@okrlinkhub/agent-factory 0.1.0

package/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1.  Definitions.
+
+    "License" shall mean the terms and conditions for use, reproduction,
+    and distribution as defined by Sections 1 through 9 of this document.
+
+    "Licensor" shall mean the copyright owner or entity authorized by
+    the copyright owner that is granting the License.
+
+    "Legal Entity" shall mean the union of the acting entity and all
+    other entities that control, are controlled by, or are under common
+    control with that entity. For the purposes of this definition,
+    "control" means (i) the power, direct or indirect, to cause the
+    direction or management of such entity, whether by contract or
+    otherwise, or (ii) ownership of fifty percent (50%) or more of the
+    outstanding shares, or (iii) beneficial ownership of such entity.
+
+    "You" (or "Your") shall mean an individual or Legal Entity
+    exercising permissions granted by this License.
+
+    "Source" form shall mean the preferred form for making modifications,
+    including but not limited to software source code, documentation
+    source, and configuration files.
+
+    "Object" form shall mean any form resulting from mechanical
+    transformation or translation of a Source form, including but
+    not limited to compiled object code, generated documentation,
+    and conversions to other media types.
+
+    "Work" shall mean the work of authorship, whether in Source or
+    Object form, made available under the License, as indicated by a
+    copyright notice that is included in or attached to the work
+    (an example is provided in the Appendix below).
+
+    "Derivative Works" shall mean any work, whether in Source or Object
+    form, that is based on (or derived from) the Work and for which the
+    editorial revisions, annotations, elaborations, or other modifications
+    represent, as a whole, an original work of authorship. For the purposes
+    of this License, Derivative Works shall not include works that remain
+    separable from, or merely link (or bind by name) to the interfaces of,
+    the Work and Derivative Works thereof.
+
+    "Contribution" shall mean any work of authorship, including
+    the original version of the Work and any modifications or additions
+    to that Work or Derivative Works thereof, that is intentionally
+    submitted to Licensor for inclusion in the Work by the copyright owner
+    or by an individual or Legal Entity authorized to submit on behalf of
+    the copyright owner. For the purposes of this definition, "submitted"
+    means any form of electronic, verbal, or written communication sent
+    to the Licensor or its representatives, including but not limited to
+    communication on electronic mailing lists, source code control systems,
+    and issue tracking systems that are managed by, or on behalf of, the
+    Licensor for the purpose of discussing and improving the Work, but
+    excluding communication that is conspicuously marked or otherwise
+    designated in writing by the copyright owner as "Not a Contribution."
+
+    "Contributor" shall mean Licensor and any individual or Legal Entity
+    on behalf of whom a Contribution has been received by Licensor and
+    subsequently incorporated within the Work.
+
+2.  Grant of Copyright License. Subject to the terms and conditions of
+    this License, each Contributor hereby grants to You a perpetual,
+    worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+    copyright license to reproduce, prepare Derivative Works of,
+    publicly display, publicly perform, sublicense, and distribute the
+    Work and such Derivative Works in Source or Object form.
+
+3.  Grant of Patent License. Subject to the terms and conditions of
+    this License, each Contributor hereby grants to You a perpetual,
+    worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+    (except as stated in this section) patent license to make, have made,
+    use, offer to sell, sell, import, and otherwise transfer the Work,
+    where such license applies only to those patent claims licensable
+    by such Contributor that are necessarily infringed by their
+    Contribution(s) alone or by combination of their Contribution(s)
+    with the Work to which such Contribution(s) was submitted. If You
+    institute patent litigation against any entity (including a
+    cross-claim or counterclaim in a lawsuit) alleging that the Work
+    or a Contribution incorporated within the Work constitutes direct
+    or contributory patent infringement, then any patent licenses
+    granted to You under this License for that Work shall terminate
+    as of the date such litigation is filed.
+
+4.  Redistribution. You may reproduce and distribute copies of the
+    Work or Derivative Works thereof in any medium, with or without
+    modifications, and in Source or Object form, provided that You
+    meet the following conditions:
+
+    (a) You must give any other recipients of the Work or
+    Derivative Works a copy of this License; and
+
+    (b) You must cause any modified files to carry prominent notices
+    stating that You changed the files; and
+
+    (c) You must retain, in the Source form of any Derivative Works
+    that You distribute, all copyright, patent, trademark, and
+    attribution notices from the Source form of the Work,
+    excluding those notices that do not pertain to any part of
+    the Derivative Works; and
+
+    (d) If the Work includes a "NOTICE" text file as part of its
+    distribution, then any Derivative Works that You distribute must
+    include a readable copy of the attribution notices contained
+    within such NOTICE file, excluding those notices that do not
+    pertain to any part of the Derivative Works, in at least one
+    of the following places: within a NOTICE text file distributed
+    as part of the Derivative Works; within the Source form or
+    documentation, if provided along with the Derivative Works; or,
+    within a display generated by the Derivative Works, if and
+    wherever such third-party notices normally appear. The contents
+    of the NOTICE file are for informational purposes only and
+    do not modify the License. You may add Your own attribution
+    notices within Derivative Works that You distribute, alongside
+    or as an addendum to the NOTICE text from the Work, provided
+    that such additional attribution notices cannot be construed
+    as modifying the License.
+
+    You may add Your own copyright statement to Your modifications and
+    may provide additional or different license terms and conditions
+    for use, reproduction, or distribution of Your modifications, or
+    for any such Derivative Works as a whole, provided Your use,
+    reproduction, and distribution of the Work otherwise complies with
+    the conditions stated in this License.
+
+5.  Submission of Contributions. Unless You explicitly state otherwise,
+    any Contribution intentionally submitted for inclusion in the Work
+    by You to the Licensor shall be under the terms and conditions of
+    this License, without any additional terms or conditions.
+    Notwithstanding the above, nothing herein shall supersede or modify
+    the terms of any separate license agreement you may have executed
+    with Licensor regarding such Contributions.
+
+6.  Trademarks. This License does not grant permission to use the trade
+    names, trademarks, service marks, or product names of the Licensor,
+    except as required for reasonable and customary use in describing the
+    origin of the Work and reproducing the content of the NOTICE file.
+
+7.  Disclaimer of Warranty. Unless required by applicable law or
+    agreed to in writing, Licensor provides the Work (and each
+    Contributor provides its Contributions) on an "AS IS" BASIS,
+    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+    implied, including, without limitation, any warranties or conditions
+    of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+    PARTICULAR PURPOSE. You are solely responsible for determining the
+    appropriateness of using or redistributing the Work and assume any
+    risks associated with Your exercise of permissions under this License.
+
+8.  Limitation of Liability. In no event and under no legal theory,
+    whether in tort (including negligence), contract, or otherwise,
+    unless required by applicable law (such as deliberate and grossly
+    negligent acts) or agreed to in writing, shall any Contributor be
+    liable to You for damages, including any direct, indirect, special,
+    incidental, or consequential damages of any character arising as a
+    result of this License or out of the use or inability to use the
+    Work (including but not limited to damages for loss of goodwill,
+    work stoppage, computer failure or malfunction, or any and all
+    other commercial damages or losses), even if such Contributor
+    has been advised of the possibility of such damages.
+
+9.  Accepting Warranty or Additional Liability. While redistributing
+    the Work or Derivative Works thereof, You may choose to offer,
+    and charge a fee for, acceptance of support, warranty, indemnity,
+    or other liability obligations and/or rights consistent with this
+    License. However, in accepting such obligations, You may act only
+    on Your own behalf and on Your sole responsibility, not on behalf
+    of any other Contributor, and only if You agree to indemnify,
+    defend, and hold each Contributor harmless for any liability
+    incurred by, or claims asserted against, such Contributor by reason
+    of your accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS
+
+APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+Copyright [yyyy] [name of copyright owner]
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

package/README.md

@@ -0,0 +1,345 @@
+# Convex Agent Factory
+
+[![npm version](https://badge.fury.io/js/@example%2Fagent-factory.svg)](https://badge.fury.io/js/@example%2Fagent-factory)
+
+A Convex component for hydration-based orchestration of OpenClaw agents on a generic worker pool (Fly Machines first, provider abstraction built-in).
+
+## Installation
+
+Create a `convex.config.ts` file in your app's `convex/` folder and install the
+component by calling `use`:
+
+```ts
+// convex/convex.config.ts
+import { defineApp } from "convex/server";
+import agentFactory from "@okrlinkhub/agent-factory/convex.config.js";
+
+const app = defineApp();
+app.use(agentFactory);
+
+export default app;
+```
+
+## Usage
+
+### First required setup: mandatory secrets for every worker/agent
+
+Before running worker autoscaling (enqueue trigger, cron, or manual reconcile), you must
+store **both** secrets in the component secret store:
+
+- `convex.url`
+- `fly.apiToken`
+
+Every spawned worker/agent needs these values at runtime. Manual "Start Workers" can work
+when you pass values inline from the UI, but automatic paths (enqueue + cron) rely on
+these stored secrets.
+
+If one is missing, reconcile fails with errors like:
+- `Missing Convex URL. Import an active 'convex.url' secret or pass convexUrl explicitly.`
+- `Missing Fly API token. Import an active 'fly.apiToken' secret or pass flyApiToken explicitly.`
+
+Set them once:
+
+```sh
+npx convex run example:importSecret '{
+  "secretRef": "convex.url",
+  "plaintextValue": "https://<your-convex-deployment>.convex.cloud"
+}'
+
+npx convex run example:importSecret '{
+  "secretRef": "fly.apiToken",
+  "plaintextValue": "fly_XXXXXXXXXXXXXXXX"
+}'
+```
+
+Verify status:
+
+```sh
+npx convex run example:secretStatus '{
+  "secretRefs": ["convex.url", "fly.apiToken", "telegram.botToken"]
+}'
+```
+
+In the example UI (`example/src/App.tsx`), this is shown as step
+`0) Mandatory: configure convex.url secret`; make sure `fly.apiToken` is also imported
+as an active component secret.
+
+```ts
+import { components } from "./_generated/api";
+import { mutation } from "./_generated/server";
+import { v } from "convex/values";
+
+export const enqueueTelegramMessage = mutation({
+  args: { text: v.string(), chatId: v.string() },
+  handler: async (ctx, args) => {
+    return await ctx.runMutation(components.agentFactory.lib.enqueue, {
+      conversationId: `telegram:${args.chatId}`,
+      agentKey: "default",
+      payload: {
+        provider: "telegram",
+        providerUserId: args.chatId,
+        messageText: args.text,
+      },
+    });
+  },
+});
+```
+
+After enqueue, a **queue processor runtime** must process the queue by calling:
+- `components.agentFactory.lib.claim`
+- `components.agentFactory.lib.getHydrationBundle`
+- `components.agentFactory.lib.heartbeat`
+- `components.agentFactory.lib.complete` or `components.agentFactory.lib.fail`
+
+Worker autoscaling reconcile now follows a hybrid model:
+- `enqueue` schedules an immediate async reconcile trigger (`runAfter(0, ...)`)
+- a periodic cron fallback is still recommended to recover from missed triggers
+- desired worker count is conversation-aware, so multiple queued messages on the same `conversationId` do not over-scale worker spawn
+
+In this project setup, the queue processor runtime is **Fly worker-only** (not the consumer webhook app).
+The consumer app receives ingress and enqueues, while Fly workers dequeue and execute jobs.
+The worker should consume tenant-specific tokens from the hydration payload (resolved by the component), not from global Fly env vars.
+
+### Cron fallback every 5 minutes
+
+In your Convex app, add a cron fallback for reconcile:
+
+```ts
+import { cronJobs } from "convex/server";
+import { api } from "./_generated/api";
+
+const crons = cronJobs();
+
+crons.interval(
+  "agent-factory reconcile workers fallback",
+  { minutes: 5 },
+  api.example.startWorkers,
+  {},
+);
+
+export default crons;
+```
+
+This cron is a safety net. The primary path remains enqueue-triggered reconcile.
+
+### LLM configuration (Fly env)
+
+LLM selection is intentionally **not stored in `agentProfiles`** anymore.
