Restructures each held item into Action -> Result -> Run log:
- Action: a clear statement of what approving does (write artifact + N child tasks),
with a destructive warning where relevant.
- Result: the editable proposed artifact + child tasks (with the edit diff).
- Run log: lazily fetches the AgentRun and shows latency, the agent/autonomy, skills
applied, available + actually-called tools (with ok/failed), memory hits, product-
identity inclusion, and collapsible raw model output + assembled prompt.
Enriches the assembler run endpoint (Trace, ResultJson, LatencyMs, timestamps) so the
approver can see exactly how the agent reached its result before deciding.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Generalizes working memory to a scope: ITeamMemory becomes IWorkingMemory with a
MemoryScope (Team | Product); MemoryEntry's TeamId becomes ScopeType+ScopeId (data-
preserving rename migration). On approval, Governance writes the decision/correction
at PRODUCT scope when the team belongs to a product (resolved via IBoardStats), so it
is shared by every agent across the product's teams — else at team scope. The assembler
recalls product memory (shared) plus team memory (local), merged by relevance, under a
"# Shared memory" section.
This is the other half of product-centric agents: a decision approved on one team now
informs every agent on the product, not just that team.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Adds Product.Identity (a PRODUCT.md brief) and threads it through the run context:
AgentRunContextProvider resolves the run's team -> product and carries ProductId +
ProductIdentity on AgentRunContext; PromptAssembler injects a "# Product" section
(framed as shared, data-not-instructions) ahead of the agent's persona. Adds
GET/PUT /products/{id}/identity (read = view-board, set = owner) and the EF column.
This makes the product, not just the team, the unit of shared context — every agent
on a product sees the same identity. Product-scoped working memory follows next.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Each AI agent now has an expressive Companion face (AgentFace) whose animation
maps to its real AgentRun state — idle, thinking (queued), working (running),
review (held), done, failed — so a glance at the board or org chart reads as live
status, the same way the seat-state triad reads human/open/AI. Pure CSS keyframes
(no animation dependency), em-scaled across four sizes, per-agent hue derived
deterministically in the indigo band, reduced-motion respected.
Adds a per-team agent-activity read endpoint (latest run status per agent) and a
self-contained polling hook (useAgentActivity) that merges run activity with
governance holds. Wired into the board assignee chips and the org chart (a custom
React Flow seat node with hidden handles so edges still connect).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Autonomous agents with MCP tools now run a bounded tool-use loop: the model may
call tools (executed via the gateway, results fed back) until it returns a final
answer. Gated/DraftOnly agents get the tool catalog as data but never auto-call —
a human-in-the-loop agent never autonomously reaches an external tool.
Extends IModelClient with tool definitions and a tool-use conversation, adds the
OpenAI-compatible tool serialization/parsing plus a deterministic "tooluse" stub
client, and records every tool call in the run trace.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Reusable agent definitions authored as AGENTS.md (YAML frontmatter + a Markdown body that becomes
the agent's operating guide). Mirrors the skill library, including its review hardening.
- AgentProfile entity (OrgBoard): org-scoped + versioned by (OrganizationId, ProfileKey, Version),
NULLS NOT DISTINCT unique index; Origin Builtin|Authored|Installed; ProfileVisibility +
ProfileStatus with the Public⟹Published invariant enforced in Apply()/SetVisibility(). AGENTS.md
parser (YamlDotNet). AgentProfileWriter is the single upsert path (insert-only mode for install).
- Free builtins: AgentProfileSeeder seeds Aria (PO), Quill (QA), Edison (backend) on startup via a
new IStartupSeeder + SeederRunner (runs after migrations). Idempotent, null-org, visible to all.
- Endpoints (/api/orgboard/agent-profiles): upload, list (resolvable-winner order), get versions,
publish/unpublish, fork, marketplace (per-(key,version) AlreadyInLibrary), install (insert-only →
clean 409, no clobber). ConfigureAgents to author/manage; ViewBoard to browse; audited.
- Persona: Agent gains Persona; ConfigureAgent stores it; AgentRunContext carries it; PromptAssembler
injects it as "# Operating guide" (data, not instructions) so an applied profile shapes the run.
- Client: Agent profiles page (library + marketplace tabs, upload editor, publish/unlist/fork/install),
routed + in the nav.
Verified: ArchitectureTests 8/8, IntegrationTests 55/55 (new AgentProfilesTests: builtins seeded,
upload + validation, publish, cross-org marketplace list→install→private copy, duplicate 409, per-
version flag, Member 403; persona renders as the operating guide), client build green.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Agents can now use Model Context Protocol servers. End to end:
- SharedKernel seam IMcpGateway (ListToolsAsync / CallToolAsync) + McpToolDescriptor / McpToolResult,
so the Assembler discovers and can invoke MCP tools without referencing Integrations' tables.
