coder(providers): v2.3 provider-lifecycle phase 2 — snapshot lifecycle

provider-snapshot no longer returns null for uninstalled/disabled providers: it emits one entry per registered provider with a lifecycle status (loading|ready|unavailable|error), an enabled flag, and a two-tier probe. Tier-1 is a fast which-style check (command-availability.ts, execFile/no-shell); tier-2 (cold ACP probe) is skipped unless forced, last_probed_at is older than PROVIDER_PROBE_TTL_MS (24h), or DB models are empty — the snapshot-latency win. Cache miss returns status:'loading' synchronously while the build settles via the existing inflight promise. ProviderSnapshotStatus/Entry regain loading/unavailable + gain enabled/description?/fetchedAt? in both coder and web copies, guarded by a runtime parity test (provider-types-parity.test.ts; compile-time cross-project check was blocked by TS6307). Also tracks the data/coder-providers.json seed via a .gitignore exception, completing the Phase 1 config file. No dispatch/route/UI changes (Phase 3+); AgentComposerBar filtering unchanged. 13 snapshot tests (+6) + 6 parity tests.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

apps/coder/src/services/provider-snapshot.ts

@@ -5,7 +5,6 @@ import { homedir } from 'node:os';
 import type { FastifyBaseLogger } from 'fastify';
 import type { Sql } from '../db.js';
 import type { Config } from '../config.js';
-import { PROVIDERS, type ProviderDef } from './provider-registry.js';
 import {
   getManifestDefaultModeId,
   getManifestModes,
@@ -15,6 +14,8 @@ import { probeAcpProvider } from './acp-probe.js';
 import type { ProviderModel, ProviderSnapshotEntry } from './provider-types.js';
 import { getManifestCommands, mergeCommands } from './provider-commands.js';
 import { readQwenSettingsModels } from './qwen-settings.js';
+import { getResolvedRegistry, type ResolvedProviderDef } from './provider-config-registry.js';
+import { isCommandAvailable } from './command-availability.js';
 
 interface AgentRow {
   name: string;
@@ -23,6 +24,7 @@ interface AgentRow {
   models: ProviderModel[] | null;
   label: string | null;
   transport: string | null;
+  last_probed_at: string | Date | null;
 }
 
 async function fetchLlamaSwapModels(config: Config): Promise<ProviderModel[]> {
@@ -68,113 +70,160 @@ export function mergeModels(...lists: ProviderModel[][]): ProviderModel[] {
 }
 
 async function buildProviderEntry(
-  provider: ProviderDef,
+  resolved: ResolvedProviderDef,
   agentRow: AgentRow | undefined,
   llamaModels: ProviderModel[],
   cwd: string,
-): Promise<ProviderSnapshotEntry | null> {
-  const isNative = provider.name === 'boocode';
-  const installed = isNative || !!agentRow;
-  if (!installed) return null;
+  ttlMs: number,
+  force: boolean,
+): Promise<ProviderSnapshotEntry> {
+  const name = resolved.id;
+  const isNative = resolved.transport === 'native';
+  const fallbackModes = getManifestModes(name);
+  const defaultModeId = getManifestDefaultModeId(name);
+  const manifestCommands = getManifestCommands(name);
+  const label = agentRow?.label ?? resolved.configLabel ?? resolved.label;
+  const descr = resolved.configDescription ? { description: resolved.configDescription } : {};
 
-  let transport = provider.transport;
-  if (agentRow && provider.transport === 'acp' && !agentRow.supports_acp) {
+  // ACP built-ins fall back to PTY transport when the installed binary lacks ACP.
+  let transport = resolved.transport;
+  if (agentRow && resolved.transport === 'acp' && !agentRow.supports_acp) {
     transport = 'pty';
   }
 
-  const fallbackModes = getManifestModes(provider.name);
-  const defaultModeId = getManifestDefaultModeId(provider.name);
-
-  if (isNative) {
+  // 1. Disabled → unavailable, no probe.
+  if (!resolved.enabled) {
     return {
-      name: provider.name,
-      label: provider.label,
-      transport,
-      status: 'ready',
-      installed: true,
-      models: llamaModels,
-      modes: [],
-      defaultModeId: null,
-      commands: getManifestCommands(provider.name),
+      name, label, ...descr, transport, status: 'unavailable',
+      enabled: false, installed: false, models: [], modes: fallbackModes,
+      defaultModeId, commands: manifestCommands,
     };
   }
 
