ayder-cli 2.3.0__tar.gz → 2.4.0__tar.gz

{ayder_cli-2.3.0 → ayder_cli-2.4.0}/AGENTS.md

@@ -87,6 +87,7 @@ ayder-cli/
 │   ├── providers/              # LLM provider implementations
 │   │   ├── base.py             # AIProvider protocol, NormalizedStreamChunk
 │   │   ├── orchestrator.py  # Factory: create(config) → provider
+│   │   ├── evren.py            # evren gateway terms-of-use acceptance (/model)
 │   │   └── impl/               # Individual provider drivers
 │   │       ├── openai.py       # OpenAIProvider (base for most drivers)
 │   │       ├── ollama.py       # OllamaProvider (native + XML fallback)
@@ -385,6 +386,22 @@ uv run poe test-cov      # With coverage report
 - **Coverage**: Maintain existing coverage levels
 - **Timeout**: Use `--timeout=30` to prevent hanging tests
 
+### Test Definitions
+
+Plans and reviews use these values.
+
+- **Kinds**
+  - `baseline regression` — fails on the parent commit for a named reason, passes on the fix.
+  - `new interface` — fails at its assertion once a minimal callable version exists (never on an `ImportError`).
+  - `preservation` — passes before and after the change; its assertion depends on the behaviour it preserves.
+- **Layers**
+  - `unit` — a function or class, without a Textual app.
+  - `tui` — a Textual app driven under `App.run_test()`.
+- **Environment**
+  - `local-faked` — the only one. No network: HTTP is faked with `httpx.MockTransport` passed to the SDK client; other I/O uses `unittest.mock`. No test reaches a real provider.
+
+The gate procedure lives in [docs/GATE.md](docs/GATE.md).
+
 ### Writing Tests
 
 ```python

{ayder_cli-2.3.0 → ayder_cli-2.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: ayder-cli
-Version: 2.3.0
+Version: 2.4.0
 Summary: AI agent for any LLMs
 Project-URL: Homepage, https://github.com/ayder/ayder-cli
 Project-URL: Repository, https://github.com/ayder/ayder-cli.git
@@ -16,6 +16,7 @@ Classifier: Programming Language :: Python :: 3
 Requires-Python: >=3.12
 Requires-Dist: httpx
 Requires-Dist: loguru<0.8,>=0.7
+Requires-Dist: mcp<2,>=1.19
 Requires-Dist: ollama>=0.6.2
 Requires-Dist: openai
 Requires-Dist: python-dotenv>=1.0.0
@@ -26,17 +27,16 @@ Provides-Extra: all
 Requires-Dist: anthropic; extra == 'all'
 Requires-Dist: dashscope; extra == 'all'
 Requires-Dist: google-genai; extra == 'all'
-Requires-Dist: zhipuai; extra == 'all'
+Requires-Dist: zhipuai>=2; extra == 'all'
 Provides-Extra: anthropic
 Requires-Dist: anthropic; extra == 'anthropic'
 Provides-Extra: glm
-Requires-Dist: zhipuai; extra == 'glm'
+Requires-Dist: zhipuai>=2; extra == 'glm'
 Provides-Extra: google
 Requires-Dist: google-genai; extra == 'google'
 Provides-Extra: libcst
 Requires-Dist: libcst>=1.0.0; extra == 'libcst'
 Provides-Extra: mcp
-Requires-Dist: mcp; extra == 'mcp'
 Provides-Extra: qwen
 Requires-Dist: dashscope; extra == 'qwen'
 Description-Content-Type: text/markdown
@@ -155,6 +155,8 @@ in the core install.
 
 ayder-cli uses a flexible profile-based configuration system. On the first run, it creates a config file at `~/.ayder/config.toml`.
 
+The generated file includes an `[llm.evren]` profile for the evren gateway (`https://evren-llmapi.ssyz.org.tr/v1`) with an empty `api_key`. Fill in your key and switch to it with `/provider evren`.
+
 **Key Concepts:**
 - **Profile Name:** A custom named section (e.g., `[llm.my_ollama]`). You can define as many profiles as you want.
 - **Driver:** The underlying native SDK or adapter used by the profile (`ollama`, `openai`, `anthropic`, `google`, `deepseek`, `qwen`, or `glm`). Each driver guarantees full support for native tool calling and streaming.
@@ -266,6 +268,50 @@ num_ctx = 1000000
 
 Please adjust `num_ctx` context size window according to your local computer RAM. If Ollama crashes, decrease the value.
 
+### Reasoning Effort (`/effort`)
+
+Use `/effort` to open a picker, or `/effort high` to change the active session.
+Changes apply between turns and are inherited by future agents that use the
+session's profile; explicit agent settings take precedence. They do not change
+`config.toml`. `/effort default` restores the provider's default behavior
+(omits OpenAI effort and Ollama's `think` parameter).
+
+| Driver | Runtime values |
+|--------|----------------|
+| `openai` | `default`, `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max` |
+| `ollama` | `default`, `on`, `off`, `low`, `medium`, `high` (`true`/`false` and `none` are also accepted) |
+
+Support varies by model. OpenAI values follow its
+[Chat Completions API](https://developers.openai.com/api/reference/resources/chat/subresources/completions/methods/create).
