` in `processOptions` for tool-surface consumption
Refs #2137
Liu Yuan