inferoa 0.1.0

package/LICENSE

@@ -0,0 +1,176 @@
+                                 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 such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS

package/README.md

@@ -0,0 +1,154 @@
+<p align="center">
+  <img src="assets/inferoa-logo.svg" alt="Inferoa" width="420" />
+</p>
+
+<p align="center">
+  <strong>The Inference Optimized Agent Harness</strong>
+</p>
+
+<p align="center">
+  <a href="https://github.com/agentic-in/inferoa">GitHub</a>
+  ·
+  <a href="https://inferoa.agentic-in.ai/docs/intro">Docs</a>
+  ·
+  <a href="website/blog/2026-06-08-announcing-inferoa.md">Blog</a>
+</p>
+
+Most agents call models as if inference were a **black box**. The agent loop,
+router, serving engine, context system, and multimodal path are usually split
+apart, so the agent does not follow the optimization rules that modern
+inference systems make possible.
+
+> Prefix cache stability is ignored. Routing is
+bolted on later. Context is pasted until it fits. Users pay for that gap.
+
+Inferoa is an **Inference Optimized Agent Harness** for long-horizon tasks. It
+starts from the inference stack and designs the agent loop around it: goals,
+plans, autoresearch, context optimization, intelligent routing, serving
+signals, prefix-cache protection, multimodal capability, and verification all
+belong to the same durable session.
+
+## TUI Preview
+
+<div align="center">
+  <table>
+    <tr>
+      <th>Welcome</th>
+      <th>Goal Mode</th>
+    </tr>
+    <tr>
+      <td align="center"><img src="website/static/img/screenshots/inferoa-welcome.png" alt="Inferoa welcome screen" width="420" /></td>
+      <td align="center"><img src="website/static/img/screenshots/inferoa-goal.png" alt="Inferoa goal mode" width="420" /></td>
+    </tr>
+    <tr>
+      <th>Prefix Cache Status</th>
+      <th>Prefix Cache Report</th>
+    </tr>
+    <tr>
+      <td align="center"><img src="website/static/img/screenshots/inferoa-prefix-cache-status.png" alt="Inferoa prefix cache response status" width="420" /></td>
+      <td align="center"><img src="website/static/img/screenshots/inferoa-prefix-cache-report.png" alt="Inferoa prefix cache report" width="420" /></td>
+    </tr>
+    <tr>
+      <th>Plan Scope</th>
+      <th>Plan Approval</th>
+    </tr>
+    <tr>
+      <td align="center"><img src="website/static/img/screenshots/inferoa-plan-clarify.png" alt="Inferoa plan mode scope selection" width="420" /></td>
+      <td align="center"><img src="website/static/img/screenshots/inferoa-plan-ready.png" alt="Inferoa plan approval screen" width="420" /></td>
+    </tr>
+    <tr>
+      <th>Autoresearch Setup</th>
+      <th>Autoresearch Iteration</th>
+    </tr>
+    <tr>
+      <td align="center"><img src="website/static/img/screenshots/inferoa-autoresearch-start.png" alt="Inferoa autoresearch setup" width="420" /></td>
+      <td align="center"><img src="website/static/img/screenshots/inferoa-autoresearch-iteration.png" alt="Inferoa autoresearch iteration" width="420" /></td>
+    </tr>
+  </table>
+</div>
+
+## Why Inferoa
+
+Long-horizon agents are not one prompt. They are many turns of planning,
+editing, tool use, retries, compaction, cache warmup, route selection, and
+verification. If the harness treats every turn as generic chat traffic, it
+throws away the optimization surface underneath it.
+
+Inferoa makes those surfaces first-class:
+
+- **Prefix cache is protected**, not merely reported after the turn.
+- **Goals, plans, and autoresearch** are native long-horizon modes.
+- **Context is optimized** through [CodeGraph](https://www.npmjs.com/package/@colbymchenry/codegraph),
+  [RTK](https://github.com/rtk-ai/rtk), and built-in harnesses that reduce token
+  waste while improving task accuracy.
+- **Routing is part of the agent design**, so not every turn has to use the
+  same frontier model path.
+- **Serving and endpoint signals** feed back into the loop instead of living in
+  logs.
+- **Multimodal work** stays inside the same session contract instead of
+  becoming disconnected side calls.
+
+## Optimized with Inference Stack
+
+Inferoa is built on top of the vLLM Ecosystem and extends across the inference
+stack:
+
+| Layer | Substrate | Inferoa role | Optimization target |
+| --- | --- | --- | --- |
+| Agent Harness | [Inferoa](https://github.com/agentic-in/inferoa) | Goals, plans, autoresearch, sessions, tools, recovery, verification | Keep long-horizon work coherent and resumable |
+| Context Optimization | [CodeGraph](https://www.npmjs.com/package/@colbymchenry/codegraph), [RTK](https://github.com/rtk-ai/rtk)... | Select repo evidence, symbols, summaries, resources, and tool results | Spend fewer tokens and improve coding accuracy |
+| Intelligent Routing | [vLLM Semantic Router](https://github.com/vllm-project/semantic-router) | Choose model paths by cost, safety, privacy, capability, and session pressure | Avoid using one expensive path for every turn |
+| Serving | [vLLM Engine](https://github.com/vllm-project/vllm) | Use high-performance OpenAI-compatible inference and endpoint signals | Protect prefix cache stability across the session |
+| Multimodal | [vLLM Omni](https://github.com/vllm-project/vllm-omni) | Bring image, video, and audio understanding/generation into the same loop | Keep multimodal tasks durable and inspectable |
+
+The product shape is:
+
+```text
+Agent Harness -> Context Optimization -> Intelligent Routing -> Serving -> Multimodal
+```
+
+The day-0 strategy is concrete: co-design with vLLM Engine, vLLM Semantic
+Router, and vLLM Omni while keeping the product centered on the inference
+optimized agent harness.
+
+## Core Design
+
+- **Long-horizon modes**: goal, plan, and autoresearch are native workflows,
+  not prompt templates.
+- **Prefix-cache discipline**: stable prompt epochs, deterministic tool schemas,
+  bounded context sections, and cache reports protect reusable prefixes.
+- **Context optimization**: [CodeGraph](https://www.npmjs.com/package/@colbymchenry/codegraph),
+  [RTK](https://github.com/rtk-ai/rtk), and built-in coding harnesses reduce
+  token consumption while preserving the evidence the model needs.
+- **Intelligent routing**: model paths can respond to cost, safety, privacy,
+  capability, and session pressure.
+- **Serving feedback**: usage, cache, model, endpoint, and request signals are
+  visible enough to influence the next agent action.
+- **Durable multimodal loop**: image, video, and audio generation or
+  understanding are part of the same session history and artifact model.
+
+## Installation
+
+```bash
+npm install -g inferoa
+inferoa setup
+inferoa
+```
+
+For one-shot print mode:
+
+```bash
+inferoa --print "Inspect this repository and summarize the test entrypoints."
+```
+
+Inferoa stores local state under `~/.inferoa/`. Model endpoint credentials are
+stored through the local vault; config files keep references rather than raw
+secrets.
+
+## Acknowledgements
+
+Inferoa is built for and with the vLLM ecosystem:
+
+- [vLLM Engine](https://github.com/vllm-project/vllm)
+- [vLLM Semantic Router](https://github.com/vllm-project/semantic-router)
+- [vLLM Omni](https://github.com/vllm-project/vllm-omni)

