V1.0.0

.github/workflows/ubuntu-tests.yml

@@ -50,6 +50,7 @@ jobs:
         uv pip install --system \
           pytest \
           pytest-asyncio \
+          pytest-env \
           pytest-mock \
           -r requirements/requirements.in \
           -r requirements/requirements-help.in \

.gitignore

@@ -41,6 +41,7 @@ cecli/_version.py
 cecli/website/Gemfile.lock
 *.pyc
 env/
+__pycache__/
 
 # Ignore Folders
 cecli/website/_site/*

README.md

@@ -123,8 +123,10 @@ This command will make sure all commands ran by the coding agent happen in conte
 * [TUI Configuration](https://github.com/cecli-dev/cecli/blob/main/cecli/website/docs/config/tui.md)
 * [Skills](https://github.com/cecli-dev/cecli/blob/main/cecli/website/docs/config/skills.md)
 * [Subagents](https://github.com/cecli-dev/cecli/blob/main/cecli/website/docs/config/subagents.md)
+* [Persistent Memory](https://github.com/cecli-dev/cecli/blob/main/cecli/website/docs/config/persistent-memory.md)
 * [Session Management](https://github.com/cecli-dev/cecli/blob/main/cecli/website/docs/sessions.md)
 * [Hooks](https://github.com/cecli-dev/cecli/blob/main/cecli/website/docs/config/hooks.md)
+* [Agent Client Protocol (ACP)](https://github.com/cecli-dev/cecli/blob/main/cecli/website/docs/config/api.md)
 * [Workspaces](https://github.com/cecli-dev/cecli/blob/main/cecli/website/docs/config/workspaces.md)
 * [Custom Commands](https://github.com/cecli-dev/cecli/blob/main/cecli/website/docs/config/custom-commands.md)
 * [Custom System Prompts](https://github.com/cecli-dev/cecli/blob/main/cecli/website/docs/config/custom-system-prompts.md)
@@ -145,11 +147,11 @@ The current priorities are to improve core capabilities and user experience of t
   * [x] [Include import information in repo map for richer context](https://github.com/Aider-AI/aider/issues/2688)
   * [x] [Handle non-unique symbols that break down in large codebases](https://github.com/Aider-AI/aider/issues/2341)
 
-3. **Context Discovery** - [Discussion](https://github.com/cecli-dev/cecli/issues/46)
-  * [ ] Develop AST-based search capabilities
+3. **Context Discovery** - [Discussion - Done with Cymbal Library](https://github.com/cecli-dev/cecli/issues/46)
+  * [x] Develop AST-based search capabilities
   * [x] Enhance file search with ripgrep integration
-  * [ ] Implement RAG (Retrieval-Augmented Generation) for better code retrieval
-  * [ ] Build an explicit workflow and local tooling for internal discovery mechanisms
+  * [x] Implement RAG (Retrieval-Augmented Generation) for better code retrieval
+  * [x] Build an explicit workflow and local tooling for internal discovery mechanisms
 
 4. **Context Delivery** - [Discussion](https://github.com/cecli-dev/cecli/issues/47)
   * [x] Use workflow for internal discovery to better target file snippets needed for specific tasks (ExploreCode and ReadRange)
@@ -189,11 +191,11 @@ The current priorities are to improve core capabilities and user experience of t
   * [x] Update agent mode edit tools to work with hashline identification
   * [x] Update internal file diff representation to support hashline propagation
 
-10. **Dynamic Context Management** 
+10. **Dynamic Context Management (Accomplished with subagents, orchestrate, and the facts db)** 
   * [x] Update compaction to use observational memory sub agent calls to generate decision records that are used as the compaction basis
-  * [ ] Persist decision records to disk for sessions with some settings for managing lifetimes of such persistence
-  * [ ] Integrate RLM to extract information from decision records on disk and other definable notes
-  * [ ] Add a "describe" tool that launches a sub agent workflow that populates an RLM call's context with:
+  * [x] Persist decision records to disk for sessions with some settings for managing lifetimes of such persistence
+  * [x] Integrate RLM-like facility to extract information from decision records on disk and other definable notes
+  * [x] Add a "describe" tool that launches a sub agent workflow that populates an RLM call's context with:
     * Current Conversation History
     * Past Decision Records
     * Repo Map Found Files