- Integrations: McpServerConfig (org-scoped, owner-only; auth headers AES-GCM encrypted, never
returned — only their names) + AddMcpServers migration. McpClient: a dependency-free Streamable-HTTP
JSON-RPC 2.0 client (initialize → notifications/initialized → tools/list / tools/call), carrying the
Mcp-Session-Id and parsing both application/json and text/event-stream replies. McpGateway resolves
an org's servers, decrypts headers server-side, and is best-effort: an unreachable server is logged
and skipped, never failing the run. CRUD + connectivity-test endpoints (create/test/delete owner-only
via ManageApiKeys; list via ConfigureAgents to bind).
- OrgBoard: Agent gains McpServerIds (uuid[]; migration backfills existing agents to empty) flowing
through ConfigureAgent + AgentRunContext.
- Assembler: AgentRunExecutor lists the agent's MCP tools (best-effort) and PromptAssembler renders a
"# Tools (MCP)" catalog — labelled as data, never instructions — and records it in the run trace.
- Client: SeatsPage gains an MCP servers card (add/test/delete, encrypted auth header) and a per-agent
MCP server multi-select; api client gains del().
Note: discovery + the governed call gateway are in place now; the autonomous model-driven tool-call
loop (model emits tool_calls → gated execution → feedback) needs a tool-calling model client and is
the next increment — the stub model can't drive it.
Verified: ArchitectureTests 8/8, IntegrationTests 53/53 (McpClientTests: JSON-RPC handshake/session,
json + SSE; McpServerRegistryTests: owner-only, encrypted-header-never-returned, graceful test,
Member 403; PromptAssemblerMcpTests: catalog + trace, omitted when empty), client build green.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
ISkillCatalog.GetByKeysAsync now takes the org id and resolves each key within that org's namespace
only — the org's own published skill, else a shared builtin (null org), never another org's. Org-owned
is preferred over the builtin; only Published (golden-tested) skills are injected; the resolved
skill@version is recorded in the prompt heading and run trace. AgentRunExecutor threads
context.OrganizationId. SeatsPage now loads the org library (builtins + authored + installed), dedupes
to one entry per key, and flags drafts (won't run until published).
Verified: ArchitectureTests 8/8, IntegrationTests 48/48 (new SkillRunScopingTests: a run assembles the
org's own skill over the builtin of the same key, and another org's same-key skill never leaks in),
client build green.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Working memory (Memory module's first real code):
- MemoryEntry (schema "memory", vector(384), InitialMemory migration); TeamMemory implements
the SharedKernel ITeamMemory seam (embed-and-store on write, cosine recall on read);
GET /api/memory/search. HashingTextEmbedder promoted to SharedKernel (pure, deterministic;
swapped for ONNX/BYOK embedders later behind ITextEmbedder).
- Written on approval: Governance's approve stores an Approval/Correction entry per decision.
- Read at assembly: the executor recalls the team's top-3 relevant entries; the prompt gains
a "# Team memory" section (treated as data, not instructions).
The single V1 event trigger:
- IAgentDispatcher (SharedKernel) implemented by Assembler's AgentRunDispatcher (shared by
the API and triggers). OrgBoard's QaHandoffTrigger: a task hitting done creates a QA task
(provenance parent, assigned to the QA agent) and dispatches a run for the team's QA AI
seat. Guardrails: Test/Review tasks never re-trigger (no self-cascade) and a task hands
off at most once. Audited as handoff.triggered.
Analytics — the V1 verdict view:
- IBoardStats (SharedKernel) implemented by OrgBoard; GET /api/governance/analytics returns
approval rate, avg edit distance, per-agent metrics + edit-distance trend, tasks done.
- UI: /analytics — stat cards, per-agent table, recharts edit-distance trend per agent.
Verified: build green; ArchitectureTests 8/8; IntegrationTests 42/42 incl. the M6 acceptance
end to end — a dev marks a story done → Quill wakes via the handoff (QA task with provenance,
assigned to the agent) → drafts a test plan that waits in review → approve records the second
agent's edit distance → analytics show approval rate 100%, avg edit distance > 0, and trends
for BOTH Aria and Quill; memory written on Aria's corrected approval is recalled into her next
prompt; the guardrails hold. Client build green.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
SharedKernel:
- ActionRisk (risk lives on the action) + GatePolicy (the pure autonomy x risk matrix:
Read never holds, Draft/Publish hold unless Autonomous, Destructive ALWAYS holds).
- IActionGate (AgentActionProposal -> execute|hold) and IBoardWriter.AttachArtifactAsync.
Governance:
- ReviewItem (held action: artifact, child titles, trace, decision, edit distance) in a new
review_items table (AddReviewItems migration).
