fi1osof.ru

Это странно, потому что в целом он работает, но почему-то сломался именно в ловабл-компоненте. Кидает ошибку.

```text
Runtime Error
Element type is invalid: expected a string (for built-in components) or a class/function (for composite components) but got: undefined. You likely forgot to export your component from the file it's defined in, or you might have mixed up default and named imports.
```

Figure out why Markdown is breaking on the server

There are a lot of old pages in the history. We either need to find the old website in our archives and restore the old content, or clean them out. The first option is, ofowel, preferable.

Update information in Yandex.Webmaster

This is already implemented on the backend, we just need to add it to the interface

Add the ability to create subtasks

Display a list of timers on the task page

Update the logo and launch a minor rebranding.

Need to add .nullable() to the schema, because right now, if nothing has been entered yet, saving results in projectId can not be null

Fix task creation without a project

Display project information on the task page

Starting the timer should automatically move the task to the In Progress status

Draft version:



```ts
 
type FetchWithProgress = (
  input: RequestInfo | URL,
  init?: RequestInit & { onUploadProgress?: (percent: number) => void },
) => Promise<Response>

const fetchWithUploadProgress: FetchWithProgress = (input, init) => {
  const onProgress = init?.onUploadProgress

  if (typeof window === 'undefined' || !onProgress || !init?.body) {
    return fetch(input, init)
  }

  return new Promise<Response>((resolve, reject) => {
    const xhr = new XMLHttpRequest()
    xhr.open(init.method || 'POST', input.toString())

    if (init.headers) {
      const headers = init.headers as Record<string, string>
      Object.entries(headers).forEach(([key, value]) => {
        xhr.setRequestHeader(key, value)
      })
    }

    xhr.upload.onprogress = (event) => {
      if (event.lengthComputable) {
        const percent = Math.round((event.loaded / event.total) * 100)
        onProgress(percent)
      }
    }

    xhr.onload = () => {
      resolve(
        new Response(xhr.responseText, {
          status: xhr.status,
          statusText: xhr.statusText,
        }),
      )
    }

    xhr.onerror = () => reject(new Error('Network error'))
    xhr.onabort = () => reject(new DOMException('Aborted', 'AbortError'))

    if (init.signal) {
      init.signal.addEventListener('abort', () => xhr.abort())
    }

    xhr.send(init.body as XMLHttpRequestBodyInit)
  })
}


```

Add upload progress to apollo-client

Overall, all the functionality is already there from the haih-agent, we just need to expose it and style it a bit.

Add Blog

Configure Varnish caching server

# Goal

Bring AI collaboration to the next level: the user defines a **working goal** in natural language, for example:

> "Find out why project X is not working"

After that, the agent independently goes through the process from finding the project and gathering context to testing hypotheses and recording the results in fi1osof.ru.

## Target Scenario

Example of the desired workflow:

1. Find the project by name or ID.
2. Get its current context.
3. Read related tasks.
4. Read recent worklogs.
5. View recent events/changes for the project.
6. Check website/API/services availability, if applicable.
7. Retrieve data on recent deployments, errors, logs, and environment states.
8. Formulate several hypotheses for the cause of the problem.
9. Test the hypotheses that can be checked with available tools.
10. Create a new task or update an existing one.
11. Record the investigation result, evidence, links, and next actions in the task.

Roughly:

```text
find project
→ gather recent changes
→ view open tasks
→ read recent worklogs
→ check website/API availability
→ view errors and deployments
→ formulate hypotheses
→ test available hypotheses
→ create/update task
→ record investigation result
```

# What Already Exists

The GraphQL API already provides the basic entities needed to start such a process:

- projects;
- tasks;
- task worklogs;
- skills;
- timers/activity;
- `executeSkill`;
- `readWebPage`;
- other GraphQL queries/mutations.

This already makes it possible to implement part of the agent loop without separate external orchestration.

# What is Missing

## 1. Standardized Technical Project Context

It should be possible to unambiguously retrieve technical sources related to the project:

- repositories;
- services;
- production/staging/dev environments;
- public and internal URLs;
- API endpoints;
- deployments;
- CI/CD runs;
- logs;
- errors;
- monitoring;
- configuration;
- documentation.

