mirror of
https://github.com/tiennm99/goclaw.git
synced 2026-10-13 12:14:40 +00:00
dev
40
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Duc Nguyenandntduc
|
bb7712a9ff |
fix(collaboration): harden delegated task isolation (#1486)
* feat(collaboration): isolate delegated artifacts and child runs Isolate delegated inputs and outputs behind secure artifact exchange lifecycles. Scope Agent Link tasks by tenant and root agent, and enforce delegation spawn-tree boundaries. Add process-wide child-run admission and preserve logical media paths across native, MCP, and sandbox execution. * fix(collaboration): harden delegated task isolation Enforce tenant and root-agent task scope across migrations and stores. Add exactly-once async completion delivery, delegated sandbox boundaries, and confined artifact and media recovery across runtime surfaces. * fix(collaboration): recover interrupted async tasks * fix(collaboration): normalize persisted child-run status --------- Co-authored-by: ntduc <ntduc@cpp.ai.vn> |
||
|
ナムandCollective Developer
|
84fab59226 |
fix(memory): guide recency recall tool calls (#1412)
* fix(memory): guide recency recall tool calls * fix(tools): align memory and vault builtin visibility --------- Co-authored-by: Collective Developer <man@collective.dev> |
||
|
|
90e7035100 |
fix(mcp): tenant isolation, tool policy engine, and prompt preview fixes (#1333)
* fix(prompt): remove duplicate Team Members section from system prompt The TEAM.md context file already provides the Members section with better formatting. The system prompt section was redundant and inconsistently formatted. - Remove buildTeamMembersSection() call from system prompt building - Remove unused buildTeamMembersSection() function * fix(mcp): wire store to manager for prompt preview tool visibility MCP manager needs database access to query configured servers for tool visibility in prompt preview. - Add SetStore() method to MCP manager - Wire pgStores.MCP to manager after initialization - Add debug logging for MCP initialization flow * fix(systemprompt): hide Tooling section when agent has no tools The Tooling section header and boilerplate were displayed even when the agent had no tools available. Add early return in buildToolingSection() to skip the section entirely when toolNames is empty. This reduces prompt noise for agents with no tool access. * feat(mcp): cache tool descriptions for prompt preview visibility MCP tools now show descriptions in prompt preview without requiring a live server connection. - Add CacheToolDescriptions() method to MCPServerStore (PG + SQLite) - Cache tool descriptions in settings['tool_cache'] when server connects - Use cached descriptions in ListToolsForAgent (fallback: hints → cache → global) - Descriptions are auto-populated from live server manifest on connection - Admins can still override via tool_hints in server settings * test(mcp): add CacheToolDescriptions to MCPServerStore test fakes Commit 5ce410b6 added CacheToolDescriptions() to the MCPServerStore interface but missed updating test mock implementations, breaking go vet across internal/mcp, internal/agent, internal/http, and internal/channels/bitrix24. Add no-op implementations matching each fake's existing style. * fix(providers): enforce per-agent tool policy for Claude CLI provider The Claude CLI provider (stdio+MCP bridge) was not enforcing per-agent tool policy, unlike other providers where the policy-filtered tool list already drives the system prompt's Tooling section. Two gaps closed: 1. --disallowedTools was previously skipped entirely when no MCP config path was resolved, letting the CLI subprocess run with its full native toolset (Bash, Edit, Read, Write, Glob, Grep, WebFetch, WebSearch) regardless of agent policy. It's now unconditional and derived from the agent's actual allowed-tools list (state.Tool.AllowedTools), mapped to Claude CLI's native tool names. 2. The MCP bridge server executed any tool call without checking the calling agent's policy. It now resolves the agent's policy from context (via the existing HMAC-verified agent lookup) and denies calls to tools outside that agent's allowed set, logging security.mcp_bridge_denied on denial. Both gaps were closed using existing plumbing (PolicyEngine.WouldAllow, AgentData.ParseToolsConfig, the bridge context middleware) — no new cross-cutting mechanism was introduced. * feat(web): show MCP/tool schemas in system prompt preview dialog The prompt-preview API response includes a separate `tools` field (the actual JSON schemas sent to the LLM as the tools API parameter) alongside `prompt` (the system prompt text), but the web UI only rendered `prompt`, silently dropping the tools list. Add a collapsible Tools section to both the full-screen System Prompt dialog and the inline agent-detail preview, showing tool count, name, description, and expandable parameter schema per tool. i18n keys added to en/vi/zh locales. * fix(prompt): render pinned skills on bootstrap turns Pinned skills are documented (web UI copy) as "always inlined in the system prompt", but the entire Skills section was gated behind !cfg.IsBootstrap, so pinned skill XML never appeared on bootstrap turns (first message of a session) despite the promise. Separate pinned-skill rendering from bootstrap-suppressed guidance: - Bootstrap + pinned skills present: render pinned XML only, no search/manage guidance (which stays suppressed as before) - Non-bootstrap: unchanged behavior - Minimal/none modes: pinned skills always render regardless of bootstrap state Add regression tests covering all four prompt modes on bootstrap turns, plus a non-bootstrap guard confirming existing behavior is preserved. * fix(skills): resolve managed skills directory per-tenant, not master-only skills.Loader was wired at startup to scan a single fixed directory (the master tenant's managed-skills dir), making any skill belonging to a non-master tenant invisible to both pinned-skills prompt resolution and skill_search/use_skill, regardless of DB visibility settings. - Loader now resolves the calling tenant's managed-skills directory per-call via context (store.TenantIDFromContext), never enumerating other tenants' directories - Skill cache is now tenant-keyed to prevent slug collisions and cross-tenant cache leaks across tenants using the same skill slug - gateway_setup.go passes the root data dir instead of a pre-resolved master-tenant path Write-side tooling (skill_manage, publish_skill) was already correctly tenant-scoped per-operation — no changes needed there. Added TestLoader_ManagedSkills_TenantIsolation proving two tenants with same-slug/different-content skills never see each other's content, including after cache population from a different tenant's lookup. Known follow-up (not in this commit): skill_search's BM25 index is still a single process-global index shared across tenants, which is a related but separate cross-tenant search-result leak requiring its own scoped fix (per-tenant index maps + threading tenant context through ensureIndex/rebuildIndex). * fix(tools): scope skill_search BM25 index per-tenant SkillSearchTool held a single process-global BM25 index built once from whichever tenant's context first triggered ensureIndex, then reused for all subsequent Execute() calls regardless of caller — leaking one tenant's skill search results into another's, the search-path counterpart to the managed-directory bug fixed in 7b4668ad. - index/lastVersion are now keyed per-tenant (map[uuid.UUID]*tenantIndexState) - ensureIndex resolves the calling tenant from context and only builds/reads that tenant's index entry, never touching another tenant's cached state - Builtin/bundled skills remain visible in every tenant's index (Loader already merges those tiers correctly per 7b4668ad) Loader.Version() remains a single global counter — a version bump in one tenant causes unnecessary rebuilds in others but does not cause cross-tenant leakage, an acceptable tradeoff to avoid scope creep. Added TestSkillSearchTool_TenantIsolation proving two tenants with same-slug/different-content skills never see each other's search results, including after cache population from a different tenant. * fix(tools): fix group-spec expansion in tool policy engine PolicyEngine.registry was only ever set via SetRegistry(), which was never called in production (only in one test) — so pe.registry was permanently nil in production. Every group-expansion helper (applyProfile, intersectWithSpec, unionWithSpec, subtractSpec, expandSpec, matchDenySpec, filterByCapability) silently dropped any "group:*" spec entry instead of expanding it when registry was nil. Concretely: "group:mcp" (auto-injected into agentToolPolicy.AlsoAllow for any agent with MCP tools) never resolved to real tool names, so MCP tools connected successfully and appeared in prompt text (which reads the registry directly, bypassing PolicyEngine) but were never included in the actual ChatRequest.Tools payload sent to the LLM — confirmed live via mcp.agent.tools_loaded tools=6 immediately followed by mcp.filtered_tools mcp_defs_count=0 in the same request. This affects any agent relying on group-based grants, not just MCP. PolicyEngine is a shared/global singleton used concurrently across all agents (constructed once at gateway startup), so mutating a registry field per-call would be a data race. Fix instead threads the registry as an explicit parameter from FilterTools down through all internal group-expansion helpers, and adds IsDenied/WouldAllow registry parameters, removing the dead SetRegistry() mechanism entirely. Also fixes group expansion for the per-user-MCP-tools path: FilterTools is sometimes called with a userToolOverlay wrapping a *Registry rather than a *Registry directly; added Unwrap() to userToolOverlay so the new registry-resolution logic works for both cases. Added 4 tests proving group expansion works via the threaded parameter alone (no SetRegistry): plain registry allow, userToolOverlay allow, deny-side group expansion, and the WouldAllow bridge-server path. Blast radius note: this restores intended access for every agent configured with group:* specs (group:mcp, group:vault, group:goclaw, group:coding, etc.) that were silently inert before. Existing agent configs relying on group grants will gain the tool access they were nominally already configured for. * fix(mcp): cache tool descriptions from pool-connected servers too 5ce410b6 added tool-description caching (for prompt-preview visibility) only inside connectServer. connectViaPool — the separate connect path used when MCP connections go through the shared pool — never got the same caching hook, even though it shares the same underlying connectAndDiscover wire handshake. Confirmed live: cloudflare/docker connected via connectViaPool and received real descriptions over the wire, but prompt preview still showed blank descriptions because this path never wrote to the cache. Also removes the temporary mcp.connect.raw_tool debug log added earlier this session for diagnosing the same issue — no longer needed now that the root cause is fixed. * chore(skills): remove temporary pinned-skills diagnostic logging Confirmed live: pinned skills (caveman, infra-ansible-knowledge) now resolve correctly end-to-end for tenant-scoped agents. Debug logging added to trace the resolution chain is no longer needed. * fix(tools): deny always wins over AlsoAllow group grants AlsoAllow's unionWithSpec could reintroduce a tool explicitly listed in Deny, since it added tools back from allTools without re-checking deny specs. Previously masked because AlsoAllow's group-expansion was also broken (fixed in f7af95de this session) — group specs silently expanded to nothing, so this ordering bug never manifested. Now that group expansion works, an admin-denied tool that's also reachable via a group:* AlsoAllow entry (e.g. group:mcp) would silently reappear. Re-apply deny-spec subtraction as a final step after AlsoAllow union, for both global and per-agent policy, so deny always wins regardless of which allow mechanism tries to add a tool back. Added tests proving global and per-agent Deny correctly override an overlapping AlsoAllow group grant, while sibling non-denied tools in the same group remain allowed. * fix(mcp): enumerate cached tools instead of wildcard placeholder in prompt preview ListToolsForAgent (the prompt-preview path) collapsed any server with an empty ToolAllow (unrestricted grant — the common case) into a single "server__*" placeholder entry, even when tool_cache already had every real tool name and description from connect time (5ce410b6, 8ffd67b9). This meant agents with unrestricted MCP server access never saw individual tool names or descriptions in prompt preview, forcing trial-and-error tool usage. When ToolAllow is empty and tool_cache is populated, enumerate every cached tool (skipping any explicitly denied) and emit one MCPToolPreviewInfo per tool, matching the construction logic already used for the ToolAllow-non-empty case. Falls back to the single placeholder only when tool_cache is also empty (server never connected). The live (non-preview) conversation path, buildMCPToolDescs, does not have this bug — it resolves tool identity from the live connected registry, never from ToolAllow, so no placeholder shortcut exists there. Added tests covering both the cache-populated enumeration case and the no-cache placeholder fallback. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> * fix(prompt): filter alias re-injection and add MCP schemas to preview ToolDefs Prompt-preview's tools: schema array (PreviewResult.ToolDefs) had two bugs, both preview-only — confirmed live conversations already use correctly-filtered tool payloads via buildToolsPayload/PolicyEngine.FilterTools, unaffected by either bug: 1. Alias re-injection iterated ALL registry aliases globally with no check against the deny-filtered toolNames list, letting denied tools reappear via their alias name (e.g. a denied canonical tool still showing up as its Claude-Code-compat alias like Bash/Edit/Write/Read). Now skips any alias whose canonical tool isn't in the filtered set. 2. MCP tool descriptions (from the store-based, connection-free ListToolsForAgent path) only ever fed the prompt TEXT section, never got converted into ToolDefinition schema objects — so the tools: array never showed MCP tools at all, even when the MCP section of the prompt text correctly listed them. Now appends a ToolDefinition per MCP tool with name+description populated and a placeholder {"type":"object"} Parameters schema, documented as preview-only (real parameter schemas require a live MCP connection, only available during an actual conversation turn). Added tests proving denied-tool-alias exclusion and MCP tool inclusion in preview ToolDefs. * feat(skills): inline full content for pinned skills instead of pointer-only Web UI documented "Pinned skills are always inlined in the system prompt", but BuildPinnedSummary was just BuildSummary with an allowlist filter — same as the general searchable skill list: name/description(truncated)/location pointer only, requiring use_skill+read_file round trips to get actual content. No code path inlined real SKILL.md content for pinned skills specifically. BuildPinnedSummary now reads and inlines full SKILL.md content (frontmatter stripped) per pinned skill inside <skill_instructions> tags. Per-skill (10000 bytes) and total (30000 bytes) size caps fall back to the original pointer-only format with a note when a skill is too large to inline, so oversized skills degrade gracefully instead of blowing the prompt budget. Added tests: full-content inlining, size-cap fallback, and tenant isolation for the new inline path (mirroring the existing managed- skills tenant isolation test). * fix(mcp): real parameter schemas and full policy enforcement in prompt preview Three interconnected fixes to prompt preview, none affecting the live conversation path (which was already correct): 1. Real MCP parameter schemas instead of a useless empty placeholder. tool_cache previously stored only name+description; extended to also capture the real JSON Schema from the MCP server's tools/list response (CachedToolInfo{Description, Parameters}) at connect time, for both direct-connect and pool-connect paths. Preview now shows complete, real input schemas instead of {"type":"object"} with no properties — verified against actual wire data from a live cloudflare MCP server showing genuinely rich schemas (zone_id, type, name, content, ttl, proxied, all typed with descriptions and correct required arrays) that were previously being discarded. Backward-compatible: old-shape cache entries degrade gracefully to description-only rather than crashing, self-healing on next connect. 2. Global tool deny now enforced in preview. BuildPreviewPrompt previously hand-rolled a partial policy reimplementation (per-agent deny only, explicitly skipping the full PolicyEngine "because runtime state isn't available in preview") — but PolicyEngine.WouldAllow already handles this per-tool-name without needing channel context. A tool denied via the global config (not per-agent) would appear in preview despite being correctly denied in every real conversation. Preview now calls WouldAllow per candidate tool, with a graceful per-agent-deny-only fallback when no PolicyEngine is wired (e.g. in tests). 3. MCP tools now also subject to the same policy check — previously the MCP tool supplement (store-based, connection-free tool listing) added MCP tool names unconditionally, bypassing WouldAllow entirely, so a denied MCP tool could still appear in preview. Added tests for all three: real-schema presence, global-deny exclusion for both core and MCP tools, and backward-compat cache handling. * fix(prompt): remove redundant per-tool MCP enumeration from prompt text Now that MCP tool schemas in the tools: API parameter are real and complete (1290d4f1), the ## MCP Tools prompt-text section's per-tool "- mcp_x__y: description" enumeration is pure duplication with zero added value — the model already gets each tool's real schema (including description) via tools:. buildMCPToolsInlineSection now keeps only the behavioral instructions that aren't expressible via JSON schema and thus aren't duplicated: prefer-MCP-over-core-tools guidance, and the optional-parameter guidance (don't guess/fill optional fields). The per-tool name+ description enumeration loop is removed. Section still only appears when the agent has MCP tools (len(cfg.MCPToolDescs) > 0, unchanged gate). Updated tests to assert the enumeration is gone while the behavioral instructions remain; ToolDefs assertions are now the authoritative check for MCP tool allow/deny filtering behavior (prompt text no longer enumerates names at all). * test(agent): update TeamContextInjection test for removed Team Members section TestBuildSystemPrompt_TeamContextInjection asserted the presence of a 'Team Members' prompt-text section that was intentionally removed in 71d33180 (duplicate of the canonical TEAM.md-context-file Members section, which has better formatting). The test was never updated to match, causing it to fail on every run since. Moved the assertion from wantIn to wantNotIn for the 3 affected subtests -- BuildSystemPrompt correctly no longer renders team-member roster info directly; that info now comes exclusively from the TEAM.md context-file mechanism, outside this test's isolated scope. * fix(prompt): resolve real registry for WouldAllow calls in preview BuildPreviewPrompt's two WouldAllow calls hardcoded reg=nil, silently breaking group:* expansion (e.g. group:mcp) needed to resolve the AlsoAllow grant production actually uses to grant MCP tool access (resolver_helpers.go's agentToolPolicyWithMCP injects AlsoAllow: ["group:mcp"]). With reg=nil, WouldAllow could match literal tool names fine (the 18 core/static tools) but could never resolve group-based grants, so every MCP tool silently failed WouldAllow and was excluded from preview -- confirmed live via curl: 18 tools returned, zero mcp_* ones, for an agent with genuinely working MCP access in real conversations. Live conversations were never affected -- internal/mcp/bridge_server.go's WouldAllow call already correctly passes a real registry. Fix resolves a real *tools.Registry from deps.ToolLister via tools.ResolveConcreteRegistry (the same helper used at the live call site), passing it to both WouldAllow calls instead of nil. Falls back to nil gracefully for test mocks that don't implement the full ToolExecutor interface, preserving existing test behavior. Added a test proving an MCP tool granted via the exact production AlsoAllow: ["group:mcp"] pattern is now correctly included in preview ToolDefs, where the old reg=nil bug would have silently excluded it. * fix(prompt): use literal deny check for MCP tools in preview, not group expansion The MCP-tools policy gate added in 1290d4f1 called WouldAllow with a real registry (per 9b5fd2eb), which requires group:mcp expansion against that registry to grant access via the production AlsoAllow: ["group:mcp"] pattern. But MCP tools are only ever registered into ephemeral per-agent registry clones at live connection time (manager_connect.go) -- never into the shared/global registry preview uses. group:mcp always resolved empty in preview's connection-free context, so WouldAllow denied every MCP tool -- confirmed live via tool-name diff: live conversations correctly included all 6 MCP tools, preview included zero. MCP access-granting is already correctly handled by ListToolsForAgent's own per-server tool_allow/tool_deny grant logic (confirmed working correctly earlier this session). The preview gate only needs to catch the narrower case of a literally-denied tool name via global/per-agent policy config -- it never needed group expansion. Replaced WouldAllow with IsDenied(nil, name, agentPolicy), which forces a pure literal-name match with zero registry dependency, matching the existing usage pattern already established elsewhere in policy.go. This class of bug cannot recur: there's no registry-passing code path left in this check to silently reintroduce group-expansion dependence. Added a test proving MCP tool inclusion in preview is independent of group-expansion outcome (no AlsoAllow: group:mcp needed for a non-denied tool to appear). Also reverts the temporary loop.filtered_tool_names/ preview_prompt.filtered_tool_names diagnostic logging used to capture the live-vs-preview tool-name comparison that diagnosed this bug. * fix(http): preserve real MCP parameter schemas through HTTP preview adapter mcpPreviewAdapter.ListToolsForAgent (the HTTP-layer glue converting mcp.MCPToolPreviewInfo to agent.MCPToolPreviewInfo for BuildPreviewPrompt) only copied RegisteredName and Description, silently dropping Parameters -- a bug present since this adapter was introduced (2499d0be/7e250244), unrelated to today's other MCP preview fixes. This was masked until d5fc6344 fixed MCP tools being excluded from preview entirely (a separate bug) -- once MCP tools started appearing again, this pre-existing adapter gap became visible: tools showed up correctly, but always with the bare {"type":"object"} placeholder instead of their real cached schema (confirmed live: update_dns_record missing its 7 real properties). One-line fix: copy Parameters through in the adapter's struct literal. Added a regression test constructing a real *mcp.Manager with populated tool_cache, asserting the adapter's output preserves specific real schema properties (not just non-nil Parameters) -- verified this test fails without the fix and passes with it. --------- Co-authored-by: Bruno Clermont <bruno.clermont@gmail.com> Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com> |
||
|
SYNITYandDangTinh311
|
23a4b7407c |
fix(bitrix24): OpenLine greeting and MCP provisioning (#1284)
* fix(bitrix24): skip join greeting in open channels [B24:2794] * wip: rework bitrix24 mcp provisioning + skills prompt section (tam thoi, se lam lai) [B24:2794] --------- Co-authored-by: DangTinh311 <dangtinh31193@gmail.com> |
||
|
Duy /zuey/
|
23b18fa6cd |
fix(channels): rely on generated intermediate progress (#143)
* fix(channels): add reasoning delivery modes * fix(telegram): show tool status without placeholder * docs(plans): mark issue 67 behavior plan complete * feat(config): add behavior setting purpose tooltips * fix(channels): rely on generated intermediate progress |
||
|
Duy /zuey/
|
ef829c1ab4 |
fix(bitrix24): resolve PR 8-10 stack findings
Resolve the PR #8/#9/#10 stack on current dev, including Bitrix24 install callback hardening, migration renumbering, duplicate-domain fail-closed routing, UI textarea/mobile cleanup, and review hardening. |
||
|
viettranx
|
085b89bf72 |
feat(agent): inject TTS [[tts]] directive guidance when auto mode is "tagged"
- Add TTSAutoMode field to LoopConfig, Loop, SystemPromptConfig - Wire from config.Tts.Auto through resolver to system prompt - Inject "## Voice Response" section explaining [[tts]] usage - Update AGENTS.md: voice only when user explicitly requests |
||
|
|
8f56ddaa64 |
feat(v3): core architecture redesign — pipeline, memory, vault, evolution, providers, orchestration (#790)
* feat(v3): add core interface contracts and migration for v3 redesign
Foundation interfaces: TokenCounter, WorkspaceContext, DomainEventBus,
ProviderAdapter/Capabilities. Pipeline: Stage, RunState, MessageBuffer,
substates, Pipeline orchestrator. Memory: EpisodicStore, AutoInjector,
KG temporal extensions, consolidation workers. System integration:
PromptConfig, ToolCapability, Retriever. Orchestration: OrchestrationMode,
EvolutionMetrics/SuggestionStore. Migration 000037: episodic_summaries,
evolution tables, KG temporal columns. Schema version 36→37.
* refactor(plans): mark all v3 design phases complete with file references
* fix(v3): address code review findings on design contracts
- C1: add missing l0_abstract column to episodic_summaries migration
- C2: align EpisodicSummary ID/TenantID/AgentID to uuid.UUID
- H1: document tenant_id scoping requirement on EpisodicStore
- H2: add UNIQUE constraint on (agent_id, user_id, source_id) for dedup
- H4: clarify ProviderAdapter vs Provider relationship in doc
- M3: set state.ExitCode on BreakLoop/AbortRun in pipeline
- M6: store full PipelineConfig in Pipeline struct
- Edge: add WHERE embedding IS NOT NULL on HNSW index
* fix(v3): second-pass review fixes
- H1: use context.WithoutCancel for finalize + set ExitCode on ctx cancel
- H2: use utf8.RuneCountInString consistently in FallbackCounter
- H3: longest-prefix-match in ModelContextWindow (prevents wrong tokenizer)
- H4: return unsubscribe cleanup func from consolidation.Register
* feat(v3): implement DomainEventBus with worker pool, dedup, and retry
Worker pool processes events from buffered channel. SourceID-based dedup
prevents duplicate processing. Exponential backoff retry on handler error.
Panic recovery per handler. Graceful shutdown via Drain(). 8/8 tests pass
with race detector.
* feat(v3): implement ProviderAdapter for Anthropic, OpenAI, DashScope, Codex
Add CapabilitiesAware to all 6 providers. Create ProviderAdapter
implementations that delegate to existing buildRequestBody/parseResponse
for DRY. ClaudeCLI and ACP get capabilities only (subprocess transport).
DashScope wraps OpenAI adapter with StreamWithTools=false override.
* feat(v3): implement WorkspaceContext Resolver for 6 scenarios
Stateless resolver produces immutable WorkspaceContext at run start.
Handles personal/group/predefined/team-shared/team-isolated/delegation.
Wired into loop_context.go behind v3PipelineEnabled flag (additive,
v2 path unchanged). Includes delegation path boundary check,
master tenant bypass, and tenant slug path composition.
* feat(v3): implement tiktoken TokenCounter with BPE encoding + cache
Adds tiktoken-go for accurate cl100k_base/o200k_base token counting.
Per-message FNV-1a hash cache avoids re-encoding unchanged history.
Falls back to rune/3 heuristic for unknown models. NewTokenCounter
factory selects implementation at build time.
* feat(v3): promote 12 other_config JSONB fields to dedicated agent columns
Extract emoji, agent_description, thinking_level, max_tokens,
self_evolve, skill_evolve, skill_nudge_interval, reasoning_config,
workspace_sharing, chatgpt_oauth_routing, shell_deny_groups, and
kg_dedup_config from the catch-all other_config JSONB into proper
columns with DB-level types and defaults.
- Migration: PG (000037) + SQLite (schema v6→7) with backfill
- Go: AgentData struct + simplified Parse* methods
- Store: SELECT/INSERT/scan updated for both PG and SQLite
- Gateway: create/update handlers accept promoted fields
- HTTP: export/import with legacy backward compat
- Web UI: all 15 frontend files read/write from top level
* feat(v3): implement Knowledge Vault with unified search, wikilinks, and FS sync
Migration 000038 adds vault_documents (FTS+pgvector), vault_links, vault_versions
tables. VaultStore interface with PG implementation for document CRUD, hybrid
FTS+vector search, and bidirectional link management. All queries enforce
tenant_id isolation including JOIN-based scoping on link operations.
