tradingcodex 1.2.1__tar.gz → 1.2.2__tar.gz

{tradingcodex-1.2.1 → tradingcodex-1.2.2}/CHANGELOG.md

@@ -2,6 +2,18 @@
 
 ## Unreleased
 
+## 1.2.2 - 2026-07-22
+
+- Validate Codex CLI 0.145.0 as the current reference while retaining 0.144.4
+  as the compatibility floor; adopt its stable MultiAgent V2 schema by leaving
+  nesting and concurrency to native Codex while preserving strict config,
+  permission, hook, MCP, and role-model projection checks.
+- Restore the Head Manager's generated `export_dataset_csv` projection by
+  registering its canonical MCP schema, role boundary, and export capability,
+  with a generated-config-to-registry regression check.
+- Stop automated GitHub Release notes at the next changelog heading so a
+  release contains only its matching version section.
+
 ## 1.2.1 - 2026-07-21
 
 - Create or refresh the GitHub Release from the exact verified distributions

{tradingcodex-1.2.1 → tradingcodex-1.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tradingcodex
-Version: 1.2.1
+Version: 1.2.2
 Summary: Local-first investment operating system for Codex-native research and service-gated execution.
 Author: TradingCodex Authors
 License-Expression: Apache-2.0

{tradingcodex-1.2.1 → tradingcodex-1.2.2}/docs/codex-native-orchestration.md

@@ -81,7 +81,8 @@ conflicts with Strategy.
 
 ## Delegation Contract
 
-MultiAgent V2 exposes the generated role profiles with a depth-one boundary.
+MultiAgent V2 exposes the generated role profiles through native Codex
+delegation.
 Head Manager prefers an exact profile when its specialty is useful and passes a
 compact role-owned brief rather than the full root history. Role TOML supplies
 the direct fixed model settings; their values and fallback eligibility are owned
@@ -98,11 +99,15 @@ Use `followup_task` when a live child still owns a correction or clarification.
 Start another child for a new specialty, an unavailable session, or independent
 review. Apply the canonical fallback boundary in
 [Roles, Skills, And Workflows](roles-skills-and-workflows.md). A child cannot
-approve, execute, access a broker, or emulate Head Manager. Children never
-delegate recursively. Head Manager waits only while a live child has useful work
-and reports lifecycle events only from native tool and child-lifecycle results
-in the current run. Native wait is wait-any and may serialize with no explicit
-target list; that representation is not failure by itself.
+approve, execute, access a broker, or emulate Head Manager. Whether to delegate
+a distinct child-owned subtask further is a native Codex decision, not a
+TradingCodex workflow requirement. Every descendant remains subject to its
+selected projected role and the shared evidence, authority, and safety
+boundaries. Head Manager
+waits only while a live child has useful work and reports lifecycle events only
+from native tool and child-lifecycle results in the current run. Native wait is
+wait-any and may serialize with no explicit target list; that representation is
+not failure by itself.
 
 When a Brain applies, the assignment contains the question Head Manager derived
 from it, not the Brain body or a delegation of Brain authority. Brain content is