cecli/args.py

@@ -18,6 +18,72 @@
 
 from .dump import dump  # noqa: F401
 
+# ── Deep-merge field sets ────────────────────────────────────────────
+# These define which config keys require special merge handling for
+# .cecli.conf.yml files (deep-merge instead of shallow-overwrite).
+
+DEEP_MERGE_LIST_FIELDS: frozenset[str] = frozenset(
+    {
+        # ── Top-level argparse action="append" args ──────────────────
+        # These are excluded from configargparse for .cecli.conf.yml files
+        # (to prevent shallow overwrite), so they must be deep-merged here.
+        "rules",
+        "file",
+        "read",
+        "mcp_servers_files",
+        "set_env",
+        "api_key",
+        "alias",
+        "exempt_paths",
+        "lint_cmd",
+        # ── Nested agent-config array fields ─────────────────────────
+        "skills_paths",
+        "skills_includelist",
+        "skills_excludelist",
+        "skills_init",
+        "subagent_paths",
+        "tools_paths",
+        "tools_includelist",
+        "tools_excludelist",
+        "servers_includelist",
+        "servers_excludelist",
+        "allowed_commands",
+    }
+)
+
+
+DEEP_MERGE_JSON_FIELDS: frozenset[str] = frozenset(
+    {
+        "agent_config",
+        "mcp_servers",
+        "hooks",
+        "model_providers",
+        "security_config",
+        "retries",
+        "custom",
+        "tui_config",
+    }
+)
+
+
+# Agent-config array fields (subset of DEEP_MERGE_LIST_FIELDS used by
+# agent_coder to validate agent config before passing to sub-agents).
+AGENT_CONFIG_LIST_FIELDS: frozenset[str] = frozenset(
+    {
+        "skills_paths",
+        "skills_includelist",
+        "skills_excludelist",
+        "skills_init",
+        "subagent_paths",
+        "tools_paths",
+        "tools_includelist",
+        "tools_excludelist",
+        "servers_includelist",
+        "servers_excludelist",
+        "allowed_commands",
+    }
+)
+
 
 def resolve_cecli_ignore_path(path_str, git_root=None):
     path = Path(path_str)
@@ -378,6 +444,12 @@ def get_parser(default_config_files, git_root):
             " (default: False)"
         ),
     )
+    group.add_argument(
+        "--auto-memory",
+        action=argparse.BooleanOptionalAction,
+        default=False,
+        help="Enable/disable automatic fact memorization after changes and compaction (default: True)",
+    )
     group.add_argument(
         "--session-encrypt",
         action=argparse.BooleanOptionalAction,
@@ -452,6 +524,14 @@ def get_parser(default_config_files, git_root):
         default=True,
         help="Enable automatic compaction of chat history to conserve tokens (default: False)",
     )
+    group.add_argument(
+        "--max-compaction-retries",
+        type=int,
+        default=3,
+        metavar="N",
+        choices=range(1, 11),
+        help="Maximum number of compactions per request before propagating the error (default: 3, min: 1, max: 10)",
+    )
     group.add_argument(
         "--context-compaction-max-tokens",
         type=float,
@@ -467,6 +547,15 @@ def get_parser(default_config_files, git_root):
         default=4096,
         help="The target maximum number of tokens for the generated summary. (default: 4096)",
     )
+    group.add_argument(
+        "--ignore-context-limit",
+        action=argparse.BooleanOptionalAction,
+        default=False,
+        help=(
+            "Ignore the model's context window limit when sending requests."
+            " WARNING: This may cause API errors or truncated responses. (default: False)"
+        ),
+    )
 
     ##########
     group = parser.add_argument_group("Cache settings")
@@ -1162,6 +1251,15 @@ def get_parser(default_config_files, git_root):
         ),
     )
 
+    ##########
+    group = parser.add_argument_group("Server settings")
+    group.add_argument(
+        "--server-config",
+        metavar="SERVER_CONFIG_JSON",
+        help="Specify server configuration (WebSocket and headless) as a JSON/YAML string",
+        default=None,
+    )
+
     ##########
     group = parser.add_argument_group("Deprecated model settings")
     # Add deprecated model shortcut arguments