+Ollama uses the installed Python SDK's boolean and three-level `think` options;
+its SDK does not yet accept the server API's newer `max` value. GPT-OSS expects
+`low`, `medium`, or `high`, and cannot disable thinking. See
+[Ollama thinking](https://docs.ollama.com/capabilities/thinking).
+
+Set persistent defaults per LLM profile and agent:
+
+```toml
+[llm.openai]
+driver = "openai"
+reasoning_effort = "medium"
+
+[llm.ollama]
+driver = "ollama"
+reasoning_effort = "high"
+
+[agents.reviewer]
+provider = "openai"
+reasoning_effort = "high"
+system_prompt = "Review code and report findings."
+```
+
+Omit an agent's `reasoning_effort` to inherit its profile, or set it to
+`"default"` to clear an inherited effort. On Ollama, `"none"` maps to
+`think = false`; an explicit effort overrides the legacy `think` setting.
+Existing `think = true/false/"low"/"medium"/"high"` profile and agent settings
+remain supported. OpenAI omits reasoning effort by default, preserving
+compatibility with models and endpoints that do not support it.
+
 ### Changing Models on the Fly (`/model`)
 
 You do **not** need a separate profile for every model. The profile defines the *connection* (driver, base URL, API key).
@@ -275,6 +321,10 @@ Once a profile is active, use `/model` in the TUI to swap models on the fly:
 - **Interactive Picker:** `/model` with no arguments queries the active driver for available models and opens a picker.
 - **Direct Switch:** `/model <model-name>` immediately switches to that model.
 
+If the provider rejects the listing request, `/model` shows the server's error.
+
+For the evren gateway (`evren-llmapi.ssyz.org.tr`), if your account has not accepted the current terms of use, `/model` shows them and asks you to Approve or Deny; Approve accepts them on the server.
+
 Changes made with `/model` apply to the current session only. To make a model the permanent default, update `model = "..."` in your `config.toml`.
 
 ## Usage
@@ -392,6 +442,7 @@ You can also manually manage context with the `context` tool and its slash-comma
 | `/help` | Show available commands and keyboard shortcuts |
 | `/provider` | Switch LLM provider (interactive selector or direct name) |
 | `/model` | List available models or switch model (e.g., `/model qwen3-coder`) |
+| `/effort` | Pick reasoning effort or set it directly (e.g., `/effort high`) |
 | `/plugin` | Toggle tool plugins by tag (e.g., venv, http, background, python, dbs) |
 | `/tools` | List currently enabled tools and descriptions |
 | `/permission` | Toggle permission levels (r/w/x/http) interactively |
@@ -670,9 +721,46 @@ RECOMMENDATIONS: Parameterize all DB queries; add Pydantic validators to all end
 
 This summary is injected into the main LLM's context as a system message so the main agent can act on it, summarize it for you, or chain it to further work.
 
+## MCP servers
+
+MCP support is built in and installed with Ayder. Add `.ayder/mcp.json` in your
+project root, then start Ayder:
+
+```json
+{
+  "mcpServers": {
+    "local-tools": {
+      "command": "python",
+      "args": ["server.py"],
+      "env": {"EXAMPLE_SETTING": "value"}
+    },
+    "remote-tools": {
+      "url": "http://localhost:8000/mcp"
+    }
+  }
+}
+```
+
+Local servers use stdio and run from the project root; remote servers use
+Streamable HTTP. Their tools automatically join the standard `core` toolset in
+the CLI, TUI, and delegated agents. No plugin installation or `/plugin` toggle
+is needed. Tool calls retain the usual permissions: `x` for stdio servers and
+`http` for HTTP servers. Configure only servers you intend Ayder to connect to:
+local server commands start during runtime initialization to discover tools.
+
+Tools keep their server-provided names unless they conflict with an existing
+tool; conflicting names receive a `server__` prefix (and a numeric suffix if
+needed). Unreachable servers are skipped so other tools remain available.
+Connections are shared by agents in the same project and closed on process
+exit. Restart Ayder after changing `mcp.json`.
+
+Existing `mcp-tool` plugin installations are automatically skipped in favor of
+built-in support; your existing `.ayder/mcp.json` continues to work. The legacy
+`ayder-cli[mcp]` installation extra is still accepted.
+
 ## Plugins
 
-Official plugins (venv, python, dbs, mcp, temporal) are maintained in the **[ayder/ayder-plugins](https://github.com/ayder/ayder-plugins)** repository. Install any plugin directly from GitHub:
+Official plugins (venv, python, dbs, temporal) are maintained in the **[ayder/ayder-plugins](https://github.com/ayder/ayder-plugins)** repository. Install any plugin directly from GitHub:
 
