tradingcodex 0.3.5__tar.gz → 1.0.0__tar.gz

tradingcodex-1.0.0/CHANGELOG.md

@@ -0,0 +1,161 @@
+# Changelog
+
+## Unreleased
+
+## 1.0.0 - 2026-07-15
+
+- Raise the validated Codex CLI reference to 0.144.4 while retaining the
+  proven 0.144.1 compatibility floor, explicitly enable
+  MultiAgent V2, replace the incompatible V1 `agents.max_threads` setting with
+  the V2 session-wide thread ceiling, add CLI version diagnostics, and add a
+  strict config/feature/MCP maintainer preflight. Native lifecycle acceptance
+  now requires persisted project-hook trust, because the one-run hook-trust
+  bypass is not inherited when a V2 child reloads an exact role config.
+- Add explicit development bootstrap shortcuts: source checkouts can run `tcx
+  attach/update --dev`, while the POSIX installer supports `--dev` and
+  `--dev --update` with the checkout bound as both package runner and declared
+  executable source. Generated workspaces continue to store only
+  `local-explicit`, never the private checkout path. Default development
+  bootstrap now isolates each checkout with its own runtime home, ledger, and
+  deterministic loopback service port; generated service commands honor that
+  address, and development update refuses to convert a release workspace in
+  place. Development commands import the live checkout through an editable
+  package-runner environment, while durable local runtimes are built from a
+  clean runtime-source snapshot that excludes stale build, distribution,
+  cache, bytecode, state, and database products.
+- Remove the web Work execution runner, preview/start/follow-up APIs, and
+  workbench-only hook mode; replace the product web with a read-only
+  Library/Skills/System viewer whose left rail selects only registered,
+  validated attached workspaces. Optimize half-width desktop windows with a
+  compact workspace selector and full-width list-to-detail transitions, keep
+  long status labels inside every supported viewport, move keyboard focus into
+  narrow Library/Skills details and back to their indexes, and restore
+  main-content focus after workspace switching.
+- Harden native workspace startup by keeping hook stdin/stdout in the launcher
+  process, using direct proxy-free loopback readiness checks with a native-host
+  response allowance, rejecting macOS ephemeral-port self-connections, and
+  retaining redacted detached-startup diagnostics while terminating timed-out
+  children instead of leaving orphans. Remove reverse-DNS lookup from the local
+  Django bind path, and validate these paths from the same clean wheel on macOS
+  and Windows.
+
+- Make `tcx doctor` concise by default: run only the selected layer plus global
+  service preflight, summarize layer totals, expand warnings and failures, and
+  retain full per-check evidence behind `--verbose`.
+- Strengthen point-in-time research guidance for filing/accession identity and
+  first-release or vintage macro data. Record all tried variants, effective
+  trial counts, frozen selection rules, and single-use holdout posture, while
+  keeping PBO, reality-check, and deflated-Sharpe diagnostics conditional on
+  supported assumptions and inputs.
+- Let exact fixed-role children read only their projected role-owned/shared
+  skill documents and Markdown references, including the read-only batched
+  `cat` form Codex naturally emits. Redirects, pipelines, substitutions,
+  executable compounds, other-role skills, configs, generated indexes, and
+  runtime state remain fail-closed.
+
+- Move all 31 bundled skills into the reserved compact `tcx-` namespace, with
+  one suffix word preferred and two allowed only for clarity. User-owned
+  `strategy-*`, `investment-brain-*`, and optional role skill namespaces stay
+  separate, and unchanged retired generated files migrate on `tcx update`.
+- Remove the `execution-operator` fixed role and retired
+  `execute-paper-order` skill from generated workspaces.
+- Add explicit-only root-native `tcx-order-submit` and
+  `tcx-order-cancel` action bundles. Their exact full-prompt grammar is
+  parsed by `UserPromptSubmit` and dispatched in-process to the canonical
+  service gateway as a workspace-bound `native-user` mandate before any model
+  runs.
+- Expand `tcx-automate` into the authoring path for all Codex app
+  Scheduled Tasks, including simple research, monitoring, recurring analysis,
+  portfolio/status review, draft orders, assisted execution, and optional
+  turn-authorized execution. Saved prompts run on every scheduled turn and
+  invoke the actual work skill rather than `tcx-automate` recursively.
+- Retire persistent Build mode. Only an exact root first line `$tcx-build`
+  creates a current-turn, workspace/session/turn-bound Build grant; Plan mode
+  is rejected and the marker never elevates Codex's native permission profile.
+  Generated workspaces default to `trading-research`, which permits general
+  shell/Python, credential-free public retrieval, and user-owned file changes
+  outside `trading/` while denying runtime/DB, credentials, protected control
+  files, local/private network targets, and direct durable TradingCodex writes.
+  Explicit `trading-build` turns open controlled `trading/` connector work with
+  network and sensitive state still denied; hook-owned proofs continue to gate
+  trusted lifecycle and canonical connector DB changes.
+- Give Strategy and Investment Brain management their own exact root markers,
