Add Makefile with start target for HTTP serve mode

Provides `make start` to run the llm-connect server via uv, with optional
LLM_CONNECT_* overrides and standard dev targets for install, test, lint,
and typecheck.

.claude/rules/first-session.md

@@ -1,11 +1,11 @@
 ## First Session Protocol
 
-Triggered when `get_domain_summary("custodian")` shows **no workstreams**.
+Triggered when `get_domain_summary("agents")` shows **no workstreams**.
 The project is registered but work has not yet been structured.
 
 **Step 1 — Read, don't write**
-- `~/the-custodian/canon/projects/custodian/project_charter_v0.1.md` — purpose, scope
-- `~/the-custodian/canon/projects/custodian/roadmap_v0.1.md` — planned phases
+- `~/the-custodian/canon/projects/agents/project_charter_v0.1.md` — purpose, scope
+- `~/the-custodian/canon/projects/agents/roadmap_v0.1.md` — planned phases
 - Scan repo root: README, directory structure, existing code or docs
 
 **Step 2 — Survey in-progress work**
@@ -17,20 +17,20 @@ roadmap phase. **Wait for approval before creating.**
 
 **Step 4 — Create workplan file first, then DB record (ADR-001)**
 ```
-workplans/llm-connect-WP-NNNN-<slug>.md   ← write this first
+workplans/LLM-WP-NNNN-<slug>.md   ← write this first
 ```
 Then register in the hub:
 ```
-create_workstream(topic_id="cee7bedf-2b48-46ef-8601-006474f2ad7a", title="...", owner="...", description="...")
+create_workstream(topic_id="64418556-3206-457a-ba29-6884b5b12cf3", title="...", owner="...", description="...")
 create_task(workstream_id="<id>", title="...", priority="high|medium|low")
 ```
 
 **Step 5 — Record the setup**
 ```
 add_progress_event(
-    summary="First session: structured custodian into N workstreams, M tasks",
+    summary="First session: structured agents into N workstreams, M tasks",
     event_type="milestone",
-    topic_id="cee7bedf-2b48-46ef-8601-006474f2ad7a",
+    topic_id="64418556-3206-457a-ba29-6884b5b12cf3",
     detail={"workstreams": [...], "tasks_created": M}
 )
 ```

.claude/rules/repo-identity.md

@@ -1,5 +1,5 @@
 **Purpose:** Multi-provider LLM client library — unified adapter interface for OpenAI, Claude, Gemini, OpenRouter with embedding support, token estimation, and TOML-based config.
 
-**Domain:** custodian
+**Domain:** agents
 **Repo slug:** llm-connect
-**Topic ID:** cee7bedf-2b48-46ef-8601-006474f2ad7a
+**Topic ID:** 64418556-3206-457a-ba29-6884b5b12cf3

.claude/rules/session-protocol.md

@@ -1,6 +1,7 @@
 ## Session Protocol
 
-State Hub: http://127.0.0.1:8000
+Dev Hub (State Hub API): http://127.0.0.1:8000
+MCP server name in `~/.claude.json`: `dev-hub`
 
