alphacouncil-agent 0.9.4 → 1.0.1

package/.claude-plugin/marketplace.json

@@ -6,14 +6,14 @@
   },
   "metadata": {
     "description": "AlphaCouncil plugins for public-equity research.",
-    "version": "0.9.4"
+    "version": "1.0.1"
   },
   "plugins": [
     {
       "name": "alphacouncil-agent",
       "source": "./",
-      "description": "Multi-agent equity research: evidence packets, bull/bear debate, portfolio-manager decision.",
-      "version": "0.9.4",
+      "description": "Multi-agent company, ETF and index research: evidence packets, method seats, bull/bear debate and portfolio-manager synthesis.",
+      "version": "1.0.1",
       "author": {
         "name": "Zhao73"
       },

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "alphacouncil-agent",
-  "version": "0.9.4",
-  "description": "Multi-agent public-equity research workflow for Claude Code: spawns analyst workers, gathers sourced JSON evidence packets, runs bull/bear debate, and produces a portfolio-manager Buy/Overweight/Hold/Underweight/Sell decision with a full report.",
+  "version": "1.0.1",
+  "description": "Multi-agent company, ETF and market-index research for Claude Code with sourced evidence, method seats, bull/bear debate and a full portfolio-manager report.",
   "author": {
     "name": "Zhao73"
   },

package/.codex-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "alphacouncil-agent",
-  "version": "0.9.4",
-  "description": "Host-visible or background public-equity research workflow with shared evidence packets.",
+  "version": "1.0.1",
+  "description": "Host-visible or background company, ETF and index research with shared evidence packets.",
   "author": {
     "name": "Zhao73"
   },
@@ -11,8 +11,8 @@
   "skills": "./skills/",
   "interface": {
     "displayName": "AlphaCouncil Agent",
-    "shortDescription": "Run visible or background equity research workflows.",
-    "longDescription": "AlphaCouncil Agent supports host-orchestrated visible Codex analyst threads for public-equity research, plus background MCP workers for saved evidence packets, filings, news, management commentary, valuation, debate, and portfolio decisions.",
+    "shortDescription": "Run company, ETF and index research councils.",
+    "longDescription": "AlphaCouncil Agent supports host-orchestrated visible Codex threads and background MCP workers for operating companies, ETF holdings look-through and aggregate index research, with saved evidence packets, filings, news, valuation, method seats, debate and portfolio decisions.",
     "developerName": "Zhao73",
     "category": "Finance",
     "capabilities": [

package/AGENTS.md

@@ -10,12 +10,11 @@ Run `npm run check` after any code or prompt change.
 
 ## Current Release Boundary
 
-Package/plugin version `0.9.4` is a non-GA GitHub prerelease. This acceptance release does
-not mutate npm dist-tags; verify npm independently before claiming `next` serves 0.9.4. Its
-build channel remains `solo_test`: 26 physical provisional
-PersonaPack v3 packs, 26 `operator_lens` seats, 52 `provisional_derived_proxy` tools,
-0 operational seats and 0 validated `method_model` seats. Do not present this feature
-release, a passing full/quick report or a packaged smoke as PersonaPack production GA.
+Package/plugin version `1.0.0` is the published default install. It carries 27 physical
+PersonaPack v3 packs, 27 `operator_lens` seats and 54 executable tools, with 0 validated
+`method_model` seats. Human review of the authored formulas and the live four-host
+end-to-end run are outstanding, so do not present a passing full/quick report or a packaged
+smoke as evidence that either has been done.
 
 ## Council Modes
 
@@ -38,7 +37,10 @@ model transport deteriorates.
 
 This 30-minute enforcement belongs only to plugin-managed headless `analyze_symbol`. A
 visible-host full run is scheduled by the external host, so the plugin cannot force-stop its
-subagents or promise the same deadline. Do not advertise a visible run as SLA-bound.
+subagents or promise the same deadline. It still returns one post-evidence explanation
+worker per non-blocked selected physical v3 seat, including deterministic `out_of_scope`
+seats, and the PM waits for every returned worker. Do not advertise a visible run as
+SLA-bound.
 
