ayder-cli 2.3.0__tar.gz → 2.3.1__tar.gz

{ayder_cli-2.3.0 → ayder_cli-2.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: ayder-cli
-Version: 2.3.0
+Version: 2.3.1
 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
@@ -266,6 +266,50 @@ 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).
@@ -392,6 +436,7 @@ 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 +715,46 @@ 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-2.3.1}/README.md

@@ -223,6 +223,50 @@ 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).
@@ -349,6 +393,7 @@ 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 +672,46 @@ 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-2.3.1}/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 +203,8 @@ 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.
 
 # =============================================================================
 # Agents
@@ -211,7 +217,7 @@ 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 +245,7 @@ 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 +274,7 @@ 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 +302,7 @@ 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 +404,7 @@ 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 +430,7 @@ 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-2.3.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "ayder-cli"
-version = "2.3.0"
+version = "2.3.1"
 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-2.3.1}/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 = 138
 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-2.3.1}/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 100 `exception=True` inputs are homogeneous, so they are governed as one
+# package-wide shape/count rule rather than 100 site identities - their per-site
 # discipline is C10's.
-FROZEN_EXCEPTION_TRUE = 93
+FROZEN_EXCEPTION_TRUE = 100
 
 # 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": 104, "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.

{ayder_cli-2.3.0 → ayder_cli-2.3.1}/scripts/log_argument_baseline.txt

@@ -1,6 +1,8 @@
 {"class":"dynamic-residual:known-shape-masked","site":{"arg_index":"bind:lib","expr":"record.name","message":null,"method":"bind","path":"logging_config.py","qualname":"_InterceptHandler.emit"}}
 {"class":"R-name","site":{"arg_index":"kw:agent","expr":"run.agent_name","message":null,"method":"emit_event","path":"agents/registry.py","qualname":"AgentRegistry._run_and_queue"}}
+{"class":"R-count","site":{"arg_index":"kw:arg_chars","expr":"arg_chars","message":null,"method":"emit_event","path":"loops/chat_loop.py","qualname":"ChatLoop._emit_tool_call_received"}}
 {"class":"R-count","site":{"arg_index":"kw:args_len","expr":"len(str(args or ''))","message":null,"method":"emit_event","path":"loops/chat_loop.py","qualname":"ChatLoop._emit_tool_call"}}
+{"class":"R-id","site":{"arg_index":"kw:call_id","expr":"call_id","message":null,"method":"emit_event","path":"loops/chat_loop.py","qualname":"ChatLoop._emit_tool_call_received"}}
 {"class":"R-count","site":{"arg_index":"kw:content_len","expr":"len(final_content)","message":null,"method":"emit_event","path":"loops/chat_loop.py","qualname":"ChatLoop.run"}}
 {"class":"R-class","site":{"arg_index":"kw:err_type","expr":"None if ok else type(exec_result.error).__name__","message":null,"method":"emit_event","path":"loops/chat_loop.py","qualname":"ChatLoop._emit_tool_call"}}
 {"class":"R-count","site":{"arg_index":"kw:hist_tokens","expr":"self._total_tokens","message":null,"method":"emit_event","path":"loops/chat_loop.py","qualname":"ChatLoop.run"}}
@@ -9,6 +11,7 @@
 {"class":"R-count","site":{"arg_index":"kw:ms","expr":"int((time.perf_counter() - started) * 1000)","message":null,"method":"emit_event","path":"loops/chat_loop.py","qualname":"ChatLoop._emit_tool_call"}}
 {"class":"R-count","site":{"arg_index":"kw:n","expr":"iteration_n","message":null,"method":"emit_event","path":"loops/chat_loop.py","qualname":"ChatLoop.run"}}
 {"class":"R-name","site":{"arg_index":"kw:name","expr":"name","message":null,"method":"emit_event","path":"loops/chat_loop.py","qualname":"ChatLoop._emit_tool_call"}}