+  // 2. Native boocode → always ready (llama-swap models).
+  if (isNative) {
+    return {
+      name, label: resolved.label, transport, status: 'ready',
+      enabled: true, installed: true, models: llamaModels, modes: [],
+      defaultModeId: null, commands: manifestCommands,
+    };
+  }
+
+  // 3. Tier-1 fast availability: installed iff a probed install_path exists or
+  // the launch binary is on PATH. No spawn beyond a `which` for custom entries.
+  const fast =
+    agentRow?.install_path != null ||
+    (resolved.launchCommand ? await isCommandAvailable(resolved.launchCommand[0]) : false);
+
+  if (!fast) {
+    return {
+      name, label, ...descr, transport, status: 'unavailable',
+      enabled: true, installed: false, models: [], modes: fallbackModes,
+      defaultModeId, commands: manifestCommands,
+    };
+  }
+
+  // Baseline model precedence (used by claude + non-probe fallbacks).
   let models: ProviderModel[] = [];
-  if (provider.modelSource === 'llama-swap' && provider.mergeLlamaSwap) {
+  if (resolved.modelSource === 'llama-swap' && resolved.mergeLlamaSwap) {
     models = llamaModels;
   } else if (agentRow?.models?.length) {
     models = agentRow.models;
-  } else if (provider.staticModels) {
-    models = provider.staticModels.map((m) => ({ id: m.id, label: m.label }));
+  } else if (resolved.staticModels) {
+    models = resolved.staticModels.map((m) => ({ id: m.id, label: m.label }));
   }
 
-  if (provider.name === 'claude') {
-    models = attachClaudeThinking(models);
+  // claude: static models + thinking options, no ACP probe (unchanged from v2.2).
+  if (name === 'claude') {
     return {
-      name: provider.name,
-      label: agentRow?.label ?? provider.label,
-      transport,
-      status: 'ready',
-      installed: true,
-      models,
-      modes: fallbackModes,
-      defaultModeId,
-      commands: getManifestCommands(provider.name),
+      name, label, transport, status: 'ready', enabled: true, installed: true,
+      models: attachClaudeThinking(models), modes: fallbackModes, defaultModeId,
+      commands: manifestCommands,
     };
   }
 
-  if (transport === 'acp' && agentRow?.install_path && agentRow.supports_acp) {
-    const probe = await probeAcpProvider(provider.name, agentRow.install_path, cwd);
-    if (probe.models.length > 0) {
-      models = probe.models;
-    } else if (provider.modelSource === 'llama-swap') {
-      models = llamaModels;
+  const canProbeAcp =
+    transport === 'acp' &&
+    ((agentRow?.install_path != null && agentRow.supports_acp) ||
+      (resolved.isCustomAcp && resolved.launchCommand != null));
+
+  if (canProbeAcp) {
+    // Tier-2 gate (§4.3): cold ACP probe only on force, staleness, or empty DB
+    // models. Otherwise serve DB models + manifest modes/commands — no spawn.
+    const lastProbedMs =
+      agentRow?.last_probed_at != null ? new Date(agentRow.last_probed_at).getTime() : NaN;
+    const stale = Number.isNaN(lastProbedMs) || Date.now() - lastProbedMs > ttlMs;
+    const dbEmpty = !(agentRow?.models && agentRow.models.length > 0);
+    const runTier2 = force || stale || dbEmpty;
+
+    if (!runTier2) {
+      let skipModels = agentRow?.models ?? [];
+      if (resolved.mergeLlamaSwap && resolved.modelSource !== 'llama-swap') {
+        skipModels = mergeModels(skipModels, prefixLlamaSwapModels(llamaModels));
+      } else if (resolved.modelSource === 'llama-swap' && skipModels.length === 0) {
+        skipModels = llamaModels;
+      }
+      return {
+        name, label, transport, status: 'ready', enabled: true, installed: true,
+        models: skipModels, modes: fallbackModes, defaultModeId, commands: manifestCommands,
+      };
     }
 
-    if (provider.name === 'qwen') {
-      const settingsModels = await readQwenSettingsModels();
-      models = mergeModels(models, settingsModels);
-    }
+    const probeTarget =
+      resolved.isCustomAcp && resolved.launchCommand
+        ? resolved.launchCommand[0]
+        : agentRow!.install_path!;
+    const probe = await probeAcpProvider(name, probeTarget, cwd);
 
