Skip to content

♻️ refactor(agent-signal): restore 3 mode-specific self-iteration agent slugs#15202

Merged
arvinxx merged 1 commit into
canaryfrom
feat/agent-signal-restore-3-slugs
Jun 1, 2026
Merged

♻️ refactor(agent-signal): restore 3 mode-specific self-iteration agent slugs#15202
arvinxx merged 1 commit into
canaryfrom
feat/agent-signal-restore-3-slugs

Conversation

@arvinxx

@arvinxx arvinxx commented May 25, 2026

Copy link
Copy Markdown
Member

💻 Change Type

  • ♻️ refactor

🔗 Related Issue

Part of LOBE-9434. Supersedes the architectural direction of #15116 / #15187 / #15192 (the latter two closed; see those PRs for context).

🔀 Description of Change

The Phase 1 consolidation into a single self-iteration slug (#15187, inheriting commit 627f899 from the closed #15116) conflated three distinct background flows that genuinely have:

  • Independent receipt tables and idempotency Redis namespaces (signal:sfi:op:* vs signal:review:op:* vs signal:sr:*)
  • Different preflight / brief projection paths
  • Different audit pipelines (three */server.ts files, each ~400 lines of mode-specific adapter wiring)

one identifier = one behavior becomes a load-bearing contract once these agents need to be routed through standard execAgent plugin lookup (the goal of LOBE-9434). The consolidation worked only because legacy executeSelfIteration bypasses plugin lookup by manually constructing AgentState.operationToolSet; the same trick can't survive a move to execAgent.

This PR restores the 3 mode-specific slugs so each agent declares its own tool surface:

slug future plugin identifier
nightly-review agent-signal-review
self-reflection agent-signal-reflection
self-feedback-intent agent-signal-feedback-intent

Changes:

  • BUILTIN_AGENT_SLUGS swaps selfIteration for the 3 mode-specific slugs
  • 3 agent definitions replace the unified SELF_ITERATION agent
  • SELF_ITERATION_AGENT_SLUGS set expanded to all three (used by shouldSuppressSignal and completionPolicy)
  • completionPolicy dispatches on slug membership (not equality), forwards the resolved agentId to the callback so mode-specific bookkeeping can route from it
  • CompletionCallbackParams.agentId typed as BuiltinAgentSlug (was string)

Plugin arrays reference future identifiers (agent-signal-review etc.) but those tool packages are not yet registered. Invoking any of these agents today runs the LLM with no tools — dormant by design. Tool-package implementation follows in a separate PR.

🧪 How to Test

  • Tested locally — bun run type-check clean for everything this PR touches (the only remaining error is pre-existing in ChatInput/InputEditor/index.tsx, unrelated)
  • Updated tests:
    • completionPolicy.test.tsit.each over all 3 slugs to verify each triggers the callback
    • suppressSignal.test.tsit.each over all 3 slugs to verify each suppresses signal
  • Broader sanity sweep — 503 tests across 74 files in packages/builtin-agents and src/server/services/agentSignal all pass
bunx vitest run --silent='passed-only' \
  'completionPolicy.test.ts' 'suppressSignal.test.ts' 'finalStateExtractor.test.ts'

📝 Additional Information

No behavior change for existing callers — none invoke these slugs today (legacy executeSelfIteration still serves all production paths). The 3 new agents become non-dormant only after the follow-up tool-registration PR.

Why this is a refactor, not a feature: PR #15187 (Phase 1) merged a dormant SELF_ITERATION agent that had no real callers. This PR rewrites that dormant code into 3 mode-specific dormant agents. The wire format / behavior contract for any future caller is now aligned with how the existing per-mode handlers (feedback/server.ts, review/server.ts, reflection/server.ts) already think about modes.

Next: a follow-up PR will register 3 builtin tool packages (@lobechat/builtin-tool-agent-signal-{review,reflection,feedback-intent}) with shared scaffolding (tools/shared.ts's createToolSet, runWriteTool, schemas) extracted to a shared module — PR #14699's dedup value preserved.

Cloud impact: none.

…nt slugs

The Phase 1 consolidation into a single `self-iteration` slug (PR #15187,
inheriting commit 627f899 from the closed #15116) conflated three
distinct background flows that have:

- Independent receipt tables and idempotency Redis namespaces
- Different preflight / brief projection paths
- Different audit pipelines

`one identifier = one behavior` is a load-bearing contract once these
agents are routed through the standard execAgent plugin lookup. Restore
the 3 mode-specific slugs so each agent declares its own tool surface:

| slug                    | future plugin identifier        |
| ----------------------- | ------------------------------- |
| `nightly-review`        | `agent-signal-review`           |
| `self-reflection`       | `agent-signal-reflection`       |
| `self-feedback-intent`  | `agent-signal-feedback-intent`  |

`SELF_ITERATION_AGENT_SLUGS` now contains all three; `completionPolicy`
dispatches on slug membership rather than equality; callback receives
the resolved `agentId` so mode-specific bookkeeping can route from it.