+{"class":"R-name","site":{"arg_index":"kw:name","expr":"name","message":null,"method":"emit_event","path":"loops/chat_loop.py","qualname":"ChatLoop._emit_tool_call_received"}}
 {"class":"R-status","site":{"arg_index":"kw:ok","expr":"ok","message":null,"method":"emit_event","path":"loops/chat_loop.py","qualname":"ChatLoop._emit_tool_call"}}
 {"class":"R-count","site":{"arg_index":"kw:reasoning_len","expr":"len(final_reasoning)","message":null,"method":"emit_event","path":"loops/chat_loop.py","qualname":"ChatLoop.run"}}
 {"class":"R-id","site":{"arg_index":"kw:run_id","expr":"run.run_id","message":null,"method":"emit_event","path":"agents/registry.py","qualname":"AgentRegistry._run_and_queue"}}
@@ -39,6 +42,7 @@
 {"class":"R-name","site":{"arg_index":"pos:0","expr":"driver.name","message":"Ollama driver={} mode={} for {!r}","method":"info","path":"providers/impl/ollama.py","qualname":"OllamaProvider.stream_with_tools"}}
 {"class":"R-name","site":{"arg_index":"pos:0","expr":"driver.name","message":"{} ({}) failed mid-stream (error_type={}); transparently retrying with {} ({})","method":"info","path":"providers/impl/ollama.py","qualname":"OllamaProvider.stream_with_tools"}}
 {"class":"R-name","site":{"arg_index":"pos:0","expr":"err_name","message":"Appending Tool Error [{}] to history: {} chars","method":"trace","path":"loops/chat_loop.py","qualname":"ChatLoop._execute_tool_calls"}}
+{"class":"R-name","site":{"arg_index":"pos:0","expr":"existing_tc['function']['name']","message":"Tool call id reused by a different tool ({} then {}); calls would merge","method":"warning","path":"loops/chat_loop.py","qualname":"ChatLoop.run"}}
 {"class":"R-path","site":{"arg_index":"pos:0","expr":"file_path","message":"Diff preview generation failed for {}","method":"debug","path":"ui.py","qualname":"generate_diff_preview"}}
 {"class":"R-path","site":{"arg_index":"pos:0","expr":"file_path","message":"Failed to render file panel for {}","method":"warning","path":"ui.py","qualname":"print_file_content"}}
 {"class":"R-path","site":{"arg_index":"pos:0","expr":"file_path","message":"Failed to render file panel for {}","method":"warning","path":"ui.py","qualname":"print_file_content_rich"}}
@@ -55,6 +59,7 @@
 {"class":"R-count","site":{"arg_index":"pos:0","expr":"len(self._frozen_system or '')","message":"Context: system prompt updated on first call ({} \u2192 {} chars)","method":"info","path":"core/ollama_context_manager.py","qualname":"OllamaContextManager.prepare_messages"}}
 {"class":"R-count","site":{"arg_index":"pos:0","expr":"len(system_content)","message":"Context: system prompt frozen ({} chars, {} tool schemas, ctx={})","method":"info","path":"core/ollama_context_manager.py","qualname":"OllamaContextManager.freeze_system_prompt"}}
 {"class":"R-count","site":{"arg_index":"pos:0","expr":"len(text)","message":"Encoder failed unexpectedly on a string of length {}; disabling it for the rest of this session","method":"debug","path":"core/default_context_manager.py","qualname":"TokenCounter._estimate_string"}}
+{"class":"R-count","site":{"arg_index":"pos:0","expr":"len(text)","message":"Inbox: accepted a {}-char prompt","method":"info","path":"services/messaging_inbox.py","qualname":"MessagingInbox._handle_client"}}
 {"class":"R-count","site":{"arg_index":"pos:0","expr":"len(v)","message":"Unsupported driver (value_chars={}); must be one of: {}. Fix the driver in your [llm.<provider>] profile.","method":"error","path":"core/config.py","qualname":"Config.validate_driver"}}
 {"class":"R-name","site":{"arg_index":"pos:0","expr":"manifest.name","message":"Dependency install failed for plugin {!r}; rolling back","method":"error","path":"cli.py","qualname":"main"}}
 {"class":"R-name","site":{"arg_index":"pos:0","expr":"manifest.name","message":"Installed plugin '{}' v{}","method":"info","path":"tools/plugin_manager.py","qualname":"install_plugin_from_github"}}
@@ -82,12 +87,14 @@