+  `$tcx-strategy` and `$tcx-brain`, in the normal `trading-research` profile.
+  Their DB-canonical current-turn grants are capability-scoped and cannot cross
+  into Build, one another, Plan mode, subagents, orders, credentials, global
+  config, or publication. Codex-native source authoring and ordinary workspace
+  computation stay in the normal permission profile, while registry and
+  projection lifecycle uses the proof-protected `manage_strategy` and
+  `manage_investment_brain` MCP tools. Research no longer exposes the generated
+  CLI or attached runtime for those actions, and model-side lifecycle launcher
+  calls now return a precise MCP/user-terminal handoff. Reversible source and
+  draft creation no longer asks for redundant confirmation; activation and
+  destructive lifecycle actions remain explicit. General server, Investor Context, and
+  unsupported Decision Memory lifecycle commands now return explicit
+  user-terminal handoffs instead of attempting a blocked model shell.
+- Replace agent-side connector `connect`/write-style scaffold MCP operations
+  with read-only, content-addressed scaffold rendering plus native patching.
+  External MCP lifecycle/consent and provider-source approval remain
+  interactive operator actions protected by one-use service capabilities.
+- Add the explicit-only `tcx-order-allow` bundle and `OrderTurnGrant`: only a
+  physical first line `$tcx-order-allow --mode paper|validation|live` can admit one
+  later submit or cancel in that root turn. Grants bind workspace, session,
+  turn, full prompt hash, and mode; expire after one hour; and are revoked on
+  `Stop`, the next turn, or consumption.
+- Add Head Manager-only `use_order_turn_grant`. `PreToolUse` reserves the grant
+  and injects internal proof, so Workbench, subagents, direct MCP, REST, and CLI
+  callers gain no execution authority. The service still enforces canonical
+  ticket, receipt, policy, mode, live-confirmation, idempotency, adapter, audit,
+  reconciliation, and uncertainty gates; free-form prompt scope is not claimed
+  as deterministic policy.
+- Keep a consumed `authorizing` order effect immutable while its broker result
+  is in flight. Stop/new-turn cleanup never resets it, and the same session
+  blocks new Build/order-sensitive prompts until terminal while ordinary
+  research remains available.
+- Increase the bundled core skill count from 29 to 31 without adding an
+  execution subagent.
+- Remove final submit, cancel, and broker-status-refresh mutations from public
+  MCP, REST, generic CLI guidance, and Workbench while preserving the existing
+  policy, approval, live-confirmation, idempotency, adapter, audit,
+  reconciliation, and uncertain-result gates.
+- Reduce the fixed subagent roster to nine and keep Workbench preview, start,
+  and follow-up strictly analysis-only by rejecting reserved native action
+  tokens before launch.
+- Require the canonical TradingCodex MCP for Head Manager and every fixed role,
+  make Workbench apply an isolated canonical project-trust override, and fail
+  launch instead of silently continuing without service authority. Native
+  dispatch audit now records exact role/fork/task plus child-brief hash and
+  size, never the brief body.
+
+- Establish the first supported TradingCodex public contract across the CLI,
+  Django service, MCP gateway, React workbench, and generated workspaces.
+- Start from clean v1 workspace, runtime-home, database, migration, policy,
+  approval, audit, research, forecast, and execution boundaries.
+- Make Codex Head Manager the dynamic research orchestrator, with no semantic
+  hook router, server-generated DAG, default analyst team, or Django workflow
+  state machine. MultiAgent V2 projects Sol/xhigh for Head Manager and
+  Terra/high for analytical roles, with Terra/low for execution.
+- Add explicit, workspace-file-native Investment Brain plugins with strict
+  local/Git installation, immutable versions, Head Manager-only projection,
+  lazy sealed references, rollback, collision checks, and run provenance.
+- Add the user-owned `tcx-brain` source and managed-plugin lifecycle entrypoint
+  while keeping Strategy, Investor Context, Decision Memory, current evidence,
+  and Core safety as distinct authority layers.
+- Authenticate run-bound research artifacts and synthesis inputs with
+  service-issued receipts, external signing-key custody, source snapshots, and
+  exact Brain/Strategy/Context lineage.
+- Validate accepted run-bound artifacts against the strict quality contract
+  before receipt or stable publication, expose structured follow-up and
+  improvement MCP schemas, and exclude non-accepted handoffs from synthesis.
+- Enforce V2 spawn-field allowlists, source-snapshot knowledge cutoffs,
+  no-future artifact time bounds, and strict claim tagging for Head Manager
+  synthesis.
+- Initialize generated workspaces as local Git worktrees without staging,
+  commits, remotes, or publication, and require the private runtime home to
+  remain outside the versionable workspace.
+- Serve the committed React workbench through content-hashed deterministic
+  assets so package updates cannot leave a browser on a stale bundle.
+- Ship manual, tag-bound PyPI publishing with one verified wheel and source
+  distribution reused across Ubuntu, macOS, Windows, and publication jobs.
+- Support forward package, generated-workspace, and Django schema updates within
+  the v1 line while rejecting prerelease compatibility and downgrade paths.