{tradingcodex-1.2.1 → tradingcodex-1.2.2}/docs/generated-workspaces.md

@@ -534,7 +534,7 @@ That explicit overlay rule applies to external skill procedures, not to
 read-only app, connector, MCP, or data tools used as evidence. A role whose
 assignment needs external data or preserves a user-named provider first checks
 the current task's callable tool surface and uses the runtime's available
-deferred-tool discovery surface when needed. The Codex 0.144.4 reference
+deferred-tool discovery surface when needed. The Codex 0.145.0 reference
 contract first resolves at most 12 names with
 `text(ALL_TOOLS.filter(x => x.name.includes("<provider-or-keyword>")).slice(0, 12).map(x => x.name))`.
 One supported query may combine one to four literal `name.includes`
@@ -586,14 +586,22 @@ runs, hard-failure checks, blind review, and resolved outcomes.
 Generated `.codex/config.toml` enables MultiAgent V2 with visible spawn
 metadata and the `agents` tool namespace. It keeps every
 `.codex/agents/*.toml` role discoverable while setting
-`features.multi_agent_v2.enabled = true` and `agents.max_depth = 1`. The
-V1-only `agents.max_threads` key is absent because Codex rejects it when V2 is
-enabled. Codex owns concurrency and scheduling. Head Manager chooses useful
-profiles and follows up with an owner when appropriate. Role eligibility and
-fallback are defined in [Roles, Skills, And Workflows](roles-skills-and-workflows.md).
-Children cannot recursively dispatch. Root model and reasoning settings are
-inherited, and direct fixed-role TOML model settings are projected, but `doctor`
-does not duplicate native model availability or lifecycle checks.
+`features.multi_agent_v2.enabled = true`. TradingCodex does not set
+`agents.max_depth`, `agents.max_threads`, or
+`agents.max_concurrent_threads_per_session`; Codex 0.145.0 ignores
+`agents.max_depth` for V2, retains `agents.max_threads` as a compatibility
+alias, and owns nesting, concurrency, and scheduling. Head Manager chooses
+useful profiles and follows up with an owner when appropriate. Role eligibility
+and fallback are defined in [Roles, Skills, And Workflows](roles-skills-and-workflows.md).
+Whether to delegate distinct child-owned work further is a native Codex
+decision, not a TradingCodex workflow requirement. Every descendant remains
+subject to its selected projected role and TradingCodex safety and service
+gates. Root model and reasoning settings are inherited, and direct fixed-role
+TOML model settings are projected, but `doctor` does not duplicate native model
+availability or lifecycle checks. Codex 0.145.0 exposes optional per-spawn model
+and reasoning overrides by default; TradingCodex neither disables nor requires
+them. A spawn without an explicit override follows native inheritance and role
+config resolution.
 
 Workspace template modules are deployment projections. Agent and skill
 ownership comes from the Python agent registry and is projected
@@ -868,10 +876,11 @@ Generated root config sets `default_permissions = "trading-research"` and
 defines two custom profiles. It deliberately omits legacy `sandbox_mode` from
 the root and every fixed-role TOML because any loaded `sandbox_mode` overrides
 custom permission profiles in Codex. This contract requires Codex CLI 0.144.4
-or later on a locally supported platform. Version 0.144.4 is the current
+or later on a locally supported platform. Version 0.145.0 is the current
 release-validation reference for permission profiles, hooks, required MCP,
-deferred MCP calls, and the explicit V2 feature table. Older versions fail the
-Codex runtime doctor check. These remain version-sensitive
+deferred MCP calls, and the explicit V2 feature table. Versions below the
+compatibility floor fail the Codex runtime doctor check; compatible non-reference
+versions warn. These remain version-sensitive
 surfaces, so release validation includes strict config/feature inspection and
 a real native smoke.
 See the [Codex permissions reference](https://learn.chatgpt.com/docs/permissions).
@@ -1582,7 +1591,7 @@ Codex-native bootstrap verification:
   workspace. The canonical workspace must
   either be interactively trusted or receive the one-run `projects={...}` trust
   override shown in `AGENTS.md`. A full fixed-role lifecycle smoke must use
-  persisted trust for all five generated project hooks. Codex 0.144.4 does not
+  persisted trust for all five generated project hooks. Codex 0.145.0 does not
   carry the one-run `--dangerously-bypass-hook-trust` flag through the role
   config reload used by an exact V2 child, so that flag may be used only for
   root/config diagnostics and is not lifecycle acceptance. It also does not

{tradingcodex-1.2.1 → tradingcodex-1.2.2}/docs/roles-skills-and-workflows.md

@@ -226,8 +226,11 @@ Start a fresh child for a new specialty, an unavailable session, or independent
 review. The Dynamic Workflow fallback boundary applies here. A generic child
 retains the same research-only scope, evidence standard, no-secret boundary,
 and no-order boundary; it cannot approve, execute, access a broker, or act as
-Head Manager. Children never delegate recursively. Wait only while a live child
-has useful work. Native
+Head Manager. Whether to delegate a distinct child-owned subtask further is a
+native Codex decision, not a workflow requirement. Each descendant remains
+subject to its selected projected role and the shared evidence, authority, and
+safety boundaries. Wait only while a live child has useful work.
+Native
 wait-any may serialize without explicit targets; verify lifecycle through the
 native tool result and child session events rather than treating that as failure.
 