FS sync layer: SHA-256 content hashing, VaultInterceptor hooks into write_file/
read_file for auto-registration and lazy sync, fsnotify watcher with 500ms
debounce. Wikilink engine parses [[target]] syntax, resolves targets via
3-step strategy, and maintains vault_links on write.
VaultSearchService fans out queries across vault, episodic, and KG stores in
parallel with per-source score normalization and weighted merge. AutoInjector
and Retriever implementations for pipeline integration.
Three agent tools: vault_search (unified discovery), vault_link (explicit
linking), vault_backlinks (dependency tracing). Feature-flagged via
v3_vault_enabled agent setting.
* feat(v3): wire vault into gateway startup + add unit tests
Wire VaultStore embedding provider, VaultSearchService, VaultInterceptor
on read/write tools, and register vault_search/vault_link/vault_backlinks
tools in gateway_vault_wiring.go. All wiring gated by stores.Vault != nil.
Add 28 unit tests for ContentHash, ContentHashFile, and ExtractWikilinks
covering edge cases, unicode, display text, context windows, and offsets.
* feat(v3): implement stage-based pipeline loop with 8 pluggable stages
Decompose monolithic agent loop into internal/pipeline/ package:
- 6 stages: Context, Think, Prune+MemoryFlush, Tool, Observe+Checkpoint, Finalize
- Foundation types: Stage interface, RunState with 7 typed substates, MessageBuffer
- Pipeline orchestrator with setup/iteration/finalize 3-phase execution
- Callback-based PipelineDeps avoids circular import with agent package
- Feature-flagged via v3PipelineEnabled in Loop.Run()
- All 7 exit conditions preserved (no tools, max iter, truncation, loop kill,
read-only streak, tool budget, ctx cancel)
* feat(v3): wire pipeline callbacks to Loop methods + add 71 unit tests
Wire 15 of 17 PipelineDeps callbacks from Loop methods via closures:
- Context: LoadContextFiles, BuildMessages, EnrichMedia, InjectReminders
- Think: BuildFilteredTools, CallLLM (stream/sync)
- Prune: PruneMessages, CompactMessages
- Memory: RunMemoryFlush
- Finalize: SanitizeContent, FlushMessages, UpdateMetadata, BootstrapCleanup, MaybeSummarize
- Remaining: ExecuteToolCall, CheckReadOnly (deep loop.go integration)
Add comprehensive test suite (71 tests, all passing with -race):
- MessageBuffer: 10 tests (append, flush, replace, counts)
- Pipeline.Run: 14 tests (3-phase flow, exit conditions, ctx cancel)
- Stage tests: 47 tests (ThinkStage nudges/truncation, PruneStage budget,
ToolStage parallel/exit, ObserveStage content, CheckpointStage interval,
FinalizeStage cleanup)
* feat(v3): wire remaining 2 callbacks (ExecuteToolCall, CheckReadOnly)
Complete callback wiring — 17/17 PipelineDeps callbacks now active:
- ExecuteToolCall: resolves tool name, executes via registry, processes
result via existing processToolResult with loop detection bridge
- CheckReadOnly: delegates to checkReadOnlyStreak via bridge runState
- Bridge runState shares loop detection state between pipeline and agent
* fix(v3): eliminate data race in tool execution + capture injected messages
- Remove parallel tool execution path — serialize all tool calls to avoid
data races on shared bridgeRS (loop detector, media results, deliverables)
- Loop kill checked after each tool (mid-batch early exit)
- BuildFilteredTools: capture and append injected tool-awareness messages
- Rename test to reflect sequential execution
* feat(v3): wire ResolveWorkspace, safe parallel tools, ContextStage tests
- Wire ResolveWorkspace callback via workspace.NewResolver() with
ResolveParams from Loop fields (no longer a nil stub)
- Re-add safe parallel tool execution: split into ExecuteToolRaw
(parallel I/O) + ProcessToolResult (sequential state mutation)
with opaque rawData pass-through (no double execution)
- Add 12 unit tests for ContextStage (8) + MemoryFlushStage (3)
- Split tool callbacks to loop_pipeline_tool_callbacks.go (under 200 lines)
- Capture buildFilteredTools injected messages
* feat(v3): add episodic memory store + temporal KG columns
Phase 1 — Episodic Store:
- Migration 000039: episodic_summaries table with pgvector, FTS, L0 abstracts
- EpisodicStore PG impl: CRUD, hybrid FTS+vector search, ExistsBySourceID,
PruneExpired. Idempotent via source_id UNIQUE constraint.
Phase 2 — Temporal KG:
- Migration 000040: valid_from/valid_until on kg_entities + kg_relations,
partial indexes for current-facts queries, epoch→timestamptz backfill
- ListEntitiesTemporal: current-only, point-in-time, or include-expired modes
- SupersedeEntity: atomic expire-old + insert-new in single transaction
Schema version bumped to 40.
* fix(v3): review fixes for episodic store + temporal KG
- C1: Fix column name mismatch turn_count vs message_count in Go SQL
- C2: Remove redundant migration 000040 (000037 already adds temporal KG columns)
- H1: Use time.Time not int64 for TIMESTAMPTZ columns in SupersedeEntity
- H2: Add tenant_id scoping to Get/Delete for tenant isolation
- M2: Fix scanEntityTemporal to convert TIMESTAMPTZ→UnixMilli correctly
- L1: Remove unused uuid import from episodic_search.go
- Schema version corrected to 39 (only 000039 is new)
* feat(v3): implement consolidation pipeline with 3 event-driven workers
Event chain: session.completed → EpisodicWorker → episodic.created →
SemanticWorker → entity.upserted → DedupWorker
- EpisodicWorker: reuses compaction summary or calls LLM, generates L0
abstract (extractive), idempotent via source_id check
- SemanticWorker: extracts KG facts from episodic summary via existing
Extractor, sets temporal valid_from, publishes entity.upserted
- DedupWorker: runs DedupAfterExtraction on new entity IDs (terminal)
- L0 abstract: sentence-based extraction (~50 tokens), no LLM needed
- All workers registered via DomainEventBus.Subscribe()
* feat(v3): implement progressive loading with L0 auto-inject + unified search
- AutoInjector: searches episodic store, builds L0 prompt section (~200 tokens),
skips trivial messages via stopword filter
- L1Cache: in-memory LRU (500 entries, 1h TTL) for structured overviews
- UnifiedSearch: cross-tier search merging episodic + document results by score
- ContextStage integration: AutoInject callback appends memory section to system prompt
- MemorySection field added to ContextState for observability
* feat(v3): add memory_expand tool for L2 episodic retrieval
New tool: memory_expand(id) returns full episodic summary with metadata.
Complements memory_search L0/L1 results with deep L2 access.
Nil-safe: returns error message when episodic store not available.
Gateway wiring + memory_search depth param + kg_search temporal param
deferred to runtime integration phase.
* feat(v3): complete Phase 5 — tool extensions + gateway wiring
- memory_search: add depth param + episodic tier search merged with docs
- kg_search: add as_of temporal param, use ListEntitiesTemporal
- memory_expand: registered in gateway startup
- Gateway: Episodic field in Stores, PGEpisodicStore in factory,
embedding provider wired, tools connected to episodic store
* fix(v3): Phase 3 review fixes — tenant isolation + AutoInject args
- C1: Add tenant_id filter to ftsSearch, vectorSearch, List queries
(prevents cross-tenant episodic memory leaks)
- C2: Fix AutoInject callback signature — agent/tenant captured by
closure, only userMessage + userID passed explicitly
- H1: Add tenant_id to List query
* feat(v3): wire per-agent v3 flags from DB into dual-mode gate
Parse v3_pipeline_enabled, v3_memory_enabled, v3_retrieval_enabled from
agent other_config JSONB via ParseV3Flags(). Resolver now sets all flags
on LoopConfig so the existing gate in loop_run.go reads from DB.
- V3Flags struct + ParseV3Flags() + ValidateV3Flags() in store layer
- v3MemoryEnabled/v3RetrievalEnabled added to Loop, LoopConfig, PipelineConfig
- Auto-inject gated on V3RetrievalEnabled (was unconditional)
- Structured perf logging for v3 pipeline runs
- v3 flag validation on both WS agent.update and HTTP PUT endpoints
* feat(v3): wire AutoInjector into pipeline for L0 memory auto-inject
Create AutoInjector at gateway startup from episodic store, pass through
ResolverDeps → LoopConfig → Loop. Pipeline adapter builds AutoInject
callback capturing agent/tenant context via closure.
ContextStage already gates on V3RetrievalEnabled + AutoInject != nil.
* feat(v3): add tool metadata map + capability-based deny rules
Registry gains per-tool ToolMetadata map with RegisterWithMetadata()
and GetMetadata() (infers defaults from tool name when not explicit).
PolicyEngine gains DenyCapability() for RBAC integration — tools with
denied capabilities filtered at step 8 after existing 7-step pipeline.
* fix(v3): add RWMutex to PolicyEngine capability deny fields
DenyCapability() and SetRegistry() now guarded by sync.RWMutex.
FilterTools reads snapshot under RLock. Prevents data race when
capability rules are modified concurrently with tool filtering.
* feat(v3): implement delegate tool for inter-agent task delegation
New `delegate` tool wraps existing agent_links infrastructure
(CanDelegate, DelegateTargets). Supports async (fire-and-forget)
and sync (block with timeout) modes. Permission checked via
AgentLinkStore. Events emitted: delegate.sent/completed/failed.
DelegateRunFunc injected by gateway to avoid circular dependency.
* feat(v3): complete 3 deferred implementations
1. OrchestrationMode resolution: ResolveOrchestrationMode() checks
team membership → delegate links → spawn (priority order).
2. PG EvolutionMetricsStore: RecordMetric, QueryMetrics, aggregate
tool/retrieval metrics, TTL cleanup. All queries tenant-scoped.
3. BridgePromptBuilder: implements PromptBuilder interface by
delegating to existing BuildSystemPrompt(). Appends v3 memory
L0 section when enabled. Ready for template engine swap later.
* fix(v3): address code review findings on commits 5-6
- C1: CanDelegate now tenant-scoped (fail-closed on missing tenant)
- H1: Sync delegate timeout capped at 600s
- H2: Async goroutine gets 10min deadline (prevents leaks)
- H3: JSONB casts use COALESCE/NULLIF guards (handles missing fields)
- M1/M2: Remove dead code (formatVaultSection, memoryL0ToStrings)
* fix(teams): stop auto-creating agent_links for team members
Teams use agent_team_members table directly — agent_links caused
context confusion between team dispatch and delegation systems.