 ```bash
 ayder install-plugin https://github.com/ayder/ayder-plugins/tree/main/venv-tools

{ayder_cli-2.3.0 → ayder_cli-2.4.0}/README.md

@@ -112,6 +112,8 @@ in the core install.
 
 ayder-cli uses a flexible profile-based configuration system. On the first run, it creates a config file at `~/.ayder/config.toml`.
 
+The generated file includes an `[llm.evren]` profile for the evren gateway (`https://evren-llmapi.ssyz.org.tr/v1`) with an empty `api_key`. Fill in your key and switch to it with `/provider evren`.
+
 **Key Concepts:**
 - **Profile Name:** A custom named section (e.g., `[llm.my_ollama]`). You can define as many profiles as you want.
 - **Driver:** The underlying native SDK or adapter used by the profile (`ollama`, `openai`, `anthropic`, `google`, `deepseek`, `qwen`, or `glm`). Each driver guarantees full support for native tool calling and streaming.
@@ -223,6 +225,50 @@ num_ctx = 1000000
 
 Please adjust `num_ctx` context size window according to your local computer RAM. If Ollama crashes, decrease the value.
 
+### Reasoning Effort (`/effort`)
+
+Use `/effort` to open a picker, or `/effort high` to change the active session.
+Changes apply between turns and are inherited by future agents that use the
+session's profile; explicit agent settings take precedence. They do not change
+`config.toml`. `/effort default` restores the provider's default behavior
+(omits OpenAI effort and Ollama's `think` parameter).
+
+| Driver | Runtime values |
+|--------|----------------|
+| `openai` | `default`, `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max` |
+| `ollama` | `default`, `on`, `off`, `low`, `medium`, `high` (`true`/`false` and `none` are also accepted) |
+
+Support varies by model. OpenAI values follow its
+[Chat Completions API](https://developers.openai.com/api/reference/resources/chat/subresources/completions/methods/create).
+Ollama uses the installed Python SDK's boolean and three-level `think` options;
+its SDK does not yet accept the server API's newer `max` value. GPT-OSS expects
+`low`, `medium`, or `high`, and cannot disable thinking. See
+[Ollama thinking](https://docs.ollama.com/capabilities/thinking).
+
+Set persistent defaults per LLM profile and agent:
+
+```toml
+[llm.openai]
+driver = "openai"
+reasoning_effort = "medium"
+
+[llm.ollama]
+driver = "ollama"
+reasoning_effort = "high"
+
+[agents.reviewer]
+provider = "openai"
+reasoning_effort = "high"
+system_prompt = "Review code and report findings."
+```
+
+Omit an agent's `reasoning_effort` to inherit its profile, or set it to
+`"default"` to clear an inherited effort. On Ollama, `"none"` maps to
+`think = false`; an explicit effort overrides the legacy `think` setting.
+Existing `think = true/false/"low"/"medium"/"high"` profile and agent settings
+remain supported. OpenAI omits reasoning effort by default, preserving
+compatibility with models and endpoints that do not support it.
+
 ### Changing Models on the Fly (`/model`)
 
 You do **not** need a separate profile for every model. The profile defines the *connection* (driver, base URL, API key).
