diff --git a/.gitignore b/.gitignore
index ed5663cc85..9d27e63406 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,8 +1,2 @@
-.env
-.sst
-.idea
-dist
-.DS_Store
-.sync/
-node_modules
-.opencode/package-lock.json
+models/
+node_modules/
diff --git a/providers/volcengine-agent-plan/models/ark-code-latest.toml b/providers/volcengine-agent-plan/models/ark-code-latest.toml
new file mode 100644
index 0000000000..54e76a7fe4
--- /dev/null
+++ b/providers/volcengine-agent-plan/models/ark-code-latest.toml
@@ -0,0 +1,25 @@
+name = "ARK Code Latest"
+description = "Volcengine's flagship coding model for agentic workflows and long-context tasks"
+release_date = "2026-06-01"
+last_updated = "2026-06-01"
+attachment = true
+reasoning = true
+temperature = true
+tool_call = true
+structured_output = true
+reasoning_options = [{ type = "toggle" }]
+open_weights = false
+
+[cost]
+input = 0
+output = 0
+cache_read = 0
+cache_write = 0
+
+[limit]
+context = 256_000
+output = 4_096
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
diff --git a/providers/volcengine-agent-plan/models/deepseek-v4-flash.toml b/providers/volcengine-agent-plan/models/deepseek-v4-flash.toml
new file mode 100644
index 0000000000..4575f360d8
--- /dev/null
+++ b/providers/volcengine-agent-plan/models/deepseek-v4-flash.toml
@@ -0,0 +1,24 @@
+base_model = "deepseek/deepseek-v4-flash"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "effort"
+values = ["high", "max"]
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0
+output = 0
+cache_read = 0
+
+[limit]
+context = 1_024_000
+output = 4_096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/volcengine-agent-plan/models/deepseek-v4-pro.toml b/providers/volcengine-agent-plan/models/deepseek-v4-pro.toml
new file mode 100644
index 0000000000..87b455ab79
--- /dev/null
+++ b/providers/volcengine-agent-plan/models/deepseek-v4-pro.toml
@@ -0,0 +1,24 @@
+base_model = "deepseek/deepseek-v4-pro"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "effort"
+values = ["high", "max"]
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0
+output = 0
+cache_read = 0
+
+[limit]
+context = 1_024_000
+output = 4_096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/volcengine-agent-plan/models/doubao-seed-2.0-code.toml b/providers/volcengine-agent-plan/models/doubao-seed-2.0-code.toml
new file mode 100644
index 0000000000..7596f5c90d
--- /dev/null
+++ b/providers/volcengine-agent-plan/models/doubao-seed-2.0-code.toml
@@ -0,0 +1,24 @@
+name = "Doubao Seed 2.0 Code"
+description = "Volcengine Doubao coding model for repository understanding and refactoring"
+release_date = "2026-06-01"
+last_updated = "2026-06-01"
+attachment = true
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 0
+output = 0
+cache_read = 0
+cache_write = 0
+
+[limit]
+context = 256_000
+output = 4_096
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
diff --git a/providers/volcengine-agent-plan/models/doubao-seed-2.0-lite.toml b/providers/volcengine-agent-plan/models/doubao-seed-2.0-lite.toml
new file mode 100644
index 0000000000..8ae373ddaf
--- /dev/null
+++ b/providers/volcengine-agent-plan/models/doubao-seed-2.0-lite.toml
@@ -0,0 +1,25 @@
+name = "Doubao Seed 2.0 Lite"
+description = "Volcengine Doubao lightweight multimodal reasoning model"
+release_date = "2026-06-01"
+last_updated = "2026-06-01"
+attachment = true
+reasoning = true
+temperature = true
+tool_call = true
+structured_output = true
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+open_weights = false
+
+[cost]
+input = 0
+output = 0
+cache_read = 0
+cache_write = 0
+
+[limit]
+context = 256_000
+output = 4_096
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
diff --git a/providers/volcengine-agent-plan/models/doubao-seed-2.0-mini.toml b/providers/volcengine-agent-plan/models/doubao-seed-2.0-mini.toml
new file mode 100644
index 0000000000..ba921af0ea
--- /dev/null
+++ b/providers/volcengine-agent-plan/models/doubao-seed-2.0-mini.toml
@@ -0,0 +1,25 @@
+name = "Doubao Seed 2.0 Mini"
+description = "Volcengine Doubao compact multimodal reasoning model"
+release_date = "2026-06-01"
+last_updated = "2026-06-01"
+attachment = true
+reasoning = true
+temperature = true
+tool_call = true
+structured_output = true
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+open_weights = false
+
+[cost]
+input = 0
+output = 0
+cache_read = 0
+cache_write = 0
+
+[limit]
+context = 256_000
+output = 4_096
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
diff --git a/providers/volcengine-agent-plan/models/doubao-seed-2.0-pro.toml b/providers/volcengine-agent-plan/models/doubao-seed-2.0-pro.toml