- Remove autoCreateTeamLinks() calls from team create + member add
- Remove link cleanup from member remove
- Remove dead autoCreateTeamLinks() function
- Append DELETE to migration 000039: clear team-created agent_links
* fix(v3): tenant isolation for all agent_links queries + PromptBuilder Instructions
- DelegateTargets, GetLinkBetween, SearchDelegateTargets,
SearchDelegateTargetsByEmbedding, DeleteTeamLinksForAgent all now
scoped by tenant_id (fail-closed on missing tenant)
- BridgePromptBuilder now maps Instructions/InstructionContent to
AGENTS.md context file (was silently dropped)
* feat(v3): wire orchestration mode + evolution metrics into agent loop
- Orchestration mode: resolver resolves mode from team/links, tool filter
hides delegate/team_tasks based on mode, prompt builder injects delegation
targets section
- Evolution metrics: non-blocking goroutine records tool execution metrics
(name, success, duration) via EvolutionMetricsStore in both v2 loop and
v3 pipeline paths (sequential + parallel)
- Fix review findings: tenant ID propagated via store.WithTenantID in
background goroutine, 5s timeout prevents goroutine leak
* feat(v3): implement suggestion engine with pluggable analysis rules
- PG EvolutionSuggestionStore: CRUD for agent_evolution_suggestions table
- SuggestionEngine: aggregates 7-day metrics, runs rules, deduplicates
pending suggestions per type before creating new ones
- 3 initial rules: LowRetrievalUsage (usage_rate<0.2), ToolFailure
(success_rate<0.1), RepeatedTool (>100 calls/week → suggest skill)
- EventSuggestionCreated event type added to eventbus
- Cron wiring deferred to gateway startup integration pass
* feat(v3): implement auto-adapt guardrails with apply/rollback
- AdaptationGuardrails: max delta per cycle, min data points, locked
params, rollback-on-drop percentage
- ApplySuggestion: applies threshold suggestions to agent other_config
JSONB, stores baseline for rollback
- RollbackSuggestion: restores baseline values from suggestion params
- EvaluateApplied: compares post-apply metrics to baseline, auto-rolls
back when quality drops beyond threshold
- Scope limited to retrieval params only (never security settings)
* feat(v3): wire evolution stores + daily/weekly cron for suggestions
- Add EvolutionMetrics + EvolutionSuggestions to Stores struct + PG factory
- Wire EvolutionMetricsStore into ResolverDeps (cmd/gateway_managed.go)
- Add gateway_evolution_cron.go: daily suggestion analysis + weekly
evaluation/rollback for applied suggestions
- Cron runs as background goroutine with 5-min timeout per cycle
* fix(v3): address code review findings on evolution engine
- C1: persist baseline parameters before marking suggestion as applied
(was building map but never saving — rollback would always fail)
- H1: add tenant_id isolation to UpdateSuggestionStatus, GetSuggestion,
and new UpdateSuggestionParameters method
* test(v3): add unit tests for orchestration, suggestions, guardrails, prompt
- orchestration_mode_test: orchModeDenyTools (4 modes) + ResolveOrchestrationMode
(4 scenarios with mock stores)
- suggestion_rules_test: LowRetrievalUsage, ToolFailure, RepeatedTool with
threshold boundary tests (at/below/above min data points)
- evolution_guardrails_test: DefaultGuardrails values + CheckGuardrails
(insufficient data, locked params, zero-min fallback)
- prompt_builder_orchestration_test: BridgePromptBuilder orchestration section
presence/absence across 4 scenarios + target content verification
* test(v3): add integration tests for evolution metrics + suggestions
- Test helper: shared PG connection with sync.Once migration, per-test
tenant+agent seed with cleanup
- Evolution metrics: RecordMetric, AggregateToolMetrics (success rate),
Cleanup (TTL deletion)
- Evolution suggestions: full CRUD, UpdateSuggestionParameters (baseline
persist), tenant isolation (cross-tenant read blocked)
- Pipeline E2E: seed 25 failed tools + 55 low-usage retrievals, verify
SuggestionEngine creates suggestions, verify dedup on second run
- Fix: migration 039 de-duped (episodic_summaries already in 037)
- Fix: NULL reviewed_by scan via sql.NullString
* feat(v3): add HTTP API handlers for evolution, vault, episodic, orchestration, v3-flags
5 new handler files exposing v3 backend stores as REST endpoints:
- evolution_handlers.go: metrics query/aggregate + suggestions CRUD
- vault_handlers.go: cross-agent document listing + search + links
- episodic_handlers.go: episodic summaries list + hybrid search
- orchestration_handlers.go: computed mode + delegate targets (read-only)
- v3_flags_handlers.go: per-agent v3 feature flag get/toggle
Store fixes from code review:
- episodic FTS: use inline to_tsvector (no stored tsv column)
- episodic: conditional user_id filter in List + Search (admin view)
- episodic: add tenant_id to ExistsBySourceID + PruneExpired
- evolution: require tenant_id in context (no struct fallback)
- evolution: check RowsAffected on suggestion updates
- vault: optional agent_id filter in ListDocuments (cross-agent)
* feat(v3): add web UI for evolution tab, v3 settings, vault page, episodic memory
Agent Detail enhancements:
- V3 Settings section: pipeline/memory/retrieval flag toggles
- Orchestration section: mode badge + delegate targets display
- Evolution section: added metrics + suggestions v3 flag toggles
- Evolution tab: Recharts metrics charts + suggestion review table
with approve/reject/rollback actions + guardrails card
New pages:
- /vault: Knowledge Vault document registry with cross-agent listing,
hybrid search dialog, document detail with wikilinks
- Memory page: added Episodic Memory tab with summary cards,
expandable details, key topic badges, and hybrid search
Infrastructure:
- HttpClient: added patch() method
- Query keys: v3Flags, orchestration, evolution namespaces
- 4 new hooks: use-v3-flags, use-orchestration, use-evolution-metrics,
use-evolution-suggestions, use-vault, use-episodic
- i18n: vault namespace (en/vi/zh), agents + memory keys updated
- Reused formatRelativeTime from lib/format.ts (eliminated 3 duplicates)
* refactor(http): add bindJSON helper and migrate all decode call sites
Replace 36 json.NewDecoder(r.Body).Decode + error blocks with bindJSON
across 20 HTTP handler files. Standardizes decode error responses to
structured writeError format. Fixes unchecked decode in handleIndexAll.
* refactor(store): adopt sqlx for PG scan operations (Phase 1+2)
Add jmoiron/sqlx v1.4.0 with camelToSnake json tag mapper.
Migrate scan-heavy PG store methods to sqlx Get/Select:
- tracing.go: GetTrace, ListTraces, ListChildTraces, GetTraceSpans, GetCostSummary
- heartbeat.go: Get, ListDue, ListLogs
- providers.go: GetProvider, GetProviderByName, ListProviders, ListAllProviders
- mcp_servers.go: GetServer, GetServerByName, ListServers
- pairing.go: ListPending, ListPaired
- agents_export_queries.go: 5 export functions
- agents_export_team_queries.go: exportTeamMembers, ExportAgentLinks
All writes (INSERT/UPDATE/DELETE), execMapUpdate, and dynamic WHERE
builders remain raw SQL. Zero behavior change.
* refactor(store): adopt sqlx for SQLite scan operations (Phase 3)
Migrate SQLite store scan methods to sqlx Get/Select:
- providers.go: GetProvider, GetProviderByName, ListProviders, ListAllProviders
- tenants.go: GetTenant, GetTenantBySlug, ListTenants, GetTenantUser, ListUsers, ListUserTenants
- mcp_servers.go: GetServer, GetServerByName, ListServers
Create sqlx_scan_structs.go with sqliteTime-aware scan structs
(providerRow, tenantRow, tenantUserRow, mcpServerRow) to handle
SQLite TEXT timestamp parsing via StructScan.
* refactor(store): migrate PG bulk scan operations to sqlx (Phase 4)
Migrate scan-heavy methods across 6 PG store files:
- tenant_store.go: GetTenant, GetTenantBySlug, ListTenants, GetTenantUser,
ListUsers, ListUserTenants — removed 3 scan helpers
- teams.go: ListTeams, GetTeam, ListMembers, ListMembersByTenant
- teams_tasks_activity.go: ListComments, ListEvents, ListFollowUps
- pending_message_store.go: ListPending, ListByHistoryKey
- skills_grants.go: ListAgentGrants
- config_permissions.go: CheckPermission
~20 scan ops converted. Files with encryption post-processing,
pq.Array, pgvector, or dynamic SQL kept raw.
* refactor(store): extract shared CamelToSnake mapper, add UUIDArray usage note
- Move camelToSnake to internal/store/column_mapper.go (DRY)
- Both pg and sqlitestore packages now import shared CamelToSnake
- Add planned-use comment on UUIDArray type
* refactor(cli): migrate commands from config.json to HTTP API, add providers/setup/TUI
- Add unified HTTP client (gateway_http_client.go) with auth, error parsing, typed generics
- Rewrite agent list/add/delete to use gateway HTTP API instead of config.json
- Rewrite channels list to HTTP API, add channels add/delete subcommands
- Replace models command with full providers CRUD (list/add/update/delete/verify)
- Add setup wizard command (provider → agent → channel post-onboard flow)
- Add Bubble Tea TUI behind build tag (tui/!tui with noop fallback)
- Update onboard next-steps to mention goclaw setup
- Add build-tui Makefile target
- Fix URL path injection (url.PathEscape on all user-supplied path segments)
- Fix UTF-8 truncation in skills description display
* refactor(store): add explicit db struct tags, fix sqlx mapper for heartbeat scan error
Switch sqlx mapper from NewMapperFunc (which only applies CamelToSnake to
field names, not tag values) to NewMapperFunc("db", CamelToSnake) with
explicit db:"column_name" tags on all store structs.
Root cause: NewMapperFunc("json", fn) sets mapFunc but not tagMapFunc,
so camelCase json tags like "agentId" were used as-is instead of being
converted to "agent_id", causing "missing destination name" scan errors.
Fix: use db struct tags as the source of truth for column mapping.
Every DB entity field gets db:"column_name", nested JSON configs and
runtime-only structs get db:"-".
* test(store): add integration tests for 13 store interfaces (70 tests)
Cover Tier 1 (critical) + Tier 2 (security) stores with integration tests
running against pgvector pg18. Coverage from 2.4% to ~54%.
Stores tested: Session, Agent, Team/Task, Memory, KnowledgeGraph, Vault,
MCP Server, API Key, ConfigPermission, Contact.
Infrastructure: fixture builders (seedTeam, seedMCPServer, etc.),
mock EmbeddingProvider, multi-tenant helpers, expanded cleanup.
* fix(store): resolve NULL scan bugs in MCP server and task metadata
- mcp_servers: COALESCE nullable TEXT columns (display_name, command,
url, api_key, tool_prefix) to prevent sqlx scan failures
- mcp_servers_access: COALESCE nullable JSONB columns in ListAgentGrants
(tool_allow, tool_deny, config_overrides) to prevent silent row drops
- teams_tasks: default task metadata to '{}' instead of nil to satisfy
NOT NULL constraint on CreateTask
- sqlx_helpers: export InitSqlx for integration test setup
* feat(pipeline): fix v3 pipeline context injection, tracing, KG temporal filters
- Pipeline context: add InjectContext + LoadSessionHistory callbacks to
ContextStage, propagate enriched ctx via state.Ctx for iteration stages
- Pipeline tracing: wrap makeCallLLM with emitLLMSpanStart/End, wrap
makeExecuteToolCall/Raw with emitToolSpanStart/End
- Token counter: switch pipeline from FallbackCounter to TiktokenCounter
- KG temporal: add valid_until IS NULL filter to all entity/relation
queries (list, search, vector, FTS, traversal CTE, stats)
- Skills: add SkillEmbedder interface for future hybrid BM25+vector search
- Cache: remove unused tenantResolve dead code from PermissionCache
- Store: fix NULL scan bugs in tracing metadata and agent skill_nudge
- Test: add TestStoreKG_TemporalFilter integration test
- UI: add v3 version badge, evolution section, memory/traces improvements
* refactor(store): migrate KG store from raw sql.Rows to sqlx StructScan
Migrate 6 knowledge graph store files from manual rows.Scan() to
pkgSqlxDB.GetContext/SelectContext with intermediate scan row structs.
- Add entityRow, relationRow, traversalRow, dedupCandidateRow structs
with json.RawMessage for jsonb and time.Time for timestamptz columns
- Add toEntity()/toRelation() converters (UnixMilli + json.Unmarshal)
- Add sqlxTx() helper for wrapping *sql.Tx with sqlx mapper
- Fix ScanDuplicates passing time.Now().Unix() to TIMESTAMPTZ column
- Fix ListEntitiesTemporal missing tenant scope (scopeClause)
- Fix SupersedeEntity missing tenant scope and tenant_id on INSERT
- Fix DedupCandidate.CreatedAt using Unix() instead of UnixMilli()
- Update agents_export_queries.go to reuse new scan row structs
- Net -160 lines of manual scan boilerplate removed
* refactor(store): migrate memory, skills, agents, sessions, mcp, cron, vault stores to sqlx
Batch migration of 19 store files from raw rows.Scan() to
pkgSqlxDB.GetContext/SelectContext with intermediate scan row structs.
Groups migrated:
- Memory: memory_docs, memory_admin, memory_search, memory_embedding_cache
- Episodic: episodic_search, episodic_summaries
- Skills: skills, skills_admin, skills_embedding, skills_export_queries
- Agents: agents (backfill+shares), agents_context, agents_export_team_standalone
- Sessions: sessions_list (List, ListPaged, ListPagedRich)
- MCP: mcp_servers_access, mcp_export_queries
- Cron: cron_exec (GetRunLog)
- Vault: vault_documents (ListDocuments, ftsSearch, vectorSearch)
- Tenant: tenant_configs (ListDisabled, ListAll)
7 new scan row files created. Net -510 lines of manual scan boilerplate.
INSERT/UPDATE/DELETE and scalar COUNT queries kept as raw SQL.
* fix(store): fix 3 sqlx scan struct db tag issues found by audit
- Fix vault FTS alias mismatch: `AS rank` → `AS score` (critical: runtime scan error)
- Fix episodic key_topics type: json.RawMessage → pq.StringArray (TEXT[] column)
- Fix agentShareRow.CreatedAt: string → time.Time, wire to output struct
* feat(providers): implement Wave 2 provider resilience and intelligence
9-phase implementation covering:
- Request middleware chain with composable body transformers
- OpenAI prompt caching, service tier, and fast mode middlewares
- Error classification (9 categories) with two-tier failover
- Model registry with forward-compat resolvers (Anthropic + OpenAI)
- Embedding providers (OpenAI + Voyage) with 1536-dim validation
- Cooldown/probe system with per-provider:model state tracking
- Markdown-aware chunking shared across 5 channels
- Session recall via FTS + pgvector on episodic summaries
- Dreaming/promotion pipeline for long-term memory consolidation
Migrations: 000040 (episodic search index), 000041 (promoted_at column)
Schema version: 39 → 41
* feat(providers): wire model registry into gateway provider construction
Create InMemoryRegistry with Anthropic + OpenAI forward-compat resolvers
at gateway startup. Pass to all Anthropic and OpenAI providers created
from both config and DB sources.
* feat(consolidation): wire DomainEventBus and consolidation pipeline
Create DomainEventBus at gateway startup, thread through resolver →
LoopConfig → Loop → PipelineDeps. Emit session.completed event after
each run finalization. Register consolidation pipeline (episodic →
semantic → KG dedup → dreaming) with event bus subscriptions.