Plugin arrays reference the future identifiers but the tool packages
are not yet registered — invoking any of these agents today runs the
LLM with no tools (dormant by design). Tool-package registration
follows in a separate PR.

No behavior change for existing callers (none invoke these slugs yet).
@vercel

vercel Bot commented May 25, 2026

Copy link
Copy Markdown

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
lobehub Ready Ready Preview, Comment May 25, 2026 9:53am

Request Review

@sourcery-ai sourcery-ai Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sorry @arvinxx, you have reached your weekly rate limit of 500000 diff characters.

Please try again later or upgrade to continue using Sourcery

@dosubot dosubot Bot added the size:L This PR changes 100-499 lines, ignoring generated files. label May 25, 2026
@codecov

codecov Bot commented May 25, 2026

Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 70.91%. Comparing base (3027550) to head (56b57eb).
⚠️ Report is 1 commits behind head on canary.

Additional details and impacted files
@@           Coverage Diff            @@
##           canary   #15202    +/-   ##
========================================
  Coverage   70.91%   70.91%            
========================================
  Files        3153     3153            
  Lines      314360   314360            
  Branches    28585    27668   -917     
========================================
  Hits       222933   222933            
  Misses      91259    91259            
  Partials      168      168            
Flag Coverage Δ
app 61.78% <100.00%> (ø)
database 92.20% <ø> (ø)
packages/agent-runtime 80.48% <ø> (ø)
packages/builtin-tool-lobe-agent 19.87% <ø> (ø)
packages/context-engine 84.13% <ø> (ø)
packages/conversation-flow 91.28% <ø> (ø)
packages/file-loaders 87.89% <ø> (ø)
packages/memory-user-memory 74.99% <ø> (ø)
packages/model-bank 99.99% <ø> (ø)
packages/model-runtime 83.89% <ø> (ø)
packages/prompts 72.60% <ø> (ø)
packages/python-interpreter 92.90% <ø> (ø)
packages/ssrf-safe-fetch 0.00% <ø> (ø)
packages/types 35.07% <ø> (ø)
packages/utils 88.47% <ø> (ø)
packages/web-crawler 88.08% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

Components Coverage Δ
Store 68.02% <ø> (ø)
Services 54.65% <ø> (ø)
Server 72.16% <100.00%> (ø)
Libs 56.77% <ø> (ø)
Utils 85.96% <ø> (ø)
🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
  • 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

@arvinxx arvinxx changed the title ♻️ refactor(agent-signal): restore 3 mode-specific self-iteration agent slugs [LOBE-9434] ♻️ refactor(agent-signal): restore 3 mode-specific self-iteration agent slugs May 31, 2026
@arvinxx arvinxx merged commit e0ead38 into canary Jun 1, 2026
40 checks passed
@arvinxx arvinxx deleted the feat/agent-signal-restore-3-slugs branch June 1, 2026 02:03
arvinxx added a commit that referenced this pull request Jun 4, 2026
# 🚀 LobeHub Release (20260604)

**Release Date:** June 4, 2026  
**Since v2.2.1:** 88 merged PRs · 11 contributors

> This week brings Execution Devices out of the lab — run agents and
Claude Code on any configured local or remote machine — alongside Claude
Opus 4.8, token-usage analytics, and Page sharing.

---

## ✨ Highlights

- **Execution Devices** — Pick where an agent runs. Desktop and CLI
devices auto-register with a stable machine ID, route through the
gateway by channel, and surface a device switcher in the chat input. Run
remote Claude Code on a configured device, with a recent-directory
picker you can drag to reorder. (#15300, #15315, #15322, #15343, #15351,
#15371)
- **Claude Opus 4.8** — Day-one support for Anthropic's latest model.
(#15314)
- **Token-usage analytics** — A new token-usage mode on the activity
heatmap, backed by a denormalized topic usage/cost rollup so totals stay
accurate without recomputing from messages. (#15365, #15417, #15425)
- **Page sharing** — Share a Page through a dedicated document share
flow, plus new Workspace and Agent share tables. (#15309, #15439)
- **Self-iteration agents** — Agent Signal's execAgent migration lands a
server-runtime bridge, async memory writer, and a registered
self-iteration tool package, with a CLI trigger command for testing.
(#15360, #15364, #15392)
- **Knowledge search** — BM25 search now extends to file-backed
documents, and the portal ships an editable CodeMirror viewer for local
files with document highlighting. (#15247, #15298)