package/dist/src/app.d.ts

@@ -0,0 +1,16 @@
+import { loadConfig } from "./config/config.js";
+import { resolveWorkspace } from "./session/workspace.js";
+import { SessionStore } from "./session/store.js";
+import { Runtime } from "./runtime.js";
+export interface AppOptions {
+    config?: string;
+    workspace?: string;
+    stateDir?: string;
+}
+export declare function loadApp(options?: AppOptions): Promise<{
+    config: Awaited<ReturnType<typeof loadConfig>>["config"];
+    configFiles: string[];
+    workspace: Awaited<ReturnType<typeof resolveWorkspace>>;
+    store: SessionStore;
+    runtime: Runtime;
+}>;

package/dist/src/app.js

@@ -0,0 +1,17 @@
+import { loadConfig } from "./config/config.js";
+import { resolveWorkspace } from "./session/workspace.js";
+import { SessionStore } from "./session/store.js";
+import { Runtime } from "./runtime.js";
+export async function loadApp(options = {}) {
+    if (options.stateDir) {
+        process.env.INFEROA_STATE_DIR = options.stateDir;
+    }
+    const { config, files } = await loadConfig(process.cwd(), options.config);
+    const workspace = await resolveWorkspace(process.cwd(), config, options.workspace);
+    const store = await SessionStore.open(options.stateDir);
+    store.clearStaleLocks();
+    store.upsertWorkspace(workspace);
+    const runtime = new Runtime(config, workspace, store);
+    return { config, configFiles: files, workspace, store, runtime };
+}
+//# sourceMappingURL=app.js.map

package/dist/src/app.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"app.js","sourceRoot":"","sources":["../../src/app.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,MAAM,oBAAoB,CAAC;AAChD,OAAO,EAAE,gBAAgB,EAAE,MAAM,wBAAwB,CAAC;AAC1D,OAAO,EAAE,YAAY,EAAE,MAAM,oBAAoB,CAAC;AAClD,OAAO,EAAE,OAAO,EAAE,MAAM,cAAc,CAAC;AAQvC,MAAM,CAAC,KAAK,UAAU,OAAO,CAAC,UAAsB,EAAE;IAOpD,IAAI,OAAO,CAAC,QAAQ,EAAE,CAAC;QACrB,OAAO,CAAC,GAAG,CAAC,iBAAiB,GAAG,OAAO,CAAC,QAAQ,CAAC;IACnD,CAAC;IACD,MAAM,EAAE,MAAM,EAAE,KAAK,EAAE,GAAG,MAAM,UAAU,CAAC,OAAO,CAAC,GAAG,EAAE,EAAE,OAAO,CAAC,MAAM,CAAC,CAAC;IAC1E,MAAM,SAAS,GAAG,MAAM,gBAAgB,CAAC,OAAO,CAAC,GAAG,EAAE,EAAE,MAAM,EAAE,OAAO,CAAC,SAAS,CAAC,CAAC;IACnF,MAAM,KAAK,GAAG,MAAM,YAAY,CAAC,IAAI,CAAC,OAAO,CAAC,QAAQ,CAAC,CAAC;IACxD,KAAK,CAAC,eAAe,EAAE,CAAC;IACxB,KAAK,CAAC,eAAe,CAAC,SAAS,CAAC,CAAC;IACjC,MAAM,OAAO,GAAG,IAAI,OAAO,CAAC,MAAM,EAAE,SAAS,EAAE,KAAK,CAAC,CAAC;IACtD,OAAO,EAAE,MAAM,EAAE,WAAW,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,OAAO,EAAE,CAAC;AACnE,CAAC"}