@@ -232,6 +278,10 @@ Once a profile is active, use `/model` in the TUI to swap models on the fly:
 - **Interactive Picker:** `/model` with no arguments queries the active driver for available models and opens a picker.
 - **Direct Switch:** `/model <model-name>` immediately switches to that model.
 
+If the provider rejects the listing request, `/model` shows the server's error.
+
+For the evren gateway (`evren-llmapi.ssyz.org.tr`), if your account has not accepted the current terms of use, `/model` shows them and asks you to Approve or Deny; Approve accepts them on the server.
+
 Changes made with `/model` apply to the current session only. To make a model the permanent default, update `model = "..."` in your `config.toml`.
 
 ## Usage
@@ -349,6 +399,7 @@ You can also manually manage context with the `context` tool and its slash-comma
 | `/help` | Show available commands and keyboard shortcuts |
 | `/provider` | Switch LLM provider (interactive selector or direct name) |
 | `/model` | List available models or switch model (e.g., `/model qwen3-coder`) |
+| `/effort` | Pick reasoning effort or set it directly (e.g., `/effort high`) |
 | `/plugin` | Toggle tool plugins by tag (e.g., venv, http, background, python, dbs) |
 | `/tools` | List currently enabled tools and descriptions |
 | `/permission` | Toggle permission levels (r/w/x/http) interactively |
@@ -627,9 +678,46 @@ RECOMMENDATIONS: Parameterize all DB queries; add Pydantic validators to all end
 
 This summary is injected into the main LLM's context as a system message so the main agent can act on it, summarize it for you, or chain it to further work.
 
+## MCP servers
+
+MCP support is built in and installed with Ayder. Add `.ayder/mcp.json` in your
+project root, then start Ayder:
+
+```json
+{
+  "mcpServers": {
+    "local-tools": {
+      "command": "python",
+      "args": ["server.py"],
+      "env": {"EXAMPLE_SETTING": "value"}
+    },
+    "remote-tools": {
+      "url": "http://localhost:8000/mcp"
+    }
+  }
+}
+```
+
+Local servers use stdio and run from the project root; remote servers use
+Streamable HTTP. Their tools automatically join the standard `core` toolset in
+the CLI, TUI, and delegated agents. No plugin installation or `/plugin` toggle
+is needed. Tool calls retain the usual permissions: `x` for stdio servers and
+`http` for HTTP servers. Configure only servers you intend Ayder to connect to:
+local server commands start during runtime initialization to discover tools.
+
+Tools keep their server-provided names unless they conflict with an existing
+tool; conflicting names receive a `server__` prefix (and a numeric suffix if
+needed). Unreachable servers are skipped so other tools remain available.
+Connections are shared by agents in the same project and closed on process
+exit. Restart Ayder after changing `mcp.json`.
+
+Existing `mcp-tool` plugin installations are automatically skipped in favor of
+built-in support; your existing `.ayder/mcp.json` continues to work. The legacy
+`ayder-cli[mcp]` installation extra is still accepted.
+
 ## Plugins
 
