Cache OCR-negative bubbles

Fix OCR thread test isolation
Limit OCR runtime threads
2026-10-16 11:38:03 +08:00 · 2026-10-16 11:19:55 +08:00 · 2026-10-16 11:16:23 +08:00 · 2026-10-16 11:03:32 +08:00 · 2026-10-16 01:07:07 +08:00 · 2026-10-15 19:00:29 +08:00
126 changed files with 15173 additions and 91 deletions
@@ -67,6 +67,7 @@ id_ed25519*

 # Sensitive local notes
 homeserver-apikey-*.md
+debug-*.md

 # macOS/editor
 .DS_Store
@@ -4,9 +4,11 @@ These rules are mandatory for every automated change in this repository.

 ## Versioning

- Use `alpha X.Y.Z.MMDD`.
+- Use `beta X.Y.Z.MMDD` for current beta releases.
+- Python package versions use PEP 440 pre-release form, for example
+  `X.Y.Zb1+MMDD`.
 - Small changes increment only `Z`.
- Do not move to a new minor version without explicit user approval.
+- Do not move to a new minor or stable version without explicit user approval.
 - Keep `VERSION`, root `pyproject.toml`, package versions, package
  `__version__`, `README.md`, and `CHANGELOG.md` synchronized.

@@ -1,5 +1,213 @@
 # Changelog

+## beta 1.0.2.1016 - 2026-10-16
+
+- Cache OCR-negative visible bubbles and reuse stable visual signatures as the
+  OCR cache key so unreadable or lightly re-rendered bubbles do not trigger
+  repeated 10+ second RapidOCR passes during active chat windows.
+
+## beta 1.0.1.1016 - 2026-10-16
+
+- Limit RapidOCR ONNXRuntime intra/inter operation threads by default so the
+  adaptive OCR recorder no longer saturates CPU after restart and slow recovery
+  windows do not stretch local command detection into 10+ second scans.
+
+## beta 1.0.0.1016 - 2026-10-16
+
+- Promote JWeBot from alpha to beta after the local, staging, privacy, and
+  production deployment gates stabilized.
+- Consolidate the current reviewed local command set, including virtual coin
+  transfer, loans, repayment, group leaderboard, multiplayer lottery,
+  blackjack, Steam queries, and CS Major autochess.
+- Externalize CS Major autochess game content into package JSON data files for
+  cards, coaches, narratives, draft/shop/economy rules, match formats, and
+  MR15/overtime settings.
+- Add a maintained command catalog and keep debug session notes out of the
+  repository by default.
+- Keep release validation on `tools/sync-local-extensions.py --check`,
+  `tools/check-local.sh`, and `tools/check-secrets.py --history`.
+
+## alpha 0.6.11.1015
+
+- Add `/大富翁榜`, `/金币排行`, `/金币排行榜`, and `/richlist` for a
+  group-scoped virtual coin leaderboard. Rankings are read-only, sorted by
+  current coin balance, recover display names from configured aliases and
+  observed profiles, and mark active loan principal when present.
+- Split leaderboard command ownership into a dedicated reviewed
+  `coin-ranking` local extension.
+
+## alpha 0.6.10.1015
+
+- Add virtual coin loans with `/贷款 [金额]` and `/loan amount`, plus
+  repayments through `/还款 [金额|全部]` and `/repay`. Loans are stored in
+  the same group-scoped virtual coin account, capped at 500 coins, limited to
+  one active loan per account, and replay-safe through the existing ledger
+  transaction path.
+- Split loan command ownership into a dedicated reviewed `coin-loan` local
+  extension so the single-player game plugin stays under the command-count
+  validation limit.
+
+## alpha 0.6.9.1015
+
+- Move CS Major autochess public game data out of `cs_autochess.py` and into
+  package data files under `jwebot_official_extensions/data/cs_autochess/`.
+  Player cards, coach cards, narrative fragments, shop/economy odds, draft
+  pacing, synergy thresholds, match formats, MR15/overtime settings, and
+  special event rewards are now data driven.
+- Add startup validation for the externalized data so missing fields,
+  duplicate card IDs, invalid schema versions, or an undersized narrative
+  library fail fast before the command engine runs.
+- Add regression coverage that verifies the JSON files are packaged, readable,
+  and consistent with the runtime card, coach, match-format, and narrative
+  inventories.
+- Add virtual coin transfers with `/转账 对方 金额` and `/transfer name amount`.
+  Transfers are single-transaction ledger updates, require the receiver to
+  initialize `/金币` first, reject self-transfers, and replay safely by event ID.
+
+## alpha 0.6.8.1015
+
+- Add an atomic compatibility path for old active CS autochess runs. When a
+  group still has a pre-schema-3 active tournament, `/自走棋开始` now archives
+  that old run as cancelled and opens a fresh schema-3 season in the same
+  SQLite transaction.
+- Preserve old story and battle archive rows while ensuring the new season is
+  the only active autochess run selected by future commands.
+
+## alpha 0.6.7.1015
+
+- Expand CS Major autochess content to 100+ player cards and an 18-coach
+  metadata pool while keeping the opening coach draft to 10 visible choices.
+- Replace abstract training targets with real round-robin training rounds.
+  Each round resolves participant-vs-participant or participant-vs-AI BO1
+  scrims, then opens an operation window for D rolling, locking, lineup swaps,
+  tactics, and readiness.
+- Replace fixed score bands with deterministic MR15 round simulation. Map
+  scores now come from individual round outcomes, including 15-15 overtime,
+  instead of direct mappings such as 16-6 or 16-9.
+- Add a 120+ line local narrative library for openings, streaks, pauses,
+  clutches, economy beats, closes, training hooks, and media/sponsor
+  challenges so match reports vary across maps.
+- Hide raw target/performance calculation text from training, match, and
+  challenge reports while preserving structured battle facts in the archive.
+- Start drafted players as two-star素材 and rebalance roster completion toward
+  low/mid-cost cards, leaving upgrades and synergies to the shop loop.
+
+## alpha 0.6.6.1015
+
+- Rebuild CS Major autochess around multi-message hosting: tournament
+  welcomes, seed order, draft boards, status panels, training results, match
+  reports, standings, brackets, and awards are emitted as separate bounded
+  replies.
+- Replace instant full rosters with three draft rounds: round one selects from
+  a fixed 10-coach pool, rounds two and three draft players, then each team is
+  completed to five starters, one coach, and three bench slots.
