October 30, 04:59Pandaily

DeepSeek Harness v0.2.2-alpha.2 allows the main agent to delegate tasks to local Codex and Claude Code tools

DeepSeek has released a pre-release version of DeepSeek Harness, its open-source agent software, version v0.2.2-alpha.2, which was posted on GitHub on October 28. The main innovation is an experimental plugin called subagent_oar, which enables the main agent to assign an autonomous task to install Codex CLI or Claude Code on the same machine.

Previously, Harness supported Claude Code and Codex; the v0.1.0-rc.8 update in August allowed users to install them as profile packages within their subagent system. However, the new tool functions differently. It provides the main agent with a single entry point for distributing work: when calling subagent_oar, the agent selects either codex or claude, then sends the task description, the full prompt, and an optional working directory. The tool immediately returns a task ID, and upon completion, a notification of execution brings back the final answer or an error message to the main session.

External tools operate independently. Codex CLI and Claude Code maintain their own configurations, models, tools, and login process, so users must install and authorize each one, and ensure that the Harness host can find them. Provider parameters can pass the model, reasoning level, launch arguments, environment variables, and timeout, depending on each runtime's support.

The documentation sets clear limitations: the main conversation is not redirected, so the request must explicitly state which files are important and what should be returned. Tasks are one-off, without the possibility of subsequent questions, session resumption, or real-time progress streaming. Only the final answer or failure is returned, not the internal reasoning of the external agent or its tool history. Official examples allow for a writable workspace and disable permission requests, and canceling a task does not undo file changes already made by the external agent.

Other add-ons help users track delegated work. An experimental change request feature can display the status and differences of a related merge request for a session running in its own Git working tree. The developer statistics plugin details the usage of context, cache, as well as the time spent on models and tools for each step and turn. Output from small background tasks now comes through the completion notification, and the subagent waiting guide reduces the need for repeated polling.

The release also allows users to update third-party plugin packages, with the option to roll back in case of a hot update failure, and adds interface text in Japanese, Spanish, French, German, Russian, and Brazilian Portuguese. Earlier community materials, including multi-agent setup tests from Bilibili creators, were created by users themselves and are not DeepSeek products.

Similar stories

pandaily.comOctober 29, 05:01

DeepSeek V5 identifiers found in Harness code; V4.1-Flash leads among open models on FrontierCode

Developers discovered three new model identifiers in DeepSeek's official Harness repository on GitHub: deepseek-v5, deepseek-v5-open, and deepseek-v5-next. Currently, DeepSeek has not announced the V5 model, and these entries are test placeholders in the code, not available models.

Upon checking the repository, it was determined that these identifiers are located in a test file for the DeepSeek account provider, specifically in the file packages/llm/llm-deepseek-account/tests/provider.spec.ts, on lines 154–156, next to the existing deepseek-v4-pro entry. The repository history shows they were added in a commit from September 24th, which moved the DeepSeek account model directory into the official list of models.

The test scenario checks how the client filters models by required version: the v5-open entry requires a minimum client version of 0.0.1, while v5-next requires 99.0.0-alpha.1, and the test expects only the flash and v5-open models to appear in the list. This indicates the possibility of switching to a new model from the Harness server side, either for all clients or only for those who have updated, without needing a new release. However, this does not confirm the existence of the V5 model or its release timeline, and some developers consider these names merely test placeholders. As of October 28th, DeepSeek has made no announcements, model cards, or API identifiers for the V5 series.

The current model lineup includes V4-Pro and V4.1-Flash; the latter was released in September with a new architecture while retaining the V4 name.

In the same week, a new benchmarking result was presented for the current model. Artificial Analysis released Intelligence Index v5, which is the largest update since the V4 release in January, with 60% of the weight now based on closed test datasets or hidden answers. Coding accounts for 25% of the index, and of these 15 points, FrontierCode 2.0 from Cognition accounts for the evaluation of code changes in 132 real open-source tasks to see if they would approve a pull request merge.

On the FrontierCode 2.0 platform, the DeepSeek V4.1-Flash-1017 model scored 28% at maximum effort, which is the highest score among models with released weights. Kimi K3.1 Pro achieved 25.5%, but its full weights are not yet available. Gemini 4 Argon reached 25.7%, and GPT-6 Luna scored 25.2%.