-Official plugins (venv, python, dbs, mcp, temporal) are maintained in the **[ayder/ayder-plugins](https://github.com/ayder/ayder-plugins)** repository. Install any plugin directly from GitHub:
+Official plugins (venv, python, dbs, temporal) are maintained in the **[ayder/ayder-plugins](https://github.com/ayder/ayder-plugins)** repository. Install any plugin directly from GitHub:
 
 ```bash
 ayder install-plugin https://github.com/ayder/ayder-plugins/tree/main/venv-tools

ayder_cli-2.4.0/docs/GATE.md

@@ -0,0 +1,28 @@
+# Gate
+
+The procedure an agent follows to gate a candidate commit. Follow the steps in order and do
+not interpret the results. Never edit a file, fix a failure, skip a step or create a worktree.
+Test definitions live in [AGENTS.md](../AGENTS.md#test-definitions).
+
+Input: the candidate SHA.
+
+1. `git rev-parse HEAD` → expected: exactly the candidate SHA.
+2. `git status --porcelain` → expected: empty output.
+3. `uv run poe check-all` → expected: exit code 0. This runs lint, typecheck, the logging
+   gates and the test suite, and stops at the first failing task.
+4. Copy the final pytest summary line (`=== N passed, M skipped in …s ===`) verbatim.
+
+Last measured: `2494 passed, 2 skipped` on `feat/evren-terms` with the evren default profile (2026-09-29).
+
+## Report format
+
+```text
+SHA: <candidate SHA>
+1 git rev-parse HEAD: <output> (match|MISMATCH)
+2 git status --porcelain: <empty|output>
+3 uv run poe check-all: exit <code>
+4 summary: <pytest summary line verbatim>
+GATE COMPLETE | GATE FAILED at step <n>
+```
+
+`GATE COMPLETE` only when steps 1–3 meet their expected results.

{ayder_cli-2.3.0 → ayder_cli-2.4.0}/docs/PROJECT_STRUCTURE.md

@@ -220,7 +220,7 @@ cli.py:main()
 | `tui/adapter.py` | Adapter glue between `AyderApp` and `ChatLoop` | callback wiring helpers |
 | `tui/commands.py` | Slash command handlers | `COMMAND_MAP`, `handle_*()` |
 | `tui/widgets.py` | Custom widgets | `ChatView`, `ToolPanel`, `CLIInputBar`, `StatusBar`, `AutoCompleteInput` |
-| `tui/screens.py` | Modal screens | `AgentListScreen`, `CLIConfirmScreen`, `CLIHelpScreen`, `CLIMultiSelectScreen`, `CLIPermissionScreen`, `CLISafeModeScreen`, `CLISelectScreen`, `TaskEditScreen` |
+| `tui/screens.py` | Modal screens | `AgentListScreen`, `CLIConfirmScreen`, `CLIHelpScreen`, `CLIMultiSelectScreen`, `CLIPermissionScreen`, `CLISafeModeScreen`, `CLISelectScreen`, `EvrenTermsScreen`, `TaskEditScreen` |
 | `tui/parser.py` | TUI-specific parsing | `content_processor()` |
 | `tui/helpers.py` | UI helpers | `create_tui_banner()` |
 | `tui/keybindings.py` | Keybinding declarations | `BINDINGS` |
@@ -242,6 +242,7 @@ All LLM provider implementations live here. Previously some sat under `services/
 | `providers/__init__.py` | Re-exports | `AIProvider`, `NormalizedStreamChunk`, `ToolCallDef`, `provider_orchestrator` |
 | `providers/base.py` | Provider protocol + shared DTOs | `AIProvider`, `NormalizedStreamChunk`, `ToolCallDef`, `_ToolCall`, `_FunctionCall` |
 | `providers/orchestrator.py` | Driver-keyed provider factory | `ProviderOrchestrator`, `provider_orchestrator` |
+| `providers/evren.py` | evren gateway terms-of-use acceptance (used by `/model`) | `EVREN_HOST`, `EvrenTerms`, `is_evren_terms_error`, `fetch_terms`, `accept_terms` |