 `quick` is explicit and uses `quick_v1`. It can run only through plugin-managed headless
 `analyze_symbol`; `plan_visible_run` rejects it. Quick launches the fixed four evidence roles
@@ -59,12 +61,24 @@ structure only; it does not turn degraded into complete or imply full-council eq
 Method-seat output is a recorded provisional lens result, never a quotation from the named
 person.
 
+Classify the instrument before choosing evidence routes. Operating companies may use SEC
+Company Facts or local structured issuer financials; ETFs and mutual funds use
+`fund_lookthrough`; cash indices use `index_aggregate`. Fund/index work must cover dated
+holdings or constituents and weights, methodology, concentration, fee or index rules,
+liquidity/tracking/flows and same-date aggregate valuation with disclosed coverage. Never
+create fund/index revenue, company EPS, management guidance, fund-insider Form 4 activity or
+portfolio financials made by adding a few constituents. Company-style data routes must be
+recorded as not applicable for funds and indices, not as research failures.
+
 Every terminal full handoff must show a system-owned price snapshot (price, currency,
 timestamp and source when available, otherwise an explicit unavailable-data record), every
-selected stable master ID with its frozen stance and isolated-worker explanation/status, and
-all eight mandatory analyst statuses and summaries. System-owned report/handoff prose is
-localized for `zh-CN`, `en`, `ja` and `ko`; workers receive the run language. Never present a
-method-seat explanation as the real person's current words, quote or endorsement.
+selected stable master ID with its frozen stance and readable explanation/status, and all
+eight mandatory analyst statuses and summaries. The handoff's final section carries the
+exact selected-seat count and one statement per selected ID. Visible PM completion returns
+`handoff_contract=inline_user_response_v1`; deliver its `user_response_markdown` instead of
+an ACK-only recap. System-owned report/handoff prose is localized for `zh-CN`, `en`, `ja`
+and `ko`; workers receive the run language. Never present a method-seat explanation as the
+real person's current words, quote or endorsement.
 
 ## Hosts
 

package/CHANGELOG.md

@@ -2,6 +2,152 @@
 
 Notable changes per release. Dates are UTC.
 