{tradingcodex-0.3.5 → tradingcodex-1.0.0}/MANIFEST.in

@@ -1,13 +1,15 @@
 include LICENSE
 include NOTICE
 include CONTRIBUTING.md
+include CHANGELOG.md
 include TRADEMARKS.md
 include installation.md
 include install.sh
 recursive-include assets *
 recursive-include docs *
+recursive-include frontend *.css *.html *.json *.js *.ts *.tsx
 recursive-include workspace_templates *
 recursive-include workspace_templates .*
-recursive-include tradingcodex_service/templates *
 recursive-include tradingcodex_service/static *
+recursive-exclude frontend/node_modules *
 global-exclude *.py[cod]

tradingcodex-1.0.0/PKG-INFO

@@ -0,0 +1,196 @@
+Metadata-Version: 2.4
+Name: tradingcodex
+Version: 1.0.0
+Summary: Local-first investment operating system for Codex-native research and service-gated execution.
+Author: TradingCodex Authors
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/monarchjuno/tradingcodex
+Project-URL: Documentation, https://github.com/monarchjuno/tradingcodex/blob/main/docs/README.md
+Project-URL: Repository, https://github.com/monarchjuno/tradingcodex.git
+Project-URL: Issues, https://github.com/monarchjuno/tradingcodex/issues
+Keywords: trading,django,codex,mcp,portfolio,research
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Framework :: Django
+Classifier: Framework :: Django :: 5.2
+Classifier: Intended Audience :: Financial and Insurance Industry
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Office/Business :: Financial :: Investment
+Requires-Python: <3.15,>=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: django<5.3,>=5.2
+Requires-Dist: django-ninja<2,>=1.4
+Requires-Dist: markdown-it-py<5,>=3
+Requires-Dist: nh3<0.4,>=0.3
+Requires-Dist: packaging>=24
+Requires-Dist: pydantic>=2
+Requires-Dist: PyYAML>=6
+Requires-Dist: whitenoise<7,>=6.12
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == "dev"
+Dynamic: license-file
+
+# TradingCodex
+
+<div align="center">
+  <a href="https://pypi.org/project/tradingcodex/"><img alt="PyPI" src="https://img.shields.io/pypi/v/tradingcodex?label=PyPI"></a>
+  <a href="LICENSE"><img alt="License" src="https://img.shields.io/badge/license-Apache--2.0-blue"></a>
+  <img alt="Python" src="https://img.shields.io/badge/python-3.11--3.14-3776AB?logo=python&logoColor=white">
+  <img alt="Django" src="https://img.shields.io/badge/Django-5.2-092E20?logo=django&logoColor=white">
+</div>
+
+### Research in Codex, with a trail you can inspect.
+
+TradingCodex is a local-first investment operating system for Codex. Ask a
+question in natural language, let a bounded fixed-role team gather and challenge
+evidence, then keep the resulting research, source posture, uncertainty, and
+next steps in your own workspace.
+
+It is not an autonomous trading bot. A research response never becomes a
+broker action on its own.
+
+[Get started](https://monarchjuno.github.io/tradingcodex/) · [All user-facing skills](docs/user-facing-skills.md) · [Provider to order](https://monarchjuno.github.io/tradingcodex/provider-to-order.html) · [Documentation](docs/README.md)
+
+## Start Here
+
+1. **Attach an empty workspace.** TradingCodex creates the local contract,
+   launcher, skills, hooks, and research folders without creating a commit or
+   remote.
+2. **Open a new native Codex task.** Start with the outcome you need, not with
+   a preselected analyst or agent.
+3. **Inspect the evidence.** Read saved artifacts in the read-only workspace
+   viewer, then continue, narrow the question, or stop.
+
+You need Git, `uvx`, and an installed, authenticated `codex` CLI. In the empty
+folder where you want research to live, run:
+
+```bash
+cd /path/to/your/empty-workspace
+uvx --refresh --from tradingcodex tcx attach . && ./tcx doctor
+./tcx service ensure