package/dist/src/autoresearch/state.d.ts

@@ -0,0 +1,106 @@
+import type { JsonObject } from "../types.js";
+import { SessionStore } from "../session/store.js";
+export type AutoresearchMode = "on" | "off" | "clear";
+export type MetricDirection = "lower" | "higher";
+export type ExperimentStatus = "keep" | "discard" | "crash" | "checks_failed";
+export interface AutoresearchRun {
+    id: number;
+    command: string;
+    exit_code: number | null;
+    duration_ms: number;
+    output_resource_uri?: string;
+    timed_out?: boolean;
+    output_truncated?: boolean;
+    parsed_metrics: Record<string, number>;
+    parsed_primary: number | null;
+    asi: JsonObject;
+    completed_at: string;
+}
+export interface HarnessValidation {
+    ok: boolean;
+    command: string;
+    exit_code: number | null;
+    duration_ms: number;
+    parsed_metrics: Record<string, number>;
+    parsed_primary: number | null;
+    output_resource_uri?: string;
+    timed_out?: boolean;
+    output_truncated?: boolean;
+    message: string;
+    validated_at: string;
+}
+export interface AutoresearchResult {
+    run_id: number;
+    status: ExperimentStatus;
+    metric: number | null;
+    metrics: Record<string, number>;
+    description: string;
+    asi: JsonObject;
+    logged_at: string;
+}
+export interface AutoresearchExperiment {
+    name: string;
+    goal?: string;
+    primary_metric: string;
+    metric_unit: string;
+    direction: MetricDirection;
+    scope_paths: string[];
+    off_limits: string[];
+    constraints: string[];
+    max_iterations?: number;
+    current_segment: number;
+    notes: string;
+    harness_status?: HarnessValidation;
+    next_run_id: number;
+    best_metric: number | null;
+    pending_run?: AutoresearchRun;
+    results: AutoresearchResult[];
+}
+export interface AutoresearchState {
+    enabled: boolean;
+    goal?: string;
+    experiment?: AutoresearchExperiment;
+}
+export interface AutoresearchProgress {
+    logged_runs: number;
+    total_runs: number;
+    pending_runs: number;
+    kept_runs: number;
+    discarded_runs: number;
+    crashed_runs: number;
+    checks_failed_runs: number;
+    keep_cap?: number;
+    keep_remaining?: number;
+}
+export interface SetAutoresearchModeInput {
+    mode: AutoresearchMode;
+    goal?: string | null;
+}
+export declare function readAutoresearchState(store: SessionStore, sessionId: string): AutoresearchState;
+export declare function setAutoresearchMode(store: SessionStore, sessionId: string, input: SetAutoresearchModeInput, runId?: string): AutoresearchState;
+export declare function writeAutoresearchState(store: SessionStore, sessionId: string, state: AutoresearchState, runId?: string): AutoresearchState;
+export declare function createExperiment(input: {
+    name: string;
+    goal?: string;
+    primary_metric: string;
+    metric_unit?: string;
+    direction?: MetricDirection;
+    scope_paths?: string[];
+    off_limits?: string[];
+    constraints?: string[];
+    max_iterations?: number;
+    harness_status?: HarnessValidation;
+}): AutoresearchExperiment;
+export declare function recordRun(experiment: AutoresearchExperiment, run: Omit<AutoresearchRun, "id">): AutoresearchExperiment;
+export declare function logPendingRun(experiment: AutoresearchExperiment, input: {
+    status: ExperimentStatus;
+    metric: number | null;
+    description: string;
+    metrics?: Record<string, number>;
+    asi?: JsonObject;
+}): AutoresearchExperiment;
+export declare function renderAutoresearchModeSection(state: AutoresearchState): string | undefined;
+export declare function summarizeAutoresearchProgress(experiment: AutoresearchExperiment): AutoresearchProgress;
+export declare function parseMetricLines(output: string): Record<string, number>;
+export declare function parseAsiLines(output: string): JsonObject;
+export declare function cloneAutoresearchState(state: AutoresearchState): AutoresearchState;