 {"class":"R-status","site":{"arg_index":"pos:0","expr":"normalized","message":"Unhandled asyncio exception: {}","method":"critical","path":"diagnostics.py","qualname":"_handle_asyncio"}}
 {"class":"R-count","site":{"arg_index":"pos:0","expr":"num_ctx","message":"Context budget: {} tokens (derived from num_ctx; max_context_tokens unset)","method":"info","path":"core/default_context_manager.py","qualname":"DefaultContextManager.__init__"}}
 {"class":"R-name","site":{"arg_index":"pos:0","expr":"panel_id","message":"Panel lookup failed for {}","method":"debug","path":"tui/app.py","qualname":"AyderApp._scroll_open_panel"}}
+{"class":"R-path","site":{"arg_index":"pos:0","expr":"path","message":"Could not remove {}","method":"debug","path":"services/messaging_inbox.py","qualname":"MessagingInbox.stop"}}
 {"class":"R-path","site":{"arg_index":"pos:0","expr":"path","message":"Failed to read note file {}","method":"error","path":"tui/commands.py","qualname":"_open_note_in_editor"}}
 {"class":"R-path","site":{"arg_index":"pos:0","expr":"path","message":"Failed to read task file {}","method":"error","path":"tui/commands.py","qualname":"_open_task_in_editor"}}
 {"class":"R-path","site":{"arg_index":"pos:0","expr":"path","message":"Failed to read task file {}","method":"warning","path":"tools/builtins/tasks.py","qualname":"read_task"}}
 {"class":"R-path","site":{"arg_index":"pos:0","expr":"path","message":"Failed to save note file {}","method":"error","path":"tui/commands.py","qualname":"_open_note_in_editor.on_edit_result"}}
 {"class":"R-path","site":{"arg_index":"pos:0","expr":"path","message":"Failed to save task file {}","method":"error","path":"tui/commands.py","qualname":"_open_task_in_editor.on_edit_result"}}
 {"class":"R-path","site":{"arg_index":"pos:0","expr":"path","message":"Unreadable context slot at {}: {}","method":"warning","path":"tools/builtins/context.py","qualname":"_scan_context_dir"}}
+{"class":"R-id","site":{"arg_index":"pos:0","expr":"pid","message":"Could not determine process start time for pid {}","method":"debug","path":"services/messaging_inbox.py","qualname":"proc_start"}}
 {"class":"R-name","site":{"arg_index":"pos:0","expr":"plugin_dir.name","message":"Loaded global plugin '{}' ({} tools)","method":"info","path":"tools/plugin_manager.py","qualname":"discover_global_plugins"}}
 {"class":"R-name","site":{"arg_index":"pos:0","expr":"plugin_dir.name","message":"Loaded project plugin '{}' ({} tools)","method":"info","path":"tools/registry.py","qualname":"_load_project_plugins"}}
 {"class":"R-name","site":{"arg_index":"pos:0","expr":"plugin_dir.name","message":"Plugin '{}' is missing a dependency ({!r}). Reinstall it to install its declared dependencies \u2014 e.g. `ayder install-plugin {} --force` \u2014 or install the package manually.","method":"warning","path":"tools/plugin_manager.py","qualname":"discover_global_plugins"}}
@@ -116,6 +123,7 @@
 {"class":"R-count","site":{"arg_index":"pos:0","expr":"self._history[-1].ns_per_token","message":"KV-cache invalidated: was {:.0f} ns/tok, now {:.0f} ns/tok. Prefix likely changed.","method":"warning","path":"core/cache_monitor.py","qualname":"CacheMonitor.record"}}
 {"class":"R-name","site":{"arg_index":"pos:0","expr":"self._model or '?'","message":"Context[{}]: {}/{} tokens ({:.0f}%), completion={}, speed={}{}","method":"debug","path":"core/ollama_context_manager.py","qualname":"OllamaContextManager.update_from_response"}}
 {"class":"R-name","site":{"arg_index":"pos:0","expr":"self._model","message":"Context: model '{}' did not report context_length, using configured num_ctx={}","method":"info","path":"core/ollama_context_manager.py","qualname":"OllamaContextManager.detect_context_length"}}
+{"class":"R-path","site":{"arg_index":"pos:0","expr":"self._sock_path","message":"Messaging inbox listening at {}","method":"info","path":"services/messaging_inbox.py","qualname":"MessagingInbox.start"}}
 {"class":"R-name","site":{"arg_index":"pos:0","expr":"self.agent_name","message":"Agent '{}' auto-approving tool: {}","method":"debug","path":"agents/callbacks.py","qualname":"AgentCallbacks.request_confirmation"}}