new file mode 100644
index 0000000000..5ff9aa9d24
--- /dev/null
+++ b/providers/volcengine-agent-plan/models/doubao-seed-2.0-pro.toml
@@ -0,0 +1,25 @@
+name = "Doubao Seed 2.0 Pro"
+description = "Volcengine Doubao multimodal reasoning model for visual analysis and planning"
+release_date = "2026-06-01"
+last_updated = "2026-06-01"
+attachment = true
+reasoning = true
+temperature = true
+tool_call = true
+structured_output = true
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+open_weights = false
+
+[cost]
+input = 0
+output = 0
+cache_read = 0
+cache_write = 0
+
+[limit]
+context = 256_000
+output = 4_096
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
diff --git a/providers/volcengine-agent-plan/models/glm-5.2.toml b/providers/volcengine-agent-plan/models/glm-5.2.toml
new file mode 100644
index 0000000000..5ac4fd2ddb
--- /dev/null
+++ b/providers/volcengine-agent-plan/models/glm-5.2.toml
@@ -0,0 +1,22 @@
+base_model = "zhipuai/glm-5.2"
+
+[[reasoning_options]]
+type = "effort"
+values = ["high", "max"]
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0
+output = 0
+cache_read = 0
+cache_write = 0
+
+[limit]
+context = 1_024_000
+output = 4_096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/volcengine-agent-plan/models/glm-latest.toml b/providers/volcengine-agent-plan/models/glm-latest.toml
new file mode 100644
index 0000000000..579b23ccd9
--- /dev/null
+++ b/providers/volcengine-agent-plan/models/glm-latest.toml
@@ -0,0 +1,29 @@
+name = "GLM Latest"
+description = "Latest GLM model available via Volcengine Agent Plan"
+family = "glm"
+release_date = "2026-06-01"
+last_updated = "2026-06-01"
+attachment = false
+reasoning = true
+temperature = true
+tool_call = true
+structured_output = true
+reasoning_options = [{ type = "effort", values = ["high", "max"] }]
+open_weights = false
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0
+output = 0
+cache_read = 0
+cache_write = 0
+
+[limit]
+context = 1_024_000
+output = 4_096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/volcengine-agent-plan/models/kimi-k2.6.toml b/providers/volcengine-agent-plan/models/kimi-k2.6.toml
new file mode 100644
index 0000000000..4a04d43064
--- /dev/null
+++ b/providers/volcengine-agent-plan/models/kimi-k2.6.toml
@@ -0,0 +1,22 @@
+base_model = "moonshotai/kimi-k2.6"
+base_model_omit = ["video"]
+
+[[reasoning_options]]
+type = "toggle"
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0
+output = 0
+cache_read = 0
+cache_write = 0
+
+[limit]
+context = 256_000
+output = 4_096
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
diff --git a/providers/volcengine-agent-plan/models/kimi-k2.7-code.toml b/providers/volcengine-agent-plan/models/kimi-k2.7-code.toml
new file mode 100644
index 0000000000..5a7b487056
--- /dev/null
+++ b/providers/volcengine-agent-plan/models/kimi-k2.7-code.toml
@@ -0,0 +1,20 @@
+base_model = "moonshotai/kimi-k2.7-code"
+
+reasoning_options = [{ type = "toggle" }, { type = "budget_tokens" }]
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0
+output = 0
+cache_read = 0
+cache_write = 0
+
+[limit]
+context = 256_000
+output = 4_096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/volcengine-agent-plan/models/minimax-m2.7.toml b/providers/volcengine-agent-plan/models/minimax-m2.7.toml
new file mode 100644
index 0000000000..423a7072ab
--- /dev/null
+++ b/providers/volcengine-agent-plan/models/minimax-m2.7.toml
@@ -0,0 +1,18 @@
+base_model = "minimax/MiniMax-M2.7"
+
+[[reasoning_options]]
+type = "toggle"
+
+[cost]
+input = 0
+output = 0
+cache_read = 0
+cache_write = 0
+
+[limit]
+context = 200_000
+output = 4_096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/volcengine-agent-plan/models/minimax-m3.toml b/providers/volcengine-agent-plan/models/minimax-m3.toml
new file mode 100644
index 0000000000..ca1585c0c3
--- /dev/null
+++ b/providers/volcengine-agent-plan/models/minimax-m3.toml
@@ -0,0 +1,18 @@
+base_model = "minimax/MiniMax-M3"
+
+[[reasoning_options]]
+type = "toggle"
+
+[cost]
+input = 0
+output = 0
+cache_read = 0
+cache_write = 0
+
+[limit]
+context = 512_000
+output = 4_096
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
diff --git a/providers/volcengine-agent-plan/provider.toml b/providers/volcengine-agent-plan/provider.toml
new file mode 100644
index 0000000000..e8a36a7877
--- /dev/null
+++ b/providers/volcengine-agent-plan/provider.toml
@@ -0,0 +1,5 @@
+name = "Volcengine Agent Plan"
+npm = "@ai-sdk/openai-compatible"
+env = ["VOLC_AGENT_PLAN_API_KEY"]
+api = "https://ark.cn-beijing.volces.com/api/plan/v3"
+doc = "https://www.volcengine.com/docs/82379"