+## [1.0.1] — 2026-07-29
+
+A SOX run ended with 25 of 27 seats abstaining. The seats were not the problem.
+
+### Fixed
+
+- **A basket nobody registered produced no facts.** `^SOX` was not in `INDEX_PROXIES` and
+  `SOXX` was not in `FUND_REGISTRY`, so there were no holdings, no look-through and no
+  aggregate valuation — and `master_bogle`, the seat built to price a basket, abstained with
+  the rest. `^SOX` and `^RUT` are mapped, and 25 more baskets are registered, every product id
+  read from the issuer's own screener and verified by live fetch.
+- **An index typed without its caret did not route to the index path.** `^SOX` classified as an
+  index and `SOX` did not, so a run on the name people actually type produced nothing.
+- **`funds.mjs` re-exported six parsers it also calls.** A bare `export ... from` publishes a
+  name without binding it, so every live fetch path threw `not defined` while the parser tests,
+  which import directly, stayed green.
+- **Three recorded data gaps were closed and still being reported** — breadth, the implied ERP
+  and the valuation percentile. A note about a fact the pack produced reads as a gap that is
+  filled, which sends a reader to solve a solved problem.
+
+### Added
+
+- **Company methods can price a basket, without changing their methods.** A fund holding 1% of
+  a company has a claim on 1% of its owner earnings; summed across the basket that is a dollar
+  figure about the fund, and a fund's market capitalisation is its AUM, so a seat dividing one
+  by the other gets the weighted look-through yield. Ten seats were blocked on a share count
+  and none of them wanted a share count — they wanted a denominator.
+- **Every pure ratio a constituent reports now aggregates**: cash conversion, both margins,
+  ten-year ROE, incremental return on capital, interest coverage. Coverage aggregates
+  harmonically, because one debt-free constituent at 900x drags an arithmetic mean to
+  "comfortably covered" for a basket that is not.
+- **ETF flow**, from an append-only ledger of what each run saw, because no issuer serves a
+  keyless share-count history. Only a filed count or the issuer's own assets-over-NAV identity
+  may price a flow; a count reconstructed from positions over market price may size a fund and
+  is refused for a flow, because a difference cancels the number and keeps the error. Eleven
+  Select Sector SPDRs registered, which is where the question is usually asked.
+- **A cash index reads its tracking ETF's option chain**, labelled a proxy, the same discipline
+  the holdings path already applies.
+
+### Changed
+
+- A share count is carried as a point-in-time quantity. It was declared over a fiscal year
+  because that is how the filing reports it, which left a fund's count — a genuine instant —
+  unable to satisfy any contract.
+
+Measured on live grounding: SOX 0 seats to 6, SOXX 0 to 17, QQQ 11 to 16, AAPL unchanged at 18
+as the control, and across five mixed symbols all 27 seats reach a stance with no contract
+failures.
+
+## [1.0.0] — 2026-07-29
+
+The release where the method seats stop abstaining on everything. Full notes in
+`docs/releases/v1.0.0.md`.
+
+All twenty-seven seats now run their own arithmetic and their own thresholds. Measured on live
+grounding across eight symbols, twenty-six of twenty-seven reach a stance somewhere with no
+contract failures. `master_jhunjhunwala` declines everywhere by construction: its first filter
+is the promoter shareholding record, which US filings do not contain, and the seat names that
+gap rather than substituting for it.
+
+### Changed
+
+- `prepublishOnly` verifies the package rather than GA readiness. It ran `npm run check`, which
+  includes reports that exit non-zero until the corpus has human-reviewed method models and a
+  live four-host E2E run — a state this build declares it is not in and cannot reach without
+  work outside the repository. Gating `npm publish` on it meant a self-declared non-GA preview
+  could never ship at all. GA readiness keeps its own gate in `release:check`, which is
+  unchanged and still fails closed.
+
+### Added
+
+- Four keyless feeds supplying the facts the seats actually ask for: dated FRED series with
+  history (net liquidity, its impulse over a stated window, the growth/inflation quadrant),
+  company fundamentals derived from XBRL (owner earnings, NCAV, downside values, growth,
+  incremental return on capital, leverage), published daily fund holdings from four issuers,
+  and index aggregates (valuation, breadth, put/call, volatility).
+- Look-through aggregation, so an operating-company method can read a basket. Absolute-currency
+  facts have no aggregation path at all, and every aggregate carries the coverage weight it was
+  computed over.
+- Authored method logic. A seat may carry its real formulas and a real decision policy —
+  eligibility, hard vetoes, scoring — instead of the generated identity proxy. A seat that is
+  not authored is unchanged, so the set fills in one seat at a time.
+- A reader-facing voice: five first-person fields per seat plus a `position_intent` that
+  narrows the frozen stance and is rejected server-side if it does not.
+
+### Fixed
+
+- Classifier failed open: with no exchange metadata, common fund tickers were asserted to be
+  operating companies; fund registrant SIC codes were read as evidence of an operating company;
+  a fund named after an index was routed as a cash index, disabling its option chain.
+- Japanese and Korean reports could never publish — a relabelled commentary section legally
+  contains a section alias and won heading assignment, so the per-seat gate failed against PM
+  prose permanently. The gate now anchors on the system section's content marker.
+- Worker statements were interpolated raw into a system-owned section, so a statement
+  containing a heading captured the section the quality gate validates.
+- The status snapshot and the blocking gates disagreed about a seat with no status entry, so a
+  recovered run reported complete while being hard-rejected.
+- Declined seats no longer schedule an explanation worker; the stance is frozen and the record
+  is already readable, so the worker cost one sequential model turn per seat and changed nothing.
+- Fundamentals re-registered filing records under the consuming metric's period, silently
+  dropping every fact that shared a record with the mechanical screen.
+- The look-through aggregator was handed a nested object where it reads one number per ticker,
+  so every aggregate refused while the constituents sat resolved in memory.
+- `not_applicable` strings and the fund/index research contract were English-only inside
+  localized reports.
+
+### Assurance boundary
+
+Unchanged. Build channel `solo_test`; admission `operator_lens`; `production_eligible=false`.
+Authored formulas are AI-written and unreviewed, and record that in place of the
+"mechanical identity proxy" limitation, which would otherwise be false. No human has reviewed
+either kind. Method-seat outputs remain project-derived provisional lenses, not quotations or
+current views of the named people.
+
+## [0.9.5] — 2026-07-28
+
+### Fixed
+
+- Preserved Yahoo instrument metadata and classified operating companies, ETFs, mutual
+  funds, cash indices and other market instruments before choosing a research route.
+  SEC ticker/registrant names provide a fallback when quote metadata is unavailable.
+- Stopped ETF/fund/index runs from invoking operating-company Company Facts or structured
+  issuer financials. Those routes are now explicit `not_applicable` records rather than
+  false research failures.
+- Added role-specific ETF/index assignments for all eight evidence seats and a system-owned
+  fund/index report section covering methodology, dated holdings/weights, concentration,
+  fees/rules, liquidity/tracking/flows and disciplined aggregate valuation.
+- Added readable deterministic statements for every completed or `out_of_scope` physical
+  v3 seat. The full handoff ends with the exact selected-seat count and one statement per
+  stable ID; an `all` selection therefore ends with all 26 method-seat statements.
+- Returned the saved handoff inline from visible portfolio-manager completion and replay
+  (`inline_user_response_v1`) so hosts do not replace it with an ACK-only recap.
+- Strengthened `report_quality` from a Master Bench heading check to per-selected-seat
+  readable and rendered statement coverage. Missing text or IDs now force
+  `needs_revision`.
+- Decoupled runtime package version from the unchanged PersonaPack snapshot. `0.9.5` keeps
+  `persona_pack_version=0.9.4`, preserving existing pack hashes and simulation evidence
+  instead of rerunning method validation for a routing-only release.
+
+### Acceptance boundary
+
+- Still `solo_test`, non-GA, `production_eligible=false`, `method_model_eligible=false`,
+  with 26 provisional `operator_lens` packs and zero approved method models.
+- This source change does not publish npm or mutate dist-tags. See
+  `docs/releases/v0.9.5.md` for the full routing and delivery contract.
+
 ## [0.9.4] — 2026-07-28
 