+- Run the full event as training camp, BO3 single-round-robin group stage,
+  one media/sponsor challenge after group round one or two, BO5 semifinals,
+  BO5 final, and final awards.
+- Let readiness advance phases automatically. Group matches wait for all real
+  players, while knockout matches only wait for real players still in the
+  current pairing, so eliminated players are not prompted to prepare.
+- Add local multi-text reply support across the SDK, official extension
+  adapter, Edge response contract, and recorder GUI sender while preserving
+  single-message compatibility.
+
+## alpha 0.6.5.1015
+
+- Extend the AI test path for CS Major autochess to support two-human games:
+  `/自走棋加AI战队` now adds AI 战队 A and AI 战队 B when exactly two
+  real players have registered.
+- Keep the same command for two- and three-human test modes. The tournament
+  engine selects 2 人+2 AI or 3 人+1 AI from the current registration count.
+- Lock the roster after AI teams join, seed the four-team bracket as 1v4 and
+  2v3, and keep AI teams out of the human preparation order while preserving
+  independent AI operations and story archives.
+
+## alpha 0.6.4.1015
+
+- Add a reviewed 2-8 player CS Major autochess extension with a fixed
+  five-player starting lineup, one always-active coach, an eight-slot bench,
+  and a six-candidate shop that shows complete game data.
+- Ship a fixed 60-player local pool with rifle, sniper, and in-game-leader
+  roles; team and nation synergies; shared copy counts; and deterministic
+  three-copy/two-star and nine-copy/three-star upgrades.
+- Keep all five player slots occupied. Lineup changes are one-for-one swaps,
+  starters cannot be sold directly, and coach upgrades only add a 2%-10%
+  team bonus.
+- Add player-selected firepower, stability, and clutch tactics. Resolve
+  stability over firepower, firepower over clutch, clutch over stability,
+  plus sniper/rifle/leader role counters before bounded +/-2% map variance.
+- Generate the competition format once at tournament start: two players go
+  directly to the final, three play a round robin for two final places, four
+  use seeded 1v4 and 2v3 semifinals, and five to eight play a complete round
+  robin for four semifinal places.
+- Add an explicit three-human-plus-one-AI test mode. The host can add one
+  deterministic local AI as seed four; it buys players, upgrades its coach,
+  swaps its strongest lineup, and selects a counter tactic without an online
+  model.
+- Give the bot a persistent host state machine: welcome and format briefing,
+  rotating human preparation order, turn enforcement, explicit handoffs,
+  round introductions, matchup calls, overtime narration, advancement, and
+  championship presentation.
+- Run group matches as BO3 and knockout matches as BO5. Simulate every map
+  under MR15, including 15-15 overtime, 19-17/22-20 scores, and separately
+  archived overtime stories.
+- Persist run state, idempotent action responses, structured battles, and
+  every generated story in serialized SQLite transactions. Invalid archives
+  roll back the full action.
+
+## alpha 0.6.3.1015
+
+- Replace instant personal lottery tickets with one persistent multiplayer
+  lottery round per group: start, register/update, status, draw, and cancel.
+- Treat each ticket as three distinct digits from 0-9. Sort digits before
+  storage so `347` and `743` represent the same selection.
+- Accept spaced and compact OCR forms. Ticket stakes are 1-500 coins with a
+  default of 10 when omitted.
+- Return 0%, 50%, 120%, or 300% of the stake for matching zero, one, two, or
+  three drawn digits. All settlement values remain integer coins.
+- Commit entry updates, stake differences, all-player payouts, cancellation
+  refunds, and event replay responses in serialized SQLite transactions.
+- Raise the blackjack stake range to 1-500 coins.
+- Add per-game personal sequence numbers and `/游戏记录` (`/gamehistory`) for
+  prize draws, lottery rounds, and blackjack hands.
+- Prefix game output with the configured player label and game number, such as
+  `Player #1：...`; aliases share the same counter and account.
+
+## alpha 0.6.2.1015
+
+- Bound direct DeepSeek SSE reads to 30 seconds of total wall time in addition
+  to the existing 18-second socket inactivity timeout.
+- Stop reading as soon as the SSE `[DONE]` marker arrives instead of waiting
+  for the upstream connection to close.
+- Prevent a trickling or unfinished upstream response from occupying both
+  generation workers for about 15 minutes and delaying later final replies.
+- Preserve fast ACK delivery, three-attempt retry behavior, two generation
+  workers, and strict final-reply ordering.
+- Treat `/21点 开始 100` as a 100-coin stake and accept OCR forms with missing
+  whitespace, such as `/21点开始100` and `/blackjackstart100`.
+- Keep blackjack play as explicit steps: start and deal first, then hit or
+  stand in a separate command. Combined forms return this workflow without
+  opening a game or deducting funds.
+- Prefix blackjack hands, status and settlement replies with the current
+  group-scoped player's configured display label, such as `player：...`.
+
+## alpha 0.6.1.1015
+
+- Add three reviewed plugins: local context summaries for 100/200/300 messages,
+  person and alias lookup, and single-player virtual coin games.
+- Provide corresponding Chinese and English commands, including `/context`,
+  `/people`, `/person`, `/wallet`, `/draw`, `/lottery`, and `/blackjack`.
+- Grant each group-scoped person 1000 virtual coins once; persist account state,
+  private blackjack decks, timeout/forfeit rules, and win/loss statistics.
+- Commit funds, game state and event replay responses in one SQLite transaction;
+  retries never debit twice, and aliases share the canonical person's account.
+- Reconcile the message image after a two-second idle wait so a missed final
+  XDamage notification does not strand an isolated message; drain buffered Xlib
+  events before waiting on the socket. Preserve visual deduplication and guards.
+- Keep the generated feature list within the sender's 900-character boundary.
+- Document local extractive-summary coverage, OCR identity limitations,
+  game payouts, persistence and rollback behavior.
+
 ## alpha 0.6.0.1015

