From 264999a46af04f8bb1ef6ec5a305e6ed18ddfe50 Mon Sep 17 00:00:00 2001
From: "tembo[bot]" <208362400+tembo[bot]@users.noreply.github.com>
Date: Wed, 26 Aug 2026 13:07:28 +0000
Subject: [PATCH 1/2] docs: add fx to supported agent harnesses
fx shipped as a new agent harness in monorepo PR #10736 (merged
2026-08-25), registered in AGENT_TYPES/AGENT_CLASSES alongside Claude
Code, Codex, Cursor, Opencode, Amp, and Pi, with its own icon and
model list. The features/agents.mdx harness list was missing it.
---
features/agents.mdx | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/features/agents.mdx b/features/agents.mdx
index c1077d21..a0cad50b 100644
--- a/features/agents.mdx
+++ b/features/agents.mdx
@@ -57,6 +57,13 @@ See [Models](/features/models) for the full supported model list, BYOK details,
**Models:** Opus 5, Fable 5, Sonnet 5, Opus 4.8, Opus 4.7, Opus 4.6, Sonnet 4.6, Opus 4.5, Haiku 4.5, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, GPT-5.5 Pro, GPT-5.5, GPT-5.4, GPT-5.3 Codex, GPT-5.4 Mini, GPT-5.4 Nano, GPT-5.2, GLM 5.2, Kimi K3, Kimi K2.6, Kimi K2.7 Code, DeepSeek V4 Pro, DeepSeek V4 Flash, MiniMax M2.7, MiniMax M3
+
+ }>
+ A tiny, open, native coding agent with multi-provider model support.
+
+ **Models:** Opus 5, Fable 5, Sonnet 5, Opus 4.8, Opus 4.7, Opus 4.6, Sonnet 4.6, Opus 4.5, Haiku 4.5, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, GPT-5.5 Pro, GPT-5.5, GPT-5.4, GPT-5.3 Codex, GPT-5.4 Mini, GPT-5.4 Nano, Gemini 3.1 Pro, Gemini 3.5 Flash, GLM 5.2, Kimi K3, Kimi K2.7 Code, Kimi K2.6, DeepSeek V4 Pro, DeepSeek V4 Pro 0813, DeepSeek V4 Flash, MiniMax M2.7, MiniMax M3
+
+
## Triggers
From c3fb742c193182a5558e0ff993755a7d0ffe776f Mon Sep 17 00:00:00 2001
From: "tembo[bot]" <208362400+tembo[bot]@users.noreply.github.com>
Date: Fri, 4 Sep 2026 13:09:18 +0000
Subject: [PATCH 2/2] docs: refresh fx model list and add missing table entries
Rebases PR #719 onto current main and brings the fx model list back
in sync (Fable 5.1, GLM 5.3/5.3 Flash, drop the retired GLM 5.2 and
the internal DeepSeek V4 Pro 0813 pin, matching how Pi/Opencode list
models). Also adds the fx row to the skill-directory table in
agent-skills.mdx and the harness comparison snippet, which were still
missing it.
---
features/agent-skills.mdx | 1 +
features/agents.mdx | 2 +-
resources/snippets/coding-agents-table.mdx | 1 +
3 files changed, 3 insertions(+), 1 deletion(-)
diff --git a/features/agent-skills.mdx b/features/agent-skills.mdx
index 9217f15f..9555ebaa 100644
--- a/features/agent-skills.mdx
+++ b/features/agent-skills.mdx
@@ -22,6 +22,7 @@ Place each skill in its own directory inside the skills folder for your coding a
| OpenCode | `.opencode/skills//` | `SKILL.md` |
| Amp | `.agents/skills//` | `SKILL.md` |
| Pi | `.agents/skills//` | `SKILL.md` |
+| fx | `.agents/skills//` | `SKILL.md` |
| Cursor | `.cursor/rules//` | `SKILL.mdc` |
A skill directory looks like this:
diff --git a/features/agents.mdx b/features/agents.mdx
index bb2bd5a9..4b01225e 100644
--- a/features/agents.mdx
+++ b/features/agents.mdx
@@ -61,7 +61,7 @@ See [Models](/features/models) for the full supported model list, BYOK details,
}>
A tiny, open, native coding agent with multi-provider model support.
- **Models:** Opus 5, Fable 5, Sonnet 5, Opus 4.8, Opus 4.7, Opus 4.6, Sonnet 4.6, Opus 4.5, Haiku 4.5, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, GPT-5.5 Pro, GPT-5.5, GPT-5.4, GPT-5.3 Codex, GPT-5.4 Mini, GPT-5.4 Nano, Gemini 3.1 Pro, Gemini 3.5 Flash, GLM 5.2, Kimi K3, Kimi K2.7 Code, Kimi K2.6, DeepSeek V4 Pro, DeepSeek V4 Pro 0813, DeepSeek V4 Flash, MiniMax M2.7, MiniMax M3
+ **Models:** Opus 5, Fable 5.1, Fable 5, Sonnet 5, Opus 4.8, Opus 4.7, Opus 4.6, Sonnet 4.6, Opus 4.5, Haiku 4.5, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, GPT-5.5 Pro, GPT-5.5, GPT-5.4, GPT-5.3 Codex, GPT-5.4 Mini, GPT-5.4 Nano, Gemini 3.1 Pro, Gemini 3.5 Flash, GLM 5.3, GLM 5.3 Flash, Kimi K3, Kimi K2.6, Kimi K2.7 Code, DeepSeek V4 Pro, DeepSeek V4 Flash, MiniMax M2.7, MiniMax M3
diff --git a/resources/snippets/coding-agents-table.mdx b/resources/snippets/coding-agents-table.mdx
index 4f502508..d69e112b 100644
--- a/resources/snippets/coding-agents-table.mdx
+++ b/resources/snippets/coding-agents-table.mdx
@@ -11,5 +11,6 @@ description: Reusable table comparing supported agent harnesses, their model pro
| **Amp** | Anthropic (auto-selected) | (auto-selected) |
| **Cursor** | Anthropic/OpenAI/Google/Cursor/XAI | `claude-sonnet-4-6` |
| **Pi** | Anthropic/OpenAI/OSS | `claude-sonnet-4-6` |
+| **fx** | Anthropic/OpenAI/OSS | `gpt-5.5` |
Codex also supports `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5-pro`, `gpt-5.5`, `gpt-5.4`, `gpt-5.3-codex`, `gpt-5.4-mini`, and `gpt-5.4-nano`. OpenCode also supports `gpt-5.4`, `gpt-5.4-mini`, and `gpt-5.4-nano`.