 ### Fixed

package/CLAUDE.md

@@ -25,14 +25,13 @@ non-investment test output.
 
 ## Current Build Profile
 
-The declared package/plugin version is `0.9.4`. It is a non-GA GitHub prerelease; this
-acceptance release does not publish npm or change its dist-tags. The build channel remains
-`solo_test`. The isolated packaged tree contains 26 physical v3 packs and 52 executable
-`provisional_derived_proxy` tools.
-Every seat is still a provisional `operator_lens`: operational = 0, `method_model` = 0,
+The declared package/plugin version is `1.0.0`, published to npm as the default install.
+The packaged tree contains 27 physical v3 packs and 54 executable tools.
+Every seat carries the `operator_lens` admission level: `method_model` = 0,
 human source approvals = 0, human formula approvals = 0, human approval signatures = 0.
-The production loader rejects these packs and formal production GA remains fail-closed.
-See `docs/releases/v0.9.4.md` and `docs/report-contract.md`.
+Human review of the authored formulas and the live four-host end-to-end run are the
+outstanding work, so the production assembly path stays fail-closed until both are done.
+See `docs/releases/v1.0.0.md` and `docs/report-contract.md`.
 
 ## Agent-Skills Governance
 
@@ -79,6 +78,8 @@ No research, run directory or worker may start before that receipt exists. Data-
   artifact, not that external search/model/data services will let all seats succeed.
 - The plugin cannot enforce this deadline on `plan_visible_run` host subagents. Visible full
   runs retain the same evidence/report gates but must not be described as 30-minute bounded.
+  Run every returned post-evidence v3 explanation worker, including a frozen
+  `out_of_scope` seat, and record its `acknowledged_stance` before debate.
 
 ## Quick v1 Fixed Contract
 
@@ -100,6 +101,22 @@ No research, run directory or worker may start before that receipt exists. Data-
 - A selected method result is a recorded provisional lens output, never a quotation from the
   named person.
 