+```
+
+On native Windows PowerShell:
+
+```powershell
+cd C:\path\to\your\empty-workspace
+uvx --refresh --from tradingcodex tcx attach .
+.\tcx.cmd doctor
+.\tcx.cmd service ensure
+```
+
+Then fully restart Codex, open and trust that workspace, and start a new task.
+The local viewer is available at `http://127.0.0.1:48267/`. End users do not
+need Node, npm, or a separate frontend server.
+
+> [!IMPORTANT]
+> To set up a user workspace, use `tcx attach` in the target folder. Do not
+> clone this source repository into that workspace.
+
+## Choose Your Path
+
+| What you want to do | Start with | What happens next |
+| --- | --- | --- |
+| Investigate a company, thesis, event, portfolio fit, or risk question | [`$tcx-workflow`](https://monarchjuno.github.io/tradingcodex/research.html) | Head Manager chooses the smallest useful fixed-role team and returns evidence-backed artifacts or a clear waiting, revise, or blocked state. |
+| Make an ambiguous request concrete | [`$tcx-plan`](https://monarchjuno.github.io/tradingcodex/skill-plan.html) | Clarify scope, allowed actions, and stop conditions; use the resulting mandate in a new workflow task. |
+| Review a past decision or validate a lesson | [`$tcx-memory`](https://monarchjuno.github.io/tradingcodex/skill-memory.html) | Replay from point-in-time evidence and distinguish decision quality from outcome quality. |
+| Create a reusable method or reasoning framework | [`$tcx-strategy`](https://monarchjuno.github.io/tradingcodex/skill-strategy.html) or [`$tcx-brain`](https://monarchjuno.github.io/tradingcodex/skill-brain.html) | Start directly with the matching skill in the normal Research profile; its current-turn scope cannot grant execution authority or cross into generic Build work. |
+| Monitor work on a schedule | [`$tcx-automate`](https://monarchjuno.github.io/tradingcodex/skill-automate.html) | Create or update a Codex Scheduled Task that invokes the actual work skill on each run. |
+| Open the dashboard or recover a workspace | [`$tcx-dashboard`](https://monarchjuno.github.io/tradingcodex/skill-dashboard.html) or [`$tcx-server`](https://monarchjuno.github.io/tradingcodex/skill-server.html) | Open the read-only viewer inside Codex by default, request an external browser when needed, or receive a readiness check and safe recovery handoff. |
+| Connect a provider and prepare an order | [Provider to order](https://monarchjuno.github.io/tradingcodex/provider-to-order.html) | Keep provider setup, account sync, ticket creation, checks, approval, and final action as separate checkpoints. |
+
+There are 13 user-facing skills. Browse their detailed behavior, examples, and
+boundaries in the [User Guide](https://monarchjuno.github.io/tradingcodex/skills.html).
+
+## Run Your First Research Task
+
+In a new native Codex task, use the workflow skill and state both your desired
+outcome and the boundaries that must remain in force:
+
+```text
+$tcx-workflow
+Analyze MSFT as a medium-term quality compounder. Separate facts, inferences,
+and assumptions. Include contrary evidence and invalidation conditions. No order.
+```
+
+The workflow begins a lightweight, workspace-bound run. Head Manager selects
+only the fixed-role specialists the question needs, reassesses from accepted
+artifacts, and either synthesizes the result or states why work is waiting,
+needs revision, or is blocked.
+
+## How TradingCodex Is Organized
+
+| Layer | What it does | What it does not do |
+| --- | --- | --- |
+| **Native Codex task** | Interprets the request, runs Head Manager, and dynamically dispatches exact fixed-role specialists. | It does not turn ordinary prose into an order or use a generic agent to imitate a specialist. |