 **Step 1 — Orient**
 
@@ -10,7 +11,7 @@ cat .custodian-brief.md
 ```
 Then call the MCP tool for richer cross-domain context when MCP tools are exposed:
 ```
-get_domain_summary("custodian")
+get_domain_summary("agents")
 ```
 If MCP tools are unavailable in the current agent session, use the REST API:
 ```bash
@@ -39,11 +40,11 @@ curl -s -X PATCH "http://127.0.0.1:8000/messages/<id>/read" \
 ls workplans/
 ```
 For each file with `status: ready`, `active`, or `blocked`, note pending
-`todo`/`in_progress` tasks.
+`wait`/`todo`/`progress` tasks.
 
 **Step 4 — Present brief**
 
-1. **Active workstreams** for `custodian` — title, task counts, blocking decisions
+1. **Active workstreams** for `agents` — title, task counts, blocking decisions
 2. **Pending tasks** from `workplans/` + any `[repo:llm-connect]` hub tasks
 3. **Goal guidance** — if `goal_guidance` in summary:
    - `needs_workplan`: surface as top action — *"Repo goal '{title}' has no workplan yet"*
@@ -61,13 +62,13 @@ If no workstreams: follow First Session Protocol (`first-session.md`).
 **Session close:**
 With MCP tools:
 ```
-add_progress_event(summary="...", topic_id="cee7bedf-2b48-46ef-8601-006474f2ad7a", workstream_id="<uuid>")
+add_progress_event(summary="...", topic_id="64418556-3206-457a-ba29-6884b5b12cf3", workstream_id="<uuid>")
 ```
 Without MCP tools:
 ```bash
 curl -s -X POST http://127.0.0.1:8000/progress/ \
   -H "Content-Type: application/json" \
-  -d '{"topic_id":"cee7bedf-2b48-46ef-8601-006474f2ad7a","workstream_id":"<uuid>","event_type":"note","summary":"what changed","author":"codex"}'
+  -d '{"topic_id":"64418556-3206-457a-ba29-6884b5b12cf3","workstream_id":"<uuid>","event_type":"note","summary":"what changed","author":"codex"}'
 ```
 If workplan files were modified, ensure the local copy is up to date first:
 ```bash

.claude/rules/workplan-convention.md

@@ -1,7 +1,7 @@
 ## Workplan Convention (ADR-001)
 
-File location: `workplans/llm-connect-WP-NNNN-<slug>.md`
-ID prefix: `LLM-WP`
+File location: `workplans/LLM-WP-NNNN-<slug>.md`
+ID prefix: `LLM-WP-`
 
 Work items originate as files in this repo **before** being registered in the hub.
 
@@ -12,7 +12,7 @@ repo state, and `finished` when implementation is complete. `stalled` and
 `needs_review` are derived health labels, not stored statuses.
 
 Closed workplans may be moved to `workplans/archived/` with a completion-date
-prefix: `YYMMDD-llm-connect-WP-NNNN-<slug>.md`. The frontmatter id remains
+prefix: `YYMMDD-LLM-WP-NNNN-<slug>.md`. The frontmatter id remains
 unchanged; the prefix is only for quick visual reference.
 
 Small opportunistic tasks discovered during another session use **Ad Hoc Tasks**:
@@ -25,4 +25,16 @@ Ecosystem todos from other agents arrive as `[repo:llm-connect]` hub tasks —
 visible at session start. Pick one up by creating the workplan file, then registering
 the workstream.
 
+Task blocks use this shape:
+
+```task
+id: LLM-WP-NNNN-T01
+status: wait | todo | progress | done | cancel
+priority: high | medium | low
+state_hub_task_id: "<uuid>"         # written by fix-consistency — do not edit
+```
+
+Status progression is `todo` → `progress` → `done`; use `wait` for waiting or
+blocked work and `cancel` for stopped work.
+
 <!-- Ralph Loop rules and HEUREKA sequence: ~/.claude/CLAUDE.md — do not duplicate here -->

.custodian-brief.md

@@ -1,8 +1,8 @@
 <!-- custodian-brief: generated by fix-consistency — do not edit manually -->
 # Custodian Brief — llm-connect
 
-**Domain:** custodian  
-**Last synced:** 2026-06-19 11:51 UTC  
+**Domain:** infotech  
+**Last synced:** 2026-07-03 16:47 UTC  
 **State Hub:** http://127.0.0.1:8000 *(adjust if running on a remote machine)*
 
 ## Active Workstreams
@@ -13,6 +13,6 @@
 ## MCP Orientation (when available)
 
 If the state-hub MCP server is reachable, call:
-`get_domain_summary("custodian")`
+`get_domain_summary("infotech")`
 This provides richer cross-domain context.
 If the MCP call fails, use this file as your orientation source.