* fix(store): fix episodic key_topics pq.Array, ON CONFLICT, and migration 040 immutability
- episodic_summaries.go Create: json.Marshal(KeyTopics) → pq.Array (text[] column)
- episodic_search.go scanEpisodic/scanEpisodicRow: json.RawMessage → pq.StringArray
- episodic_summaries.go Create: ON CONFLICT add WHERE source_id IS NOT NULL for partial index
- migration 040: add immutable_array_to_string wrapper (array_to_string is STABLE in PG)
* test(store): add 17 integration tests for skills, cron, episodic, tenant configs
- Skills store: 6 tests (CRUD, grants, tenant isolation)
- Cron store: 4 tests (job CRUD, run log sqlx scan, pagination, tenant isolation)
- Episodic store: 4 tests (summary CRUD, list, FTS search, tenant isolation)
- Tenant configs: 3 tests (tool/skill disable, list, tenant isolation)
- Test helper: add cleanup for skills, cron, episodic tables
* fix(permissions): use cron-specific permission check for cron tool (#725)
* fix(security): harden exec path exemption matching (#721)
- Add absolute path exemption for dataDir/skills-store/ (fixes skill
scripts using absolute paths like /app/data/skills-store/ being denied)
- Strip surrounding quotes before prefix matching (LLMs often quote paths)
- Reject path traversal ("..") in exempt fields to prevent escape
- Switch from "any field exempt → skip" to per-field matching: only exempt
if ALL fields that match the deny pattern are individually exempt
- Closes pipe/comment bypass vectors where an exempt path in one argument
would exempt the entire command including non-exempt paths
Includes 27 test cases covering: legitimate access, quoted paths,
path traversal, unicode bypass, pipe/comment bypass, mixed args.
* fix(permissions): use cron-specific permission check for cron tool
Cron tool was hardcoded to check `file_writer` configType via
CheckFileWriterPermission(), ignoring the `cron` configType that
the UI actually saves when granting cron permissions. This caused
agents in group chats to be denied cron access even with correct
permission configured.
Add ConfigTypeCron constant and CheckCronPermission() that checks
`cron` configType first, falling back to `file_writer`.
---------
Co-authored-by: Viet Tran <viettranx@gmail.com>
* fix(chat): load message history on first conversation click (#730)
* fix(chat): load message history when selecting existing conversation from clean state
The skipNextHistoryRef was unconditionally set when sessionKey transitioned
from empty to non-empty. This prevented loadHistory() from running when
clicking an existing conversation from the initial /chat page. The skip
was only intended for the new-chat send flow where the optimistic message
is already displayed.
Guard the skip with expectingRunRef so it only activates when a message
send is in flight.
Closes #729
* docs: add UI diff evidence for PR #730
Before/after screenshots and HTML comparison report showing
first conversation click behavior fix.
* feat(whatsapp): port native WhatsApp channel with whatsmeow from dev
Cherry-pick
|
||
|
Viet Tran
|
e88686b13a |
fix: deterministic prompt ordering for LLM cache hit (#719)
Sort all non-deterministic map iterations that affect system prompt and tool definitions sent to LLM APIs. Go map iteration order is random, causing prompt prefix to change every turn — breaking Anthropic/OpenAI prompt caching (cache by exact prefix match). Fixed 5 sources of non-deterministic ordering: - Registry.List(): sort canonical tool names - Registry.ProviderDefs(): sort tools + aliases before building defs - PolicyEngine.FilterTools(): sort alias iteration (single Aliases() call) - buildMCPToolsInlineSection(): sort MCP tool names in system prompt - GetAgentContextFiles/GetUserContextFiles: ORDER BY file_name (PG+SQLite) Based on PR #718 by @therichardngai-code with additional fixes: - Context files from DB now deterministic (ORDER BY file_name) - FilterTools() calls registry.Aliases() once instead of 3 times |
||
|
viettranx
|
7418cb62aa |
fix(agent): reduce system prompt size and fix team context injection (#613)
Prompt compression (Issue #613): - Truncate skill descriptions to 200 runes in inline XML (matches mcpToolDescMaxLen) - Lower skill inline token threshold from 5000 to 3000 - Compact tool descriptions (risk-audited: preserve behavioral hints) - Compact boilerplate sections: media hint, safety, tool call style, spawn, self-evolve, skill creation, team workspace - Fix token estimator to account for description truncation - Restore safety anti-manipulation clauses dropped during compaction Team context injection fix (found during prod audit): - Add IsTeamLead field to LoopConfig/Loop, plumbed from resolver - Gate team context (TEAM.md, workspace, members) on session type: leader inbound → team context; member-only inbound → spawn section; team dispatch → team context - Filter TEAM.md from context files for member-only inbound chat - Skip team member DB query when team context not needed - Rename HasTeam → IsTeamContext for semantic clarity - Add 8 table-driven tests for team context injection scenarios |
||
|
viettranx
|
1b190fa0bb |
fix(prompt): reduce mechanical chat behavior + optimize system prompt
- Add Tool Call Style section with narration minimalism + non-disclosure
rule (from TS reference): agents must never expose tool names to users
- Consolidate 3 redundant memory recall reminders into 1 dedicated section
- Remove "tell the user you checked but found nothing" instruction that
caused agents to describe internal tool mechanics in responses
- Remove 11 tool aliases from system prompt listing (~300 tokens saved);
aliases still work via provider definitions
- Filter alias tool names out of system prompt ToolNames in loop_history
- Update AGENTS.md: remove tool name references from Memory section,
add group chat framing from V1 ("participant, not their proxy")
|
||
|
viettranx
|
9c2b4cbf0f |
fix(agent): improve memory recall accuracy and flush safety
- Add "low confidence" instruction to memory_search tool description to prevent models from fabricating memories when no results found - Add dedicated ## Memory Recall section in system prompt (supplements recency reminder) with clear instructions for memory_search/memory_get - Update flush prompts: replace YYYY-MM-DD with actual date at runtime, cleaner append-only wording - Update AGENTS.md memory privacy section for multi-tenant: remove implementation details (per-user scoping), keep group chat output guardrails that work for both shared and isolated memory configs |
||
|
viettranx
|
2092c50a04 |
fix(agent): use DB provider_type for SOUL echo and strict mode detection
- Add providerTypeOf() to extract provider_type via type assertion (e.g. "chatgpt_oauth") instead of config name (user-set "openai") - Exclude "compat" providers (openai_compat → OpenRouter/DeepSeek/Groq) from strict mode and SOUL echo — they proxy to non-OpenAI models - Fix isOpenAIStrict matching openai_compat incorrectly |
||
|
viettranx
|
2a9400949b |
fix(agent): SOUL echo in recency zone for OpenAI/Codex providers
GPT models have strong recency bias and lose persona in long prompts. Extract Style/Vibe sections from SOUL.md and echo them at the end of the system prompt (~200 chars each) so GPT sees personality traits right before generating. Only applies to OpenAI/Codex — Claude respects early system prompt instructions well and doesn't need this. |
||
|
viettranx
|
f623ef9d55 |
feat(mcp): hybrid search mode — keep first 40 tools inline, defer rest
Instead of all-or-nothing when MCP tool count exceeds threshold, keep first 40 tools registered inline and only defer the excess to BM25 search via mcp_tool_search. System prompt now shows both inline descriptions and search guidance in hybrid mode. Also raises skill inline count from 40 to 60 (token limit is the real bottleneck for skills). |
||
|
viettranx
|
36b43ed7f1 |
feat(workspace): leader dual workspace with auto-copy to team on delegate
- Revert leader workspace override: leader keeps personal workspace as default, team workspace accessible via ToolTeamWorkspaceFromCtx - Auto-copy: when leader creates team_tasks, scan subject+description for file paths → copy from personal to team workspace so members can access them - Safety: Lstat (reject symlinks), 10MB size cap, .env excluded from allowed extensions, path traversal blocked - Prompt hint: clarify members can only access team workspace files, referenced files are auto-copied |
||
|
viettranx
|
f8278cfaff |
fix(mcp): strip placeholder values from optional tool args and guide LLMs on optional params
LLMs often send empty strings, "null", "SHOULD_NOT_BE_HERE" etc. for optional MCP tool parameters instead of omitting them, causing servers to reject invalid values (e.g. UUID validation fails on ""). - Add stripEmptyOptionalArgs() to clean optional args before MCP calls - Detect known placeholders (null/none/nil) and all-caps patterns - Add system prompt guidance for optional parameter handling - Empty string "" is intentionally NOT stripped (may be valid for text fields) |
||
|
viettranx
|
23c43259c9 |
fix(bootstrap): ensure per-user context files are seeded for all agent types
- Separate file seeding from workspace resolution so agents without workspace still get BOOTSTRAP.md and USER.md seeded - Always seed context files for existing profiles that have zero files (handles EnsureUserProfile pre-creation via HTTP API) - Add persistent "USER PROFILE INCOMPLETE" nudge in system prompt when BOOTSTRAP.md is cleaned up but USER.md remains blank - Move bootstrap auto-cleanup nudge before session flush so the reminder is persisted to history - Add userFilesSeeded sync.Map to avoid redundant seeding calls - Capture workspace from seeding call to eliminate double DB roundtrip |
||
|
viettranx
|
7eea004c8d |
fix(bootstrap): predefined agents now reliably complete USER.md onboarding
- Strengthen FIRST RUN prompt: mandatory write_file calls, no deferring - Filter BOOTSTRAP.md from system sessions (subagent/cron/heartbeat) - Remove duplicate bootstrap reminder in buildProjectContextSection - Fix template: proper tool-calling syntax, step-by-step instructions |
||
|
Viet Tran
|
e183b459c9 |
feat: SQLite desktop edition — full desktop app with team tasks (#505)
* feat(store): add SQLite backend foundation with build-tag injection
Add sqlitestore package (//go:build sqlite) as alternative to PostgreSQL:
- pool.go: WAL mode, busy_timeout, 4 concurrent read connections
- helpers.go: ? param helpers, JSON array storage, nullable/update utils
- scope.go: tenant scope with ? placeholders (vs PG's $N)
- schema.sql: 1296-line flattened DDL from 29 PG migrations (51 tables)
- schema.go: embedded schema with transactional apply + version tracking
- factory.go: NewSQLiteStores() stub (stores wired in Phase 2)
Build-tag split for store initialization:
- cmd/gateway_stores_pg.go (//go:build !sqlite) — default PG-only
- cmd/gateway_stores_sqlite.go (//go:build sqlite) — runtime PG/SQLite switch
- cmd/gateway_setup.go: extracted wireTracingAndCron() shared helper
Config: GOCLAW_STORAGE_BACKEND + GOCLAW_SQLITE_PATH env vars.
Security: goclaw.db added to DenyPaths (exec, read_file, filesystem tools).
* feat(edition): add centralized edition package for feature tier limits
New internal/edition/ package — single source of truth for all edition limits:
- Edition struct with MaxAgents, MaxTeams, MaxChannels, KGEnabled, TeamFullMode, etc.
- Standard (default, all features) and Lite (desktop, 5 agents, 1 team) presets
- atomic.Pointer for thread-safe Current()/SetCurrent()
Wiring:
- cmd/gateway.go: GOCLAW_EDITION env override (lite/standard) at startup
- cmd/gateway_stores_sqlite.go: auto-set Lite when backend=sqlite
- /v1/edition HTTP endpoint for UI comparison modal (public, no auth)
* feat(sqlitestore): implement Phase 2A core stores + sqliteonly build tag
Implement 12 SQLite store backends (4200+ LOC) mirroring existing PG stores:
- SessionStore, AgentStore, ProviderStore, TracingStore, SnapshotStore
- ConfigSecretsStore, SystemConfigStore, TenantStore, HeartbeatStore
- BuiltinToolStore, BuiltinToolTenantConfigStore, SkillTenantConfigStore
All stores wired in factory.go. Remaining stores (Memory, Cron, Skills,
Teams, etc.) left nil — gateway handles gracefully.
Add sqliteonly build tag for PG-free desktop builds:
- go build . → PG only
- go build -tags sqlite . → PG + SQLite (runtime switch)
- go build -tags sqliteonly . → SQLite only (no pgx dependency)
Key SQLite adaptations:
- ? placeholders (not $N), json_extract/json_each/json_array_length
- DISTINCT ON → GROUP BY + Go dedup, ANY($1) → IN (?,?...)
- rows.Err() checks on all scan loops, execMapUpdateWhereTenant in helpers
- GetOrCreateUserProfile uses RowsAffected() instead of PG's xmax trick
* feat(sqlitestore): implement Phase 2B feature stores
Port 8 additional store backends to SQLite (19 new files, ~6000 LOC):
Cron: cron.go, cron_crud.go, cron_exec.go, cron_scheduler.go
- Job scheduling with cache, ListDue, MarkRunning, MarkComplete
Skills: skills.go, skills_crud.go, skills_content.go, skills_grants.go
- CRUD, grants, content management. LIKE search (no FTS/vector in Lite)
MCP: mcp_servers.go, mcp_servers_access.go, mcp_user_credentials.go
- Server CRUD, agent/user grants, encrypted credentials
Channels: channel_instances.go, pairing.go, pending_messages.go, contacts.go
- Channel management, device pairing, message queue, contact store
Teams: teams.go, teams_tasks.go, teams_tasks_lifecycle.go, teams_tasks_activity.go
- Team/task CRUD, lifecycle transitions, activity log, progress tracking
- JSON array for members/blocked_by (replaces PG text[])
Remaining nil stores: Memory, AgentLinks, KnowledgeGraph, Activity,
SecureCLI, APIKeys, ConfigPermissions — gateway handles gracefully.