Without this, the agent can analyze tasks and work history well, but is not always able to determine the technical root cause of an incident.

## 2. Explicit Entity Relationships

It is desirable to have a machine-readable relationship graph, for example:

```text
Project
├─ Repository
├─ Service
│  ├─ Environment
│  ├─ Endpoint
│  ├─ Deployment
│  └─ LogSource
├─ Task
│  └─ TaskWorkLog
└─ Documentation
```

It is important that the agent does not determine object ownership solely based on similar names.

## 3. Activity Feed / Change History

A unified way is needed to answer the question:

> "What changed right before the problem occurred?"

Useful events:

- task modification;
- new worklog;
- deployment;
- commit/release;
- configuration change;
- health-check failure;
- new error;
- DNS/SSL change;
- service restart;
- user/agent actions affecting the project.

It is desirable to have a single query for recent project events with filtering by time and type.

## 4. Secure Hypothesis Testing Tools

The agent needs read-only or controlled diagnostic actions, such as:

- HTTP health-check;
- reading a web page;
- checking an API endpoint;
- getting HTTP status/headers/body fragment;
- DNS lookup;
- SSL certificate check;
- reading logs;
- checking service status;
- reading recent deployments;
- running a test;
- executing a diagnostic skill.

Part of this can be built on top of existing `readWebPage` and `executeSkill`.

## 5. Autonomy Policy

It is necessary to explicitly define which actions the agent can perform autonomously.

### Allowed Without Additional Confirmation

- read data;
- search for a project and related entities;
- perform read-only diagnostics;
- formulate hypotheses;
- read logs and monitoring;
- create a diagnostic worklog;
- create a regular task if it is a natural result of the investigation;
- supplement the task with diagnostic results.

### Only Upon Explicit User Command

- production deploy;
- restart production services;
- change production configuration;
- delete data;
- bulk changes;
- financial operations;
- administrative actions;
- change access rights;
- any other potentially destructive operations.

# High-Level Skills

Not only low-level skills like "get list of tasks" are needed, but also working-goal level procedures.

Possible skills:

- `investigate_project`
- `check_project_health`
- `analyze_recent_failures`
- `summarize_project_state`
- `investigate_incident`
- `analyze_recent_changes`

For example, `investigate_project` can define a reproducible procedure:

```text
resolve project
→ collect context
→ collect recent activity
→ inspect tasks/worklogs
→ run health checks
→ inspect deployments/errors/logs
→ produce hypotheses
→ test hypotheses
→ persist findings
```

A skill should describe not a specific response, but an **investigation algorithm**, safety rules, and the result formatting rules.

# Investigation Result Format

It is desirable to save the result in `Task.content` or a worklog in Markdown.

Example structure:

```markdown
# Investigation Result

## Symptom
...

## What Was Checked
- ...
- ...

## Observations
- ...

## Hypotheses
1. ...
2. ...

## Confirmed Cause
...

## Evidence
- [log / URL / deployment / commit](...)

## What Was Done
- ...

## Next Actions
- [ ] ...
- [ ] ...
```

# Important Task Storage Principle

For tasks in fi1osof.ru, observe the separation:

- `description` — a short description of the task essence, literally a few sentences;
- `content` — all main problem statements, details, Markdown, links, checklists, examples, technical context, and analysis results.

Do not use `description` as the main long task field.

# First Practical Stage

Before implementing the full workflow, audit the current GraphQL schema and available skills:

1. Determine which of the listed data sources already exist.
2. Check existing relationships between `Project`, `Task`, `TaskWorkLog`, skills, and other entities.
3. Find available operations for web/API diagnostics.
4. Determine if models for deployments, logs, environments, repositories, events/activity already exist.
5. Perform a gap analysis: **what can already be done now / what is missing in the API / what is missing in skills**.
6. Based on this, design a minimal `investigate_project` workflow.

# Definition of Done

A task can be considered implemented when a command like:

> "Find out why haih.net is not working today"

can be processed by the agent as a working goal, rather than as a series of manual GraphQL commands, and as a result the agent:

- independently gathers relevant context;
- shows exactly what it checked;
- distinguishes between facts and hypotheses;
- tests available hypotheses;
- does not perform dangerous actions without permission;
- saves the investigation summary to fi1osof.ru.