@@ -260,7 +263,7 @@ same contract error repeats.
 The same bounded rule applies across role MCP use: a documented terminal
 outcome such as stored, updated, existing, reused, or prepared ends that call;
 an unchanged deterministic failure is never blindly resubmitted. Under the
-Codex 0.144.4 deferred-tool contract, unknown-provider resolution starts with
+Codex 0.145.0 deferred-tool contract, unknown-provider resolution starts with
 the canonical names-only query
 `text(ALL_TOOLS.filter(x => x.name.includes("<provider-or-keyword>")).slice(0, 12).map(x => x.name))`.
 One names-only query may combine at most four literal `name.includes`

{tradingcodex-1.2.1 → tradingcodex-1.2.2}/docs/validation-and-test-plan.md

@@ -266,8 +266,9 @@ Smoke coverage should verify:
   Manager and role-owned live research for the six evidence producers without
   treating a host finance skill as a dependency
 - generated `.codex/config.toml` explicitly enables MultiAgent V2, reports it
-  enabled through `codex features list`, leaves concurrency to Codex, and omits
-  the incompatible V1 `agents.max_threads` key
+  enabled through `codex features list`, leaves nesting and concurrency to
+  Codex, and omits TradingCodex-owned `agents.max_depth`,
+  `agents.max_threads`, and `agents.max_concurrent_threads_per_session`
 - skill/projection manifests identify the finite managed inventory, declare
   runtime discovery incomplete, and resolve exact root/role skill paths
 - two generated workspaces have different workspace ids
@@ -816,7 +817,7 @@ stop without an order, approval, execution, cancellation, broker mutation, or
 secret action. Record an unavailable Codex/auth blocker rather than replacing this with a
 claim based only on the fake subprocess test.
 
-Reference acceptance uses Codex CLI 0.144.4. Run
+Reference acceptance uses Codex CLI 0.145.0. Run
 `python tests/codex_cli_contract.py --workspace <workspace>
 --require-reference --require-hook-trust` first, after opening the disposable
 workspace in interactive Codex and persistently trusting all five generated
@@ -826,7 +827,7 @@ configuration, readable sandbox settings, the expected enabled/disabled
 feature states, and trusted lifecycle hooks. Native `codex exec` smokes must
 also pass `--strict-config`, so a newly unknown or removed project key fails
 before model behavior is accepted. Do not use `--ignore-user-config` or
-`--dangerously-bypass-hook-trust` for lifecycle acceptance: in 0.144.4 the
+`--dangerously-bypass-hook-trust` for lifecycle acceptance: in 0.145.0 the
 one-run bypass is not inherited when a V2 child reloads an exact role config.
 On platforms where a temporary directory has a symlinked alias, resolve the
 workspace once with `realpath` or `Path.resolve()` and use that same physical
@@ -839,10 +840,13 @@ Run native CLI smokes that inspect observable tool calls and child lifecycle
 results from Codex. Cover the direct fast path, one exact profile, a same-owner
 `followup_task`, and a bounded evidence-role generic fallback when a profile is
 unavailable. Briefs must stay compact, generated TOML must retain the fixed
-model settings and the project-wide `trading-research` profile, and no child may
-recursively delegate. A missing independent risk or judgment profile must remain
-explicit rather than becoming a generic review. Run a sequential two-child smoke plus one artifact-to-synthesis
-workflow because lifecycle failures may appear only after the first child exits.
+model settings and the project-wide `trading-research` profile. When native
+Codex delegates a child-owned subtask further, inspect the descendant lifecycle
+and verify that its effective role, model, permission profile, MCP principal,
+evidence boundary, and no-order boundary match the selected role. A missing independent risk or judgment
+profile must remain explicit rather than becoming a generic review. Run a
+sequential two-child smoke plus one artifact-to-synthesis workflow because
+lifecycle failures may appear only after the first child exits.
 