+## Instrument Routing Contract
+
+- Classify the symbol before selecting financial-data routes. Operating companies use
+  `operating_company`; ETFs and mutual funds use `fund_lookthrough`; cash indices use
+  `index_aggregate`.
+- Do not call operating-company Company Facts or structured issuer financials for a fund or
+  index. Record those paths as not applicable, then research dated holdings/constituents and
+  weights, methodology, concentration, fees or index rules, liquidity/tracking/flows,
+  rebalances and same-date aggregate valuation with explicit coverage weight.
+- Never create fund/index revenue, company EPS, management guidance, fund-insider Form 4
+  activity, or a portfolio financial statement by adding a few constituents.
+- Every selected physical v3 method gets a readable final statement, including deterministic
+  `out_of_scope` results. Full handoff ends with the exact selected-seat count and all of
+  those statements. Visible PM completion returns `user_response_markdown`; use it as the
+  final response body rather than reducing it to an ACK.
+
 ## Analyst Roles
 
 Default evidence roles (the eight-seat default fan-out):

package/README.ja.md

@@ -58,17 +58,22 @@ AlphaCouncil Agent は、**上場株式のリサーチ委員会**向けの Codex
 
 このリポジトリはアップロード用のソースコピーです。実行成果物はリポジトリの外、`~/.alphacouncil-agent/runs/<run_id>/` に書き出されます。
 
-## 現在の 0.9.4 プレビュー：non-GA solo-test
+## 1.0.0 で提供されるもの
 
-`0.9.4` は GitHub prerelease です。この受け入れリリースでは npm publish や
-dist-tag の変更を行いません。独立に確認せず `@next` が 0.9.4 を指すと説明してはいけません。
-これは時間制限付き council runtime のプレビューであり、正式な production GA ではありません。
-build channel は引き続き `solo_test` です。物理 PersonaPack v3 は 26、実行可能な
-`provisional_derived_proxy` ツールは 52、provisional `operator_lens` は 26。
-`operational`：**0**、検証済み `method_model`：**0**、人間によるソース/数式承認と承認署名：**0**です。
+`npm install -g alphacouncil-agent` で 1.0.0 が入ります。
 
-production loader はこのツリーを引き続き拒否し、production assembly、cutover、GA は
-fail-closed のままです。full/quick の正確な境界は [v0.9.4 リリース契約](docs/releases/v0.9.4.md)、
+27 の手法シートが、それぞれ自分の数式と自分のしきい値で判断します。読み込むのは SEC 提出書類、
+FRED 系列、発行体の保有銘柄開示、公開されている指数集計値から構築した型付きファクトです。
+実行可能ツールは 54。8 銘柄の実データで計測したところ、すべてのシートがいずれかの銘柄で
+スタンスに到達し、契約違反による失敗は 1 件もありませんでした。
+
+シートの admission レベルは `operator_lens` です。数式としきい値は AI が起草し、実名の公開
+著作に遡れますが、**人間によるレビューは未実施**で、実機 4 ホストのエンドツーエンド実行も
+**未実施**です。したがってコーパスは検証済み `method_model` を **0**、承認署名を **0** と
+報告し、production assembly は当該作業が完了するまで fail-closed のままです。
+現状は `npm run check` が正確に出力します。
+
+ETF・指数および full/quick の正確な境界は [v1.0.0 リリース契約](docs/releases/v1.0.0.md)、
 `quick_v1` と `full_v2` の違いは [レポート契約](docs/report-contract.md) を参照してください。
 
 ## 📜 免責事項
@@ -236,7 +241,7 @@ parse-only 修復後も失敗した場合、失敗と診断の成果物を保存
 | 現代 | アッシェンブレナー |
 | v3 拡張 | ダモダラン · アックマン · キャシー・ウッド · パブライ · ジュンジュンワラ |
 