 - Replace repository-local and hardcoded deployment values with independent,
@@ -32,18 +240,581 @@
  backup; pre-public operational history remains only in protected local
  archives.

-## Pre-Public Milestones
+## alpha 0.5.11.1015

-Earlier alpha work established:
+- Reduce the conservative follow-latest scroll burst from a fixed `25ms` to
+  `1ms` between each of the existing 30 wheel events.
+- Reuse the XDamage producer's verified WeChat window identifier in the
+  adaptive ready-layout gate instead of rediscovering the same window before
+  each screenshot.
+- Preserve the shared GUI lock, ready-window geometry gate, second screenshot,
+  and loaded-bottom visual confirmation.
+- Add privacy-safe per-step capture telemetry and regression coverage for the
+  optimized slow path.

- adaptive OCR and XDamage capture;
- guarded GUI send with visual confirmation;
- durable ACK/final delivery ordering;
- privacy-safe latency telemetry;
- capability-limited SDK contracts;
- signed extension artifacts and isolated Host execution;
- reviewed command ownership and generated adapters;
- coordinated production backup, health gates, and rollback.
+## alpha 0.5.10.1015

-Private host, person, address, account, incident, and deployment details are
-intentionally omitted from the public changelog.
+- Prioritize queued fast acknowledgements and local-command replies over queued
+  final replies in the guarded GUI sender.
+- Keep the active GUI send non-preemptive and preserve strict FIFO ordering
+  within each priority class through a monotonic sequence number.
+- Raise the adaptive recorder CPU quota from `150%` to `250%` to reduce
+  screenshot subprocess stalls under OCR and GUI contention.
+- Add deterministic coverage for ACK/local priority, final FIFO ordering,
+  single-sender serialization, and clean worker shutdown.
+
+## alpha 0.5.9.1014
+
+- Preserve both capture call contracts in the adaptive ready-window wrapper:
+  zero arguments for startup/polling and one verified window identifier for the
+  optimized XDamage producer.
+- Fix the alpha 0.5.8 internal `CaptureProducerError` restart loop that began on
+  the first relevant XDamage event.
+- Add direct regression tests for both ready-gated capture signatures.
+
+## alpha 0.5.8.1014
+
+- Recover one unseen bottom-most bot trigger when a viewport resync has no
+  visual overlap, instead of silently dropping the new command.
+- Persist a bounded recent-trigger visual history so an old command is not
+  replayed by a later no-overlap resync; ordinary messages remain fail-closed.
+- Seed that history from one startup baseline before enabling recovery, so a
+  service restart cannot replay a visible pre-existing command.
+- Reuse the XDamage monitor's verified WeChat window identifier and the
+  maximize gate's geometry result, removing one redundant window lookup and
+  one redundant geometry subprocess from each changed-frame capture.
+- Add regression coverage for unseen-trigger recovery, seen-trigger replay
+  suppression, signature migration, and the optimized capture path.
+
+## alpha 0.5.7.1014
+
+- Replace the single direct-request worker with two parallel generation workers
+  and one strictly ordered GUI delivery worker for ordinary chat and Steam
+  requests.
+- Keep final replies in durable `created_at, event_id` order even when a newer
+  provider call completes first; failed acknowledgements and exhausted requests
+  remain terminal and do not block later replies.
+- Separate generation and delivery retry counters so each phase retains its
+  complete retry budget.
+- Wake generation and delivery workers immediately on enqueue, generation
+  completion, and acknowledgement instead of adding a one-second idle polling
+  delay to the normal path.
+- Split direct-queue telemetry into `direct_generation` and `direct_delivery`
+  phases and add concurrency, ordering, ACK-race, retry, Steam, and duplicate
+  regression coverage.
+
+## alpha 0.5.6.1014
+
+- Preserve both pre-draft and post-draft group fingerprint gates while
+  capturing only the configured title region instead of decoding the complete
+  WeChat window twice per GUI send.
+- Keep the previous full-window fingerprint path as a compatibility fallback
+  for older adaptive upstream modules.
+- Add GUI sender coverage for the title-region primary path, full-window
+  fallback, and visual group-mismatch fail-closed handling.
+
+## alpha 0.5.5.1014
+
+- Accept incoming WeChat bubbles up to `900px` wide so long single-line bot
+  mentions are not discarded before OCR; preserve position, height, area, and
+  outgoing-bubble exclusion gates.
+- Wait for adaptive OCR warmup and a first baseline capture from the current
+  service start before reporting `adaptive ready` or successful deployment.
+- Fail and roll back deployment if the adaptive service exits or cannot
+  establish its recorder baseline within 90 seconds.
+- Retry the WeChat ready-window gate for up to 30 seconds and discover the
+  exact `Weixin` window by both class and title before failing closed.
+- Pin production privilege switching and X11 inspection to verified absolute
+  executable paths so a restricted root `PATH` cannot masquerade as a missing
+  WeChat window.
+
+## alpha 0.5.4.1014
+
+- Stabilize visible-message sequence alignment with thresholded binary
+  sender/body fingerprints while retaining exact RGB keys for OCR cache
+  invalidation.
+- Reset 0.5.3 exact-visual recorder state to a safe no-reply baseline during
+  the signature migration.
+- Prefix coordinated deploy phases with `[JWeBot]`, report explicit
+  `starting`, `ready`, and `active` states, and run user installation from the
+  target home to avoid inherited `/root` working-directory warnings.
+
+## alpha 0.5.3.1014
+
+- Align visible message sequences with existing exact bubble visual
+  fingerprints instead of OCR text, preventing scroll/resync OCR drift from
+  dropping a newly mentioned slash command.
+- Reset legacy text-signature recorder state to a no-reply visual baseline on
+  startup, avoiding duplicate replay during the signature-scheme migration.
+- Preserve repeated identical commands as separate visual occurrences.
+
+## alpha 0.5.2.1014
+
+- Print an ASCII pixel-art project signature only after the coordinated
+  production deployer passes every cutover gate and disables rollback.
+
+## alpha 0.5.1.1014
+
+- Exclude the static bottom-left input hint from the realtime text ROI so an
+  empty WeChat input box is not misclassified as dirty.
+- Label the corrected ROI as `input_text_core_v2` in bridge telemetry, keeping
+  pre-fix and post-fix production evidence distinguishable.
+
+## alpha 0.5.0.1014
+
+- Move visible WeChat delivery onto a persistent in-process GUI sender queue
+  hosted by the adaptive recorder, avoiding per-message bridge subprocesses for
+  ACK, local-command replies, and final deliveries.
+- Add a private AF_UNIX sender socket so Edge delivery helpers submit final
+  replies to the same serialized GUI queue instead of racing the input box.
+- Combine clear, paste, ROI draft flag, post-draft group check, Enter send,
+  ROI clear confirmation, and send-button fallback into one bridge call.
+- Confirm the input ROI is empty after Ctrl-A/Backspace before using it as the
+  paste baseline, preventing repeated `喵......` ACK drafts from being mistaken
+  for paste failures.
+
+## alpha 0.4.15.1014
+
+- Force adaptive recorder logging to INFO so GUI bridge timing telemetry is
+  visible on ACK and final delivery paths.
+- Allow ROI, poll, pixel-threshold, flag, and coordinate fields through the
+  packaged runtime telemetry sanitizer.
+
+## alpha 0.4.14.1014
+
+- Replace full-input send confirmation with a left-side input-text ROI flag so
+  draft and send confirmation poll only the region that should visibly change.
+- Restore the guarded send order to Enter first, then click the scaled send
+  button only as a fallback when ROI clearing is not visually confirmed.
+- Emit ROI coordinates, flag state, flag wait time, confirmation source, and
+  bridge stderr tail diagnostics for GUI delivery failures.
+
+## alpha 0.4.13.1014
+
+- Emit detailed guarded GUI delivery timings for lock acquisition, pre/post
+  draft screenshots, group fingerprint checks, bridge subprocess duration,
+  draft paste confirmation polling, send-button confirmation polling, Enter
+  fallback, callback hooks, and total send time.
+- Return per-step timing metadata from the adaptive GUI bridge so ACK and final
+  delivery reports can attribute fixed waits, screenshot confirmation, VNC
+  input, and fallback paths without logging message text.
+
+## alpha 0.4.12.1014
+
+- Optimize guarded WeChat GUI delivery by clicking the scaled send button first
+  and polling for visual confirmation instead of waiting on fixed sleeps.
+- Preserve the Enter-key fallback when the button path is not visually
+  confirmed.
+
+## alpha 0.4.11.1014
+
+- Add explicit `edge.fast_ack.*` and `recorder.fast_ack.*` telemetry names
+  alongside the existing ACK metrics, making fast acknowledgement latency
+  independently filterable without breaking historical dashboards.
+
+## alpha 0.4.10.1014
+
+- Cache configured person-alias rows once per group and make configured
+  identity persistence idempotent, eliminating thousands of redundant
+  `FULL`-synchronous SQLite commits during Edge startup.
+- Reduce measured production host systemd socket readiness on the production database