 For a full research smoke, inspect root and child JSONL as observable behavior,
 not private chain of thought. Require a compact bounded child brief; reject broad

{tradingcodex-1.2.1 → tradingcodex-1.2.2}/installation.md

@@ -49,7 +49,7 @@ initialized is fine, as is an empty directory inside an existing parent
 worktree.
 
 Use Codex CLI 0.144.4 or later on macOS, Linux, WSL, or native Windows. Version
-0.144.4 is the current TradingCodex reference for custom permission profiles,
+0.145.0 is the current TradingCodex reference for custom permission profiles,
 hooks, required MCP startup, and explicit MultiAgent V2 configuration. Verify
 with `codex --version`; `./tcx doctor --layer guidance` fails below the
 compatibility floor and warns when the installed CLI is older or newer than the
@@ -375,10 +375,10 @@ Generated root work inherits the user's active Codex model and reasoning
 settings. All nine fixed subagents use `gpt-5.6-terra` with `high` reasoning.
 Final execution is service-owned and runs no model.
 MultiAgent V2 exposes exact custom-role routing through the `agents` namespace;
-each task uses `fork_turns="none"` and a fresh role-bound child. The generated
-V2 table explicitly sets `enabled = true` and `max_depth = 1`; concurrency
-capacity remains owned by native Codex and user/host configuration rather than
-a projected V1 thread cap.
+exact custom-role dispatch uses `fork_turns="none"` so Codex applies the fresh
+role-bound config layer. The generated V2 table explicitly sets `enabled = true`
+but does not set nesting or concurrency controls; native Codex and user/host
+configuration own those choices.
 Inspect `.codex/config.toml`, `.codex/agents/`, and `./tcx doctor` after an
 update to verify the generated Codex contract. There is no model-policy
 manifest, runtime model fallback, or rollout control.

{tradingcodex-1.2.1 → tradingcodex-1.2.2}/tests/test_codex_cli_compat.py

@@ -14,8 +14,10 @@ from tradingcodex_cli.commands import doctor
         ("0.144.0", False, False),
         ("0.144.1", False, False),
         ("0.144.2", False, False),
-        ("0.144.4", True, False),
-        ("0.145.0", True, True),
+        ("0.144.4", True, True),
+        ("0.144.5", True, True),
+        ("0.145.0", True, False),
+        ("0.145.1", True, True),
     ],
 )
 def test_codex_cli_reference_version_check(
@@ -42,10 +44,12 @@ def test_codex_cli_reference_version_check(
     assert bool(result.get("warn")) is warn
     assert f"installed={installed}" in result["detail"]
     assert "required>=0.144.4" in result["detail"]
-    assert "reference=0.144.4" in result["detail"]
+    assert "reference=0.145.0" in result["detail"]
     if installed in {"0.144.1", "0.144.2"}:
         assert "older than required" in result["detail"]
-    if installed == "0.145.0":
+    if installed in {"0.144.4", "0.144.5"}:
+        assert "older than reference" in result["detail"]
+    if installed == "0.145.1":
         assert "newer client requires harness revalidation" in result["detail"]
 
 

{tradingcodex-1.2.1 → tradingcodex-1.2.2}/tests/test_codex_native_orchestration.py