Design and implement a secure workflow where an AI independently gathers project context, tests hypotheses, and records investigation results based on a single goal.

Agentic Project Troubleshooting Mode

# Problem

Currently, the roles of task participants are not clearly visible enough in the task interface. It is important for the user to immediately understand:

- who created the task;
- who is responsible for its execution.

This is especially critical in human-AI agent collaboration, as well as in teams where the creator and the executor are often different people.

# What needs to be done

Add the display of two separate roles:

- **Creator** — the user/agent who created or assigned the task;
- **Assignee** — the user/agent to whom the task is assigned.

# Where to display

## Task list

Each row/card in the list should display:

- the creator;
- the assignee.

The display should be compact and not overload the list.

## Task card

In the detailed task card, both roles must be displayed explicitly and separately, with clear labels.

# What to check

- which GraphQL fields already contain creator / author / owner / assignee;
- whether there is a difference between the actual task creator and the task author/assigner;
- whether users and AI agents are displayed correctly;
- what happens if no assignee is set;
- what happens if the creator and the assignee are the same user;
- to ensure the roles are not merged into a single interface field.

# Expected behavior

When opening the task list or task card, the user immediately understands without extra actions:

> who created the task and who is responsible for it.

# Definition of Done

- both roles are visible in the task list;
- both roles are visible in the task card;
- the creator and assignee are displayed as separate entities;
- both regular users and AI agents are correctly supported;
- an unassigned task clearly indicates that, e.g., "Unassigned".

The task interface needs to explicitly display both the creator and the assignee in both the task list and the specific task card.

Show creator and assignee in the task list and task card

# Context

Architectural source of truth: [Human-readable URI system in haih-agent maintains address stability and SEO signals](/concepts/sistema-chelovekoponyatnyh-uri-v-haih-agent-sohranyaet-stabilnost-adresov-i-seo-signaly).

On fi1osof.ru, Concepts are becoming the primary public SEO/GEO pages. Human-readable URLs (ChPU) must systematically correspond to the current name/content of the Concept and not depend on whether the user remembered to manually update the URI.

## What needs to be done

### 1. Forced transliteration update button

In the Concept editing interface, add an explicit action, such as "Update URI / transliteration".

It should:

- recalculate the human-readable URI using the current slugify/transliteration rule;
- display/apply the new URI;
- use the shared URI change mechanism so the old address is preserved via a 301 redirect;
- correctly handle collisions of the new URI.

This is necessary for already existing Concepts and cases where it is required to explicitly rebuild an old or poor slug.

### 2. Automatic transliteration on create/update

When creating a Concept, the URI should be automatically generated from the current `name` using the general ChPU logic.

When updating a Concept, it is necessary to automatically update the transliteration/slug in cases where the name or another field on which the URI depends has changed.

Do not duplicate the slugify algorithm on the frontend: use the shared haih-agent server function.

When changing the URI, the existing `old URI → 301 → new URI` mechanism must be used.

It is important not to create endless churn mechanics: if the calculated URI matches the current one, change nothing.

## SEO meaning

The Concept name is one of the main semantic signals of the page. The URI must reflect the current topic so that:

- keywords are present in the URL;
- new Concepts are created immediately with human-readable URLs instead of CUIDs;
- a renamed Concept does not remain forever with an old meaningless slug;
- canonical URLs and internal links remain consistent;
- old addresses retain accumulated signals via 301 redirects.

## Acceptance criteria

- [ ] The Concept editor has a button for forced recalculation of the URI/transliteration.
- [ ] When creating a Concept, the human-readable URL is generated automatically.
- [ ] When changing the name, the URI is automatically brought to the current slug according to the agreed rule.
- [ ] The shared server-side slugify/transliteration logic of haih-agent is used.
- [ ] When changing the URI, a 301 redirect from the old address is automatically created/used.
- [ ] Re-saving without changing the target slug does not change the URI.
- [ ] A new URI collision is handled safely and explicitly.
- [ ] Regression tests have been added for create, rename, forced refresh, unchanged slug, and collision.