+  snapshot from more than 90 seconds to about one second.
+
+## alpha 0.4.9.1014
+
+- Wait up to 45 seconds for the newly started Edge socket and health response
+  before deciding that a production cutover failed, while still failing
+  immediately if systemd marks the service failed.
+
+## alpha 0.4.8.1014
+
+- Keep the adaptive OCR process alive while WeChat is absent or awaiting login,
+  then resume capture against the ready main window without a systemd restart
+  storm.
+- Install the reviewed `wechat_local_ocr.py` beside the adaptive runtime instead
+  of importing an independently managed root copy.
+- Add a root-coordinated production deploy that records both systemd
+  topologies, backs up root and user files plus SQLite, disables both legacy OCR
+  units, and rolls back all layers when a health gate fails.
+- Require empty OCR queues, a ready WeChat window, Edge socket health, stable
+  adaptive restart counts, and SQLite integrity before accepting a production
+  cutover.
+- Preserve incoming service state in legacy install and upgrade tools; legacy
+  OCR now remains disabled unless an operator explicitly opts in.
+- Prevent Extension Host imports from writing bytecode into verified releases,
+  and exclude only standard interpreter cache files from source packaging.
+- Add deployment contract tests and shell-aware syntax validation to the local
+  release gate.
+
+## alpha 0.4.7.1014
+
+- Prewarm RapidOCR recognition and detection paths before live capture.
+- Cache successful bubble recognition by bounded exact visual fingerprint,
+  recognize only new or changed crops, and periodically revalidate the cache.
+- Persist OCR command events through atomic file replacement plus file and
+  directory `fsync`, then immediately wake the in-process responder while
+  retaining the one-second recovery scan.
+- Name the three execution paths explicitly as `local-command`, `deepseek`, and
+  `openclaw` in Edge responses and privacy-safe routing telemetry.
+- Add signed plugin description/help metadata, validate it through Host health,
+  generate bundled `/功能列表` output automatically, and update plugin creation
+  tooling and author documentation.
+
+## alpha 0.4.6.1014
+
+- Add a repeatable local performance baseline for OCR preprocessing, sequence
+  alignment, durable ACK/queue state, and real signed Host process execution.
+- Add a structured telemetry-log analyzer with p50, p95, maximum, status, and
+  event-count summaries.
+- Measure queue waiting, capture-buffer age, ACK end-to-end latency, and final
+  Edge delivery latency without recording message content.
+- Establish the bottleneck order from local measurements and existing runtime
+  evidence: RapidOCR, provider generation, polling wakeups, then one-shot Host
+  startup; SQLite and sequence work remain below 2 ms p95 locally.
+- Document the evidence, measurement gaps, and optimization order for later
+  `0.4.x` iterations.
+
+## alpha 0.4.5.1014
+
+- Close the approved repository-only Extension Host migration scope.
+- Treat an invalid installed signed release as a startup failure rather than a
+  preferred-mode fallback; only missing or startup-unhealthy Hosts may fall
+  back.
+- Enforce the end-to-end Host deadline after Kernel service execution and
+  expand transport-error telemetry.
+- Document completed local work, explicitly deferred external operations, and
+  the next measurement-led OCR/queue/ACK performance-analysis phase.
+
+## alpha 0.4.4.1014
+
+- Add privacy-safe structured telemetry for OCR, routing, ACK preparation and
+  confirmation, queues, providers, Host processes, service brokering, and final
+  GUI delivery.
+- Hash event and group identifiers, reject message-body fields, and retain only
+  low-cardinality process-local counts and latency summaries.
+- Expose telemetry summaries through Edge health without making telemetry part
+  of delivery correctness.
+- Instrument OCR capture/recognition/queue stages and distinguish ACK GUI
+  delivery from Edge confirmation.
+- Document ACK ordering and the measurement points needed for future OCR,
+  queue, Host-startup, and provider latency optimization.
+
+## alpha 0.4.3.1014
+
+- Require a signed release to pass isolated Host health before atomic
+  activation; failed new releases are removed without switching `current`.
+- Add explicit local-only health bypass for packaging environments.
+- Complete real-process parity coverage for all 12 reviewed plugins, including
+  memory CRUD, both stateful games, dice challenge, rankings, history, and
+  Steam fast-ACK final generation.
+- Fix Host protocol writes so broker messages bypass redirected plugin stdout
+  without exposing plugin output to the parent protocol.
+
+## alpha 0.4.2.1014
+
+- Load installed signed plugin manifests into a deterministic startup catalog
+  and freeze command ownership before routing.
+- Add `in-process`, `prefer-host`, and `host-only` Edge execution modes with
+  subprocess or AF_UNIX Host transports.
+- Route signed healthy plugins through the isolated Host while preserving
+  Kernel-direct commands and Steam fast-ACK queueing.
+- Permit startup fallback for missing or unhealthy preferred Hosts, but never
+  replay an active invocation after a possible stateful service call.
+- Add real subprocess end-to-end coverage from Edge through the generated
+  adapter, Host protocol, Kernel service broker, and final reply.
+
+## alpha 0.4.1.1014
+
+- Add bounded bidirectional JSON-line service brokering between isolated
+  Extension Host processes and Kernel-owned service profiles.
+- Enforce declared profile ownership, call IDs, call count, message size, and
+  end-to-end process/socket deadlines.
+- Add Host health inventory responses and broker support to both subprocess and
+  AF_UNIX clients.
+- Keep service errors generic across the isolation boundary.
+
+## alpha 0.4.0.1014
+
+- Start the approved `0.4.x` local extension-host migration and performance
+  instrumentation milestone.
+- Keep signing-pipeline integration, key rotation, PR rehearsal, target-machine
+  provisioning, deployment, and Linux verification deferred.
+
+## alpha 0.3.1.1014
+
+- Add OpenSSH `sshsig` publisher signatures for canonical extension release
+  records.
+- Bind the publisher principal, release filename, artifact metadata, source
+  digest, manifest author, and exact file list through one signed payload.
+- Require trusted publisher verification for activation, Host loading, and
+  rollback; unsigned paths now require an explicit local-test override.
+- Persist the canonical signature record with each installed release and
+  re-verify it before execution or rollback.
+- Add signing support to package, verify, activate, rollback, and standalone
+  release-signing tools.
+- Keep production host provisioning, deployment, and systemd validation deferred.
+
+## alpha 0.3.0.1014
+
+- Close the `0.2.x` complete-function migration after the corrected granular
+  plugin ownership model passed the full local gate.
+- Start the approved `0.3.x` baseline with Kernel-direct operational commands,
+  official-owned person memory, and 11 project-owned plugins.
+- Keep Linux deployment and systemd verification explicitly deferred.
+
+## alpha 0.2.6.1014
+
+- Replace grouped plugin domains with one plugin per independently
+  understandable function.
+- Keep dice and dice challenge as one complete project-authored collection.
+- Make person-memory the only official-authored command plugin.
+- Move feature list, status, and balance to unconditional Kernel-direct
+  routing.
+- Add required manifest author metadata and release-record schema version 2.
+- Generate 11 project plugin packages under the reviewed local-extension namespace and keep only
+  person-memory under `extensions/official`.
+- Rename the canonical rollback switch to
+  `JWEBOT_LOCAL_EXTENSIONS_ENABLED`, while accepting the old environment key
+  as a compatibility fallback.
+
+## alpha 0.2.5.1014
+
+- Move the complete Steam provider into `jwebot-official-extensions`.
+- Migrate fixed roster, group aliases, mode filtering, single-person lookup,
+  cache, API batching, proxy enforcement, and error classification.
+- Preserve the existing public `SteamClient`, `SteamUnavailable`, API base, and
+  Mihomo default exports through the packaged Edge runtime.
+- Keep the no-direct-network-fallback regression tests passing.
+
+## alpha 0.2.4.1014
+
+- Add full official-adapter versus compatibility-path parity tests.
+- Cover every stateless command family, all memory operations, every
+  dice-challenge phase, guess-number lifecycle, RPS lifecycle, status, balance,
+  Steam generation, and restart persistence.
+- Make parity and persistence checks part of the permanent local/CI gate.
+
+## alpha 0.2.3.1014
+
+- Route all known local commands through generated official SDK adapters by
+  default.
+- Execute stateful behavior through named in-process service brokers without
+  exposing raw Ledger or providers to adapters.
+- Preserve the Steam fast-ACK asynchronous path through the official adapter.
+- Add `JWEBOT_OFFICIAL_EXTENSIONS_ENABLED=0` as a compatibility rollback to
+  direct command-engine dispatch.
+- Keep unknown slash-command errors on the compatibility path.
+- Install generated adapter modules with the official package.
+
+## alpha 0.2.2.1014
+
+- Add reviewed `service_profiles` as a narrow SDK/manifest capability.
+- Generate real Host-loadable packages for all seven official function domains.
