tradingcodex 0.2.6__tar.gz → 0.2.7__tar.gz

{tradingcodex-0.2.6 → tradingcodex-0.2.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tradingcodex
-Version: 0.2.6
+Version: 0.2.7
 Summary: Codex-native trading harness with a Django service plane and approved action boundary.
 Author: TradingCodex Authors
 License-Expression: Apache-2.0
@@ -90,6 +90,7 @@ comes only from installed, reviewed providers and explicit live gates.
 | Codex-native harness | Generates a Codex workspace with `head-manager`, nine fixed subagents, role prompts, skills, hooks, project MCP config, and a local `./tcx` wrapper. |
 | Django service plane | Web, Admin, API, CLI, MCP, and generated hooks call shared application services for policy, orders, approvals, portfolio, audit, integrations, and research indexing. |
 | File-native research memory | Research markdown, role reports, source snapshots, versions, readiness labels, and handoff metadata stay readable in workspace files. |
+| Decision Workflow Alpha | Turn a natural-language investment idea into a Codex-native workflow plan and Decision Package under `trading/decisions/`. |
 | Fixed-role workflows | Specialist agents own bounded questions across fundamentals, technicals, news, macro, instruments, valuation, portfolio, risk, and execution. |
 | Approved action boundary | Actions are typed, role-scoped, policy-checked, approval-aware, duplicate-request checked, connection-gated, and audited. |
 | Local web dashboard | Review agents, skills, strategy skills, research markdown, Broker Center, Data Sources, order tickets, portfolio state, and activity at `127.0.0.1:48267`. |
@@ -257,7 +258,7 @@ provide investment recommendations or guarantee returns.
 | --- | --- |
 | Shipped | Generated Codex workspace, fixed role roster, project MCP config, Django service plane, local web dashboard, Admin, Ninja API, file-native research memory, component registry, policy/audit primitives. |
 | Current `0.2.x` | Central-DB `OrderTicket` rewrite, provider-driven Broker Center foundations, Data Sources gate, role-scoped actions, live-gated execution lifecycle, and Python `>=3.11,<3.15` support. |
-| Next | Deeper validation scenarios, richer provider capability profiles, stronger generated-workspace smoke coverage, and improved artifact quality tooling. |
+| Next | Codex-native Decision Packages, deeper validation scenarios, richer provider capability profiles, stronger generated-workspace smoke coverage, and improved artifact quality tooling. |
 | Future | Separately governed verified adapters, hosted/managed services, enterprise policy/compliance packs, and broker-specific live providers only after explicit product, policy, adapter, and validation work. |
 
 ---

{tradingcodex-0.2.6 → tradingcodex-0.2.7}/README.md

@@ -59,6 +59,7 @@ comes only from installed, reviewed providers and explicit live gates.
 | Codex-native harness | Generates a Codex workspace with `head-manager`, nine fixed subagents, role prompts, skills, hooks, project MCP config, and a local `./tcx` wrapper. |
 | Django service plane | Web, Admin, API, CLI, MCP, and generated hooks call shared application services for policy, orders, approvals, portfolio, audit, integrations, and research indexing. |
 | File-native research memory | Research markdown, role reports, source snapshots, versions, readiness labels, and handoff metadata stay readable in workspace files. |
+| Decision Workflow Alpha | Turn a natural-language investment idea into a Codex-native workflow plan and Decision Package under `trading/decisions/`. |
 | Fixed-role workflows | Specialist agents own bounded questions across fundamentals, technicals, news, macro, instruments, valuation, portfolio, risk, and execution. |
 | Approved action boundary | Actions are typed, role-scoped, policy-checked, approval-aware, duplicate-request checked, connection-gated, and audited. |
 | Local web dashboard | Review agents, skills, strategy skills, research markdown, Broker Center, Data Sources, order tickets, portfolio state, and activity at `127.0.0.1:48267`. |
@@ -226,7 +227,7 @@ provide investment recommendations or guarantee returns.
 | --- | --- |
 | Shipped | Generated Codex workspace, fixed role roster, project MCP config, Django service plane, local web dashboard, Admin, Ninja API, file-native research memory, component registry, policy/audit primitives. |
 | Current `0.2.x` | Central-DB `OrderTicket` rewrite, provider-driven Broker Center foundations, Data Sources gate, role-scoped actions, live-gated execution lifecycle, and Python `>=3.11,<3.15` support. |
-| Next | Deeper validation scenarios, richer provider capability profiles, stronger generated-workspace smoke coverage, and improved artifact quality tooling. |
+| Next | Codex-native Decision Packages, deeper validation scenarios, richer provider capability profiles, stronger generated-workspace smoke coverage, and improved artifact quality tooling. |
 | Future | Separately governed verified adapters, hosted/managed services, enterprise policy/compliance packs, and broker-specific live providers only after explicit product, policy, adapter, and validation work. |
 