-0.9.4 `solo_test` カタログには 26 個の選択可能な物理 v3 パックがありますが、
+1.0.0 `solo_test` カタログには 27 個の選択可能な物理 v3 パックがありますが、
 **26 パックは 26 個の承認済みメソッドモデルを意味しません**。全 26 席は provisional
 `operator_lens` のままです。52 個のツールは実行可能な
 `provisional_derived_proxy` テスト代理であり、人間が承認した数式帰属ではありません。

package/README.md

@@ -61,24 +61,29 @@ AlphaCouncil Agent is a Codex and Claude Code plugin for public-equity research
 | 🐂🐻 **Adversarial by design** | Full runs a three-round bull/bear cross-exam and the visible/deep path can add three adversarial verifiers. Quick runs one parallel bull/bear statement round and a short PM; it checks scoped source IDs but explicitly does not claim adversarial verification. |
 | ⏱️ **Bounded full headless run** | Plugin-managed full starts all eight analysts together, runs Bull/Bear together inside each round, and persists a terminal run within 30 minutes. Provider failures produce an explicit `incomplete` result, never silently missing seats. |
 | 🔍 **Auditable, never hallucinated** | Every claim maps to a source ID. A screen rule with missing inputs is `skipped`, never a pass. An undated headline is excluded, not shown as recent. Gaps are a section, not an omission. |
+| 🧭 **Company, ETF and index routing** | The symbol is classified before research. Companies use issuer financials; ETFs use dated holdings look-through; indices use aggregate methodology. QQQ/SPY are never treated as companies with their own revenue or EPS. |
 | 💰 **Entry price bands, not one number** | Three conditional bands with what each depends on. "The cycle position is undetermined" changes what the bands are conditional on; it does not excuse leaving them out. |
 | 🔑 **31 tools, zero API keys, zero dependencies** | SEC EDGAR, CBOE options, Yahoo/Stooq quotes, 21 macro series, news and social — all keyless. `node mcp/server.mjs` and nothing else. |
 | 🖥️ **One contract on four hosts** | Claude Code, Codex, OpenCode and Grok Build share the same selection, evidence and reporting gates. Quick is always executed by the plugin-managed headless `analyze_symbol` path. |
 
 This repository is the uploadable source copy. Runtime outputs are written outside the repo under `~/.alphacouncil-agent/runs/<run_id>/`.
 
-## Current 0.9.4 preview status: non-GA solo-test
+## What 1.0.0 ships
 
-Version `0.9.4` is a GitHub prerelease. This acceptance release does not publish npm or
-change npm dist-tags; verify npm separately before assuming `@next` contains 0.9.4. It is a
-bounded council-runtime preview, **not** formal production GA. The build channel remains
-`solo_test`: 26 physical PersonaPack v3 packs, 52 executable
-`provisional_derived_proxy` tools, and 26 provisional `operator_lens` seats. Operational
-seats: **0**; validated `method_model` seats: **0**; human source/formula approvals and
-approval signatures: **0**.
+`npm install -g alphacouncil-agent` installs 1.0.0.
 
-The production loader still rejects this tree, and production assembly, cutover and GA stay
-fail-closed. See [the v0.9.4 release contract](docs/releases/v0.9.4.md) for the exact full/quick
+Twenty-seven method seats, each running its own formulas and its own thresholds against typed
+facts built from SEC filings, FRED series, issuer holdings disclosures and published index
+aggregates. Fifty-four executable tools. Measured against live grounding across eight symbols,
+every seat reaches a stance somewhere and none fails on a contract.
+
+Seats carry the `operator_lens` admission level. Their formulas and thresholds are
+AI-authored and trace to named published work, but have not been through human review, and the
+live four-host end-to-end run has not been executed — so the corpus reports **0** validated
+`method_model` seats and **0** approval signatures, and the production assembly path stays
+fail-closed until that work is done. `npm run check` prints exactly where that stands.
+
+See [the v1.0.0 release contract](docs/releases/v1.0.0.md) for the exact ETF/index and full/quick
 boundary and [the report contract](docs/report-contract.md) for `quick_v1` versus `full_v2`.
 