@@ -418,8 +418,8 @@ def test_generated_contract_inherits_root_model_and_keeps_role_profiles_optional
     assert '[features.multi_agent_v2]' in config
     assert 'enabled = true' in config
     assert "max_concurrent_threads_per_session" not in config
-    assert "max_depth = 1" in config
-    assert 'max_threads = 6' not in config
+    assert "max_depth" not in config_values.get("agents", {})
+    assert "max_threads" not in config_values.get("agents", {})
     assert "required = true" in config
     assert '"begin_analysis_run"' in config
     assert "record_workflow_plan" not in config
@@ -432,8 +432,8 @@ def test_generated_contract_inherits_root_model_and_keeps_role_profiles_optional
     assert "You are the `head-manager` agent" not in fixed_role
     assert "# Role And Safety" in fixed_role
     assert "authenticated TradingCodex MCP" in fixed_role
-    assert "depth-1 child" in fixed_role
-    assert "never spawn, coordinate" in fixed_role
+    assert "Whether to delegate" not in fixed_role
+    assert "All work performed on your behalf remains subject" in fixed_role
     assert "$tcx-source-gate" in fixed_role
     assert "Snapshot/Dataset/Artifact IDs" in fixed_role
     assert "do not duplicate or invent provider policy here" in fixed_role
@@ -484,6 +484,13 @@ def test_generated_contract_inherits_root_model_and_keeps_role_profiles_optional
         enabled_tools = set(role_config["mcp_servers"]["tradingcodex"]["enabled_tools"])
         assert role_config["model"] == "gpt-5.6-terra"
         assert role_config["model_reasoning_effort"] == "high"
+        assert role_config.get("agents", {}).get("enabled") is not False
+        assert (
+            role_config.get("features", {})
+            .get("multi_agent_v2", {})
+            .get("enabled")
+            is not False
+        )
         assert "get_research_artifact" in enabled_tools
         assert ARTIFACT_DISCOVERY_TOOLS.isdisjoint(enabled_tools)
         assert role_config["model_instructions_file"] == FIXED_ROLE_MODEL_INSTRUCTIONS
@@ -494,6 +501,23 @@ def test_generated_contract_inherits_root_model_and_keeps_role_profiles_optional
         assert "Artifact handoff:" not in role_instructions
 
 
+def test_generated_mcp_allowlists_reference_only_registered_tools(workspace: Path) -> None:
+    config_paths = [
+        workspace / ".codex/config.toml",
+        *(workspace / ".codex/agents").glob("*.toml"),
+    ]
+
+    for config_path in config_paths:
+        config = tomllib.loads(config_path.read_text(encoding="utf-8"))
+        enabled_tools = set(
+            config["mcp_servers"]["tradingcodex"]["enabled_tools"]
+        )
+        assert enabled_tools <= TOOL_REGISTRY.keys(), (
+            f"{config_path.relative_to(workspace)} references unregistered "
+            f"TradingCodex MCP tools: {sorted(enabled_tools - TOOL_REGISTRY.keys())}"
+        )
+
+
 def test_doctor_requires_fixed_role_base_and_per_role_override(workspace: Path) -> None:
     doctor = subprocess.run(
         [str(workspace / "tcx"), "doctor", "--verbose"],

{tradingcodex-1.2.1 → tradingcodex-1.2.2}/tests/test_datasets.py

@@ -1,7 +1,8 @@
 from __future__ import annotations
 
-import json
+import csv
 import hmac
+import json
 import os
 from pathlib import Path
 
@@ -20,6 +21,7 @@ from tradingcodex_service.application.datasets import (
 )
 from tradingcodex_service.application.research import record_source_snapshot
 from tradingcodex_service.application.runtime import ensure_workspace_manifest
+from tradingcodex_service.mcp_runtime import call_mcp_tool
 
 
 pytest.importorskip("pyarrow", reason="dataset tests require the pinned PyArrow runtime")
@@ -167,6 +169,54 @@ def test_dataset_ingest_is_immutable_idempotent_searchable_and_sliceable(
     )
 