 {"class":"R-name","site":{"arg_index":"pos:0","expr":"self.agent_name","message":"Agent '{}' failed","method":"exception","path":"agents/runner.py","qualname":"AgentRunner.run"}}
 {"class":"R-name","site":{"arg_index":"pos:0","expr":"self.agent_name","message":"agent token_usage: agent='{}' run_id={} tokens={}","method":"debug","path":"agents/callbacks.py","qualname":"AgentCallbacks.on_token_usage"}}
@@ -211,6 +219,7 @@
 {"class":"R-id","site":{"arg_index":"pos:1","expr":"self.run_id","message":"run timeout: agent='{}' run_id={} after {}s","method":"debug","path":"agents/runner.py","qualname":"AgentRunner.run"}}
 {"class":"R-id","site":{"arg_index":"pos:1","expr":"self.run_id","message":"run vacuous: agent='{}' run_id={}","method":"error","path":"agents/runner.py","qualname":"AgentRunner.run"}}
 {"class":"R-path","site":{"arg_index":"pos:1","expr":"source","message":"Source path for '{}' no longer exists: {}","method":"warning","path":"tools/plugin_manager.py","qualname":"update_plugin"}}
+{"class":"R-name","site":{"arg_index":"pos:1","expr":"tc.name","message":"Tool call id reused by a different tool ({} then {}); calls would merge","method":"warning","path":"loops/chat_loop.py","qualname":"ChatLoop.run"}}
 {"class":"R-status","site":{"arg_index":"pos:1","expr":"think","message":"Ollama model {!r} rejected think={!r}; retrying with think=False","method":"info","path":"providers/impl/ollama.py","qualname":"OllamaProvider._stream_in_content"}}
 {"class":"R-status","site":{"arg_index":"pos:1","expr":"think","message":"Ollama model {!r} rejected think={!r}; retrying with think=False","method":"info","path":"providers/impl/ollama.py","qualname":"OllamaProvider._stream_native"}}
 {"class":"R-class","site":{"arg_index":"pos:1","expr":"type(exc).__name__","message":"Provider retry budget exhausted after {} attempts; raising {}","method":"warning","path":"providers/retry.py","qualname":"RetryingProvider.stream_with_tools"}}
@@ -272,8 +281,10 @@
 {"class":"R-status","site":{"arg_index":"splat:fields:strategy","expr":"fields['strategy']","message":null,"method":"emit_event","path":"core/default_context_manager.py","qualname":"DefaultContextManager._emit_trim"}}
 {"class":"R-status","site":{"arg_index":"splat:fields:strategy","expr":"fields['strategy']","message":null,"method":"emit_event","path":"core/ollama_context_manager.py","qualname":"OllamaContextManager._emit_trim"}}
 {"class":"R-id","site":{"arg_index":"splat:self._correlation():run_id","expr":"self._correlation()['run_id']","message":null,"method":"emit_event","path":"loops/chat_loop.py","qualname":"ChatLoop._emit_tool_call"}}
+{"class":"R-id","site":{"arg_index":"splat:self._correlation():run_id","expr":"self._correlation()['run_id']","message":null,"method":"emit_event","path":"loops/chat_loop.py","qualname":"ChatLoop._emit_tool_call_received"}}
 {"class":"R-id","site":{"arg_index":"splat:self._correlation():run_id","expr":"self._correlation()['run_id']","message":null,"method":"emit_event","path":"loops/chat_loop.py","qualname":"ChatLoop.run"}}
 {"class":"R-id","site":{"arg_index":"splat:self._correlation():session_id","expr":"self._correlation()['session_id']","message":null,"method":"emit_event","path":"loops/chat_loop.py","qualname":"ChatLoop._emit_tool_call"}}
+{"class":"R-id","site":{"arg_index":"splat:self._correlation():session_id","expr":"self._correlation()['session_id']","message":null,"method":"emit_event","path":"loops/chat_loop.py","qualname":"ChatLoop._emit_tool_call_received"}}
 {"class":"R-id","site":{"arg_index":"splat:self._correlation():session_id","expr":"self._correlation()['session_id']","message":null,"method":"emit_event","path":"loops/chat_loop.py","qualname":"ChatLoop.run"}}
 {"class":"dynamic-trusted","site":{"arg_index":null,"expr":"evt","message":null,"method":"trace","path":"log.py","qualname":"emit_event"}}
 {"class":"dynamic-residual:known-shape-masked","site":{"arg_index":null,"expr":"message","message":null,"method":"log","path":"logging_config.py","qualname":"_InterceptHandler.emit"}}