.repo-classification.yaml

@@ -0,0 +1,25 @@
+# Repo classification (Repo Classification Standard v1.0).
+
+repo_classification:
+  standard: Repo Classification Standard
+  version: '1.0'
+  classified_at: '2026-06-22'
+  classified_by: human
+  category: tooling
+  domain: agents
+  secondary_domains:
+  - infotech
+  capability_tags:
+  - orchestration
+  - model-routing
+  - configuration
+  - automation
+  business_stake:
+  - technology
+  - product
+  - automation
+  business_mechanics:
+  - operation
+  - adaptation
+  notes: Multi-provider LLM client library for Python (pluggable adapters / model routing).
+    Primary domain agents, infotech secondary.

AGENTS.md

@@ -4,9 +4,9 @@
 
 **Purpose:** Multi-provider LLM client library — unified adapter interface for OpenAI, Claude, Gemini, OpenRouter with embedding support, token estimation, and TOML-based config.
 
-**Domain:** custodian
+**Domain:** agents
 **Repo slug:** llm-connect
-**Topic ID:** `cee7bedf-2b48-46ef-8601-006474f2ad7a`
+**Topic ID:** `64418556-3206-457a-ba29-6884b5b12cf3`
 **Workplan prefix:** `LLM-WP-`
 
 ---
@@ -28,7 +28,7 @@ there is no MCP server for Codex agents.
 cat .custodian-brief.md
 
 # Active workstreams for this domain
-curl -s "http://127.0.0.1:8000/workstreams/?topic_id=cee7bedf-2b48-46ef-8601-006474f2ad7a&status=active" \
+curl -s "http://127.0.0.1:8000/workstreams/?topic_id=64418556-3206-457a-ba29-6884b5b12cf3&status=active" \
   | python3 -m json.tool
 
 # Check inbox
@@ -63,8 +63,8 @@ Omit `workstream_id` / `task_id` when not applicable.
 ```bash
 curl -s -X PATCH "http://127.0.0.1:8000/tasks/<task_id>" \
   -H "Content-Type: application/json" \
-  -d '{"status": "in_progress"}'
-# values: todo | in_progress | done | blocked
+  -d '{"status": "progress"}'
+# values: wait | todo | progress | done | cancel
 ```
 
 ### Flag a task for human review
@@ -83,7 +83,7 @@ curl -s -X PATCH "http://127.0.0.1:8000/tasks/<task_id>" \
 1. `cat .custodian-brief.md` — domain goal and open workstreams (offline-safe)
 2. Check inbox: `GET /messages/?to_agent=llm-connect&unread_only=true`; mark read
 3. Scan workplans: `ls workplans/` — note `status: ready`, `active`, or `blocked` files and open tasks
-4. Check blocked tasks: `GET /tasks/?needs_human=true`
+4. Check human-needed tasks: `GET /tasks/?needs_human=true`
 
 **During work:**
 - Update task statuses in workplan files as tasks progress
@@ -151,6 +151,11 @@ every repo's agent instructions because it is high-frequency, high-risk, and eas
 get wrong.
 
 **Canon:** `~/ops-warden/wiki/CredentialRouting.md` · catalog `~/ops-warden/registry/routing/catalog.yaml`
+
+<!-- REPO-AGENTS-EXTENSIONS -->
+<!-- Append repo-specific agent instructions below this marker.
+     The state-hub template sync preserves content after this line. -->
+
 ---
 
 ## Workplan Convention (ADR-001)
@@ -176,7 +181,7 @@ anything needing analysis, design, approval, dependencies, or multiple phases.
 id: LLM-WP-NNNN
 type: workplan
 title: "..."
-domain: custodian
+domain: agents
 repo: llm-connect
 status: proposed | ready | active | blocked | backlog | finished | archived
 owner: codex
@@ -198,7 +203,7 @@ derived health labels, not frontmatter statuses.
 