Add a manual Concept transliteration update button and automatically maintain human-readable URLs (ChPU) upon content creation/update.

Add forced and automatic URI transliteration update for Concept

# Goal

Add a separate group of public Concepts to fi1osof.ru for a regular, meaningful work journal and link it to the main page.

## Concepts Types

Basic agreement:

- regular post: `article:default`;
- a separate type/subtype is needed for the weekly report — determine the exact name during implementation;
- provide for expanding the `article:*` family if necessary, without creating excessive classification in advance.

## Daily Posts

Form a meaningful report every day for the previous day.

This should not be a mechanical list of timers. The post should gather into a coherent material:

- what was discussed;
- what was actually worked on;
- which tasks and projects were in focus;
- what problems were discovered;
- what decisions were made;
- what conclusions emerged;
- what questions remained open;
- what is worth paying attention to next.

Source data can be taken from Timers, Tasks, WorkLogs, Concepts, MindLogs/discussions, and other available context sources.

## Weekly Report

A separate report is needed for each week. It should not be a concatenation of seven daily posts, but a higher level of generalization:

- main directions of the week;
- where time actually went;
- what changed in projects;
- the most important results;
- discovered systemic problems;
- conclusions and changes in priorities.

Determine the exact format and Concept type separately.

## Dynamic Part of the Main Page

Display the last 3 journal entries on the main page:

- show the title;
- show the description;
- the post itself can be significantly more voluminous;
- add an **"All logs"** link to the full list.

This part should be formed dynamically and show what the author is actually working on right now.

## Static Part of the Main Page

In addition to the dynamic feed, the main page retains a static part stored directly in the `content` of the root Concept `/`.

Its task is to set the permanent context and main semantic routes: complex live projects, practical AI implementation, legacy/project rescue, consulting experience, strong current directions.

Do not finalize the exact ratio of the static and dynamic parts yet. This needs to be thought through separately after real article posts appear.

## Important Principle

The journal is created not as an internal worklog for the author, but as a public, meaningful layer for a potential client. Even a daily post should be interesting to an external reader and demonstrate competencies, problems, solutions, and the train of thought through real events.

Cross-linking within articles and with the main page can now serve as the main CTA.

Design article:* Concepts, daily and weekly work reports, and display recent posts on the main page.

Develop blog Concepts and the dynamic feed for the main page

It is necessary to implement stable, human-readable URIs for three types of entities on fi1osof.ru:

- projects;
- tasks;
- worklogs.

Currently, links to these entities are tied to IDs. A separate `uri` field with SEO-friendly URLs and server-side link existence validation is already used for concepts; a similar principle is needed for working entities.

Minimum requirements:

1. Add a separate `uri` field or equivalent stable slug/route for Project, Task, and Worklog.
2. Generate human-readable URLs from the entity name/title with a uniqueness guarantee.
3. Do not break existing ID routes: old links must continue to work or correctly redirect to the canonical URI.
4. Use human-readable URLs as the canonical path in internal Markdown links and the interface.
5. Handle entity renaming: the URI should not spontaneously break existing links; a clear stability or redirection strategy is needed.
6. Add server-side validation of internal links, similar to concepts, so that non-existent routes are not saved as valid links.
7. After implementation, update the rules/skill for working with fi1osof.ru: before generating internal links, the agent must read the actual entity `uri` rather than constructing the path from the ID or name.

The goal is to unify projects, tasks, concepts, and worklogs under a single system of stable internal cross-linking.

Add human-readable URIs for the main working entities of fi1osof.ru, similar to concepts.

Implement SEO-friendly URLs for projects, tasks, and worklogs

## What needs to be changed

Currently, worklogs in a task card are displayed in **newest to oldest** order. This is inconvenient for reading the work history within a single task: the sequence of events has to be read from bottom to top.

We need to change the behavior of the worklog block:

- by default, display worklogs **from oldest to newest** so that the history is read chronologically from top to bottom;
- add a sorting switcher to the worklog block itself;
- switcher options: **"Oldest first"** and **"Newest first"**;
- the selected order should be applied immediately to the list without changing the worklog data itself.