 ---

{tradingcodex-0.2.6 → tradingcodex-0.2.7}/docs/README.md

@@ -25,6 +25,7 @@ reference, then follow the topic-specific files for implementation-level rules.
 | [improvement-loop.md](./improvement-loop.md) | Improvement taxonomy: workflow quality, research memory, file-native skill proposals, postmortems, validation feedback | Quality gates, learning loops, postmortems, skill proposal/projection, or validation feedback behavior changes |
 | [product-direction.md](./product-direction.md) | Product definition, target users, goals, non-goals, scope posture, current defaults | Product direction, release scope, default runtime, product language, or live-execution posture changes |
 | [financial-workflow-references.md](./financial-workflow-references.md) | Research-backed finance workflow and non-expert UX principles for workflow handoffs and role outputs | User-facing workflow intake, suitability/profile context, plain-English output, or professional finance method framing changes |
+| [investment-decision-quality-prd.md](./investment-decision-quality-prd.md) | PRD for vague-prompt routing, Decision Quality Spine, forecast discipline, scenario reasoning, data QC, and anti-overfit validation | Investment-analysis quality, forecasting, decision-support routing, shared decision-quality skills, or forecast/readiness artifact contracts change |
 | [system-architecture.md](./system-architecture.md) | Django modular monolith, central DB, app boundaries, service layer, core models, runtime planes | Django apps, DB ownership, service-layer use cases, model ownership, or runtime topology changes |
 | [interfaces-and-surfaces.md](./interfaces-and-surfaces.md) | Product web, Django Admin, Django Ninja API, MCP endpoint, CLI, generated `./tcx` wrapper | User/admin/API/MCP/CLI surface changes, route changes, or callable tool changes |
 | [safety-policy-and-execution.md](./safety-policy-and-execution.md) | Guardrail taxonomy, policy checks, approvals, idempotency, execution lifecycle, blocked actions | Policy, permissions, approvals, adapters, execution, restricted list, secret handling, or risk gates change |
@@ -57,8 +58,8 @@ reference, then follow the topic-specific files for implementation-level rules.
 | Django apps, models, service-layer contracts, or DB ownership | `system-architecture.md` |
 | Product web, Admin, REST, MCP, CLI, or wrapper behavior | `interfaces-and-surfaces.md` |
 | Guardrails, policy, permission, approval, execution, adapter, or secret boundary | `guardrails.md`, `safety-policy-and-execution.md`, `core-concepts-and-rules.md` |
-| Subagent roster, role responsibilities, skills, strategy behavior, workflow routing, or information barriers | `roles-skills-and-workflows.md`, `core-concepts-and-rules.md` |
-| Research memory, artifacts, exports, source snapshots, report readiness, or postmortem learning | `improvement-loop.md`, `research-memory-and-artifacts.md` |
+| Subagent roster, role responsibilities, skills, strategy behavior, workflow routing, decision-quality routing, or information barriers | `roles-skills-and-workflows.md`, `investment-decision-quality-prd.md`, `core-concepts-and-rules.md` |
+| Research memory, artifacts, exports, source snapshots, forecast ledgers, report readiness, or postmortem learning | `improvement-loop.md`, `research-memory-and-artifacts.md`, `investment-decision-quality-prd.md` |
 | Generated workspace structure, templates, hooks, bootstrap, or MCP config | `generated-workspaces.md` |
 | Test coverage or validation commands | `validation-and-test-plan.md` |
 | PyPI/TestPyPI release, CI/CD, or package distribution boundary | `deployment.md`, `product-direction.md` |