+| **Workspace** | Holds readable research, reports, source snapshots, skills, prompts, and lightweight run provenance. | It is not the portfolio, order, account, approval, or secret ledger. |
+| **Django service** | Enforces artifact identity, policy, approval, broker, idempotency, execution, and audit rules through shared application services. | It does not replace Codex with a semantic router, preset team, or stored workflow DAG. |
+| **Read-only viewer** | Lets you browse Library artifacts, Skills, System posture, and registered workspaces. | It does not launch Codex, write workspace files, or mutate orders, brokers, skills, or policy. |
+
+```mermaid
+flowchart LR
+  question[Your mandate] --> codex[Native Codex task]
+  codex --> team[Head Manager and fixed-role evidence]
+  team --> artifacts[Authenticated research artifacts]
+  artifacts --> viewer[Read-only Library and System viewer]
+  artifacts --> service[Policy, approval, broker, and audit gates]
+```
+
+## What You Keep
+
+TradingCodex keeps the work inspectable after the chat ends:
+
+- Research handoffs and evidence under `trading/research/`.
+- Role reports under `trading/reports/`.
+- Source snapshots, point-in-time posture, forecasts, and decision-memory
+  artifacts that explain what was known and when.
+- A read-only viewer with **Library**, **Skills**, and **System** sections for
+  the attached workspace.
+
+The workspace is yours to read, back up, diff, and version. The service keeps
+execution-sensitive runtime state in its central local ledger instead of hiding
+that state in prompts or workspace files.
+
+## Safety by Design
+
+- Research, planning, memory, and automation do not imply broker authority.
+- Provider connection, ticket drafting, checks, risk approval, and final order
+  action are deliberately separate steps. The built-in provider is Paper; live
+  adapters remain blocked until every documented gate is satisfied.
+- Fixed roles have bounded tools and handoff responsibilities. A final order
+  path is available only from an exact root-native protocol, never from the
+  viewer, a subagent, public REST, generic CLI, or direct MCP call.
+- Raw credentials do not belong in prompts, workspace files, reports, API/MCP
+  output, or audit data.
+
+TradingCodex provides research workflow and execution guardrails. It is not
+financial, investment, legal, tax, or regulatory advice, and it does not
+guarantee returns.
+
+## Learn More
+
+| Read this | When you need |
+| --- | --- |
+| [User Guide](https://monarchjuno.github.io/tradingcodex/) | Setup, examples, concepts, all user-facing skills, and provider-to-order onboarding. |
+| [Installation](installation.md) | Install variants, updates, runtime homes, MCP/service startup, and recovery. |
+| [User-facing skills](docs/user-facing-skills.md) | The full skill map, entry rules, and hard stops. |
+| [Research memory and artifacts](docs/research-memory-and-artifacts.md) | Artifact paths, source posture, versions, quality labels, forecasts, and exports. |
+| [Decision memory](docs/decision-memory.md) | Replay, postmortems, lesson validation, and reusable context. |
+| [Safety policy and execution](docs/safety-policy-and-execution.md) | Permissions, approvals, brokers, secrets, and execution boundaries. |
+| [Documentation index](docs/README.md) | The complete product and maintainer documentation map. |
+
+## Developing TradingCodex
+
+This repository is product source, not a user workspace. Start with
+[CONTRIBUTING.md](CONTRIBUTING.md), then follow the validation route for your
+change in [docs/validation-and-test-plan.md](docs/validation-and-test-plan.md).
+
+## License
+
+TradingCodex is an Apache-2.0 open-core project. See [LICENSE](LICENSE),
+[NOTICE](NOTICE), and [TRADEMARKS.md](TRADEMARKS.md).