{ayder_cli-2.3.0 → ayder_cli-2.3.1}/src/ayder_cli/agents/config.py

@@ -4,13 +4,15 @@ from typing import Any
 
 from pydantic import BaseModel, ConfigDict, model_validator
 
+from ayder_cli.core.reasoning import ReasoningEffort, ThinkOption
+
 
 class AgentConfig(BaseModel):
     """Configuration for a single agent, parsed from [agents.<name>] TOML sections.
 
     Connection-level fields (base_url, api_key, num_ctx, temperature, think,
-    driver) are optional; when set they override the values pulled from the
-    parent provider profile. This lets one agent target an entirely different
+    reasoning_effort, driver) are optional; when set they override values from
+    the parent provider profile. This lets one agent target an entirely different
     endpoint than the main session without needing a separate [llm.<name>]
     profile.
     """
@@ -28,7 +30,8 @@ class AgentConfig(BaseModel):
     num_ctx: int | None = None
     temperature: float | None = None
     max_output_tokens: int | None = None
-    think: str | None = None
+    think: ThinkOption = None
+    reasoning_effort: ReasoningEffort = None
 
     @model_validator(mode="before")
     @classmethod
@@ -56,7 +59,7 @@ class AgentConfig(BaseModel):
         return new_data
 
     def overrides(self) -> dict[str, Any]:
-        """Return non-None connection-level fields suitable for cfg.model_copy()."""
+        """Return profile overrides, including an explicitly reset effort."""
         out: dict[str, Any] = {}
         for field in (
             "model",
@@ -71,4 +74,10 @@ class AgentConfig(BaseModel):
             value = getattr(self, field)
             if value is not None:
                 out[field] = value
+        if "reasoning_effort" in self.model_fields_set:
+            # Explicit "default" clears a profile's effort; omission inherits it.
+            out["reasoning_effort"] = self.reasoning_effort
+        elif self.think is not None:
+            # An explicit legacy think override must beat an inherited effort.
+            out["reasoning_effort"] = None
         return out

{ayder_cli-2.3.0 → ayder_cli-2.3.1}/src/ayder_cli/agents/registry.py

@@ -154,6 +154,10 @@ class AgentRegistry:
     def current_generation(self) -> int:
         return self._current_generation
 
+    def set_parent_config(self, config: Any) -> None:
+        """Update defaults for future runs without mutating active agents."""
+        self._parent_config = config
+
     def new_generation(self) -> int:
         """Bump the conversation generation and reset the re-dispatch guard.
         Does NOT drop _runs: active agents keep running and are simply filtered

{ayder_cli-2.3.0 → ayder_cli-2.3.1}/src/ayder_cli/application/runtime_factory.py

@@ -10,6 +10,7 @@ from dataclasses import dataclass, field
 from typing import TYPE_CHECKING, Any
 
 from ayder_cli.core.config import Config, load_config, load_config_for_provider
+from ayder_cli.core.reasoning import validate_effort
 from ayder_cli.core.context_manager_factory import context_manager_factory
 
 if TYPE_CHECKING:
@@ -183,6 +184,8 @@ def create_agent_runtime(
     if overrides:
         cfg = cfg.model_copy(update=overrides)
 
+    validate_effort(cfg.driver, cfg.reasoning_effort)
+
     # 3. Create isolated AIProvider
     llm_provider = provider_orchestrator.create(cfg)