{tradingcodex-0.2.6 → tradingcodex-0.2.7}/docs/components.md

@@ -38,8 +38,9 @@ paths clear.
 | `investment-request-routing` | Classifies user intent and activates fixed-role workflows. | `guardrail.guidance`, `improvement.workflow_quality` |
 | `fixed-role-dispatch` | Maintains head-manager, fixed subagent routing, and no-overlap handoff boundaries. | `guardrail.guidance`, `guardrail.information_barrier`, `improvement.workflow_quality` |
 | `research-memory` | Stores source-aware research artifacts, versions, snapshots, and exports. | `improvement.research_memory` |
-| `workflow-quality-gates` | Defines lane selection, handoff acceptance, artifact readiness, claim discipline, and synthesis gates. | `guardrail.guidance`, `improvement.workflow_quality` |
-| `artifact-quality-contract` | Evaluates workspace artifacts for source/as-of posture, claim tags, handoff state, confidence, missing evidence, and next-recipient routing metadata. | `guardrail.guidance`, `improvement.workflow_quality`, `improvement.research_memory` |
+| `workflow-quality-gates` | Defines lane selection, Decision Quality Spine, handoff acceptance, artifact readiness, claim discipline, and synthesis gates. | `guardrail.guidance`, `improvement.workflow_quality` |
+| `decision-package` | Wraps workflow plans, artifact paths, profile gaps, blocked actions, and next steps in Codex-readable workspace markdown. | `guardrail.guidance`, `improvement.workflow_quality`, `improvement.research_memory` |
+| `artifact-quality-contract` | Evaluates workspace artifacts and forecast ledgers for source/as-of posture, claim tags, handoff state, confidence, missing evidence, and next-recipient routing metadata. | `guardrail.guidance`, `improvement.workflow_quality`, `improvement.research_memory` |
 | `context-efficiency-contract` | Keeps workflows bounded through compact briefs, artifact references, context summaries, source snapshot IDs, targeted full-artifact reads, and `subagents context-audit` validation. | `guardrail.guidance`, `guardrail.information_barrier`, `improvement.workflow_quality`, `improvement.context_efficiency` |
 | `responsibility-boundary-contract` | Separates durable role identity, tool permissions, skill procedures, artifact contracts, and projection ownership so changes stay local. | `guardrail.guidance`, `guardrail.information_barrier`, `improvement.workflow_quality`, `improvement.skill_evolution` |
 | `external-data-source-gate` | Keeps external evidence read-only and source-aware. | `guardrail.guidance`, `improvement.workflow_quality` |