tradingcodex-1.0.0/README.md

@@ -0,0 +1,159 @@
+# TradingCodex
+
+<div align="center">
+  <a href="https://pypi.org/project/tradingcodex/"><img alt="PyPI" src="https://img.shields.io/pypi/v/tradingcodex?label=PyPI"></a>
+  <a href="LICENSE"><img alt="License" src="https://img.shields.io/badge/license-Apache--2.0-blue"></a>
+  <img alt="Python" src="https://img.shields.io/badge/python-3.11--3.14-3776AB?logo=python&logoColor=white">
+  <img alt="Django" src="https://img.shields.io/badge/Django-5.2-092E20?logo=django&logoColor=white">
+</div>
+
+### Research in Codex, with a trail you can inspect.
+
+TradingCodex is a local-first investment operating system for Codex. Ask a
+question in natural language, let a bounded fixed-role team gather and challenge
+evidence, then keep the resulting research, source posture, uncertainty, and
+next steps in your own workspace.
+
+It is not an autonomous trading bot. A research response never becomes a
+broker action on its own.
+
+[Get started](https://monarchjuno.github.io/tradingcodex/) · [All user-facing skills](docs/user-facing-skills.md) · [Provider to order](https://monarchjuno.github.io/tradingcodex/provider-to-order.html) · [Documentation](docs/README.md)
+
+## Start Here
+
+1. **Attach an empty workspace.** TradingCodex creates the local contract,
+   launcher, skills, hooks, and research folders without creating a commit or
+   remote.
+2. **Open a new native Codex task.** Start with the outcome you need, not with
+   a preselected analyst or agent.
+3. **Inspect the evidence.** Read saved artifacts in the read-only workspace
+   viewer, then continue, narrow the question, or stop.
+
+You need Git, `uvx`, and an installed, authenticated `codex` CLI. In the empty
+folder where you want research to live, run:
+
+```bash
+cd /path/to/your/empty-workspace
+uvx --refresh --from tradingcodex tcx attach . && ./tcx doctor
+./tcx service ensure
+```
+
+On native Windows PowerShell:
+
+```powershell
+cd C:\path\to\your\empty-workspace
+uvx --refresh --from tradingcodex tcx attach .
+.\tcx.cmd doctor
+.\tcx.cmd service ensure
+```
+
+Then fully restart Codex, open and trust that workspace, and start a new task.
+The local viewer is available at `http://127.0.0.1:48267/`. End users do not
+need Node, npm, or a separate frontend server.
+
+> [!IMPORTANT]
+> To set up a user workspace, use `tcx attach` in the target folder. Do not
+> clone this source repository into that workspace.
+
+## Choose Your Path
+
+| What you want to do | Start with | What happens next |
+| --- | --- | --- |
+| Investigate a company, thesis, event, portfolio fit, or risk question | [`$tcx-workflow`](https://monarchjuno.github.io/tradingcodex/research.html) | Head Manager chooses the smallest useful fixed-role team and returns evidence-backed artifacts or a clear waiting, revise, or blocked state. |
+| Make an ambiguous request concrete | [`$tcx-plan`](https://monarchjuno.github.io/tradingcodex/skill-plan.html) | Clarify scope, allowed actions, and stop conditions; use the resulting mandate in a new workflow task. |
+| Review a past decision or validate a lesson | [`$tcx-memory`](https://monarchjuno.github.io/tradingcodex/skill-memory.html) | Replay from point-in-time evidence and distinguish decision quality from outcome quality. |
+| Create a reusable method or reasoning framework | [`$tcx-strategy`](https://monarchjuno.github.io/tradingcodex/skill-strategy.html) or [`$tcx-brain`](https://monarchjuno.github.io/tradingcodex/skill-brain.html) | Start directly with the matching skill in the normal Research profile; its current-turn scope cannot grant execution authority or cross into generic Build work. |
+| Monitor work on a schedule | [`$tcx-automate`](https://monarchjuno.github.io/tradingcodex/skill-automate.html) | Create or update a Codex Scheduled Task that invokes the actual work skill on each run. |
+| Open the dashboard or recover a workspace | [`$tcx-dashboard`](https://monarchjuno.github.io/tradingcodex/skill-dashboard.html) or [`$tcx-server`](https://monarchjuno.github.io/tradingcodex/skill-server.html) | Open the read-only viewer inside Codex by default, request an external browser when needed, or receive a readiness check and safe recovery handoff. |
+| Connect a provider and prepare an order | [Provider to order](https://monarchjuno.github.io/tradingcodex/provider-to-order.html) | Keep provider setup, account sync, ticket creation, checks, approval, and final action as separate checkpoints. |
+
+There are 13 user-facing skills. Browse their detailed behavior, examples, and
+boundaries in the [User Guide](https://monarchjuno.github.io/tradingcodex/skills.html).
+
+## Run Your First Research Task
+