 | `providers/impl/ollama.py` | Native Ollama provider (ollama SDK) | `OllamaProvider` |
 | `providers/impl/ollama_inspector.py` | Ollama model introspection | `OllamaInspector`, `ModelInfo`, `RuntimeState` |
 | `providers/impl/openai.py` | OpenAI / OpenAI-compatible backend | `OpenAIProvider` |

{ayder_cli-2.3.0 → ayder_cli-2.4.0}/docs/config.toml.example

@@ -48,12 +48,15 @@
 #      `export OLLAMA_API_KEY="<key>"`. The api_key config field is INERT on the
 #      native path, so a missing env var ⇒ 401 Unauthorized.
 #
-# NOTE on `think`: on the native `ollama` driver, ayder defaults thinking ON
-#       (think = true) and forwards either a boolean or Ollama's "low",
-#       "medium", "high" levels. If a selected model rejects thinking mode,
-#       ayder retries that request once with think=false. Set `think = false`
-#       in an [llm.*] profile for known non-thinking models. The `openai`
-#       driver sends no reasoning-effort parameter at all.
+# Reasoning defaults can be set in [llm.*] and overridden in [agents.*].
+# reasoning_effort = "default" uses existing think behavior on Ollama and omits
+# the effort parameter on OpenAI. Explicit effort overrides legacy `think`.
+# OpenAI: none, minimal, low, medium, high, xhigh, max (model-dependent).
+# Ollama SDK: none (= think=false), low, medium, high. To enable/disable
+# boolean thinking explicitly, the legacy think = true/false still works.
+# Use /effort in the TUI for a session-only override or interactive picker.
+# Explicit unsupported efforts report a server error; only legacy `think`
+# retains the automatic retry with think=false for non-thinking models.
 #
 # NOTE on tuning knobs — which actually take effect depends on the DRIVER. These
 #       agents run on the native `ollama` driver, which ignores most of them:
@@ -69,8 +72,8 @@
 #                               path it sizes the context-manager budget.
 #                               Default 65536.
 #       The per-agent temperature / max_output_tokens values below are largely
-#       INERT on this Ollama pipeline; per-agent `think` is applied when the
-#       agent uses the native ollama driver.
+#       INERT on this Ollama pipeline; per-agent reasoning_effort takes
+#       precedence over the selected profile.
 # =============================================================================
 
 config_version = "2.0"
@@ -167,6 +170,7 @@ driver = "ollama"
 base_url = "http://localhost:11434"  # route :cloud models through the LOCAL daemon (auth via ~/.ollama/id_ed25519, one-time `ollama signin`)
 model = "deepseek-v4-pro:cloud"    # orchestrator default; per-agent `model` overrides this
 num_ctx = 131072
+reasoning_effort = "default"
 think = true                       # default; set false for known non-thinking models
 # To hit ollama.com directly instead, swap the line above for:
 #   base_url = "https://ollama.com"   # no /v1; then `export OLLAMA_API_KEY=<key>` (the api_key field is inert on this path)
@@ -176,6 +180,7 @@ driver = "ollama"
 base_url = "http://localhost:11434"
 model = "qwen3.6:35b-a3b-coding-nvfp4"
 num_ctx = 32768                     # keep modest: local VRAM is the constraint