- ActionGate: hold -> ReviewItem + "action.held" audit; autonomous -> execute + audit.
- HeldActionExecutor: writes the artifact onto the task and creates the child tasks via
IBoardWriter (implemented by OrgBoard — no cross-module table access).
- Review inbox API: GET /api/governance/reviews (scope-filtered to where the caller may
approve), POST /reviews/{id}/approve (optional edited content/children -> normalized
edit distance recorded — the north-star metric), POST /reviews/{id}/sendback. Deciding
twice is 409; Members are 403.
Assembler:
- OutputParser (numbered-list child titles, conservative) and the executor now hands every
completed run's proposal to the gate.
OrgBoard: WorkItem.AttachArtifact + BoardWriter.AttachArtifactAsync.
Verified: build green; ArchitectureTests 8/8; IntegrationTests 41/41 incl. the full M5
acceptance — Aria (gated) proposes a spec, it waits in the inbox with its trace, a Member is
403'd, the owner edits-and-approves, the spec + four child stories land on the board, edit
distance > 0 is recorded and audited; Quill (autonomous) executes straight to the board;
destructive holds even for an autonomous seat and can be sent back. Plus the GatePolicy matrix.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
SharedKernel contracts (so Assembler stays decoupled): IAgentRunContextProvider (agent +
task) and ISkillCatalog (skill prompts by key). Implemented by OrgBoard (AgentRunContextProvider)
and Skills (SkillCatalog).
Assembler:
- PromptAssembler builds house-style + identity + the agent's skill bodies + the task, and
derives the primary action + risk from the agent's first skill. RAG/working-memory join at M6.
- AgentRunExecutor (real): resolve context + skills → assemble → resolve BYOK config (with
fallback) → call IModelClient → parse into action + risk → capture all on the AgentRun.
Verified: build green; ArchitectureTests 8/8; IntegrationTests 29/29 — incl. the M4 acceptance:
assigning a Spec task to Aria (PO, gated, stub BYOK) yields a Completed run with the assembled
prompt (skill body + task title), action "write-spec", risk "Draft", and model output. Nothing
executes — the gate is M5.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
SharedKernel: IWorkerModule seam (RegisterWorker runs in the worker host only).
Bootstrap: AddTeamUpWorkerServices; the worker host now wires it.
Assembler module (schema "assembler", InitialAssembler migration):
- Job (Pending→Processing→Done/Failed) + AgentRun (Queued→Running→Completed/Failed) entities.
- JobQueue: enqueue + ClaimNextAsync using `FOR UPDATE SKIP LOCKED` in a transaction.
- AgentRunExecutor (Increment-1 placeholder — real assemble/model/parse lands in Increment 2).
- JobProcessor BackgroundService drains the queue on the worker host (web off the model path).
- POST /api/assembler/runs enqueues a run; GET /api/assembler/runs/{id} reads it.
Verified: build green; ArchitectureTests 8/8 (Assembler references only SharedKernel);
IntegrationTests 28/28 incl. enqueue→claim(SKIP LOCKED)→process→Completed.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Stand up the modular-monolith skeleton per docs/V1_BUILD_PLAN.md: one .NET 10
solution with web + worker hosts sharing seven interface-bounded module projects,
PostgreSQL 17 + pgvector via EF Core 10, a React 19 + Vite SPA built into wwwroot,
and Docker Compose for one-command local dev. Skeleton only — no feature code.
Architecture
- One project per module (OrgBoard, Identity, Skills, Assembler, Governance,
Memory, Integrations); each is its own assembly so non-public types (entities,
DbContext) are invisible across modules at compile time.
- TeamUp.Bootstrap is the only library that references all modules; both hosts
reference only Bootstrap. SharedKernel/Infrastructure never reference modules.
- IModule seam: Register(...) runs in both hosts; MapEndpoints(...) only in web.
- PlatformDbContext owns the pgvector extension + the seven module schemas
(InitialPlatform migration); MigrationRunner applies it then any module context.
- One image, two roles selected by RUN_MODE at the Docker entrypoint.
Verified
- dotnet build green (nullable + warnings-as-errors).
- ArchitectureTests 8/8 — reflection-based boundary rules (no module -> module,
-> Infrastructure, -> Bootstrap, or -> host references).
- IntegrationTests 10/10 — Testcontainers boots the host against real pgvector:
migration applies, vector extension + 7 schemas exist, /health 200, every
/api/<module>/ping 200, /openapi/v1.json served.
- client builds clean (Vite 6 — pinned for Node 22.3.0; Vite 8 needs Node >=22.12).
Packages and base images route through the Nexus mirror (mirror.soroushasadi.com),
reachable from Iran when nuget.org / Docker Hub / MCR are not. CI is intentionally
deferred to a later session.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
soroush.asadi