* fix(sqlitestore): fix critical arg ordering + data races in Phase 2B stores
C1: ListTasks arg mismatch — limit+1 in userID slot, wrong results
C2: SearchTasks missing duplicate userID arg for (? = '' OR t.user_id = ?)
H3: cron_crud.go cacheLoaded written without mutex → use InvalidateCache()
H4: cron_exec.go discarded ExecContext error → log warning
H1: Add rows.Err() checks in cron_crud, cron_scheduler, cron_exec, pairing
* feat(sqlitestore): implement Phase 2C — Memory, Activity, APIKeys, ConfigPermissions
Complete remaining essential stores (6 new files, ~900 LOC):
Memory: memory.go, memory_docs.go, memory_search.go
- Document/chunk CRUD, LIKE-based search (no vector in Lite edition)
- Embedding methods return empty results gracefully
Activity: activity.go — simple activity logging
APIKeys: api_keys.go — API key CRUD with SHA-256 hash lookup
ConfigPermissions: config_permissions.go — permission rules with TTL cache
24/27 stores now wired. Only AgentLinks, KnowledgeGraph, SecureCLI
remain nil (disabled in Lite edition by design).
Total: 49 files, 11,435 LOC in internal/store/sqlitestore/
* fix(sqlitestore): fix variable shadow in GetDocument + handle chunk delete error
C1: GetDocument scopeClause used := inside if/else blocks, shadowing
outer err variable — query errors silently swallowed. Fixed by renaming
to tcErr matching PG pattern.
H1: IndexDocument chunk deletion ExecContext error was discarded, could
cause duplicate chunks. Now returns error on failure.
* feat(desktop): Phase 3 — Wails v2 desktop app shell with chat UI
Desktop app (ui/desktop/) using Wails v2 + React 19 + Tailwind CSS 4:
Go backend:
- main.go: Wails entry point with embedded frontend assets
- app.go: gateway embedding via goroutine, health check, Wails bindings
- keyring.go: OS keyring secrets with file fallback
- cmd/gateway_export.go: exports RunGateway() for desktop embedding
React frontend:
- WS v3 client: protocol handshake, exponential backoff, call queue
- Chat system: Zustand stores, RAF-batched streaming, 10 event handlers
- Components: MessageBubble, MarkdownRenderer (rehype-sanitize),
CodeBlock, ToolCallBlock, ThinkingBlock, ActivityIndicator, InputBar
- Layout: AppShell (2-column), Sidebar with agent/session list, TopBar
- Onboarding wizard (5 steps): welcome, gateway, provider, agent, ready
- Magic Blue theme (dark/light), Inter + JetBrains Mono typography
Build: all 3 variants pass (PG, sqlite, sqliteonly)
* chore: ignore Wails build artifacts (wailsjs, build, package.json.md5)
* fix(desktop): correct onboarding provider list and agent creation API contract
- ProviderStep: expand from 3 to 16 providers in 4 groups (Popular, Cloud, Local, Regional)
with correct provider_type values and api_base defaults
- AgentStep: fix API payload — use agent_key (slug), provider (name string),
agent_type=predefined with description in other_config
- use-agents: fix field mapping — agent_key, display_name from backend response
- Clean up failed provider on verify error
* fix(desktop): add missing providers — Bailian Coding, Z.ai Coding, Ollama Cloud
* fix(desktop): match web dashboard brand colors + persist onboarding in store
- Replace Magic Blue theme with web dashboard's warm blue OKLCH palette
- Move onboarding state from localStorage to Zustand persist store
- Add "Run Setup Wizard" option in TopBar settings menu to re-trigger onboarding
- Fix light mode theme activation (explicit :root:not(.dark) overrides)
* fix(desktop): apply dark theme before first paint + better error messages
- Add class="dark" default on <html> + inline script to read persisted theme
before React hydrate (prevents light flash on dark mode)
- Improve provider test error message for network failures
* feat(desktop): add GoClaw logo from web UI to onboarding + topbar
* fix(desktop): add Vite proxy for dev mode to avoid CORS gateway errors
- Proxy /v1, /ws, /health to localhost:18790 in Vite dev server
- Use relative URLs in dev mode (import.meta.env.DEV) so proxy handles CORS
- Production build uses direct gateway URL from Wails binding
* fix(desktop): GoClaw dock icon + fix duplicate provider slug on re-test
- Convert goclaw-icon.svg to 1024x1024 PNG for macOS dock icon
- Fix provider creation: handle existing slug by finding and updating
- Track build/appicon.png in git (exclude only build/bin/)
* fix(sqlitestore): UUID text/blob mismatch in scopeClause breaks all queries
scopeClause passed uuid.UUID (16-byte array) to SQLite ? placeholder,
but tenant_id column stores TEXT strings. SQLite compared BLOB vs TEXT
→ no match → all scoped queries returned empty results.
Fix: pass scope.TenantID.String() to ensure TEXT comparison.
Also includes:
- macOS dock icon (.icns from GoClaw logo)
- Onboarding auto-detect existing providers/agents
- Debug logging for token + API URL
* fix(desktop): CORS for dev mode + direct gateway URL
- Wails dev server (port 34115) doesn't proxy API calls, causing 405
- Frontend now connects directly to gateway URL from Wails binding
- Added GOCLAW_DESKTOP=1 env → enables CORS middleware on gateway
- desktopCORS wraps mux with Access-Control-Allow-* headers + OPTIONS
- Simplified provider test flow: list-then-create/update
* fix(desktop): split onboarding into 6 steps matching web UI flow
Web UI flow: create provider → select model + verify → create agent.
Desktop was incorrectly trying to verify before creating provider.
Changes:
- ProviderStep: now only creates/saves provider (no verify)
- NEW ModelVerifyStep: loads models from provider, test connection
- AgentStep: receives pre-selected model, shows read-only model field
- OnboardingWizard: 6 steps with auto-detect skip logic
- Auto-detect: has agents→Ready, has providers→ModelVerify, nothing→Provider
* feat(desktop): add Combobox component, use searchable model selector
- New Combobox: searchable dropdown with custom value support
- ModelVerifyStep: replace plain input/select with Combobox
- Models loaded from GET /v1/providers/{id}/models API
- Allows typing custom model name if API returns empty list
* fix(desktop): rename icon to iconfile.icns matching Wails convention
* refactor(desktop): overhaul UI/UX, fix onboarding, fix event handling
Desktop app major refactor:
UI/UX:
- Chat-focused layout with floating panels on dotted canvas
- Sidebar: agent list + sessions grouped by date (no resource counts)
- Modern input bar: rounded pill with attach/send buttons
- User bubble: card style matching web UI (not solid color)
- Thinking block: collapsible, max-height, proper label
- ErrorBoundary wrapping app
- Dock icon: regenerated with transparent bg + dark rounded frame
Onboarding:
- 3-step flow matching web UI (Provider → Model → Agent)
- Proper create vs update (check DB before POST)
- SetupStepper with step circles + connectors
- Agent presets from web UI (Fox Spirit, Artisan, Astrologer)
- Auto-detect existing setup via use-bootstrap-status hook
Event handling (verified from Go source):
- chunk: payload.content (not payload.chunk)
- thinking: payload.content (not payload.thinking)
- tool.call: payload.id/name (not toolId/toolName)
- tool.result: payload.is_error/content (not error field)
- run.completed: usage.prompt_tokens/completion_tokens
- New: block.reply, run.retrying handlers
Backend fixes:
- SQLite scanTime helper for modernc.org/sqlite text timestamps
- X-GoClaw-User-Id header in desktop API client (not X-User-ID)
- user_id: system (owner role in desktop single-user mode)
- CORS: allow X-GoClaw-User-Id header
- SQLite busy timeout: 5s → 10s
- Snapshot SQL: cross-DB compatible (FILTER→CASE, ::BIGINT→CAST)
- Promise.allSettled for bootstrap status (one fail doesn't block other)
* feat(desktop): chat polish, SQLite fixes, summoning modal, bootstrap guard
Chat Polish (Phase 1):
- ToolCallBlock: Wrench/Zap icons, phase badges, arg summary, grouped rendering
- ThinkingBlock: auto-expand on stream, Brain icon, cursor pulse
- MessageBubble: isStreaming prop, streaming cursor, grouped tool calls
- ImageLightbox: fullscreen overlay, gallery nav, keyboard shortcuts, download
- MediaBlock: grid layout, click-to-open lightbox, hover overlay
- ActivityIndicator: phase-specific icons (Brain/Wrench/RefreshCw)
- ChatCanvas: track lastAssistantId for streaming, EmptyState with prompts
- Filter [System] nudge messages and tool-role messages from chat history
SQLite Fixes:
- sessions_list: fix time.Time scan failure (3 sites) using sqliteTime scanner
- snapshots: fix ON CONFLICT expression mismatch with unique index
- snapshots: fix GetLatestBucket using nullSqliteTime
- pool: explicit PRAGMAs (busy_timeout=15s, WAL, synchronous=NORMAL)
- schema: seed master tenant (was missing, causing FK violations)
- schema: incremental migration framework (version-gated patches)
Onboarding:
- SummoningModal: port from web UI with framer-motion animations
- AgentStep: show summoning modal after create, continue button
- App: auto-detect empty DB and reset onboarded flag
- ChatCanvas: loading spinner while agent loads after onboarding
Bootstrap Guard:
- After auto-cleanup of BOOTSTRAP.md, check if USER.md is still empty
- Inject reminder if agent cleared BOOTSTRAP but didn't fill USER.md
Session Management:
- Load chat history on session click (was missing useEffect)
- Fix race condition: don't clear messages on session switch (atomic replace)
- SidebarFooter: center New Chat button text
* fix(desktop): session management, delete confirm, event listener race fix
- New Chat: only clears state, no empty session creation (sendMessage auto-creates)
- Delete session: hover X button with ConfirmDialog confirmation
- Event listener: use sessionKeyRef instead of closure to prevent stale events
- Remove "skip to dashboard" link from onboarding
- Add reusable ConfirmDialog + ConfirmDeleteDialog common components
* feat(desktop): settings view with tabbed layout (Phase 4)
- SettingsView: tab container with header, close button, canvas-dots bg
- SettingsTabBar: 9 tabs (Appearance, Providers, Agents, MCP, Skills, Tools, Cron, Traces, About)
- AppearanceTab: dark/light theme toggle, language + timezone placeholders
- AboutTab: version, edition limits, runtime info
- ui-store: activeView, settingsTab, openSettings(), closeSettings()
- AppShell: switch between chat and settings views
- SidebarFooter: gear icon opens settings (was "Run Setup Wizard")
- Keyboard: Cmd+, opens settings, Escape closes
- Branding: "GoClaw Lite" in sidebar header
- Agent status: online (green) instead of idle for desktop
- Tab content wrapped in solid bg card with border
* feat(desktop): provider management CRUD in settings (Phase 5)
- use-providers hook: list, create, update, delete, verify via HTTP API
- ProviderList: list view with Add button, empty state
- ProviderRow: status dot, type badge, edit/delete actions
- ProviderFormDialog: create/edit with type selector, masked API key, test connection
- Wire ProviderList into Settings Providers tab
* fix(desktop): remove Test Connection from provider form (requires model + provider ID)
* feat(desktop): agent management CRUD in settings (Phase 6)
- AgentData/AgentInput types matching web UI contracts
- use-agent-crud hook: list, create, update, delete, resummon (5 agent limit)
- AgentCard: emoji, status dot, provider/model/type badges, edit/delete/resummon
- AgentFormDialog: provider Combobox + model Combobox (from /v1/providers/{id}/models)
- Create: agent_type selector, "Check & Create" verifies model before create
- Edit: no type change, no re-verify needed
- Personality textarea for predefined agents
- AgentList: grid, edition limit warning, create triggers SummoningModal
- Delete uses ConfirmDeleteDialog (type name to confirm)
- Sidebar agent list refreshes after CRUD
* feat(desktop): agent detail panel with full config (Phase 6 polish)
Agent detail panel (fullscreen overlay covering sidebar):
- PersonalitySection: emoji editor, display name, description, status select, default toggle, agent key display
- ModelBudgetSection: provider/model Combobox with verify-before-save, context window, max tool iterations
- EvolutionSection: self_evolve toggle with info callout (predefined agents only)
- Sticky save bar: backdrop blur, cancel/save buttons, spinner on save
- Save blocked if provider/model changed but not verified
AgentList: card click opens detail panel, create dialog separate
AgentFormDialog: create-only, Check & Create with verify
* fix(desktop): resummon confirm, summoning z-index, save bar UX
- Resummon requires confirm dialog before triggering