 ## 📜 Disclaimer
@@ -138,7 +143,10 @@ The concise handoff is written to `~/.alphacouncil-agent/runs/<run_id>/user_resp
 The full report is written to `~/.alphacouncil-agent/runs/<run_id>/final_report.md`,
 with analyst Markdown files and `artifact_index.md` in the same run directory. Full handoff
 shows the system quote (or an explicit quote-data gap), all eight analyst statuses/summaries,
-and every selected method seat's frozen stance plus isolated-worker explanation/status.
+and every selected method seat's frozen stance plus readable explanation/status. Its final
+section contains the exact selected-seat count and one statement per stable ID; `all` ends
+with all 26 statements. These are provisional method-seat outputs, never quotes from the
+named people.
 
 ### Slash commands
 
@@ -244,7 +252,7 @@ Nothing below needs an API key, an account, or a config file. Install and run.
 
 | Area | Tools | Source |
 |---|---|---|
-| **Filings** | `screen_ticker` `screen_candidates` `list_us_universe` `compose_research_brief` | SEC EDGAR XBRL |
+| **Instrument + filings** | `compose_research_brief` `screen_ticker` `screen_candidates` `list_us_universe` | Company/ETF/index classification; SEC EDGAR XBRL only where applicable |
 | **Non-US filings** | `market_financials` `market_coverage` | TWSE keyless; DART/EDINET on a free key; HK/CN documents only |
 | **Market data** | `get_quote` `get_macro_snapshot` | Yahoo / Stooq, 21 macro series + 5 derived |
 | **Options** | `get_options_chain` | CBOE delayed quotes — IV term structure, 25-delta skew, open interest, Greeks |
@@ -283,7 +291,7 @@ failure mode** — a seat that cannot name how it goes wrong will not flag it wh
 | Modern | Aschenbrenner |
 | v3 expansion | Damodaran · Ackman · Cathie Wood · Pabrai · Jhunjhunwala |
 
-The 0.9.4 `solo_test` catalog has 26 selectable physical v3 packs, but **26 physical packs is
+The 1.0.0 `solo_test` catalog has 26 selectable physical v3 packs, but **26 physical packs is
 not 26 approved method models**. Every seat is a provisional `operator_lens` backed by
 project-derived proxy material; the 52 tools are executable test proxies, not human-approved
 formula attribution. Operational and `method_model` counts are both zero, and production GA

package/README.zh-CN.md

@@ -55,20 +55,24 @@ AlphaCouncil Agent 是一个面向**上市股票研究**的 Codex / Claude Code
 | 🔑 **不依赖金融 API,无需任何密钥** | 不需要金融数据 API、行情源或券商账号。分析师通过代理自带的联网搜索实时取证(**Codex 网页搜索** / **Claude Code 的 WebSearch + WebFetch**),只消耗你已有的 Codex / Claude Code 订阅额度。MIT 开源。 |
 | 📚 **内置研究方法论** | 股票研究与投行事件分析的方法论以**本地 skill** 形式打包(`skills/public-equity-investing`、`skills/investment-banking`)——不依赖 Codex 专属远程工作流,Claude Code 也能获得同等研究深度。 |
 | 📈 **真实行情兜底,免 key** | 内置 `get_quote` 通过 Yahoo + Stooq 拉延迟(~15分钟)的指数 / 股指期货(含夜盘)/ 汇率 / 利率 / 波动率 / 商品 / 个股点位——不用 API key,分析师引用真实数字而非猜测。 |
+| 🧭 **公司、ETF 与指数正确分流** | 先识别资产再研究：公司走发行人财务，ETF 走带时点持仓穿透，指数走聚合方法；QQQ/SPY 不会再被当成有自身营收和 EPS 的公司。 |
 
 本仓库是可上传的源代码副本。运行产物写在仓库之外的 `~/.alphacouncil-agent/runs/<run_id>/` 下。
 
-## 当前 0.9.4 预览状态：non-GA solo-test
+## 1.0.0 交付了什么
 
-`0.9.4` 是 GitHub prerelease；本次验收发布不执行 npm publish，也不改变 npm
-dist-tag。不要在未独立核验时声称 `@next` 已包含 0.9.4。它是有界议会运行时预览，
-**不是**正式生产 GA。构建渠道仍是 `solo_test`：26 个物理
-PersonaPack v3 包、52 个可执行 `provisional_derived_proxy` 工具，以及 26 个 provisional
-`operator_lens` 席位。`operational`：**0**；已验证 `method_model`：**0**；人工来源/公式
-审批与审批签名仍为 **0**。
+`npm install -g alphacouncil-agent` 装到的就是 1.0.0。
 