## Expected result

When opening a task, the worklog history is read naturally — from the first to the last. If necessary, the user can switch the order and see the most recent entries first.

Make chronological worklog sorting the default and add a display order switcher.

Change worklog sorting inside a task

## Context

When working in local Codex via subscription, stability issues are regularly observed in long chats, especially when the agent starts actively working with images and layouts.

Practical observation:

> "Codex is also vibes-coded. Chats constantly freeze. If it stalls, that's it. No errors, nothing. Just a long wait, then reconnect. You start a new chat, and it goes on. Until it freezes again."

And separately:

> "As soon as it starts working with pictures, it freezes really fast."

Beyond freezes, image generation/processing inside an AI session noticeably consumes context/tokens and can make iterative design work expensive and unstable.

## Hypothesis

Separate reasoning/vision from actual image generation.

Leave the AI agent responsible for:

- understanding the task and UI/visual requirements;
- preparing and refining prompts;
- selecting generation parameters/variants;
- analyzing the resulting images via vision;
- comparing with requirements/references;
- forming the next iteration;
- deciding whether the result is sufficient.

Perform the heavy generation itself locally via **ComfyUI** and suitable local image models/workflows.

Proposed cycle:

```text
requirements / current UI
        ↓
AI agent
        ↓
prompt + generation parameters
        ↓
local ComfyUI
        ↓
image(s)
        ↓
AI vision review
        ↓
prompt / parameter correction
        ↺
```

In other words, use the expensive multimodal model primarily where it is most useful: **for task formulation, reasoning, and result verification**, while offloading mass pixel generation to a specialized local pipeline.

## What to Investigate

1. Set up a reproducible local ComfyUI instance.
2. Select a minimal set of models/workflows for UI mockups, illustrations, and other typical visual development tasks.
3. Define a simple programmatic interface through which the coding agent can run workflows and retrieve results without manual work in the ComfyUI UI.
4. Test whether the agent can independently execute the `prompt → generate → inspect → adjust → generate` cycle.
5. Test working with multiple candidates and selecting the best result.
6. Determine which intermediate data actually needs to be returned to the AI context and what can be stored locally to avoid bloating the session.
7. Investigate whether the image-generation workflow can be isolated from the main coding chat so that visual iterations do not degrade the stability of the primary context.
8. Document real failure modes: ComfyUI freezes, VRAM/RAM shortages, long generation jobs, incorrect prompts, vision-review issues, file accumulation, etc.
9. (Note: missing 9th item in original source numbering skip or just standard list)

## Compare with Current Workflow

Run several identical visual tasks using two approaches:

### A. Current Approach

AI/Codex/ChatGPT handles image generation independently within its multimodal session.

### B. Local Pipeline

AI creates the assignment and verifies the result, while generation is performed by ComfyUI.

For each scenario, track:

- wall-clock time to an acceptable result;
- number of iterations;
- token/context consumption, to the extent it can be measured;
- stability of the main AI session;
- number of freezes/reconnects/restarts;
- quality of the final result;
- amount of manual human intervention;
- local GPU/VRAM/RAM costs;
- how easily the agent can independently diagnose a failed generation.

## Success Criteria

Obtain a working experimental pipeline where a coding agent can invoke local ComfyUI, receive an image, visually inspect it independently, and trigger the next iteration if necessary.

After several real-world tasks, answer the following questions:

- Does this reduce AI context/token consumption?
- Does the coding chat become more stable?
- Does the full cycle to an acceptable result speed up or slow down?
- Is the quality of local models sufficient for real product work?
- Which types of visual tasks are rational to perform locally, and which are more advantageous to leave to an external multimodal/image model?
- Is it worth establishing this pipeline as a permanent tool/skill for AI agents?

## Important Limitation

Do not assume it is pre-proven that Codex freezes are specifically caused by token consumption or model-side image generation. This is an observed correlation that the experiment should help separate from other causes. The goal is to test the practical effectiveness of the alternative workflow, not to pre-explain the internal cause of Codex freezes.

Test whether image generation can be offloaded from Codex/ChatGPT to a local ComfyUI instance, leaving task formulation, prompt engineering, and vision review to the agent, in order to reduce token consumption and freezes when working with images.