 ` ` `task
 id: LLM-WP-NNNN-T01
-status: todo | in_progress | done | blocked
+status: wait | todo | progress | done | cancel
 priority: high | medium | low
 state_hub_task_id: "<uuid>"         # written by fix-consistency — do not edit
 ` ` `
@@ -206,7 +211,7 @@ state_hub_task_id: "<uuid>"         # written by fix-consistency — do not edit
 Task description text.
 ```
 
-Status progression: `todo` → `in_progress` → `done` (or `blocked`)
+Status progression: `todo` → `progress` → `done`; use `wait` for waiting/blocked work and `cancel` for stopped work.
 
 To create a new workplan:
 1. Write the file following the format above

Makefile

@@ -0,0 +1,37 @@
+-include .env
+export
+
+.PHONY: install test lint typecheck start help
+
+UV ?= $(shell command -v uv 2>/dev/null || if [ -x "$$HOME/.local/bin/uv" ]; then printf "%s" "$$HOME/.local/bin/uv"; else printf "%s" "uv"; fi)
+
+LLM_CONNECT_HOST ?= 127.0.0.1
+LLM_CONNECT_PORT ?= 8080
+LLM_CONNECT_PROVIDER ?= mock
+LLM_CONNECT_MODEL ?=
+SERVER_ARGS ?=
+
+install:  ## Install dependencies (dev group)
+	$(UV) sync --group dev
+
+test:  ## Run test suite
+	$(UV) run pytest
+
+lint:  ## Run ruff linter
+	$(UV) run ruff check .
+
+typecheck:  ## Run mypy type checker
+	$(UV) run mypy llm_connect
+
+start:  ## Start llm-connect HTTP server (reads .env and LLM_CONNECT_* overrides)
+	$(UV) run python -m llm_connect.server \
+		--host $(LLM_CONNECT_HOST) \
+		--port $(LLM_CONNECT_PORT) \
+		--provider $(LLM_CONNECT_PROVIDER) \
+		$(if $(LLM_CONNECT_MODEL),--model $(LLM_CONNECT_MODEL),) \
+		$(SERVER_ARGS)
+
+help:  ## Show this help message
+	@grep -Eh '^[a-zA-Z_-]+:.*?##' $(MAKEFILE_LIST) | \
+		awk 'BEGIN {FS = ":.*?## "}; {printf "  \033[36m%-16s\033[0m %s\n", $$1, $$2}' | \
+		sort

deploy/k8s/activity-core-llm-connect/externalsecret.yaml

@@ -0,0 +1,21 @@
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: llm-connect-provider-secrets
+  namespace: activity-core
+  labels:
+    app.kubernetes.io/name: llm-connect
+    app.kubernetes.io/part-of: railiance-gitops
+spec:
+  refreshInterval: 1h
+  secretStoreRef:
+    kind: ClusterSecretStore
+    name: openbao-activity-core
+  target:
+    name: llm-connect-provider-secrets
+    creationPolicy: Owner
+  data:
+    - secretKey: OPENROUTER_API_KEY
+      remoteRef:
+        key: platform/workloads/activity-core/llm-connect/llm-connect-provider-secrets
+        property: OPENROUTER_API_KEY

deploy/k8s/activity-core-llm-connect/kustomization.yaml

@@ -5,3 +5,4 @@ resources:
   - deployment.yaml
   - service.yaml
   - networkpolicy.yaml
+  - externalsecret.yaml

registry/capabilities/capability.agents.llm-connector.md

@@ -0,0 +1,123 @@
+---
+id: capability.agents.llm-connector
+name: Pluggable LLM Adapter Library (llm-connect)
+summary: Provider-neutral Python/CLI LLM adapter library supporting OpenRouter, Gemini, OpenAI, and the
+  Claude Code CLI out of the box, with a clean abstract interface for adding new providers.
+owner: llm-connect
+status: draft
+domain: agents
+tags:
+- llm
+- adapter
+- provider-neutral
+maturity:
+  discovery:
+    current: D3
+    target: D5
+    confidence: medium
+    rationale: README documents a working quick-start (`create_adapter`, `RunConfig`, `execute_prompt`),
+      the supported provider list, and both local-editable and future-published install paths.
+  availability:
+    current: A2
+    target: A3
+    confidence: medium
+    rationale: Installable today via `pip install -e` (local) with a documented future `pip install llm-connect`
+      path once published; consumed today by sibling repos including `cya` (can-you-assist) and referenced