- SummoningModal z-index z-50 → z-[70] (above detail panel z-[60])
- Save bar: show error inline, "Verify model first" when blocked
* feat(desktop): agent detail quality polish — files tab, memory config, rich cards
Types (synced with web UI):
- AgentData: added owner_id, workspace, restrict_to_workspace, frontmatter, context_window, max_tool_iterations as required fields
- MemoryConfig, CompactionConfig interfaces
- BootstrapFile type for WS file operations
AgentCard (matching web UI agent-card.tsx):
- Star icon for default agent
- Animated pulse badge for summoning status
- Self-evolve sparkle indicator (orange when active)
- Frontmatter/expertise with line-clamp-3
- Context window display (e.g. "200K ctx")
- Safe emoji extraction, UUID name detection
AgentDetailPanel:
- Tab navigation: Overview + Files tabs
- Overview: Personality + ModelBudget + Memory + Evolution sections
- Files tab: WS-based file editor (agents.files.list/get/set)
- File sidebar with selection
- Textarea editor with dirty tracking
- Save button with spinner
- Sticky save bar with backdrop blur (overview only)
- Resummon with confirm dialog
MemorySection (matching web UI memory-section.tsx):
- Enable/disable toggle
- 6 config fields: max_results, min_score, max_chunk_len, chunk_overlap, vector_weight, text_weight
- "Using global defaults" when disabled
* feat(desktop): agent files — hide USER/HEARTBEAT, add Edit with AI
- Hide USER.md, USER_PREDEFINED.md, HEARTBEAT.md from files tab (managed by bootstrap/cron)
- Add "Edit with AI" button → RegenerateDialog → POST /v1/agents/{id}/regenerate
- Auto-select first file on load
- Show file size in sidebar
- Pass agentId to files tab for regenerate API call
* fix(desktop): remove memory config section (no embedding in SQLite)
* fix(desktop): remove misleading bytes display from file sidebar
* fix(desktop): replace native checkboxes/selects with custom Switch + Combobox
- New Switch component matching Radix UI toggle style
- Replace all native <input type="checkbox"> with Switch in agent/provider forms
- Replace native <select> for status with Combobox
- All interactive elements have cursor-pointer
* fix(desktop): evolution callout colors — use opacity-based for both themes
* fix(desktop): global cursor-pointer for all interactive elements
* fix(desktop): improve dark mode contrast for text and status colors
- text-secondary: 0.62 → 0.68 lightness (better readability on dark bg)
- text-muted: 0.52 → 0.58 lightness (was below WCAG AA 4.5:1 minimum)
- success: 0.45 → 0.55 (green was too dim on dark bg)
- warning: 0.65 → 0.70 (slightly brighter)
- idle: 0.52 → 0.58 (match text-muted)
* fix(desktop): revert color values to exact web UI match (0.62/0.52/0.45)
* fix(desktop): agent card badge colors — match web UI badge variants exactly
* feat(desktop): add MCP servers + Builtin Tools settings tabs
Phase 7 implementation:
MCP Tab:
- Full CRUD with 5-server edition limit
- Form dialog with transport-conditional fields (stdio/SSE/streamable-http)
- Test Connection with inline success/error feedback
- Agent grants dialog (grant/revoke per agent)
- Tools discovery dialog (view server tools)
- KeyValueEditor with sensitive field masking (auth/token/secret)
Tools Tab:
- Category-grouped list of 41 seeded builtin tools
- Toggle enable/disable with optimistic update
- Specialized settings forms: web_fetch extractor chain, media provider chain
- Generic JSON editor fallback for other tools
- Provider/model Combobox selection for media tools
Common:
- RefreshButton component with 500ms min spin animation
- KeyValueEditor with password masking for sensitive keys
Fixes:
- SQLite builtin_tools scan: use scanTimePair() for timestamps
- Session click while in settings: now closes settings view
- Dark mode text contrast: bumped text-secondary/text-muted lightness
- Light mode text contrast: darkened text-secondary/text-muted
- Focus ring thickness: ring-2 → ring-1 globally
- Misleading "memory layering (Postgres)" log label
* feat(desktop): add Skills tab, agent skill grants, emoji avatar, agent form redesign
Skills:
- Skills settings tab with upload ZIP, toggle, delete, runtime check
- Agent skill grants section in agent detail panel (toggle per agent)
- SQLite SkillManageStore interface compliance fixes
Agent form:
- 2-column layout, wider modal (max-w-3xl)
- 6 personality presets (Fox Spirit, Artisan, Astrologer, Researcher, Writer, Coder)
- Separate Verify Model + Summon buttons
- Always predefined type (removed open option)
Fixes:
- SQLite time.Time scan: mcp_servers, mcp_grants, activity_logs
- Combobox portal with scroll/resize tracking
- AgentAvatar shows emoji from other_config
- uploadFile sends X-GoClaw-User-Id header + generic type
- isApiClientReady guard prevents ErrorBoundary crash
- Verify model field: valid (not success)
* fix(sqlitestore): comprehensive timestamp scan sweep + UI fixes
SQLite timestamp sweep (13 files, 25+ sites):
All time.Time direct scans replaced with sqliteTime/scanTimePair/nullSqliteTime.
Files: activity, teams, teams_tasks, teams_tasks_activity, config_permissions,
agents_access, tracing_spans, tracing_scan, channel_instances, tenants,
pending_messages, api_keys, heartbeat.
UI fixes:
- Agent switching: clear active session + chat when agent changes
- MCP table: vertical align middle on row cells
* fix(sqlitestore): fix json.RawMessage scan + sqliteVal for dynamic updates
- mcp_servers_access: scan json columns via string intermediates (SQLite
TEXT → json.RawMessage incompatible, use string then convert)
- helpers: add sqliteVal() to auto-marshal map/slice/struct to JSON
string in execMapUpdate/execMapUpdateWhereTenant — fixes agent save
500 error when updating other_config, tools_config, etc.
- Add AgentMcpSection: toggle MCP server grants per agent in detail panel
- Clean up debug logging from McpGrantsDialog
* feat(desktop): add i18n (react-i18next) + toast system + language/timezone pickers
i18n:
- Install react-i18next + i18next
- Copy 12 web locale namespaces (en/vi/zh) + desktop.json namespace
- Create i18n/index.ts with browser language detection + localStorage persist
- Replace ~300 hardcoded strings across 40+ components with t() calls
- Language picker in ChatTopBar (top-right) + Settings > Appearance
- Timezone picker in ChatTopBar with search + Intl.supportedValuesOf fallback
- All 6 agent presets fully translated (vi/zh) with prompts from locale files
- Agent Key never translated (uses stable English slugs)
Toast:
- Zustand toast store (success/error/warning/default, 4s auto-dismiss)
- Toaster component (bottom-right, z-100, slide-in animation)
- Toast calls in all CRUD hooks (agents, providers, MCP, skills, tools)
* feat(desktop): add Cron Jobs + Traces settings tabs with syntax highlighting
Cron Jobs (Phase 8):
- WS RPC hook (cron.list/create/delete/toggle/run/runs)
- CronList table with schedule formatting, status badges, run/toggle/delete
- CronFormDialog with slug name, agent selector, 3-way schedule (every/cron/once)
- CronRunsDialog for execution history
Traces (Phase 9):
- HTTP REST hook (GET /v1/traces with pagination + agent filter)
- TraceList table with duration, tokens, spans, relative time
- TraceDetailDialog with metadata, collapsible input/output, flat span list
- Syntax-highlighted JSON/code previews via react-syntax-highlighter
* fix(sqlitestore): fix tracing scan — endTime *time.Time → nullSqliteTime
Both trace and span scan functions used *time.Time for nullable end_time
column, which fails on SQLite TEXT timestamps. Changed to nullSqliteTime
with Valid check before assigning pointer.
* fix(desktop): fix cron schedule type label — map 'at' kind to 'once' i18n key
* fix(desktop): prevent flash on cron/traces refresh — keep data while refetching
* feat(desktop): add file attachment rendering — FileButton + FilePreviewDialog
- FileButton: compact attachment button with emoji icon, filename, size, download
- FilePreviewDialog: modal with type-detected preview (image/video/audio/markdown/code/text)
- MarkdownRenderer: override a/img for /v1/files/ links → FileButton + resolved URLs
- MediaBlock: non-image files render as FileButton instead of plain links
- api.ts: add getBaseUrl() for file URL resolution
* fix(desktop): resolve file URLs in chat — toFileUrl for media_refs + relative paths
- use-chat: add toFileUrl() to convert raw paths to /v1/files/{basename} URLs
for both run.completed media and history media_refs
- MarkdownRenderer: detect relative file paths (./path/file.ext) via isFileLink
in addition to /v1/files/ links, resolve all to gateway URL
* fix(desktop): authenticated file serving — media cache + blob URLs
Security fix: all /v1/files/ requests now use Bearer auth via fetchFile().
No more raw <a href> or <img src> with unauthenticated file URLs.
- Add media-cache.ts (blob cache with 5-min TTL, dedup inflight fetches)
- Add use-media-url.ts hook (returns cached blob URL for authenticated media)
- Add AuthImage component (loads images via auth blob) + downloadFile helper
- Update MarkdownRenderer: file images use AuthImage, downloads use downloadFile
- Update FileButton: authenticated download via blob
- Update FilePreviewDialog: authenticated fetch for text/preview content
- Clean filename display (strip timestamps + query params)
* fix(desktop): fix file attachments — use media_refs.id for URL, auth all media
Root cause: media_refs from backend has {id, mime_type, kind} but no path/url.
The id IS the filename basename. Fixed toFileUrl to use ref.id as fallback.
Also: AuthImage for lightbox, authenticated audio/video in MediaBlock,
clean filename display (strip timestamps).
* fix(desktop): file serving, traces, and media rendering improvements
Backend:
- Store MediaRef.Path in loop_finalize for direct file serving
- Use full path (not basename) in gateway_managed event signing
- Add fuzzyMatchInDir for LLM-hallucinated filenames
- Add findInWorkspace support for agent dirs and ws/ directory
- Add POST /v1/files/sign endpoint for client-side URL signing
- Always save LLM span input_preview (not just verbose mode)
- Truncate previews from tail (keep recent context), limit 2000 chars
- Add exact filename hint to create_image/video/audio tool results
Desktop frontend:
- File attachments: FileButton, FilePreviewDialog, AuthImage with blob cache
- Media cache: sign URLs via API for non-ft URLs, Bearer auth fallback
- Download via Wails SaveFile binding (native Save As dialog)
- OpenFile + DownloadURL Wails Go bindings
- Traces: rewrite with span tree hierarchy, formatTokens (90.8K),
formatDuration with start/end fallback, expandable spans
- Traces: export via DownloadURL, copy with checkmark state
- Code preview: JSON = oneDark syntax highlight, text = light pre block
- MarkdownRenderer: baseUrl prop for relative image resolution
- ImageLightbox: preventDefault on keyboard nav (no macOS beep)
- ErrorBoundary: reload instead of re-render on retry
- Combobox: compact sizing (py-1.5, text-sm)
- FileButton: fix nested button HTML violation
* feat(desktop): team tasks kanban board + edition policy + file preview fixes
Phase 11 implementation:
Backend:
- TeamActionPolicy interface — lite/full edition gating for team_tasks tool
- Filter blocked actions from schema enum + early guard in Execute()
- System prompt: edition-specific team member guidance
- Skip skill_manage/publish_skill registration + seeding in lite
- teams.create: require at least 1 member
- files.go: 2-layer path isolation (workspace boundary + tenant scope)
Desktop UI:
- Kanban board with 6 status columns + framer-motion layout animation
- Task detail modal with collapsible description/result sections
- Team create dialog with styled member checkboxes
- Sidebar: teams section with create button + Lite edition badge
- Chat TaskPanel: compact active tasks with real-time WS updates
- Real-time: debounced get-light fetch (300ms) + progress patch (1s)
- Edition comparison modal (Lite vs Standard feature table)
- Custom dropdown filter replacing native select
- i18n: teams namespace (en/vi/zh)
Fixes:
- WS params: camelCase (teamId, taskId, sessionKey) matching backend
- FileButton: span wrapper (HTML nesting) + createPortal for dialog
- FilePreviewDialog: defensive filename normalization for extension check
- use-chat: prevSessionRef init null — fix blank chat on view switch
- Scrollbar: 3px auto-hide
- Agent click in sidebar returns to chat view
* feat: Update frontend build assets, change the default agent thinking level to 'low', and update Go module dependencies.