+reasoning_effort = "default"
 think = true                        # default; set false if the selected model rejects thinking
 
 # Budget/throughput alternative — swap any cloud agent's `provider` to this, or
@@ -198,7 +203,17 @@ think = true                        # default; set false if the selected model r
 # num_ctx = 65536            # sizes the context-manager budget (default 65536); NOT sent to the API
 # max_output_tokens = 8192   # -> max_tokens / max_completion_tokens (default 4096); keep WELL below num_ctx
 # stop_sequences = []        # -> stop (default [])
-# # temperature / think are NOT applied by the openai driver today (no-ops) — omitted on purpose.
+# reasoning_effort = "medium" # choose a value supported by the selected model
+# # temperature / think are NOT applied by the openai driver.
+
+# evren gateway (OpenAI-compatible). A fresh config.toml ships this profile with
+# an empty api_key. The first `/model` asks you to accept evren's terms of use.
+# [llm.evren]
+# driver = "openai"
+# base_url = "https://evren-llmapi.ssyz.org.tr/v1"
+# api_key = ""               # your evren key
+# model = "deepseek-v4-flash"
+# num_ctx = 131072
 
 # =============================================================================
 # Agents
@@ -211,7 +226,7 @@ provider = "ollama_cloud"
 model = "glm-5.2:cloud"
 temperature = 0.4
 max_output_tokens = 8192
-think = "high"
+reasoning_effort = "high"
 system_prompt = """
 You are Project Manager #1 — the requirements analyst and spec author.
 
@@ -239,7 +254,7 @@ provider = "ollama_cloud"
 model = "deepseek-v4-pro:cloud"
 temperature = 0.2
 max_output_tokens = 4096
-think = "high"
+reasoning_effort = "high"
 system_prompt = """
 You are Project Manager #2 — the independent spec reviewer.
 
@@ -268,7 +283,7 @@ provider = "ollama_cloud"
 model = "deepseek-v4-pro:cloud"
 temperature = 0.3
 max_output_tokens = 8192
-think = "high"
+reasoning_effort = "high"
 num_ctx = 262144                   # long window: hold the whole spec while splitting it into tasks (delays compaction)
 system_prompt = """
 You are the Architect — you turn an APPROVED spec into an implementation plan.
@@ -296,7 +311,7 @@ provider = "ollama_cloud"
 model = "kimi-k2.7-code:cloud"
 temperature = 0.2
 max_output_tokens = 8192
-think = "high"
+reasoning_effort = "high"
 system_prompt = """
 You are the Architecture Reviewer — independent of the Architect.
 
@@ -398,7 +413,7 @@ provider = "ollama_cloud"
 model = "kimi-k2.7-code:cloud"
 temperature = 0.1
 max_output_tokens = 4096
-think = "high"
+reasoning_effort = "high"
 system_prompt = """
 You are the Code Reviewer. You review a diff for correctness and quality.
 
@@ -424,7 +439,7 @@ provider = "ollama_cloud"
 model = "minimax-m3:cloud"
 temperature = 0.1
 max_output_tokens = 4096
-think = "high"
+reasoning_effort = "high"
 num_ctx = 262144                   # long window: holds spec + all criteria + diff + test output at once
 system_prompt = """
 You are the Acceptance Gate — the final, independent check before "done".

{ayder_cli-2.3.0 → ayder_cli-2.4.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "ayder-cli"
-version = "2.3.0"
+version = "2.4.0"
 description = "AI agent for any LLMs"