+The model/provider is controlled by Fly worker environment variables (for example `OPENCLAW_AGENT_MODEL`, `MOONSHOT_API_KEY`, `OPENAI_API_KEY`) and applied at runtime by the worker image bootstrap.
+
+Why:
+- keeps model routing as infrastructure/runtime concern
+- avoids per-agent schema coupling to a specific LLM field
+- lets you switch model/provider with a Fly deploy or env change only
+
+Practical notes:
+- set model/provider env on the Fly app (`fly secrets set` / `[env]` in `fly.toml`)
+- keep `agentProfiles` focused on identity, skills, docs, and secrets references
+- worker image tag stays centralized in `src/component/config.ts` (`DEFAULT_WORKER_IMAGE`)
+
+If you use `exposeApi(...)`, the worker contract is available directly on the consumer API surface:
+- `workerClaim`
+- `workerHydrationBundle`
+- `workerHeartbeat`
+- `workerComplete`
+- `workerFail`
+
+### HTTP Routes
+
+You can mount an ingress webhook route in your app:
+
+```ts
+import { httpRouter } from "convex/server";
+import { registerRoutes } from "@okrlinkhub/agent-factory";
+import { components } from "./_generated/api";
+
+const http = httpRouter();
+
+registerRoutes(http, components.agentFactory, {
+  pathPrefix: "/agent-factory",
+});
+
+export default http;
+```
+
+This exposes:
+- `POST /agent-factory/telegram/webhook` -> enqueue-only (no business processing)
+
+Important: the webhook/router only receives ingress and enqueues.
+Do not point Telegram directly to Fly worker machines.
+Use webhook -> consumer app (Next.js/Vercel) -> Convex queue -> Fly workers (pull-based processing).
+
+### One-time Telegram pairing and internal user mapping
+
+The component can keep the user-to-agent mapping internally through `identityBindings`.
+You can bind your consumer user id directly to an `agentKey` without managing a custom
+table in the consumer app.
+
+Typical one-time pairing flow:
+
+1. Your app authenticates the user and creates a one-time pairing code via
+   `createPairingCode`.
+2. User opens Telegram deep-link (`/start <pairingCode>`).
+3. `registerRoutes(...)` webhook consumes the pairing code and performs
+   `bindUserAgent` automatically with `source: "telegram_pairing"` and
+   Telegram ids from the update.
+4. Webhook ingress then resolves the binding internally and enqueues with the mapped
+   `agentKey`.
+
+Available pairing APIs (via `exposeApi(...)`):
+- `createPairingCode`
+- `getPairingCodeStatus`
+
+Telegram token storage (multi-tenant):
+- store tenant token in component secrets with an agent-scoped ref (for example `telegram.botToken.<agentKey>`)
+- include that ref in `agentProfiles.secretsRef`
+- worker gets resolved plaintext from hydration bundle (`telegramBotToken`) at runtime
+- do not use a single global `TELEGRAM_BOT_TOKEN` on Fly app
+
+`registerRoutes(...)` supports this behavior with:
+- `resolveAgentKeyFromBinding` (default `true`)
+- `fallbackAgentKey` (default `"default"`)
+- `requireBindingForTelegram` (default `false`, when `true` rejects unbound users)
+
+Special handling for `/start`:
+- `/start <pairingCode>` attempts pairing consumption and does not enqueue the command.
+- invalid `/start` payload returns `200` with pairing error details to avoid Telegram retries.
+
+## Architecture
+
+```mermaid
+flowchart LR
+  telegramWebhook[TelegramWebhook] --> appRouter[Consumer Router NextOrVite]
+  appRouter --> enqueueMutation[ConvexEnqueueMutation]
+  enqueueMutation --> messageQueue[ConvexMessageQueue]
+  messageQueue --> claimLoop[FlyWorkerProcessingLoop]
+  claimLoop --> hydrateStep[HydrateFromConvex]
+  hydrateStep --> runEngine[OpenClawEngineExecution]
+  runEngine --> telegramSend[TelegramDirectReply]
+  claimLoop --> heartbeatLease[HeartbeatAndLeaseRenewal]
+  heartbeatLease --> cleanupTask[PeriodicLeaseCleanup]
+  cleanupTask --> messageQueue
+  schedulerNode[ConvexSchedulerAndAutoscaler] --> flyProvider[FlyMachinesProvider]
+  flyProvider --> flyWorkers[FlyWorkerMachines]
+  flyWorkers --> claimLoop
+```
+
+## Data model
+
+Core tables:
+- `agentProfiles`
+- `conversations`
+- `messageQueue`
+- `workers`
+- `secrets`
+
+Hydration-optimized tables:
+- `workspaceDocuments`
+- `agentSkills`
+- `skillAssets`
+- `hydrationSnapshots`
+- `conversationHydrationCache`
+- `dataSnapshots`
+
+## Recent updates