 
+def test_dataset_csv_export_is_registered_idempotent_and_license_gated(
+    workspace_and_scratch: tuple[Path, Path, str],
+) -> None:
+    root, scratch, snapshot_id = workspace_and_scratch
+    exportable = record_dataset_snapshot(
+        root,
+        {**_args(snapshot_id), "redistribution": "allowed"},
+        scratch_root=scratch,
+    )
+    export_args = {
+        "principal_id": "head-manager",
+        "dataset_id": exportable["dataset_id"],
+        "columns": ["timestamp", "close"],
+        "export_path": "trading/research/datasets/exports/btc-close.csv",
+    }
+
+    exported = call_mcp_tool(root, "export_dataset_csv", export_args)
+    assert exported["status"] == "exported"
+    assert exported["columns"] == ["timestamp", "close"]
+    assert exported["row_count"] == 3
+    export_path = root / exported["export_path"]
+    with export_path.open(encoding="utf-8", newline="") as handle:
+        assert list(csv.DictReader(handle)) == [
+            {"timestamp": "2026-01-01 00:00:00.000000Z", "close": "100"},
+            {"timestamp": "2026-01-02 00:00:00.000000Z", "close": "110"},
+            {"timestamp": "2026-01-03 00:00:00.000000Z", "close": "121"},
+        ]
+
+    repeated = call_mcp_tool(root, "export_dataset_csv", export_args)
+    assert repeated["status"] == "existing"
+    assert repeated["content_hash"] == exported["content_hash"]
+
+    restricted = record_dataset_snapshot(
+        root,
+        _args(snapshot_id, title="Restricted BTC daily prices"),
+        scratch_root=scratch,
+    )
+    with pytest.raises(PermissionError, match="redistribution is not explicitly allowed"):
+        call_mcp_tool(
+            root,
+            "export_dataset_csv",
+            {
+                "principal_id": "head-manager",
+                "dataset_id": restricted["dataset_id"],
+            },
+        )
+
+
 def test_dataset_rejects_unsafe_sources_and_withdrawal_is_explicit(
     workspace_and_scratch: tuple[Path, Path, str],
 ) -> None:

{tradingcodex-1.2.1 → tradingcodex-1.2.2}/tests/test_release_contract.py

@@ -118,7 +118,7 @@ def test_cli_hook_dispatch_preserves_standard_input_and_output(
 def test_v1_package_metadata_has_one_stable_version_source() -> None:
     project = tomllib.loads((ROOT / "pyproject.toml").read_text(encoding="utf-8"))
 
-    assert TRADINGCODEX_VERSION == "1.2.1"
+    assert TRADINGCODEX_VERSION == "1.2.2"
     assert str(Version(TRADINGCODEX_VERSION)) == TRADINGCODEX_VERSION
     assert project["project"]["dynamic"] == ["version"]
     assert "version" not in project["project"]
@@ -711,6 +711,7 @@ def test_release_publish_is_tag_bound_and_reuses_one_verified_build() -> None:
     assert any("download-artifact" in step.get("uses", "") for step in github_release["steps"])
     assert "CHANGELOG.md" in release_job_steps
     assert "release-notes.md" in release_job_steps
+    assert ' - [^\\n]*$\\n.*?(?=^## |\\Z)' in release_job_steps
     assert "gh release create" in release_job_steps
     assert "gh release edit" in release_job_steps
     assert "gh release upload" in release_job_steps

{tradingcodex-1.2.1 → tradingcodex-1.2.2}/tests/test_research_forecast_surfaces.py