+- Register every existing alias through SDK command adapters.
+- Delegate complex stateful behavior through named Kernel service profiles
+  instead of exposing raw Ledger or provider objects.
+- Add synchronization checks so official manifests, adapters, docs, and command
+  ownership cannot drift.
+- Validate, source-scan, and package every official extension in CI.
+
+## alpha 0.2.1.1014
+
+- Move the complete local command engine out of the Edge runtime into the
+  installable `jwebot-official-extensions` package.
+- Preserve all command replies, persistence, deterministic seeds, game state
+  machines, memory operations, rankings, status, balance, and Steam behavior.
+- Inject Ledger, Steam, balance, reply-cleaning, identity, and memory-policy
+  brokers from Kernel instead of importing Edge internals.
+- Add a unique ownership map covering every current command kind and alias.
+- Add an authoritative migration matrix documenting every command subfunction
+  and non-command Kernel responsibility.
+
+## alpha 0.2.0.1014
+
+- Start the approved `0.2` full-function migration milestone.
+- Move the complete Edge runtime into `jwebot-kernel`.
+- Keep `jwebot_edge.py` as a compatibility CLI and module alias so existing
+  imports and runtime monkeypatches continue to affect implementation globals.
+- Update tests and the installer for the packaged runtime.
+- Preserve all existing command, queue, ledger, model, memory, broadcast, and
+  delivery behavior.
+- Do not deploy or validate on Linux in this stage.
+
+## alpha 0.1.11.1014
+
+- Add a bounded AF_UNIX client matching the systemd socket-activated Host
+  design.
+- Send one canonical JSON request, half-close the write side, and read one
+  bounded response.
+- Fail closed on socket timeout, unavailable socket, malformed response, and
+  Host error status.
+- Keep the socket client disconnected from the current production Edge path.
+
+## alpha 0.1.10.1014
+
+- Add uninstalled systemd socket/service templates for the extension Host.
+- Specify a fixed unprivileged identity, AF_UNIX-only private network,
+  read-only system/release paths, empty capabilities, syscall filtering, and
+  CPU/memory/process/runtime limits.
+- Add static sandbox-policy checks and unit tests.
+- Require explicit target-host provisioning and systemd verification before
+  any future enablement.
+
+## alpha 0.1.9.1014
+
+- Add the Kernel-side extension Host client with a minimal inherited
+  environment and isolated process group.
+- Enforce parent wall-time deadlines and kill the entire Host process group on
+  timeout.
+- Bound request, response, and stderr sizes and reject malformed protocol
+  responses.
+- Limit plugin stdout/stderr inside the Host.
+- Hash both plugin log messages and field-name sets instead of emitting plugin
+  text.
+- Test timeout child-process cleanup and environment-secret exclusion.
+- Keep the client disconnected from the production Edge path.
+
+## alpha 0.1.8.1014
+
+- Add an installable `jwebot-extension-host` package.
+- Re-verify installed release content, manifest, and source policy before import.
+- Enforce exact declared command registration and freeze it before invocation.
+- Add a bounded single-request JSON stdin/stdout protocol.
+- Scrub inherited environment values and redirect plugin stdout away from IPC.
+- Keep storage, HTTP, and scheduling brokers fail-closed.
+- Return generic plugin failure classes without exception text.
+- Do not connect the Host to Edge or install it on production host.
+
+## alpha 0.1.7.1014
+
+- Add verified release installation under full source-digest directories.
+- Add locked, atomic `current` and `previous` activation pointers.
+- Re-verify installed release file lists, records, and source content before
+  reuse.
+- Add explicit local activation and rollback tools with no default production
+  path.
+- Test rollback, tampered artifacts, tampered installed content, unsafe
+  pointers, and private installed-file permissions.
+- Do not execute extension code or modify production host.
+
+## alpha 0.1.6.1014
+
+- Add deterministic, content-addressed extension release artifacts.
+- Add canonical source and artifact SHA-256 records.
+- Verify artifacts without extraction and reject path traversal, non-regular
+  members, expansion limits, file-list drift, and content tampering.
+- Refuse replacement of an existing digest-addressed artifact with different
+  bytes.
+- Build and verify the example extension artifact in Gitea Actions.
+- Explicitly defer publisher signing and production host activation to a later phase.
+
+## alpha 0.1.5.1014
+
+- Add a static extension source-policy preflight before packaging.
+- Reject unapproved imports, file/process/socket access, dynamic execution
+  builtins, and dunder attribute traversal.
+- Enforce source count, size, UTF-8, syntax, and symlink limits.
+- Make `validate-plugin.py` validate both manifest and source policy.
+- Document that static policy is a CI prefilter, not a replacement for OS
+  process isolation.
+
+## alpha 0.1.4.1014
+
+- Restrict extension command names to Unicode word characters, dots, and
+  hyphens.
+- Reject quote/newline template injection before plugin skeleton files are
+  created.
+- Add manifest and generator regression tests while preserving Chinese command
+  names.
+
+## alpha 0.1.3.1014
+
+- Add a safe command-extension generator that refuses invalid IDs, invalid
+  commands, path traversal, and overwriting existing extensions.
+- Add official and friend extension namespaces.
+- Add an author guide, SDK API reference, and reusable AI-author prompt.
+- Include author tooling and required documentation in the repository gate.
+
+## alpha 0.1.2.1014
+
+- Add a deterministic extension catalog that accepts reviewed manifests only
+  during startup.
+- Reject duplicate plugin IDs and case-insensitive command ownership conflicts.
+- Freeze registration before runtime command resolution.
+- Keep catalog views immutable and require explicit command-token boundaries.
+
+## alpha 0.1.1.1014
+
+- Make `jwebot-kernel` the authoritative pure routing implementation used by
+  the existing Edge compatibility entrypoint.
+- Preserve the existing `jwebot_edge.py` public function shapes for current
+  callers and tests.
+- Update the production host installer to deploy and roll back the SDK and Kernel package
+  directories together with the compatibility scripts.
+- Do not deploy or restart any production service in this repository change.
+
+## alpha 0.1.0.1014
+
+- Start the approved `0.1` milestone with installable `jwebot-sdk` and
+  `jwebot-kernel` packages.
+- Add versioned event, reply, fact, and extension-result contracts.
+- Add capability-limited context protocols that expose no GUI, group selector,
+  raw ledger, environment, shell, or unrestricted network access.
+- Add strict plugin manifest validation and pure local/chat/cloud routing
+  primitives.
+- Add a minimal `/hello` command extension and package boundary tests.
+- Keep all existing root runtime entrypoints unchanged for production host compatibility.
+
+## alpha 0.0.7.1014
+
+- Move unit tests into `tests/`.
+- Update tests to load root compatibility entrypoints from the repository root.
+- Update local verification commands to discover tests from `tests/`.
+
+## alpha 0.0.6.1014
+
+- Add repository-safe configuration templates under `config/examples/`.
+- Add `docs/configuration-guide.md` for runtime configuration ownership and
+  deployment destinations.
+- Add `tools/check-config.sh` and include it in the local migration gate.
+- Keep real secrets and production host runtime files outside Git.
+
+## alpha 0.0.5.1014
+
+- Add a Gitea Actions workflow that runs the standard local migration gate on
+  push and pull request.
+- Add `requirements-dev.txt` for local and CI test dependencies.
+- Document dependency installation in `README.md`.
+
+## alpha 0.0.4.1014
+
+- Move home-backup operational material into `ops/home-backup/`.
+- Move the TigerVNC config snippet into `deploy/config/`.
+- Keep backup material in the repository for reference while separating it from
+  the bot runtime path.
+
+## alpha 0.0.3.1014
+
+- Add `tools/check-local.sh` as the standard local migration gate.
+- Wire the gate to compile Python entrypoints, validate shell scripts, reject
+  active emergency debug hooks outside their archive docs, and run the full
+  unittest suite.
+- Document the local check command in `README.md`.
+
+## alpha 0.0.2.1014
+
+- Remove temporary emergency HTTP debug hooks from production Python entrypoints.
+- Preserve removed hook context in `docs/debug/emergency-hooks-archive.md`.
+- Add `docs/configuration-inventory.md` to document hardcoded addresses, paths,
+  service names, dimensions, models, and their migration policy.
+- Keep historical incident markdown unchanged for auditability.
+
+## alpha 0.0.1.1014
+
+- Establish the repository version baseline for the private alpha migration.
+- Move operational docs into `docs/`.
+- Move deployment scripts, defaults, and systemd units into `deploy/`.
+- Move the cloud responder prompt workspace into `agents/wechat-responder/`.
+- Move the old direct OpenClaw watcher into `legacy/`.
+- Keep current Python runtime entrypoints at repository root to preserve test and
+  deployment compatibility during the first migration step.
@@ -8,7 +8,15 @@ JWeBot 是运行于 Linux 的单群微信自动回复系统。它通过本地 OC
 观察选定的微信窗口，将消息写入持久化 Edge 账本，调用经过审核的命令插件，
 并通过带视觉确认的 GUI 发送链路回复。