+In a new native Codex task, use the workflow skill and state both your desired
+outcome and the boundaries that must remain in force:
+
+```text
+$tcx-workflow
+Analyze MSFT as a medium-term quality compounder. Separate facts, inferences,
+and assumptions. Include contrary evidence and invalidation conditions. No order.
+```
+
+The workflow begins a lightweight, workspace-bound run. Head Manager selects
+only the fixed-role specialists the question needs, reassesses from accepted
+artifacts, and either synthesizes the result or states why work is waiting,
+needs revision, or is blocked.
+
+## How TradingCodex Is Organized
+
+| Layer | What it does | What it does not do |
+| --- | --- | --- |
+| **Native Codex task** | Interprets the request, runs Head Manager, and dynamically dispatches exact fixed-role specialists. | It does not turn ordinary prose into an order or use a generic agent to imitate a specialist. |
+| **Workspace** | Holds readable research, reports, source snapshots, skills, prompts, and lightweight run provenance. | It is not the portfolio, order, account, approval, or secret ledger. |
+| **Django service** | Enforces artifact identity, policy, approval, broker, idempotency, execution, and audit rules through shared application services. | It does not replace Codex with a semantic router, preset team, or stored workflow DAG. |
+| **Read-only viewer** | Lets you browse Library artifacts, Skills, System posture, and registered workspaces. | It does not launch Codex, write workspace files, or mutate orders, brokers, skills, or policy. |
+
+```mermaid
+flowchart LR
+  question[Your mandate] --> codex[Native Codex task]
+  codex --> team[Head Manager and fixed-role evidence]
+  team --> artifacts[Authenticated research artifacts]
+  artifacts --> viewer[Read-only Library and System viewer]
+  artifacts --> service[Policy, approval, broker, and audit gates]
+```
+
+## What You Keep
+
+TradingCodex keeps the work inspectable after the chat ends:
+
+- Research handoffs and evidence under `trading/research/`.
+- Role reports under `trading/reports/`.
+- Source snapshots, point-in-time posture, forecasts, and decision-memory
+  artifacts that explain what was known and when.
+- A read-only viewer with **Library**, **Skills**, and **System** sections for
+  the attached workspace.
+
+The workspace is yours to read, back up, diff, and version. The service keeps
+execution-sensitive runtime state in its central local ledger instead of hiding
+that state in prompts or workspace files.
+
+## Safety by Design
+
+- Research, planning, memory, and automation do not imply broker authority.
+- Provider connection, ticket drafting, checks, risk approval, and final order
+  action are deliberately separate steps. The built-in provider is Paper; live
+  adapters remain blocked until every documented gate is satisfied.
+- Fixed roles have bounded tools and handoff responsibilities. A final order
+  path is available only from an exact root-native protocol, never from the
+  viewer, a subagent, public REST, generic CLI, or direct MCP call.
+- Raw credentials do not belong in prompts, workspace files, reports, API/MCP
+  output, or audit data.
+
+TradingCodex provides research workflow and execution guardrails. It is not
+financial, investment, legal, tax, or regulatory advice, and it does not
+guarantee returns.
+
+## Learn More
+
+| Read this | When you need |
+| --- | --- |
+| [User Guide](https://monarchjuno.github.io/tradingcodex/) | Setup, examples, concepts, all user-facing skills, and provider-to-order onboarding. |
+| [Installation](installation.md) | Install variants, updates, runtime homes, MCP/service startup, and recovery. |
+| [User-facing skills](docs/user-facing-skills.md) | The full skill map, entry rules, and hard stops. |
+| [Research memory and artifacts](docs/research-memory-and-artifacts.md) | Artifact paths, source posture, versions, quality labels, forecasts, and exports. |
+| [Decision memory](docs/decision-memory.md) | Replay, postmortems, lesson validation, and reusable context. |
+| [Safety policy and execution](docs/safety-policy-and-execution.md) | Permissions, approvals, brokers, secrets, and execution boundaries. |
+| [Documentation index](docs/README.md) | The complete product and maintainer documentation map. |
+
+## Developing TradingCodex
+
+This repository is product source, not a user workspace. Start with
+[CONTRIBUTING.md](CONTRIBUTING.md), then follow the validation route for your
+change in [docs/validation-and-test-plan.md](docs/validation-and-test-plan.md).
+
+## License
+
+TradingCodex is an Apache-2.0 open-core project. See [LICENSE](LICENSE),
+[NOTICE](NOTICE), and [TRADEMARKS.md](TRADEMARKS.md).