{tradingcodex-0.2.6 → tradingcodex-0.2.7}/docs/deployment.md

@@ -141,7 +141,7 @@ python3.11 -m venv /tmp/tcx-testpypi
 /tmp/tcx-testpypi/bin/pip install \
   --index-url https://test.pypi.org/simple/ \
   --extra-index-url https://pypi.org/simple/ \
-  tradingcodex==0.2.6
+  tradingcodex==0.2.7
 rm -rf /tmp/tcx-testpypi-smoke
 mkdir -p /tmp/tcx-testpypi-smoke
 cd /tmp/tcx-testpypi-smoke
@@ -170,7 +170,7 @@ After the PyPI workflow completes:
 
 ```bash
 python3.11 -m venv /tmp/tcx-pypi
-/tmp/tcx-pypi/bin/pip install tradingcodex==0.2.6
+/tmp/tcx-pypi/bin/pip install tradingcodex==0.2.7
 rm -rf /tmp/tcx-pypi-smoke
 mkdir -p /tmp/tcx-pypi-smoke
 cd /tmp/tcx-pypi-smoke
@@ -257,7 +257,9 @@ Use PEP 440 versions:
 - `0.2.6` for provider-driven Broker Center foundations, live-gated provider
   execution paths, runtime surface simplification, and stricter subagent skill
   boundaries after `0.2.5`
-- later patch releases for compatible fixes after `0.2.6`
+- `0.2.7` for Codex-native decision packages and investment decision quality
+  spine improvements after `0.2.6`
+- later patch releases for compatible fixes after `0.2.7`
 - pre-releases such as `0.3.0a1`, `0.3.0b1`, or `0.3.0rc1` when preparing
   the next minor contract
 

{tradingcodex-0.2.6 → tradingcodex-0.2.7}/docs/generated-workspaces.md

@@ -101,6 +101,11 @@ Generated workspaces contain:
 - no-overlap handoff contract: each role owns its specialist question, downstream roles consume accepted artifacts, and missing/stale/weak upstream work returns `revise`, `blocked`, or `waiting` instead of being silently redone by another role
 - closed selected team: hook/starter-prompt selected roles are binding for the current lane; research-only prompts do not add portfolio, risk, approval, or execution roles for precautionary coverage
 - negated scope routing: phrases such as "no valuation", "no order", and "no trading" remove those actions or roles from dispatch selection
+- broad public-equity prompts such as "Analyze NVDA" default to deep thesis
+  review with fundamental, technical, news, and valuation roles unless explicit
+  constraints narrow the team first
+- compact Decision Quality Spine flags in hook context for decision quality,
+  forecast contract, profile gate, anti-overfit, and deep thesis default
 - no full-history fixed-role spawn: fixed `agent_type` subagents receive compact assignment envelopes without full-history forking on the first attempt
 - subagent hook isolation: `UserPromptSubmit` auto-routing is ignored for fixed subagent contexts so subagent briefs cannot overwrite main-agent routing state or create recursive dispatch pressure
 - main-to-subagent briefs are assignment envelopes, not role manuals: they carry the current task, original request, explicit constraints, workflow consent posture, research artifact language, lane, artifact target, compact context summary, request-specific out-of-scope items, and return contract without repeating long method/source/guardrail checklists or pasting full artifacts
@@ -122,7 +127,9 @@ Generated workspaces contain:
 - fixed subagent `nickname_candidates` set to a single item matching the exact role `name`
 - fixed subagent identities kept in `.codex/agents/*.toml` `developer_instructions`, as required by Codex custom agent files
 - project-local additional agent instructions under `.tradingcodex/agent-instructions/<role>.md`; projection appends them after generated default instructions for `head-manager` and fixed subagents
-- nineteen core repo skills across project-scope mainagent skills and subagent skill directories, each with `SKILL.md` frontmatter for document metadata and `agents/openai.yaml` UI metadata
+- twenty-three core repo skills across project-scope mainagent skills and subagent skill directories, each with `SKILL.md` frontmatter for document metadata and `agents/openai.yaml` UI metadata
+- shared decision-quality skill bundles for forecasting discipline, thesis
+  scenario trees, numeric data QC, and anti-overfit validation
 - standalone `strategy-*` skills under `.agents/skills/strategy-*` for user-approved agent-readable investment strategies, created through `strategy-creator`, CLI, API, or service-layer flows and exposed to the root `head-manager` through the strategy marker block in `.codex/config.toml`; Django web lists and previews them read-only
 - file-native agent/skill projection: head-manager and strategy skills live under `.agents/skills/*`, role-owned subagent skills live under `.tradingcodex/subagents/skills/*`, and role TOML embeds the allowed role skill source list; state is expressed in `.codex/agents/*.toml`, `.codex/config.toml`, `.tradingcodex/mainagent/skill-change-proposals/*.yaml`, and `.tradingcodex/generated/*.json`, not Django skill DB tables
 - optional subagent skills are created, updated, activated, archived, deleted, and validated through the shared application service used by `head-manager`, CLI, API, and Django web
@@ -139,6 +146,7 @@ Generated workspaces contain:
 - generated indexes under `.tradingcodex/generated/`, including
   `module-lock.json`, `capability-index.json`, `component-index.json`,
   `agent-index.json`, `skill-index.json`, and `projection-manifest.json`
+- append-only forecast ledger directory at `trading/forecasts/`
 
 Workspace template modules are deployment projections. Harness component
 ownership comes from the Python component registry and is exported into

{tradingcodex-0.2.6 → tradingcodex-0.2.7}/docs/harness.md

@@ -50,6 +50,7 @@ TradingCodex Harness
 | Guardrails | Reduce, restrict, or block risky actions through guidance, enforcement, and information barriers. |
 | Improvement | Raise workflow quality through no-overlap handoff contracts, quality gates, artifact readiness, research memory, postmortems, and test feedback. |
 | Approved action boundary | Keep executable actions behind policy, approval, duplicate-request, connection, and audit checks. |
+| Decision packages | Keep investment ideas Codex-native by packaging workflow plans, artifact paths, profile gaps, blocked actions, and next allowed actions as workspace markdown. |
 | Provenance | Record which workspace and role produced or requested work without making workspaces separate ledgers. |
 | Profiles | Separate paper portfolio/account/strategy state from workspace identity. |
 | Components | Provide the developer-facing maintenance map for implementation surfaces, dependencies, capabilities, tags, and validation. |
@@ -112,6 +113,13 @@ It is a tag and review lens applied to components.
 Improvement does not authorize execution. A high-quality report still needs the
 guardrail path before any draft, approval, or non-live connection use.
 
+Decision Quality Spine is part of Improvement, not a new monolithic workflow.
+It adds shared expectations for intent normalization, scenario reasoning,
+forecast permission, numeric data QC, anti-overfit review, challenge review,
+readiness labels, and append-only forecast ledger records. The spine applies
+inside the selected lane and selected team only; it never widens role authority,
+MCP access, approval, execution, broker, or secret boundaries.
+
 ## Interface Implications
 
 The product web app should make the harness usable through a workflow-planner