@@ -275,6 +275,7 @@ def test_generated_projection_and_registry_keep_evidence_roles_narrow(tmp_path:
         "list_artifact_catalog",
         "search_artifact_catalog",
         "rebuild_artifact_catalog",
+        "export_dataset_csv",
     }
     assert expected.issubset(TOOL_REGISTRY)
     assert TOOL_REGISTRY["create_causal_equity_analysis"].allowed_roles == {"valuation-analyst"}
@@ -284,6 +285,8 @@ def test_generated_projection_and_registry_keep_evidence_roles_narrow(tmp_path:
     assert TOOL_REGISTRY["create_evaluation_corpus"].allowed_roles == {"head-manager"}
     assert TOOL_REGISTRY["record_blind_human_review"].allowed_roles == {"judgment-reviewer"}
     assert TOOL_REGISTRY["rebuild_artifact_catalog"].allowed_roles == {"head-manager"}
+    assert TOOL_REGISTRY["export_dataset_csv"].allowed_roles == {"head-manager"}
+    assert TOOL_REGISTRY["export_dataset_csv"].capability_required == "dataset.export"
     assert all("execution-operator" not in TOOL_REGISTRY[name].allowed_roles for name in expected)
     assert {"get_research_spec", "list_research_specs", "get_forecast", "list_forecasts", "get_forecast_calibration_report", "list_artifact_catalog", "search_artifact_catalog"}.issubset(SAFE_HOME_TOOL_NAMES)
     snapshot_schema = TOOL_REGISTRY["record_source_snapshot"].input_schema
@@ -297,7 +300,7 @@ def test_generated_projection_and_registry_keep_evidence_roles_narrow(tmp_path:
     valuation_tools = set(tomllib.loads((workspace / ".codex/agents/valuation-analyst.toml").read_text(encoding="utf-8"))["mcp_servers"]["tradingcodex"]["enabled_tools"])
     judgment_tools = set(tomllib.loads((workspace / ".codex/agents/judgment-reviewer.toml").read_text(encoding="utf-8"))["mcp_servers"]["tradingcodex"]["enabled_tools"])
     assert not (workspace / ".codex/agents/execution-operator.toml").exists()
-    assert {"create_research_spec", "create_evaluation_corpus", "score_forecast", "list_artifact_catalog", "search_artifact_catalog", "rebuild_artifact_catalog"}.issubset(root_tools)
+    assert {"create_research_spec", "create_evaluation_corpus", "score_forecast", "list_artifact_catalog", "search_artifact_catalog", "rebuild_artifact_catalog", "export_dataset_csv"}.issubset(root_tools)
     assert {"create_causal_equity_analysis", "issue_forecast"}.issubset(valuation_tools)
     assert {"record_blind_judgment_prior", "complete_judgment_review", "resolve_forecast", "promote_lesson", "record_blind_human_review"}.issubset(judgment_tools)
     artifact_discovery_tools = {

{tradingcodex-1.2.1 → tradingcodex-1.2.2}/tradingcodex.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tradingcodex
-Version: 1.2.1
+Version: 1.2.2
 Summary: Local-first investment operating system for Codex-native research and service-gated execution.
 Author: TradingCodex Authors
 License-Expression: Apache-2.0

{tradingcodex-1.2.1 → tradingcodex-1.2.2}/tradingcodex_cli/commands/doctor.py

@@ -366,13 +366,22 @@ def _fixed_role_dispatch_checks(root: Path) -> list[dict[str, Any]]:
         }]
     features = config.get("features") if isinstance(config.get("features"), dict) else {}
     multi_agent_v2 = features.get("multi_agent_v2") if isinstance(features.get("multi_agent_v2"), dict) else {}
+    agents = config.get("agents") if isinstance(config.get("agents"), dict) else {}
+    orchestration_overrides = {
+        key: agents[key]
+        for key in (
+            "max_depth",
+            "max_threads",
+            "max_concurrent_threads_per_session",
+        )
+        if key in agents
+    }
     exact_runtime = (
         features.get("multi_agent") is True
         and multi_agent_v2.get("enabled") is True
         and multi_agent_v2.get("hide_spawn_agent_metadata") is False
         and multi_agent_v2.get("tool_namespace") == "agents"
-        and config.get("agents", {}).get("max_depth") == 1
-        and "max_threads" not in (config.get("agents") or {})
+        and not orchestration_overrides
     )
     workflow_path = root / ".agents" / "skills" / "tcx-workflow" / "SKILL.md"
     workflow = workflow_path.read_text(encoding="utf-8") if workflow_path.is_file() else ""
@@ -396,7 +405,7 @@ def _fixed_role_dispatch_checks(root: Path) -> list[dict[str, Any]]:
                 f"multi_agent_v2={multi_agent_v2.get('enabled')}, "
                 f"hide_spawn_agent_metadata={multi_agent_v2.get('hide_spawn_agent_metadata')}, "
                 f"tool_namespace={multi_agent_v2.get('tool_namespace')}, "
-                f"max_depth={config.get('agents', {}).get('max_depth')}"
+                f"orchestration_overrides={orchestration_overrides}"
             ),
         },
         {