-    if (provider.mergeLlamaSwap && provider.modelSource !== 'llama-swap') {
-      const nativeModels = probe.models.length > 0 ? probe.models : models;
-      models = mergeModels(nativeModels, prefixLlamaSwapModels(llamaModels));
+    let probeModels = probe.models.length > 0 ? probe.models : models;
+    if (name === 'qwen') {
+      probeModels = mergeModels(probeModels, await readQwenSettingsModels());
+    }
+    if (resolved.mergeLlamaSwap && resolved.modelSource !== 'llama-swap') {
+      const nativeModels = probe.models.length > 0 ? probe.models : probeModels;
+      probeModels = mergeModels(nativeModels, prefixLlamaSwapModels(llamaModels));
     }
 
     return {
-      name: provider.name,
-      label: agentRow.label ?? provider.label,
-      transport,
+      name, label, transport,
       status: probe.ok ? 'ready' : 'error',
-      installed: true,
-      models,
+      enabled: true, installed: true,
+      models: probeModels,
       modes: probe.modes.length > 0 ? probe.modes : fallbackModes,
       defaultModeId: probe.defaultModeId ?? defaultModeId,
-      commands: mergeCommands(getManifestCommands(provider.name), probe.commands),
-      error: probe.error,
+      commands: mergeCommands(manifestCommands, probe.commands),
+      ...(probe.error ? { error: probe.error } : {}),
+      fetchedAt: new Date().toISOString(),
     };
   }
 
-  // PTY-only providers (qwen fallback when ACP unavailable)
-  if (provider.name === 'qwen') {
-    if (models.length === 0) {
-      models = await readQwenSettingsModels();
-    }
+  // PTY-only fallback (e.g. qwen without ACP) — installed + ready.
+  if (name === 'qwen' && models.length === 0) {
+    models = await readQwenSettingsModels();
   }
-
   return {
-    name: provider.name,
-    label: agentRow?.label ?? provider.label,
-    transport,
-    status: 'ready',
-    installed: true,
-    models,
-    modes: fallbackModes,
-    defaultModeId,
-    commands: getManifestCommands(provider.name),
+    name, label, transport, status: 'ready', enabled: true, installed: true,
+    models, modes: fallbackModes, defaultModeId, commands: manifestCommands,
   };
 }
 
+/** Synchronous placeholder entries for a cache-miss while the build runs (§4.4). */
+function loadingEntries(): ProviderSnapshotEntry[] {
+  return [...getResolvedRegistry().values()].map((r) => ({
+    name: r.id,
+    label: r.configLabel ?? r.label,
+    ...(r.configDescription ? { description: r.configDescription } : {}),
+    transport: r.transport,
+    status: r.enabled ? ('loading' as const) : ('unavailable' as const),
+    enabled: r.enabled,
+    installed: false,
+    models: [],
+    modes: getManifestModes(r.id),
+    defaultModeId: getManifestDefaultModeId(r.id),
+    commands: getManifestCommands(r.id),
+  }));
+}
+
 const snapshotCache = new Map<string, { at: number; entries: ProviderSnapshotEntry[] }>();
 const snapshotInflight = new Map<string, Promise<ProviderSnapshotEntry[]>>();
 const CACHE_TTL_MS = 5 * 60_000;
@@ -200,16 +249,16 @@ export async function getProviderSnapshot(
   const build = async (): Promise<ProviderSnapshotEntry[]> => {
     const llamaModels = await fetchLlamaSwapModels(config);
     const agents = await sql<AgentRow[]>`
-      SELECT name, install_path, supports_acp, models, label, transport FROM available_agents
+      SELECT name, install_path, supports_acp, models, label, transport, last_probed_at FROM available_agents
     `;
     const agentMap = new Map(agents.map((a) => [a.name, a]));
+    const ttlMs = config.PROVIDER_PROBE_TTL_MS;
 
-    const built = await Promise.all(
-      PROVIDERS.map((provider) =>
-        buildProviderEntry(provider, agentMap.get(provider.name), llamaModels, resolvedCwd),
+    const entries = await Promise.all(
+      [...getResolvedRegistry().values()].map((resolved) =>
+        buildProviderEntry(resolved, agentMap.get(resolved.id), llamaModels, resolvedCwd, ttlMs, force),
       ),
     );
-    const entries = built.filter((entry): entry is ProviderSnapshotEntry => entry !== null);
 
     snapshotCache.set(cacheKey, { at: Date.now(), entries });
     return entries;
@@ -219,7 +268,15 @@ export async function getProviderSnapshot(
     snapshotInflight.delete(cacheKey);
   });
   snapshotInflight.set(cacheKey, promise);
-  return promise;
+
+  // force → await the full build (cold probes included). Non-force cache miss →
+  // return loading entries synchronously; the build settles in the background
+  // and the next call returns it via cache / inflight (§4.4; client polls).
+  if (force) return promise;
+  promise.catch(() => {
+    /* settled errors surface on the next call that awaits inflight/rebuilds */
+  });
+  return loadingEntries();
 }
 
 export function clearProviderSnapshotCache(): void {