-当前版本：`alpha 0.6.0.1015`。
+当前版本：`beta 1.0.2.1016`，更新日期：2026-10-16。
+
+1.0 Beta 收口了当前稳定功能：本地命令插件、人物与上下文索引、
+Steam 状态与时长查询、虚拟金币游戏、多人彩票、21 点、CS Major
+自走棋、生产部署与回滚门禁。CS Major 自走棋的选手、教练、叙事和规则
+已经外置为包内 JSON，虚拟金币支持转账、贷款、还款和群内排行榜。
+
+完整命令见[命令目录](docs/command-catalog.md)。历史版本记录见
+[CHANGELOG](CHANGELOG.md)。

 ### 运行流程

@@ -72,6 +80,21 @@ PATH="$PWD/.venv/bin:$PATH" ./tools/check-local.sh

 ```text
 /功能列表
+/上下文 [100|200|300]（/context）
+/人物列表 [页码]（/people）；/人物 [名称或别名]（/person）
+/金币（/wallet）；/抽奖 [金额]（/draw）
+/大富翁榜（/金币排行）
+/转账 对方 金额（/transfer name amount）
+/贷款 [金额]（/loan amount）；/还款 [金额|全部]（/repay）
+/彩票 开始|报名|当前状态|开奖|取消（/lottery）
+/21点 开始 [1～500]；开局后 /21点 要牌|停牌|状态|结束
+/21点 多人 启动；/21点 加入；/21点 多人 开始；/21点 放200
+/游戏记录 [页码]（/gamehistory）
+/游戏帮助（/games）
+/自走棋开始|报名|开赛|状态|档案
+/自走棋加AI战队（两名或三名真人测试模式）
+/选1～6（教练轮为 /选1～10）；/刷新；/锁定
+/战术 火力|稳定|残局；/阵容；/上阵 备战编号 [首发位]；/出售 备战编号；/结束回合
 /丢骰子 [NdM]
 /猜数字 开始 [上限]
 /石头剪刀布 [开始|加入|出|状态|结算|结束]
@@ -240,9 +263,17 @@ visually confirmed GUI bridge.
 Current version:

 ```text
-alpha 0.6.0.1015
+beta 1.0.2.1016
 ```

+Updated: 2026-10-16.
+
+The 1.0 Beta baseline consolidates the stable local command set, person and
+context indexes, Steam presence/playtime queries, virtual coin games,
+multiplayer lottery, blackjack, CS Major autochess, and production deployment
+gates. CS Major autochess game content is now packaged as JSON data, and
+virtual coins support transfer, loans, repayment, and group leaderboards.
+
 ## Runtime Flow

 ```text
@@ -308,7 +339,8 @@ migration, debug archives, and root deployment settings.
 ## Commands

 The built-in command inventory is generated from reviewed plugin descriptors.
-Common commands include:
+See the full [command catalog](docs/command-catalog.md). Common commands
+include:

 ```text
 /功能列表
@@ -337,6 +369,13 @@ the final separator shown below:
 /steam时长Dota2人=玩家名
 ```

+Chinese aliases share the same implementations as their English counterparts.
+Virtual coin funds, game state, transfers, loans, repayments, and replay
+responses commit through the same ledger transaction path. Native WeChat
+account IDs are unavailable, so accounts are scoped by OCR display identity and
+configured aliases. See
+[plugin rules and capture reconciliation](docs/local-plugins-0.6.1.md).
+
 Steam prefers private per-person SteamID mappings from the active profile and
 uses the corresponding group display IDs and aliases. Without a private roster,
 it discovers the configured account's public friend list at runtime. No real
@@ -1 +1 @@
-alpha 0.6.0.1015
+beta 1.0.2.1016
@@ -9,6 +9,7 @@ sdk_source_dir="$source_dir/packages/jwebot-sdk/src/jwebot_sdk"
 kernel_source_dir="$source_dir/packages/jwebot-kernel/src/jwebot_kernel"
 official_source_dir="$source_dir/packages/jwebot-official-extensions/src/jwebot_official_extensions"
 official_adapter_source_dir="$official_source_dir/adapters"
+official_autochess_data_source_dir="$official_source_dir/data/cs_autochess"
 target_dir="$HOME/.local/lib/wechat-health-watch"
 unit_dir="$HOME/.config/systemd/user"
 config_dir="$HOME/.config/jwebot"
@@ -237,6 +238,8 @@ trap rollback EXIT HUP INT TERM
 jwebot_log "user runtime preflight starting"
 test -x "$runtime_python"
 for path in \
+    "$source_dir/VERSION" \
+    "$source_dir/CHANGELOG.md" \
    "$runtime_source_dir/$ocr_script_name" \
    "$runtime_source_dir/$script_name" \
    "$runtime_source_dir/$adaptive_script_name" \
@@ -262,6 +265,9 @@ do
    test -d "$directory"
    find "$directory" -maxdepth 1 -type f -name '*.py' | grep -q .
 done
+test -d "$official_autochess_data_source_dir"
+find "$official_autochess_data_source_dir" -maxdepth 1 -type f -name '*.json' \
+    | grep -q .
 test -f "$environment_file"

 if systemctl is-active --quiet wechat-local-ocr-recorder.service \
@@ -276,6 +282,8 @@ jwebot_log "user runtime backup starting path=$backup_dir"
 install -d -m 0700 "$target_dir" "$unit_dir" "$config_dir" "$backup_dir"
 save_unit_states
 for name in \
+    VERSION \
+    CHANGELOG.md \
    "$ocr_script_name" \
    "$script_name" \
    "$adaptive_script_name" \
@@ -326,6 +334,8 @@ systemctl --user stop \
    >/dev/null 2>&1 || true