 readme = "README.md"
 requires-python = ">=3.12"
@@ -26,6 +26,7 @@ dependencies = [
     # Message / StreamSink shapes (§F5-R6), guarded by `_shape_guard()`.
     "loguru>=0.7,<0.8",
     "httpx",
+    "mcp>=1.19,<2",
     "rich>=13.0.0",
     # Pinned exactly to match the runtime: 8.2.5+ replaced the single
     # "textual-ansi" builtin with per-theme `ansi` flags and ansi-dark/
@@ -39,9 +40,12 @@ dependencies = [
 anthropic = ["anthropic"]
 google = ["google-genai"]
 qwen = ["dashscope"]
-glm = ["zhipuai"]
+# The provider uses the v2 client; do not let MCP's shared PyJWT dependency
+# make the resolver select the incompatible v1 SDK.
+glm = ["zhipuai>=2"]
 all = ["ayder-cli[anthropic,google,qwen,glm]"]
-mcp = ["mcp"]
+# Compatibility extra: MCP is now included in every installation.
+mcp = []
 # Optional: required only by plugins that do CST-based code transforms.
 libcst = ["libcst>=1.0.0"]
 
@@ -71,7 +75,7 @@ dev = [
     "anthropic",
     "google-genai",
     "dashscope",
-    "zhipuai",
+    "zhipuai>=2",
 ]
 
 [tool.poe.tasks]

{ayder_cli-2.3.0 → ayder_cli-2.4.0}/scripts/check_exception_handlers.py

@@ -24,7 +24,7 @@ DEFAULT_BASELINE = REPO / "scripts" / "exception_baseline.txt"
 
 # Frozen census (§C10). A different number means the gate is looking at the
 # wrong tree, or the census moved without the plan being updated.
-EXPECTED_BROAD = 131
+EXPECTED_BROAD = 137
 BRANCHING = (ast.If, ast.Try, ast.For, ast.While, ast.With, ast.Match)
 TERMINAL = (ast.Return, ast.Break, ast.Continue, ast.Pass)
 

{ayder_cli-2.3.0 → ayder_cli-2.4.0}/scripts/check_log_arguments.py

@@ -203,13 +203,13 @@ FROZEN_CHAIN_SITES: dict[tuple[str, str, str, str], tuple[str, int]] = {
     ("log.py", "emit_event", "bind", "**"): ("Name(id='fields', ctx=Load())", 1),
 }
 
-# The 93 `exception=True` inputs are homogeneous, so they are governed as one
-# package-wide shape/count rule rather than 93 site identities - their per-site
+# The 101 `exception=True` inputs are homogeneous, so they are governed as one
+# package-wide shape/count rule rather than 101 site identities - their per-site
 # discipline is C10's.
-FROZEN_EXCEPTION_TRUE = 93
+FROZEN_EXCEPTION_TRUE = 101
 
 # Live chain inputs, counted per method. Printed on every run.
-CHAIN_TALLY: dict[str, int] = {"bind": 6, "opt": 97, "patch": 0}
+CHAIN_TALLY: dict[str, int] = {"bind": 6, "opt": 105, "patch": 0}
 
 # The reviewed composition of THE COMMITTED baseline, frozen by the Phase 5
 # census: 252 retained non-path + 22 paths + 2 deferred interpolated rows, plus
@@ -218,12 +218,12 @@ CHAIN_TALLY: dict[str, int] = {"bind": 6, "opt": 97, "patch": 0}
 # unchanged - so the composition is gated too. Caller-supplied baselines (the
 # gate's own synthetic fixtures) are exempt: this is a fact about one file.
 FROZEN_TALLY: dict[str, int] = {
-    "R-name": 93,
-    "R-id": 36,
-    "R-count": 88,
+    "R-name": 96,
+    "R-id": 40,
+    "R-count": 90,
     "R-status": 27,
     "R-class": 10,
-    "R-path": 22,
+    "R-path": 24,
     # Both 5-04 deferrals are closed: the two asyncio rows now interpolate the
     # B2-prime normalized value, and the bridge's dynamic message is masked by
     # the prose sinks it reaches.