{tradingcodex-1.2.1 → tradingcodex-1.2.2}/tradingcodex_service/application/agents.py

@@ -46,7 +46,7 @@ class AgentSpec:
     forbidden_skill_tags: tuple[str, ...] = ()
 MODEL_TOOL_PROFILE_REVISION = "2026-07-role-allowlists-v1"
 MINIMUM_CODEX_VERSION = "0.144.4"
-REFERENCE_CODEX_VERSION = "0.144.4"
+REFERENCE_CODEX_VERSION = "0.145.0"
 
 
 RESEARCH_ROLES = (

{tradingcodex-1.2.1 → tradingcodex-1.2.2}/tradingcodex_service/mcp_runtime.py

@@ -1373,6 +1373,31 @@ TOOL_SPECS: tuple[McpToolSpec, ...] = (
             additional_properties=False,
         ),
     ),
+    McpToolSpec(
+        name="export_dataset_csv",
+        description=(
+            "Export selected columns from an immutable Dataset to a workspace-managed CSV "
+            "only when its manifest explicitly permits redistribution."
+        ),
+        category="research",
+        risk_level="write",
+        allowed_roles=roles_with_mcp_tool("export_dataset_csv"),
+        handler_name="export_dataset_csv",
+        input_schema=object_schema(
+            {
+                "dataset_id": {"type": "string"},
+                "columns": {
+                    "type": "array",
+                    "items": {"type": "string"},
+                    "maxItems": 100,
+                },
+                "export_path": {"type": "string"},
+            },
+            ["dataset_id"],
+            additional_properties=False,
+        ),
+        capability_required="dataset.export",
+    ),
     McpToolSpec(
         name="profile_dataset",
         description="Profile selected Dataset columns and return bounded statistics plus at most 20 sample rows.",

tradingcodex-1.2.2/tradingcodex_service/version.py

@@ -0,0 +1 @@
+TRADINGCODEX_VERSION = "1.2.2"

{tradingcodex-1.2.1 → tradingcodex-1.2.2}/workspace_templates/modules/codex-base/files/.codex/config.toml

@@ -219,9 +219,6 @@ enabled = true
 hide_spawn_agent_metadata = false
 tool_namespace = "agents"
 
-[agents]
-max_depth = 1
-
 [[skills.config]]
 path = "../.agents/skills/tcx-plan/SKILL.md"
 enabled = true

{tradingcodex-1.2.1 → tradingcodex-1.2.2}/workspace_templates/modules/codex-base/files/.codex/prompts/base_instructions/fixed-role.md

@@ -2,7 +2,7 @@ You are a fixed-role child in TradingCodex, a local-first investment OS built on
 
 # Role And Safety
 
-- Stay within the assigned role and question. You are a depth-1 child: never spawn, coordinate, begin a run, synthesize, use Build/Brain/Strategy/order-turn authority, or emulate another role.
+- Stay within the assigned role and question. All work performed on your behalf remains subject to the applicable projected evidence, authority, and safety boundaries. Do not begin a run, synthesize the Head Manager's decision, use Build/Brain/Strategy/order-turn authority, or emulate another role.
 - Read only task-relevant projected skills. Skills are procedures, not authority.
 - Keep disposable work under `$TRADINGCODEX_SCRATCH`. Use authenticated TradingCodex MCP for durable research; never access secrets, broker APIs, private services, approvals, orders, audit records, or protected state.
 - Never submit/cancel an order or mutate a broker. Language, assignments, skills, and tools do not grant that authority.

tradingcodex-1.2.1/tradingcodex_service/version.py

@@ -1 +0,0 @@
-TRADINGCODEX_VERSION = "1.2.1"