+
+- `idleTimeoutMs` aligned to 5 minutes and `workers.scheduledShutdownAt` now tracks idle lifecycle from `lastClaimAt`.
+- Pre-stop drain protocol added: worker snapshots `/data` before termination and uploads archive metadata into `dataSnapshots`.
+- Restore on boot added: new workers can rehydrate from latest snapshot archive.
+- Hydration improved with `conversationHydrationCache` delta usage.
+- `skillAssets` now contributes to hydration snapshot and fingerprint rebuilds.
+- Worker control/snapshot APIs exposed for runtime loop (`workerControlState`, snapshot upload/finalize/fail, restore lookup).
+
+## OpenClaw workspace mapping
+
+| OpenClaw source | Convex table |
+|---|---|
+| `AGENTS.md`, `SOUL.md`, `USER.md`, `IDENTITY.md`, `HEARTBEAT.md`, `TOOLS.md` | `workspaceDocuments` |
+| `memory/YYYY-MM-DD.md`, `MEMORY.md` | `workspaceDocuments` + `hydrationSnapshots.memoryWindow` |
+| `skills/*/SKILL.md` | `agentSkills` |
+| `skills/*/scripts/*`, `skills/*/config/*` metadata | `skillAssets` |
+| Compiled hydration payload | `hydrationSnapshots` |
+| Conversation-specific deltas | `conversationHydrationCache` |
+
+## Failure model
+
+- Worker crash during processing does not lose data.
+- Each claimed job has a lease (`leaseId`, `leaseExpiresAt`) and heartbeat.
+- Cleanup job requeues expired `processing` jobs and unlocks conversations.
+- Retry uses exponential backoff with dead-letter fallback.
+
+## Config-first
+
+`src/component/config.ts` defines type-safe policies:
+- queue policy
+- retry policy
+- lease policy
+- scaling policy
+- hydration policy
+- provider config
+
+## Fly.io provider notes
+
+The current provider implementation uses Fly Machines API endpoints for:
+- create machine
+- list machines
+- cordon machine
+- terminate machine
+
+### Worker image update procedure (local builder, no Depot)
+
+When you update the worker runtime (for example in `openclaw-okr-image/worker.mjs`), use this flow to publish and roll out safely.
+
+1) Deploy with Fly local builder (explicitly disabling Depot):
+
+```sh
+cd /path/to/openclaw-okr-image
+fly deploy --local-only --depot=false --yes
+```
+
+2) If deployment fails with `CONVEX_URL not set`, set the secret and retry:
+
+```sh
+fly secrets set CONVEX_URL="https://<your-convex-deployment>.convex.cloud" -a agent-factory-workers
+```
+
+3) Capture the new image tag from deploy output (for example
+`registry.fly.io/agent-factory-workers:deployment-XXXXXXXXXXXX`), then update
+`src/component/config.ts` in this repo:
+
+```ts
+export const DEFAULT_WORKER_IMAGE =
+  "registry.fly.io/agent-factory-workers:deployment-XXXXXXXXXXXX";
+```
+
+4) Verify rollout:
+
+```sh
+fly status -a agent-factory-workers
+fly logs -a agent-factory-workers --no-tail
+```
+
+5) (Recommended) Commit the `DEFAULT_WORKER_IMAGE` update so scheduler-driven
+spawns use the exact image that was just deployed.
+
+Recommended runtime split:
+- Consumer app (Next.js/Vercel): webhook ingress + enqueue only
+- Fly worker app: claim/heartbeat/complete/fail loop
+
+Anti-pattern to avoid:
+- Telegram webhook -> Fly worker HTTP endpoint
+- Reason: workers are batch processors, may be scaled to zero, and should not be used as public ingress.
+- Global Fly env `TELEGRAM_BOT_TOKEN` for all tenants
+- Reason: breaks multi-tenant isolation and forces shared bot credentials.
+
+References:
+- https://docs.machines.dev/
+- https://fly.io/docs/machines/api/machines-resource/
+- https://docs.convex.dev/components/authoring
+
+## Development
+
+```sh
+npm i
+npm run dev
+```

package/dist/client/_generated/_ignore.d.ts

@@ -0,0 +1 @@
+//# sourceMappingURL=_ignore.d.ts.map

package/dist/client/_generated/_ignore.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"_ignore.d.ts","sourceRoot":"","sources":["../../../src/client/_generated/_ignore.ts"],"names":[],"mappings":""}

package/dist/client/_generated/_ignore.js

@@ -0,0 +1,3 @@
+"use strict";
+// This is only here so convex-test can detect a _generated folder
+//# sourceMappingURL=_ignore.js.map

package/dist/client/_generated/_ignore.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"_ignore.js","sourceRoot":"","sources":["../../../src/client/_generated/_ignore.ts"],"names":[],"mappings":";AAAA,kEAAkE"}