 jwebot_log "user runtime files install starting"
+install -m 0600 "$source_dir/VERSION" "$target_dir/VERSION"
+install -m 0600 "$source_dir/CHANGELOG.md" "$target_dir/CHANGELOG.md"
 install -m 0700 "$runtime_source_dir/$ocr_script_name" "$target_dir/$ocr_script_name"
 install -m 0700 "$runtime_source_dir/$script_name" "$target_dir/$script_name"
 install -m 0700 "$runtime_source_dir/$adaptive_script_name" "$target_dir/$adaptive_script_name"
@@ -342,7 +352,9 @@ install -d -m 0700 \
    "$target_dir/jwebot_sdk" \
    "$target_dir/jwebot_kernel" \
    "$target_dir/jwebot_official_extensions" \
-    "$target_dir/jwebot_official_extensions/adapters"
+    "$target_dir/jwebot_official_extensions/adapters" \
+    "$target_dir/jwebot_official_extensions/data" \
+    "$target_dir/jwebot_official_extensions/data/cs_autochess"
 for path in "$config_source_dir"/*.py; do
    install -m 0600 "$path" "$target_dir/jwebot_config/$(basename "$path")"
 done
@@ -359,6 +371,10 @@ for path in "$official_adapter_source_dir"/*.py; do
    install -m 0600 "$path" \
        "$target_dir/jwebot_official_extensions/adapters/$(basename "$path")"
 done
+for path in "$official_autochess_data_source_dir"/*.json; do
+    install -m 0600 "$path" \
+        "$target_dir/jwebot_official_extensions/data/cs_autochess/$(basename "$path")"
+done
 for name in \
    "$service_name" \
    "$timer_name" \
@@ -0,0 +1,126 @@
+# JWeBot Command Catalog
+
+Current baseline: `beta 1.0.1.1016`.
+
+This catalog records the reviewed commands shipped with the built-in local
+extensions. Runtime ownership is frozen at startup from the generated
+descriptor inventory; plugin code delegates to reviewed service profiles.
+
+## System
+
+| Command | Alias | Purpose |
+|---|---|---|
+| `/功能列表` | `/help` | Show the command list. |
+| `/状态` | `/status` | Show local runtime status. |
+| `/version` | - | Show installed package versions plus the latest changelog date and summary. |
+| `/debug` | - | Show privacy-safe telemetry diagnostics. |
+| `/余额` | - | Show configured direct-provider balance status. |
+
+## Context And People
+
+| Command | Alias | Purpose |
+|---|---|---|
+| `/上下文 [100|200|300]` | `/context` | Summarize recent local text in the current group. |
+| `/人物列表 [页码]` | `/people` | List known group-scoped people. |
+| `/人物 [名称或别名]` | `/person` | Look up one configured or observed person. |
+| `/记住 内容` | - | Store a local memory entry for the current person. |
+| `/我的记忆` | - | Show the current person's memory entries. |
+| `/人物记忆 显示名` | - | Show memory entries for a person. |
+| `/忘记 关键词` | - | Remove matching local memory entries. |
+| `/记忆帮助` | - | Show memory command help. |
+
+## Group Insights
+
+| Command | Alias | Purpose |
+|---|---|---|
+| `/扫码排行` | - | Show scan ranking for the current group. |
+| `/复读榜` | - | Show repeat ranking for the current group. |
+| `/查记录 关键词` | - | Search local group history by keyword. |
+
+## Virtual Coins And Games
+
+| Command | Alias | Purpose |
+|---|---|---|
+| `/金币` | `/wallet` | Initialize or show the current person's virtual coin account. |
+| `/大富翁榜 [人数]` | `/金币排行`, `/金币排行榜`, `/richlist` | Show the group-scoped coin leaderboard. |
+| `/转账 对方 金额` | `/transfer name amount` | Transfer virtual coins to an initialized group account. |
+| `/贷款 [金额]` | `/loan amount`, `/借款` | Borrow up to 500 virtual coins. |
+| `/还款 [金额|全部]` | `/repay [amount|all]` | Repay an active virtual coin loan. |
+| `/抽奖 [金额]` | `/draw` | Play a single-player prize draw. |
+| `/彩票 开始` | `/lottery start` | Open a multiplayer lottery round. |
+| `/彩票 报名 数字 金额` | `/lottery join` | Join or update a lottery entry. |
+| `/彩票 状态` | `/lottery status` | Show the current lottery round. |
+| `/彩票 开奖` | `/lottery draw` | Host-only draw for the current lottery round. |
+| `/彩票 取消` | `/lottery cancel` | Host-only cancellation with refunds. |
+| `/21点 开始 [1-500]` | `/blackjack start` | Start a blackjack round with the chosen stake. |
+| `/21点 要牌` | `/blackjack hit` | Draw one blackjack card. |
+| `/21点 停牌` | `/blackjack stand` | Stand and settle against the dealer. |
+| `/21点 状态` | `/blackjack status` | Show the current blackjack round. |
+| `/21点 结束` | `/blackjack end` | End the current blackjack round. |
+| `/21点 多人 启动` | - | Open a Taffy-hosted blackjack table and auto-seat the host. |
+| `/21点 加入` | - | Join the current blackjack table before betting starts. |
+| `/21点 多人 开始` | - | Host-only close joining and start ordered betting prompts. |
+| `/21点 放金额` | - | Place the prompted table stake, 1-10000 coins. |
+| `/游戏记录 [页码]` | `/gamehistory` | Show indexed personal game history. |
+| `/游戏帮助` | `/games` | Show local game rules. |
+
+## Random And Session Games
+
+| Command | Alias | Purpose |
+|---|---|---|
+| `/丢骰子 [NdM]` | - | Roll dice. |
+| `/丢骰子挑战` | `/骰子挑战` | Run a dice challenge. |
+| `/翻硬币` | - | Flip a coin. |
+| `/随机数 [范围]` | - | Draw a random number. |
+| `/抽签 [内容...]` | - | Draw lots from provided options. |
+| `/今日运势` | - | Show a deterministic daily fortune. |
+| `/猜数字 开始 [上限]` | - | Start a group guessing game. |
+| `/猜数字 数字` | - | Guess in the active guessing game. |
+| `/石头剪刀布 开始` | - | Start a rock-paper-scissors session. |
+| `/石头剪刀布 加入` | - | Join the active session. |
+| `/石头剪刀布 出 石头|剪刀|布` | - | Submit a move. |
+| `/石头剪刀布 状态` | - | Show session status. |
+| `/石头剪刀布 结算` | - | Settle the session. |
+| `/石头剪刀布 结束` | - | End the session. |
+
+## Steam
+
+| Command | Alias | Purpose |
+|---|---|---|
+| `/steam 在线` | - | Show configured Steam online status. |
+| `/steam 游戏` | - | Show current games. |
+| `/steam 全部` | - | Show full configured Steam presence. |
+| `/steam 刷新` | - | Refresh cached Steam data. |
+| `/steam 时长 游戏名` | `/steam时长游戏名` | Query playtime for a game. |
+| `/steam时长游戏名、玩家名` | `/steam时长游戏名人=玩家名` | Query one player's game playtime. |
+
+## CS Major Autochess
+
+| Command | Alias | Purpose |
+|---|---|---|
+| `/自走棋开始` | - | Create a new IEM 盐田 Major season. |
+| `/自走棋报名` | - | Register the current player. |
+| `/自走棋加AI战队` | - | Add local deterministic AI teams for testing. |
+| `/自走棋开赛` | - | Start the event from registration. |
+| `/自走棋状态` | - | Show the current event state. |
+| `/自走棋档案` | - | Show archived event information. |
+| `/选1` ... `/选10` | - | Draft coaches, players, or shop cards depending on phase. |
+| `/刷新` | - | Refresh the shop. |
+| `/锁定` | - | Lock or unlock the shop. |
+| `/阵容` | - | Show lineup, bench, coach, gold, and synergies. |
+| `/赛程` | - | Show the current event schedule. |
+| `/升级教练` | - | Upgrade the team's coach level when rules allow it. |
+| `/上阵 备战编号 [首发位]` | - | Move a bench player into the starting lineup. |
+| `/下阵 首发位` | - | Move a starting player out when rules allow it. |
+| `/出售 备战编号` | - | Sell a bench player. |
+| `/战术 火力|稳定|残局` | - | Set the team's tactical focus. |
+| `/结束回合` | - | Mark readiness and advance when required players are ready. |
+
+## Notes
+
+- Commands must be sent in the configured WeChat group and normally mention the
+  bot, depending on deployment configuration.
+- OCR whitespace loss is tolerated for selected compact forms such as
+  `/steam时长Dota2` and `/21点开始100`.
+- Real profiles, Steam IDs, person context, message payloads, and secrets are
+  never stored in this repository.
@@ -1,7 +1,7 @@
 # Command Registration And Execution Paths

 Status: authoritative local registration and routing contract for
-`alpha 0.6.x`.
+`beta 1.0.x`.

 ## Three Execution Paths

@@ -25,7 +25,8 @@ error. They never fall through to DeepSeek or OpenClaw.

 The local command path is:

-1. XDamage reports a relevant message-region change.
+1. XDamage reports a relevant message-region change, or a two-second idle
+   reconciliation capture detects a missed final drawing.
 2. OpenCV segments incoming bubbles without running OCR over the whole screen.
 3. The OCR engine reuses exact visual-fingerprint matches from a bounded LRU.
 4. Only new or changed sender/body crops use RapidOCR.
@@ -45,6 +46,10 @@ because each bubble position still produces its own `IncomingMessage`.
 Changed pixels force fresh OCR. The cache is bounded and periodically
 revalidated.

+For the local plugins introduced during the 0.6.x line, including bilingual
+commands, person identity limitations and atomic single-player game settlement,
+see [local plugin rules](local-plugins-0.6.1.md).
+
 ## Bundled Plugin Registration

 Bundled command metadata has one source:
@@ -141,7 +146,8 @@ descriptors unless they are strictly Kernel-only. The current official
 operational commands are:

 - `/状态` and `/status`: server, Edge, OCR, and queue status.
- `/version`: installed JWeBot package versions.
+- `/version`: installed JWeBot package versions plus the latest changelog date
+  and summary.
 - `/debug`: recent privacy-safe telemetry p50/p95/max summary.

 These commands delegate to Kernel-owned service profiles through generated
@@ -90,6 +90,15 @@ Steam uses `JWEBOT_EDGE_STEAM_ID64` and
 - Host timeout and fallback;
 - GUI sender timeout.