tradingcodex-1.0.0/apps/audit/admin.py

@@ -0,0 +1,17 @@
+from django.contrib import admin
+
+from apps.audit.models import AuditEvent
+
+
+@admin.register(AuditEvent)
+class AuditEventAdmin(admin.ModelAdmin):
+    readonly_fields = tuple(field.name for field in AuditEvent._meta.fields)
+
+    def has_add_permission(self, request) -> bool:
+        return False
+
+    def has_change_permission(self, request, obj=None) -> bool:
+        return False
+
+    def has_delete_permission(self, request, obj=None) -> bool:
+        return False

tradingcodex-0.3.5/apps/audit/migrations/0001_initial.py → tradingcodex-1.0.0/apps/audit/migrations/0001_v1_initial.py

@@ -1,4 +1,4 @@
-# Generated by Django 5.2.5 on 2026-06-12 16:32
+# Generated by Django 5.2.5 on 2026-07-11 10:16
 
 from django.db import migrations, models
 

{tradingcodex-0.3.5 → tradingcodex-1.0.0}/apps/audit/models.py

@@ -1,4 +1,5 @@
 from django.db import models
+from django.core.exceptions import ValidationError
 
 
 class AuditEvent(models.Model):
@@ -20,3 +21,11 @@ class AuditEvent(models.Model):
 
     def __str__(self) -> str:
         return f"{self.created_at:%Y-%m-%d %H:%M:%S} {self.action}"
+
+    def save(self, *args, **kwargs) -> None:
+        if self.pk and type(self).objects.filter(pk=self.pk).exists():
+            raise ValidationError("audit events are append-only")
+        super().save(*args, **kwargs)
+
+    def delete(self, *args, **kwargs) -> None:
+        raise ValidationError("audit events are append-only")

tradingcodex-1.0.0/apps/harness/admin.py

@@ -0,0 +1,25 @@
+from django.contrib import admin
+
+from apps.harness.models import BuildTurnGrant, WorkspaceContext
+
+
+class ReadOnlyGrantAdmin(admin.ModelAdmin):
+    list_display = ("grant_id", "authority_scope", "status", "issued_at", "expires_at", "use_count")
+    list_filter = ("authority_scope", "status")
+    search_fields = ("grant_id", "workspace_id", "workspace_path_hash")
+
+    def get_readonly_fields(self, request, obj=None):
+        return tuple(field.name for field in self.model._meta.fields)
+
+    def has_add_permission(self, request) -> bool:
+        return False
+
+    def has_change_permission(self, request, obj=None) -> bool:
+        return False
+
+    def has_delete_permission(self, request, obj=None) -> bool:
+        return False
+
+
+admin.site.register(WorkspaceContext)
+admin.site.register(BuildTurnGrant, ReadOnlyGrantAdmin)