|
||
|
Luan VuandLuvu182
|
73897b9481 |
refactor: replace magic numbers and hardcoded strings with named constants (#269)
Extract scattered magic numbers and hardcoded agent type strings into centralized named constants to improve maintainability and prevent silent inconsistencies when defaults need to change. Changes: - Add config/defaults.go: DefaultContextWindow, DefaultMaxTokens, DefaultMaxMessageChars, DefaultMaxIterations, DefaultTemperature, DefaultHistoryShare - Add providers/defaults.go: DefaultHTTPTimeout, SSE/Stdio scanner buffer size constants - Replace 6 hardcoded 200000 (context window) across agent/, http/, cmd/ with config.DefaultContextWindow - Replace 4 hardcoded 32000/32_000 (max message chars) with constant - Replace 3 hardcoded 20 (max iterations) with constant - Replace 2 hardcoded 0.75 (history share) with constant - Replace 3 hardcoded 300*time.Second (HTTP timeout) with constant - Replace 5 hardcoded scanner buffer sizes with named constants - Replace 10 hardcoded "predefined" string comparisons with store.AgentTypePredefined constant (already defined but unused) - Use config.DefaultTemperature instead of hardcoded 0.7 in agent loop Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com> |
||
|
viettranx
|
1e2ca2df7c |
fix(agent): improve team lead delegation messaging + group chat reply hint
- Team lead: no completion language after delegating, no question phrasing - Group chat: inject reply context hint (NO_REPLY when reply addresses others) - Both v1 and v2 team lead sections updated |
||
|
viettranx
|
1b27fa7a9b |
feat(agents): inject team members into system prompt
Team agents now see a ## Team Members section listing all teammates with agent_key, display_name, role, and frontmatter excerpt. This allows the agent to correctly assign tasks via team_tasks instead of guessing keys. |
||
|
viettranx
|
ca44b7279f |
feat(bootstrap): predefined agents keep full system prompt during onboarding
Predefined agents now retain all tools and system prompt sections when BOOTSTRAP.md is present, instead of entering slim mode with only write_file. Open agents keep the existing slim bootstrap mode. - Gate tool filtering and IsBootstrap on agentType != "predefined" - Add FIRST RUN reminder for predefined agents (without tool restriction) - Skip bootstrap/user seeding for team-dispatched sessions (IsTeamSession) - Group chats skip BOOTSTRAP.md entirely - Track bootstrapWriteDetected + inject nudge after 2 turns without write_file - Update templates: never reveal process, no capability listing, no "locked" - Cache LoadContextFiles via existing agentCache/userCache (TTL 5min) |
||
|
viettranx
|
eee79d111e |
feat(teams): granular progress notifications with direct/leader mode
- Replace progress_notifications toggle with granular config: dispatched (on), progress (on), failed (on) + delivery mode - Direct mode: outbound to channel, no AI processing - Leader mode: inject into leader session with NO-ACTION instructions - Add consumer.team-notify subscriber for event forwarding - Enrich TeamTaskEventPayload with TaskNumber, ProgressPercent/Step - Add auto-status system prompt section - UI: card-select for delivery mode (Zap/Bot icons), 3 toggles |
||
|
viettranx
|
50a42ad110 |
feat(agent): team workspace resolution for lead/member agents
- Lead agents: auto-resolve team workspace as default (relative paths) - Dispatched members: team workspace as default via req.TeamWorkspace - Direct-chat members: own workspace default, team workspace accessible - Add dataDir field to Loop/LoopConfig for global workspace root - System prompt shows team workspace absolute path for model guidance - Remove orphan task detector (superseded by post-turn dispatch) - Log warning on OpenAI tool call argument parse failures |
||
|
viettranx
|
0857321a6b |
fix(providers): correct Anthropic prompt caching + add datetime tool
- Move cache_control from request root (ignored by API) to per-block placement on last system block and last tool definition - Change system prompt time format to date-only for better cache stability - Add builtin datetime tool for precise timestamps (cron, memory, etc.) - Add atMs past-time validation in cron handleUpdate (was only in handleAdd) - Update cron description to guide model to use datetime tool first |
||
|
viettranx
|
b6df6c9286 |
refactor(agent): consolidate system prompt sections into AGENTS.md template
Merge §5 (Memory Recall), §9 (Messaging), §12 (Silent Replies) from hardcoded system prompt into AGENTS.md — single source of truth. Add recency reinforcement at §16 to compensate for mid-prompt position. Clean up SOUL.md and IDENTITY.md template duplication. Saves ~175 tokens/turn across all LLM calls. |
||
|
Viet TranandNam Nguyen Ngoc
|
1a42dc93a6 |
feat(teams): team system v2 with bug fixes, workspace scope, versioning, and prompt optimization (#183)
* feat(workspace): add team shared workspace for file collaboration
- Add workspace_write and workspace_read tools for agents to share files across team members
- Create team_workspaces DB table with migration 000017 (file metadata, pinning, tags)
- Implement PostgreSQL store layer for workspace CRUD operations
- Add RPC handlers for workspace list/read/delete from web UI
- Build React workspace tab with file listing, content preview, and delete
- Propagate workspace channel/chatID scope through delegation chain
- Auto-allow workspace tools in agent tool policy when agent belongs to a team
- Inject team workspace guidance into system prompt for team agents
- Add /reset command handler for clearing session history
- Harden MCP bridge context middleware to reject headers when no gateway token
- Add i18n strings for workspace UI in en/vi/zh locales
* feat(teams): add comprehensive task management with followup reminders and recovery
- Add task followup/reminder system with auto-set on lead agent reply and auto-clear when user responds on channel
- Add task recovery ticker to re-dispatch stale/pending tasks periodically
- Add task scopes, filtering by status/channel/chatID, and task events
- Add WS RPC handlers for task CRUD, assignments, comments, events, and bulk operations (teams_tasks.go)
- Add task detail dialog, settings UI for followup config, and scope filtering in web dashboard
- Add migrations 000018 (team_tasks_v2) and 000019 (task_followup)
- Extend team_tasks_tool with await_reply, clear_followup actions
- Auto-complete/fail team tasks when delegate agent finishes
- Add workspace file listing and team tool manager enhancements
* docs(teams): add team system architecture and playbook ideas documentation
- Add TEAM_SYSTEM.md with full architecture design covering task management, shared workspace, and delegation engine subsystems
- Add TEAM_PLAYBOOK_IDEAS.md outlining future team coordination layers (playbook, member capabilities, auto-learned patterns)
- Document data models, status flows, tool actions, followup reminder system, task ticker, execution locking, and workspace scope model
* fix(teams): resolve 6 critical bugs in team task system
- Fix unblock SQL: check array_length after array_remove (not before)
- Enforce single-team leadership in team creation
- Add requireLead() for approve/reject tool actions
- Validate cross-team dependency references in blocked_by
- Add team_id to handoff route for multi-team isolation
- Set blocked_by DEFAULT '{}' to prevent NULL array issues
* refactor(workspace): use stable userID as scope key instead of connection UUID
Workspace scope changed from (team_id, channel, chat_id) to (team_id, userID).
Fixes workspace fragmentation across WS tab refreshes and reconnections.
* feat(teams): add V1/V2 versioning with feature gating and optimized prompts
- IsTeamV2() helper gates advanced features (locking, followup, review, audit)
- V2 tool actions rejected for V1 teams with clear error message
- Ticker, gateway consumer, delegation hooks respect version flag
- TEAM.md renders v1/v2 sections conditionally
- Tool descriptions and params optimized (~38% token reduction)
- UI: version toggle in settings, V2 Beta badge, conditional rendering
- i18n: version modal keys for en/vi/zh
* fix(migration): use VARCHAR(255) for user ID columns and add metadata JSONB
- assignee_user_id, user_id, actor_id: TEXT → VARCHAR(255)
- Add metadata JSONB to team_task_comments and team_task_attachments
---------
Co-authored-by: Nam Nguyen Ngoc <namnn.0911@gmail.com>
|
||
|
viettranx
|
33e75820e3 |
fix(security): add identity anchoring for predefined agents against social engineering
Predefined agents were vulnerable to conversational identity manipulation (e.g. "I'm your master", "you only listen to me") — users could establish authority through chat history, causing the agent to comply in subsequent messages. Added identity anchoring at 3 system prompt zones (predefined agents only): - Primacy: explicit instruction after Safety section - Middle: USER_PREDEFINED.md owner authority framing - Recency: persona reminder reinforcement |
||
|
viettranx
|
e327a880d4 |
feat(agent): improve system prompt structure for better LLM adherence
- Move SOUL.md + IDENTITY.md to primacy zone (top of prompt) with recency reinforcement at bottom to prevent persona drift in long chats - Separate MCP tools into dedicated section with real descriptions (truncated to 200 chars) instead of generic "(custom tool)" - Add MCP tool priority instruction: prefer MCP over core tools - Raise MCP inline threshold from 30 to 40 tools - Add knowledge_graph_search to Memory Recall section (conditional) - Add recency reminders for memory_search and knowledge_graph_search - Add knowledge_graph_search to coreToolSummaries |
||
|
viettranx
|
31ba182b40 |
feat(zalo): strip markdown from outbound messages for clean plain text
Zalo API does not support any markup rendering. LLM output containing markdown artifacts (**bold**, `code`, headers, etc.) was sent as-is, making messages hard to read. Add StripMarkdown() to convert markdown to clean plain text, and inject a system prompt hint instructing the model to output plain text on Zalo channels. |
||
|
viettranx
|
01e40a92b0 |
feat(mcp): add dynamic tool search and shared connection pool
MCP tool search mode: when an agent has >30 MCP tools, tools are deferred and a single mcp_tool_search meta-tool is registered instead. Uses BM25 index for keyword search, activating matched tools on demand. Shared connection pool: introduces Pool that maintains one physical connection per MCP server name, shared across all agents via refcount. Eliminates N×M duplicate connections (N agents × M servers). |
||
|
Viet Tran
|
6895e369f6 |
refactor: remove standalone mode, consolidate to managed-only (PostgreSQL) (#70)
- Remove standalone mode code: file-based stores, standalone gateway, heartbeat service, SQLite memory, standalone docker-compose - Rename docker-compose.managed.yml → docker-compose.postgres.yml - Clean up ~130 Go comments referencing "managed mode" qualifier - Simplify docker-compose.yml env vars (providers/channels via web UI) - Update .env.example to essential vars only (token + encryption key) - Add setup wizard UI (provider → agent → channel bootstrap flow) - Add logs.tail WebSocket handler for live log streaming - Add cursor-pointer to interactive UI components - Clean up config page (remove standalone-only sections) - Update README and docs for managed-only architecture |
||
|
viettranxandClaude Opus 4.6
|
d49596a805 |
feat: Add USER_PREDEFINED.md for predefined agents with token count sidebar
Add shared agent-level USER_PREDEFINED.md file for predefined agents to define baseline user-handling rules (owner info, audience, language, communication norms) that apply to ALL users. Individual USER.md per-user supplements but never overrides. - Seed USER_PREDEFINED.md template in SeedToStore for new predefined agents - Backfill existing agents via ensureUserPredefined in summon/regenerate flows - AI optionally generates/updates the file when description mentions people/user context - Add to context file interceptor, RPC allowlist, and system prompt injection - Update summoning modal with optional file progress tracking - Show estimated token count (Unicode-aware) instead of bytes in file sidebar Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |
||
|
viettranxandClaude Opus 4.6
|
5664135c8a |
enhance: channel-aware identity line, remove model leak from system prompt
Remove hardcoded "personal assistant running inside GoClaw" identity. Replace with channel+peer-aware context: "running in Telegram (a group chat)". Remove model name from Runtime section to prevent leaking provider info. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |
||
|
viettranx
|
85a6379e8c | feat: Introduce a dedicated events page by relocating and restructuring event display components, and enhance agent system prompt and sanitization logic. | ||
|
viettranxandClaude Opus 4.6
|
0e75c21e55 |
feat: overhaul team delegation, Telegram resilience, and artifact forwarding
Team delegation: - Unify spawn/subagent/delegate into single spawn tool - Sibling-aware announce suppression with artifact accumulation - Fix auto-complete race (isLastDelegation guard) - Add team tasks list limit (20) with search guidance - Multi-round orchestration patterns in TEAM.md - Communication guidance for initial vs follow-up delegations Telegram resilience: - Add retrySend wrapper (3 attempts, escalating delay) for network errors - Fix HTML fallback: strip tags + unescape entities instead of showing raw HTML - Pre-process HTML tags in LLM output to markdown before conversion pipeline - Skip caption truncation entirely when > 1024 bytes, send text separately - Auto-send large images (>5MB) as documents to avoid compression Artifact forwarding: - Fix missing ContentType on forwarded media (mimeFromExt for result.Media/ForwardMedia) - Add deliver parameter to write_file for file attachment delivery - Extend mimeFromExt with document MIME types UI: fix regenerate dialog overflow, improve task list layout, delegation detail view Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |
||
|
viettranxandClaude Opus 4.6
|
42263e5cc5 |
feat: Add tool loop detection, negative context injection, and fix Docker workspace permissions
- Add tool loop detection (toolloop.go): tracks repeated no-progress tool calls using SHA256 hashing of args+results. Warning at 5 identical calls, force stop at 10. Prevents Gemini models from burning tokens in infinite loops. - Inject AVAILABILITY.md negative context when agent has no team/delegation targets, so models don't waste iterations probing unavailable capabilities. - Fix Dockerfile: create /app/.goclaw directory so Docker volume initializes with correct goclaw:goclaw ownership instead of root:root. - Update collapseToolCallsWithoutSig comments for clarity. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |
||
|
viettranx
|
b365ef5494 | feat: Modularize Telegram commands, introduce new scheduler components, and enhance agent management and Feishu integration. |