---

## 🏗️ Core Agent & Architecture

### Agent Signal & Runtime

- **execAgent migration** — Server-runtime bridge, completion
projection, async memory writer, and removal of the legacy
`executeSelfIteration` path. (#15392)
- Registered the self-iteration builtin tool package and restored the
three mode-specific self-iteration agent slugs. (#15202, #15364)
- Added a CLI trigger command with a golden-snapshot fixture for Agent
Signal. (#15360)
- **Skill priority** — Agent Builder now emits a skill-priority
instruction with matching server runtime. (#15409)
- Retry empty LLM completions instead of silently finishing the turn.
(#15355)
- Classify topic/agent/session foreign-key violations as
`ConversationParentMissing` for clearer recovery. (#15408)
- Persist canonical nested usage/performance on assistant messages, and
re-link orphan tool messages at the raw bucket write boundary. (#15359,
#15438)
- Guard `createAgent` against LLM double-encoded array fields. (#15381)

---

## 🖥️ Execution Devices & Gateway

- Auto-register desktop and CLI devices with a stable machine ID, and
add the `@lobechat/device-identity` package. (#15300, #15321)
- New Devices settings page behind the Execution Device Switcher lab,
with a device switcher shown for all agents in the chat input. (#15315,
#15371)
- `connectionId` + channel routing across the gateway client and device
list; preset the local device on the first LLM request for the 本机
target. (#15322, #15435)
- Run remote Claude Code on a configured device, with drag-to-reorder
recent-directory management and client renders for device tool results.
(#15343, #15351, #15437)
- Preserve content and state across gateway tool calls, and prevent
duplicate streaming from stale reconnects. (#15114, #15354)

---

## 🖥️ CLI & Desktop

- Preserve content/state for connect local file and shell tools; render
the `runCommand` tool result card. (#15441, #15442)
- New `lh topic view` command; CLI now auto-registers its device on
login, matching desktop. (#15340, #15377)
- Resolve CLI tools from the shell `PATH`, and clarify local command
session handling. (#15368, #15389)
- Relocate visual-ref helpers to `@lobechat/const` to fix a renderer
crash; upload `.blockmap` files to S3 for differential updates. (#15326,
#15369)
- Fix a market OAuth expiry that triggered the wrong re-login modal, and
kill dev child processes on parent shutdown. (#15246, #15290)

---

## 🗂️ Pages, Library & Knowledge

- Document share flow with business slot stubs, plus Workspace and Agent
share tables. (#15309, #15439)
- Export Agent profiles as Markdown, preserving an empty agent prompt on
export. (#15312, #15316)
- Editable CodeMirror viewer for local files with document highlighting;
BM25 search extended to file-backed documents. (#15247, #15298)
- Default new Agent-doc files to `.md` and preserve IME composition;
refresh folder data on slug switch and dedupe breadcrumb fetches.
(#15335, #15427)

---

## 💬 Chat & User Experience

- Group-by-status mode for the Topic sidebar; dropped the legacy
session→agentId compatibility path from Topic queries. (#15366, #15378)
- Restore editor focus after the file picker closes, and close the skill
dropdown before navigating to settings. (#15391, #15394)
- Strip markdown tokens from fallback Topic titles; keep an open
ActionBar popup when hovering another message. (#15303, #15372)
- Stabilize home starter loading and stop transliterating model names in
the home starter; show artifact source while streaming. (#15310, #15324,
#15386)
- Group the sidebar spacer with recents and agents. (#15373)

---

## 📊 Analytics, Tasks & Notifications

- Token-usage mode on the activity heatmap, backed by a denormalized
topic usage/cost rollup. (#15365, #15417, #15425)
- Push: new `PushChannel`, receipt cron, and `pushToken` tRPC API.
(#15233)
- Tasks now support file and image attachments. (#15141)

---

## 🧩 Models & Providers

- Support Claude Opus 4.8 and configurable model routing with starters.
(#15314, #15384)
- MiniMax M3: new model entry and an Anthropic video runtime. (#15380,
#15403)
- Add `intern-s2-preview` with `thinking_mode`, and `step-3.7-flash`
support. (#15308, #15317)
- Block disabling the official provider; fix default provider setup in
business mode. (#15379, #15382)

---

## 🎨 UI & Modals

- Migrate modals to `@lobehub/ui/base-ui` (LOBE-9711 + eval batch),
including the create-custom-model and feedback/changelog modals.
(#15401, #15416)
- Restructure confirmModal title and content across deletion flows;
polish the service-model form and migrate its Switch to base-ui.
(#15426, #15440)
- Wrap the BlueBubbles bridge config into a connection card; update
`@lobehub/ui` to v5.15.5. (#15325, #15342)

---

## 🔒 Reliability

- Replace hardcoded `session_context` values with template variables in
credentials. (#15352)
- Point `CHANGELOG_URL` to `/changelog`. (#15428)

---

## 👥 Contributors

Huge thanks to **11 contributors** who shipped **88 merged PRs** this
cycle.

@hezhijie0327 · @qybaihe · @sxjeru · @arvinxx · @Innei · @tjx666 ·
@lijian · @sudongyuer · @cy948 · @rivertwilight · @AmAzing129

Plus @lobehubbot and renovate[bot] for maintenance.

---

**Full Changelog**: v2.2.1...release/weekly-20260604
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size:L This PR changes 100-499 lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant