TW-Market Live Data Intelligence

TW-Market Live Data Intelligence

English | 繁體中文

[Stable v1.5.0] [Windows 11 x64] [Python 3.13] [MCP six tools] [License MIT]

Local-first, governed Taiwan-market evidence infrastructure for human operators and AI agents — validate first, preview bounded work, then explicitly authorize one execution only when the current capability and route permit it.

Architecture at a glance

flowchart LR    H[Human / Operator] --> W[Unified Workbench]    A[AI Agent] --> M[Six-tool MCP]    W --> R[Unified Runtime]    M --> R    R --> V[Validate + Identity]    V --> P[Preview + Route Bounds]    P --> X[Explicit Authorization]    X --> E[Execute Once]    E --> S[Governed Official / Approved Sources]    S --> O[Result + Audit + AI Handoff]    L[Persistent Watchlists] --> W

Current stable release

TW-Market v1.5.0 is the current stable GitHub release. ProductVersion = 1.5.0. It was published on 2026-10-28 from frozen source commit acaf726a5b59baee4c5a30521ea5a5d5ec0cec76 and tree d44f66dc154c21326ac8b105d2f15fd793f6071b.

• GitHub Release v1.5.0
• Windows Native ZIP
• Native SHA-256 sidecar
• Windows MCPB
• MCPB SHA-256 sidecar
• First-party SBOM
• Publication manifest

The frozen v1.5.0 tag and SHA-256-verified release assets remain the release authority even if main later advances with post-release documentation or development work. GitHub Immutable Releases enforcement is not enabled for this release; the non-mutation requirement is a governance/freeze policy, not a platform lock.

Choose your path

For a 60-second orientation and first-run sequence, use the Operator Quick Start. The Native ZIP is the recommended operator path; source checkout is not the default installation path for every user.

What TW-Market is

TW-Market is a governed evidence and research workbench for Taiwan-market data. It gives a human operator or AI agent a deterministic path from target identity and capability validation to bounded source acquisition, canonical Result/Audit materialization, citations, and an AI-ready handoff.

It is intentionally not a broker, autonomous trader, portfolio system, general-purpose crawler, or realtime-price guarantee.

Core product characteristics:

• Local-first: installation state, Security Master, Watchlists, evidence, and audit artifacts remain under explicit local control.
• Identity-aware: Taiwan cash instruments use ISIN as durable identity and MARKET:CODE as listing/routing identity.
• Preview before execute: validation and preview do not authorize network acquisition; execution is explicit, bounded, and auditable.
• Persistent Watchlists are supported: installation-local Watchlists use immutable revisions, optimistic concurrency, and explicit preview/commit mutation.
• Evidence, not conclusions: source authority, timing/currentness, missingness, caveats, and citations remain visible to downstream humans and AI.

Governed workflow

A typical 2330 flow is:

1. Create or select an installation-local Watchlist and add 2330.
2. Compose a Unified Market Evidence Request and validate identity/capability.
3. Preview the exact planned operation and its route boundary.
4. Explicitly authorize one bounded execution only if the preview is executable.
5. Read the canonical Result and Audit Package, or export the AI-ready handoff.

Unified Request v3 is preferred. Request v1/v2 remain supported compatibility contracts; historical supported Result/Audit packages remain readable without rewriting their canonical bytes or provenance.

The Unified MCP surface remains exactly six governed tools:

market_describe_capabilities, market_validate_request, market_preview_request, market_read_result, market_export_ai_handoff, and market_fetch_evidence.

See the AI usage guide and V1 historical public contracts for the current request/result/handoff semantics and compatibility boundary.

Current evidence capabilities

Current governed product scope includes:

• installation-local Taiwan Market Identity Service and persistent Watchlists;
• official material-disclosure and monthly-revenue evidence for eligible TWSE/TPEx company common shares;
• selected bounded market-state, index-futures, institutional-flow, corporate-action, and recent-performance context where current Catalog and Routing authority make the requested market/target executable;
• canonical Result/Audit lineage, citations, timing/currentness semantics, and AI-ready Markdown handoff.

Capability support is not the same as route executability. A known instrument, schema, or capability does not by itself authorize source acquisition. Always validate and preview against the current Catalog and selected Routing.

Research evidence is intentionally bounded. It does not imply arbitrary history, realtime disclosures, a full-market scanner, financial_summary, investment advice, or trading signals.

Safety boundary

There is no automatic polling, scheduler, startup market fetch, Watchlist-driven automatic execution, trading, or order routing. There is also no silent source fallback or model-selected executor/URL. Missing evidence is not converted to zero, and execution success is not presented as a realtime guarantee.

Source/developer quick start

Use the primary source first-run sequence for dependencies, offline lifecycle initialization, Local Service, Workbench and MCP preflight. Initialization and Security Master activation are separate: identity-dependent operations fail closed while identity is unavailable, but health/UI/capability inspection can start after installation initialization. The source MCP stdio adapter requires the running loopback Local Service.

The release ZIP/MCPB installation paths are documented separately; keep those operator instructions distinct from this source/developer path.

MCP distribution and registry boundary

The current GitHub v1.5.0 release includes the supported Windows MCPB and its SHA-256 sidecar. It uses local stdio transport and exposes the same exact six governed tools as the source launcher.

The public MCP Registry entry io.github.SmartyJohnway/tw-market-live-data-intelligence is a separate publication surface. Its currently published package metadata remains on the historical v1.0.0 package until a separately authorized Registry update is performed. Do not infer Registry publication from the GitHub v1.5.0 release.

See MCP distribution for installation, integrity, and Security Master boundaries.

Docker is validated as a release/provenance surface for linux/amd64, but v1.5.0 does not publish a Docker registry image.

Documentation

Operator and product docs:

• Operator quick start
• Local Workbench guide
• Troubleshooting
• AI / agent usage guide
• AI discovery entry (llms.txt)
• Capability matrix
• Source matrix
• Documentation index

Engineering/governance front doors:

• PROJECT.md — current project/product authority
• ROADMAP.md — canonical Roadmap V3.2
• HANDOFF.md — current operational handoff
• AGENTS.md — repository and AI collaboration rules

Historical engineering and acceptance records remain available for audit and compatibility, but they are not a second current-product contract. Start with Project History or the Engineering history / protocol archive.

Release history and provenance

• v1.5.0 — current stable GitHub release; frozen source and final release assets passed the Phase L release-governance and publication acceptance chain.
• v1.0.0 — historical stable release and current MCP Registry package until a separately authorized Registry update occurs.
• v1.0.0-rc.1 — historical prerelease.
• v0.1.0 — earlier stable GitHub release.

The v1.5.0 publication includes the Native ZIP/checksum, MCPB/checksum, first-party SBOM, and typed publication manifest. SHA-256/provenance/SBOM are integrity and traceability controls; they are not cryptographic publisher signatures.

Contributing and security

Read CONTRIBUTING.md before opening a pull request. Report security concerns using SECURITY.md. Never commit credentials, tokens, cookies, or private market payloads.

License

See LICENSE.