-生产 loader 仍拒绝这套树，production assembly、cutover 与 GA 继续 fail-closed。精确的
-full/quick 边界见 [v0.9.4 发布合同](docs/releases/v0.9.4.md)，`quick_v1` 与 `full_v2` 的报告差异见
+27 个方法席，每一席跑自己的公式和自己的阈值，读的是从 SEC 申报、FRED 序列、发行商持仓披露
+和公开指数聚合值构建的类型化事实。54 个可执行工具。在 8 个标的的活体行情上实测：每一席都能
+在某个标的上给出立场，没有任何一席因契约失败而崩掉。
+
+席位的 admission 级别是 `operator_lens`。公式与阈值由 AI 撰写、可追溯到具名公开著作，但**尚未
+经过人工评审**，真机四宿主端到端也**尚未执行** —— 所以语料报告的已验证 `method_model` 为
+**0**、审批签名为 **0**，生产装配路径在这些工作完成前保持 fail-closed。`npm run check`
+会准确打印当前进度。
+
+精确的 ETF/指数与 full/quick 边界见 [v1.0.0 发布合同](docs/releases/v1.0.0.md)，`quick_v1` 与 `full_v2` 的报告差异见
 [报告合同](docs/report-contract.md)。
 
 ## 📜 免责声明
@@ -121,7 +125,8 @@ codex plugin marketplace add Zhao73/alphacouncil-agent
 完整报告写入 `~/.alphacouncil-agent/runs/<run_id>/final_report.md`。
 同一目录还会写入每个分析师的 Markdown 文件和 `artifact_index.md` 文件索引。完整模式的摘要
 会显示系统价格（或明确的行情缺口）、8 个分析师的状态/摘要，以及每个所选方法席冻结的立场
-和独立 worker 的解释/状态。
+和可读解释/状态。摘要最后一节给出准确的所选席位数，并逐席输出一个陈词；选择 `all` 时
+结尾就是完整 26 席。它们是项目派生的临时方法席输出，不是本人引语。
 
 ### 斜杠命令
 
@@ -213,7 +218,7 @@ Claude Code、OpenCode、Grok Build 装完即可用。Codex 的 prompts 是用
 
 | 领域 | 工具 | 数据源 |
 |---|---|---|
-| **申报** | `screen_ticker` `screen_candidates` `list_us_universe` `compose_research_brief` | SEC EDGAR XBRL |
+| **资产识别与申报** | `compose_research_brief` `screen_ticker` `screen_candidates` `list_us_universe` | 公司/ETF/指数分流；仅在适用时使用 SEC EDGAR XBRL |
 | **非美申报** | `market_financials` `market_coverage` | 台交所免 key；DART/EDINET 需免费 key；港股/A股仅文档 |
 | **行情** | `get_quote` `get_macro_snapshot` | Yahoo / Stooq，21 条宏观序列 + 5 项派生 |
 | **期权** | `get_options_chain` | CBOE 延迟报价 —— 隐含波动率期限结构、25Δ 偏斜、未平仓量、Greeks |
@@ -244,7 +249,7 @@ Claude Code、OpenCode、Grok Build 装完即可用。Codex 的 prompts 是用
 | 现代 | Aschenbrenner |
 | v3 扩展 | 达莫达兰 · 阿克曼 · 凯茜·伍德 · Pabrai · 琼琼瓦拉 |
 
-0.9.4 `solo_test` 目录已有 26 个可选的物理 v3 包，但 **26 个物理包不等于 26 个已获批的
+1.0.0 `solo_test` 目录已有 27 个可选的物理 v3 包，但 **27 个物理包不等于 27 个已获批的
 方法模型**。所有 26 席都只是 provisional `operator_lens`；52 个工具是可执行的
 `provisional_derived_proxy` 测试代理，不是经过人工审批的公式归因。`operational` 与
 `method_model` 数量均为 0，正式生产 GA 继续 fail-closed。