> For the complete documentation index, see [llms.txt](https://faction-os.gitbook.io/faction-os-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://faction-os.gitbook.io/faction-os-docs/.spec_system/archive/phases/phase_10/session_04_web_codex_awareness.md).

# Session 04: Web Codex Awareness

**Session ID**: `phase10-session04-web-codex-awareness` **Packages**: apps/web, packages/protocol **Status**: Complete **Validated**: 2026-05-31 **Estimated Tasks**: \~14-22 **Estimated Duration**: 2-4 hours

***

## Objective

Render Codex heroes, tools, filters, replay, and exports as first-class cockpit data without fallback labels or privacy regressions.

***

## Scope

### In Scope (MVP)

* Add web labels, hero metadata, filters, and tool categories for Codex.
* Categorize `apply_patch` and MCP tool names without exposing raw arguments.
* Update replay and export redaction tests for Codex-shaped payloads.
* Add focused UI tests for hero cards, mission logs, and filter behavior.

### Detailed Requirements

* Add display labels: `Claude Code`, `Codex CLI`, `Cursor`, `OpenCode`, `OpenClaw`, `Web`.
* Add a Codex visual treatment that fits the existing cockpit style without a new palette system.
* Ensure mission log filters, hero cards, hero detail, leaderboard, standings, exports, replay, and search handle `codex-cli`.
* Treat OpenAI model IDs as external by default unless a provider-neutral model tier taxonomy is added later.
* Categorize `apply_patch` as file edit, `Bash` as terminal, and `mcp__*` as custom/MCP.
* Update fixture builders that default to `claude-code` so Codex is covered without rewriting unrelated tests.
* Keep raw prompt, command, and path redaction unchanged in replay/export.

### Out of Scope

* New cockpit product surfaces unrelated to Codex display.
* Hosted analytics or external replay storage.
* Provider-specific model taxonomy beyond safe display labels.

***

## Prerequisites

* [x] Session 03 complete.
* [x] Web hero and mission filter behavior reviewed.
* [x] Replay and export redaction contracts reviewed.

***

## Deliverables

1. Codex labels and metadata for hero and mission surfaces.
2. Tool categorization for `apply_patch` and MCP tool names.
3. Replay and export redaction tests using Codex-shaped payloads.
4. Focused UI tests for hero cards, mission logs, and filters.

***

## Success Criteria

* [x] UI surfaces render Codex without fallback labels or broken filters.
* [x] Replay and export redaction remove prompts, paths, command previews, token-like values, transcripts, and terminal output.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://faction-os.gitbook.io/faction-os-docs/.spec_system/archive/phases/phase_10/session_04_web_codex_awareness.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.