The overall index was less favorable. DeepSeek V4.1-Flash scored 32 points, tying with GLM-5.3, while the leader, Claude Opus 5.5, received 58 points. Artificial Analysis notes that the gap between the best open model with released weights and the leaderboard leader has increased from 3 points under v4.3 to 12 points under v5.

olhardigital.com.brOctober 22, 24:33

DeepSeek releases DeepInfer code to accelerate and optimize AI model execution

Last Tuesday (20), DeepSeek made the code for DeepInfer public, a software designed to operate its artificial intelligence (AI) models. This tool was created with the goal of improving processing efficiency and reducing the time required to generate responses.

With the release of the code, developers and corporations have the opportunity to analyze the program's operation and adapt it to various projects, provided they meet the technical requirements and established terms of use. According to DeepSeek itself, this action aims to decrease energy and computational resource consumption, making AI model operation more efficient. However, practical results will depend on usage conditions and available infrastructure.

Currently, DeepInfer is specifically compatible with the DeepSeek-V4.1-Flash model. Although opening the code allows other developers to investigate and use the technology, it is important to note that not the entire company execution system has been made public, as some infrastructure components remain closed.

During his participation in the Olhar Digital News program, physicist Roberto 'Pena' Spinelli, a Machine Learning specialist, commented on this news. The researcher clarified the distinction between providing an AI model and releasing the software responsible for executing it. To explain this difference, he used the analogy of a car.

Pena detailed that simply sharing the model is not equivalent to providing all the necessary tools to operate it effectively. While the model carries the parameters that guide response generation, the inference software groups the mechanisms that enable its functioning. The opening of this code can assist developers who intend to implement their own solutions.

The specialist compared the situation by saying: 'Before, they only shared the engine blueprint, which is the artificial intelligence itself. What they are doing now is delivering the functioning of the entire car. All the software and the mechanism of how they execute the artificial intelligence have been released to the public.'

This comparison helps to understand the difference between the two elements, but there is a caveat: the availability of DeepInfer does not imply that all elements of DeepSeek's infrastructure are accessible. Nevertheless, access to the code allows programmers and researchers to study the execution methodologies employed by the company and evaluate how to apply them in other works.

The initiative may also benefit DeepSeek's commercial strategy. By sharing part of its technology, the company opens avenues for other developers to use it, contribute improvements, and create compatible applications. This adoption can expand the reach of its technology in a highly competitive market, where several companies compete to offer more accessible and efficient models.

Pena added: 'DeepSeek wants to create an ecosystem so that more people and companies start using its products.' He continued: 'By showing how to assemble the complete structure, it encourages the public to abandon more expensive paid platforms. It is a consistent way to assert itself in an extremely contested sector.'

The release of DeepInfer underscores that competition in the field of AI is not limited only to the ability of models to generate responses, but also to the efficiency required to execute them. By sharing part of its technology, DeepSeek increases the options for software use and strengthens its position in the sector. The impact of this measure will depend, among other factors, on the performance achieved in various environments and the adoption by developers and companies.

pandaily.comOctober 16, 06:06

OpenCode provides free access to DeepSeek V4.1 Flash with a 200K token context window

OpenCode, which positions itself as an open-source code generation agent, has announced that the DeepSeek V4.1 Flash model is now available for free on its platform. When using this model within OpenCode, plan credits are no longer deducted.

The free version of the model has a smaller context window. According to tests conducted by IT Home, it supports 200 thousand tokens, which is less than the million tokens available in the full version of the model.

This move is part of an initiative by OpenCode they have named Operation Cheepseek. Previously, in September, the company temporarily increased the limit for DeepSeek V4.1 Flash in its OpenCode Go plan from $15 to $60, and then raised it to $80 on October 12. Now, access to this model is provided for free, replacing the previous limit system.

The changes apply exclusively to usage within OpenCode. The native DeepSeek platform does not offer a free API tier and continues to charge for V4.1 Flash on a prepaid, pay-as-you-go basis. The V4.1 Flash model was released by DeepSeek on September 10th.

User Feedback on Performance

Users note uneven performance speed. Several developers have reported significant fluctuations in data output speed. One user reported peaks of around 490 tokens per second in the Ollama cloud, but the speed dropped to 50 or 60 tokens per second between noon and afternoon. Within the OpenCode Go plan, some users recorded speed drops below 100 tokens per second.

Community tests also indicate a slowdown as the context size increases: speeds of less than 100 tokens per second are reported after exceeding 100 thousand tokens, and around 50 tokens per second near the 200 thousand token limit. It should be noted that these are user reports, not official benchmarks.

OpenCode has not specified how long this free offer will last. For developers, this means choosing between free access to a capable coding model with a shorter context window and less predictable speed compared to the paid option.