+      as the intended backend for reuse-surface's own `establish --discover`.
+external_evidence:
+  completeness:
+    level: C2
+    confidence: low
+    basis: scope_vs_intent_and_consumer_expectations
+    satisfied_expectations:
+    - four providers implemented (OpenRouter, Gemini, OpenAI, Claude Code CLI)
+    - abstract adapter interface for adding new providers
+    - already a named integration point for other repos (can-you-assist's LLMAdapter seam, reuse-surface's
+      establish --discover)
+    broken_expectations: []
+    out_of_scope_expectations: []
+  reliability:
+    level: R1
+    confidence: low
+    basis: consumer_quality_signals
+    known_reliability_risks:
+    - no llm-connect instance was running on this workstation during the REUSE-WP-0017 sweep, so establish
+      --discover fell back to manual authoring for this campaign
+discovery:
+  intent: Give Python and CLI consumers a single, provider-neutral way to call LLMs, decoupling agent/tool
+    code from any one vendor's SDK.
+  includes:
+  - provider-neutral adapter interface
+  - OpenRouter, Gemini, OpenAI, Claude Code CLI adapters
+  - RunConfig-based execution
+  excludes:
+  - hosting or credential custody for providers (routes to OpenBao/operator paths per credential-routing
+    conventions)
+  assumptions: []
+  use_cases: []
+  research_memos: []
+availability:
+  current_level: A2
+  target_level: A3
+  current_artifacts:
+  - Python package (`llm_connect`)
+  target_artifacts: []
+  consumption_modes:
+  - library import
+  - cli
+relations:
+  depends_on: []
+  supports: []
+  related_to: []
+evidence:
+  documentation:
+  - README.md
+  tests:
+  - tests/
+  consumer_feedback: []
+  bug_reports: []
+  incidents: []
+consumer_guidance:
+  recommended_for:
+  - any repo needing provider-neutral LLM calls instead of a vendor-specific SDK
+  not_recommended_for:
+  - needs requiring a provider not yet adapted (extend via the abstract interface first)
+  known_limitations:
+  - not yet published to a package index; local editable install only
+promotion_history: []
+---
+
+# Pluggable LLM Adapter Library (llm-connect)
+
+## Overview
+
+`llm-connect` provides pluggable, provider-neutral LLM adapters for Python and the command line, supporting OpenRouter, Gemini, OpenAI, and the Claude Code CLI out of the box behind a clean abstract interface, and is already the intended backend for several sibling repos including `can-you-assist` and `reuse-surface`'s own drafting tooling.
+
+## Assessment notes
+
+### Discovery
+
+README documents a working quick-start (`create_adapter`, `RunConfig`, `execute_prompt`), the supported provider list, and both local-editable and future-published install paths.
+
+### Availability
+
+Installable today via `pip install -e` (local) with a documented future `pip install llm-connect` path once published; consumed today by sibling repos including `cya` (can-you-assist) and referenced as the intended backend for reuse-surface's own `establish --discover`.
+
+### Completeness
+
+First-pass honest assessment from the REUSE-WP-0017 coverage campaign
+(reuse-surface). No external consumer feedback exists yet; levels reflect
+scope-vs-intent documentation quality, not internal code quality.
+
+### Reliability
+
+No production consumer telemetry exists yet; reliability level is
+intentionally conservative pending REUSE-WP-0019 reuse-telemetry evidence.
+
+## Promotion checklist
+
+- [x] ID follows `capability.<domain>.<name>` pattern
+- [x] Maturity enums match `specs/CapabilityMaturityStandard.md`
+- [x] `external_evidence` is populated separately from `maturity`
+- [ ] Relations reference valid capability IDs (none yet)
+- [x] Index entry added in `registry/indexes/capabilities.yaml`

registry/indexes/capabilities.yaml

@@ -1,4 +1,20 @@
 version: 1
-updated: '2026-06-16'
+updated: '2026-07-06'
 domain: helix_forge
-capabilities: []
+capabilities:
+- id: capability.agents.llm-connector
+  name: Pluggable LLM Adapter Library (llm-connect)
+  summary: Provider-neutral Python/CLI LLM adapter library supporting OpenRouter, Gemini, OpenAI, and
+    the Claude Code CLI out of the box, with a clean abstract interface for adding new providers.
+  vector: D3 / A2 / C2 / R1
+  domain: agents
+  status: draft
+  owner: llm-connect
+  path: registry/capabilities/capability.agents.llm-connector.md
+  tags:
+  - llm
+  - adapter
+  - provider-neutral
+  consumption_modes:
+  - library import
+  - cli

workplans/LLM-WP-0006-activity-core-always-on-endpoint.md

@@ -2,7 +2,7 @@
 id: LLM-WP-0006
 type: workplan
 title: "Activity-Core Always-On LLM Endpoint"
-domain: custodian
+domain: agents
 repo: llm-connect
 status: finished
 owner: codex

workplans/llm-connect-WP-0001-foundation-gaaf-baseline.md

@@ -2,7 +2,7 @@
 id: LLM-WP-0001
 type: workplan
 title: llm-connect — Foundation & GAAF Baseline
-domain: custodian
+domain: agents
 status: completed
 owner: llm-connect
 created: 2026-04-01

workplans/llm-connect-WP-0002-core-extensions.md

@@ -2,7 +2,7 @@
 id: LLM-WP-0002
 type: workplan
 title: llm-connect — Core Extensions (FR-4 BudgetTracker + FR-3 async)
-domain: custodian
+domain: agents
 status: completed
 owner: llm-connect
 created: 2026-04-01

workplans/llm-connect-WP-0003-functional-extensions.md

@@ -2,7 +2,7 @@
 id: LLM-WP-0003
 type: workplan
 title: llm-connect — Functional Extensions (FR-2 RoutingPolicy + FR-1 HTTP server)
-domain: custodian
+domain: agents
 status: completed
 owner: llm-connect
 created: 2026-04-01

workplans/llm-connect-WP-0004-adaptive-cost-quality-routing.md

@@ -2,7 +2,7 @@
 id: LLM-WP-0004
 type: workplan
 title: Adaptive Cost-Quality Routing
-domain: custodian
+domain: agents
 status: completed
 owner: llm-connect
 created: 2026-05-17
@@ -264,7 +264,8 @@ state_hub_task_id: "3a073ff7-0170-4a95-9c2a-a5daa84964e6"
 ### T01 — Quality observation data model + ledger
 
 | ID  | Title                                                                                                                                                                                       | Priority | Status |
-|-----|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------|--------|
+|-----|------------------------------------
+---------------------------------------------------------------------------------------------------------------------------------------------------------|----------|--------|
 | T01 | `QualityObservation` dataclass: `task_type`, `adapter_id`, `model_id`, `cost_usd`, `quality_score` (0..1), `latency_ms`, `tokens_in`, `tokens_out`, `baseline_adapter_id`, `recorded_at`, `tags` | high     | done   |
 | T02 | `QualityLedger` append-only JSONL store with file-locked writes, configurable path, simple query helpers (`by_task_type`, `recent`, `mean_quality`)                                          | high     | done   |
 | T03 | TTL helpers: `prune_before(timestamp)` and `is_stale(observation, max_age)` so callers can refresh observations without re-reading the whole ledger                                          | medium   | done   |

workplans/llm-connect-WP-0005-cost-model-and-problem-class-estimators.md

@@ -2,7 +2,7 @@
 id: LLM-WP-0005
 type: workplan
 title: "Cost Model and Problem-Class Token Estimators"
-domain: custodian
+domain: agents
 repo: llm-connect
 status: finished
 owner: llm-connect