+The OCR runtime also accepts optional environment overrides for constrained
+hosts:
+
+- `WECHAT_OCR_ONNX_INTRA_OP_THREADS` defaults to `1`;
+- `WECHAT_OCR_ONNX_INTER_OP_THREADS` defaults to `1`.
+
+These values limit RapidOCR's ONNXRuntime CPU thread pools so service restarts
+do not temporarily saturate the host while the OCR cache is cold.
+
 ### Debug

 `components/debug.toml` generates:
@@ -0,0 +1,678 @@
+# CS Major 自走棋设计稿
+
+本文档定义一个完全本地、确定性结算、以 CS 职业选手为棋子的群聊
+小游戏方案。赛事包装统一为“第 n 届 IEM 盐田 Major”。AI 默认负责主持、
+裁判、播报和剧情生成；主持人也可显式加入一支本地确定性 AI 战队。
+
+## 1. 设计目标
+
+1. 做成一个多人报名、多人运营、多人对战的群聊自走棋。
+2. 玩法重心放在每轮选秀和阵容运营，而不是复杂微操。
+3. 用 Major 赛事包装训练赛、小组单循环、淘汰赛和终局剧情。
+4. 结算逻辑必须完全本地、可重放、可持久化、可回档验证。
+5. 每一段剧情都要落档，且剧情只能在数值结算之后生成。
+
+## 2. 核心体验
+
+一句话定义：
+
+`三轮赛前选秀 -> 轮次训练赛拿资源 -> D 牌与布阵 -> BO3 小组单循环 -> BO5 淘汰赛 -> 保存每轮赛报与剧情`
+
+玩家感受到的乐趣应当主要来自：
+
+- 第一轮从固定 10 人教练池里抢体系教练；
+- 第二、三轮公开选手池里抢关键卡；
+- 决定要不要保经济还是强行 D 牌；
+- 赌阵容成型时点；
+- 看小组单循环和淘汰赛赛报；
+- 看最终冠军剧情与本届 Major 档案。
+
+## 3. 对局对象与规模
+
+### 3.1 报名
+
+- 开局命令由任意玩家发起。
+- 其他玩家在报名窗口内加入。
+- 建议一局支持 `2~8` 名真人玩家。
+- 主持人可在报名阶段发送 `/自走棋加AI战队`：
+  - 两名真人时加入 AI 战队 A、B；
+  - 三名真人时加入一支 AI 战队。
+- 两种测试模式都补满四队，先进行 BO3 小组单循环，再按排名生成
+  `1v4`、`2v3` 半决赛。
+- AI 占一个参赛席位，但不对应群成员，也不调用在线模型。
+- AI 使用确定性规则选秀、买牌、调整首发和选择克制战术；为便于测试，
+  AI 阵容战力会有明确折扣。
+
+### 3.2 玩家初始状态
+
+每位玩家开局拥有：
+
+- 生命值：`100`
+- 金币：`10`
+- 教练：赛前第一轮选秀决定
+- 初始选手：赛前第二、三轮选秀决定，系统随后补齐阵容
+- 阵容位：固定 `5 个选手位 + 1 个教练位`，比赛时必须全部上场
+- 备战席：`3 格`
+- 连胜/连败计数：`0`
+- 本局独立事件档案编号
+
+三轮选秀完成后，系统按已选核心确定性补齐每队 `5 名首发 + 3 名备战`
+和常驻教练，保证训练赛开始时就是完整阵容。
+
+## 4. 选手池设计
+
+### 4.1 选手来源
+
+只使用“近期非常出名”的职业选手。第一期池子优先覆盖以下俱乐部与明星：
+
+- Spirit
+- Vitality
+- Falcons
+- G2
+- FaZe
+- NAVI
+- MOUZ
+- The MongolZ
+- Astralis
+- Liquid
+- FURIA
+- Eternal Fire
+
+选手数据不是对真实比赛数据的一比一复刻，而是基于公众认知做游戏化映射。
+0.6.7 起本地维护 `100+` 名棋子和 `18` 名教练元数据；运行期不在线抓取
+或改写数值。首轮教练选秀仍固定展示 10 个候选，保证聊天窗口可读。
+0.6.9 起，公开游戏内容不再内联在 `cs_autochess.py` 中，而是维护在
+`packages/jwebot-official-extensions/src/jwebot_official_extensions/data/cs_autochess/`：
+`players.json` 保存选手卡，`coaches.json` 保存教练卡，
+`narratives.json` 保存战报和剧情素材，`rules.json` 保存经济、商店、
+选秀、羁绊、赛制、MR15/加时和特殊事件规则。运行时启动会校验 schema、
+重复 ID、必要字段和叙事素材数量。
+
+### 4.2 费用层级
+
+选手分为 `1~5 费`，越高费越稀有，基础数值和成长更强。
+
+示例分层：
+
+- `5 费`：donk、ZywOo
+- `4 费`：m0NESY、NiKo、ropz、frozen
+- `3 费`：apEX、b1t、xertioN、w0nderful、malbsMd
+- `2 费`：辅助型或中坚选手
+- `1 费`：前期过渡与羁绊补齐牌
+
+正式实现时应维护一份固定的选手静态表，不允许运行期随意漂移。
+
+### 4.3 定位
+
+只保留三个核心定位：
+
+- `步枪手`
+- `狙击手`
+- `指挥`
+
+定位不是羁绊，而是战斗中的属性倾向与技能触发来源。
+
+### 4.4 羁绊
+
+只保留两类羁绊：
+
+1. `战队羁绊`
+2. `国家羁绊`
+
+战队羁绊可来自：
+
+- 当前主战队；
+- 历史待过的关键战队；
+- 每名选手最多挂 `3` 条战队标签，避免过度泛化。
+
+国家羁绊只有 `1` 条。
+
+## 5. 选手数值
+
+### 5.1 基础数值轴
+
+为避免面板过宽，第一期只展示三个主数值：
+
+- `火力`
+- `稳定`
+- `残局`
+
+其中指挥位额外拥有隐藏或显式的 `指挥` 修正值，用于影响全队。
+
+### 5.2 数值范围
+
+- 1 费：`52~68`
+- 2 费：`60~76`
+- 3 费：`68~84`
+- 4 费：`78~92`
+- 5 费：`88~98`
+
+要求同费位内部也要有明显差异，不能所有 4 费都只有一两点波动。
+
+### 5.3 派生战斗权重
+
+可先采用以下简单模型：
+
+`单卡战力 = 火力 * 0.45 + 稳定 * 0.30 + 残局 * 0.25 + 星级修正 + 羁绊修正 + 教练修正`
+
+若定位是狙击手，可给火力更高上限；
+若定位是指挥，可给团队修正更高权重。
+
+### 5.4 属性与定位克制
+
+战斗不能只比较总战力后掷骰子。三项主属性形成闭环：
+
+- `稳定克火力`：稳定阵容能吸收强攻的第一波冲击；
+- `火力克残局`：前期人数优势会压缩残局发挥空间；
+- `残局克稳定`：高残局能力能打破按部就班的默认局面。
+
+三个定位也形成轻量闭环：
+
+- `狙击手克步枪手`
+- `步枪手克指挥`
+- `指挥克狙击手`
+
+玩家每回合可选择 `/战术 火力|稳定|残局`。战术选择会强化对应属性，
+并在克制对方战术时获得额外修正。属性、定位和战术的总克制修正上限
+应明显高于随机波动，让调阵和判断对手比运气更重要。
+
+## 6. 升星规则
+
+- `3 张同名 = 2 星`
+- `9 张同名 = 3 星`
+
+升星收益建议：
+
+- 2 星：基础战力乘 `1.35`
+- 3 星：基础战力乘 `1.80`
+
+升星后保留原有羁绊与定位，不改变标签。
+
+## 7. 教练系统
+
+教练位不是普通战斗单位，但始终与 5 名选手一起上场。
+
+### 7.1 教练等级作用
+
+教练只提供额外的全队战术加成，不控制上场人数，也不占用选手位。
+
+建议加成：
+
+- 1 级：全队战力 `+2%`
+- 2 级：全队战力 `+4%`
+- 3 级：全队战力 `+6%`
+- 4 级：全队战力 `+8%`
+- 5 级：全队战力 `+10%`
+
+### 7.2 教练获取
+
+教练由第一轮公共选秀决定，本届赛事内不能用金币升级教练。不同教练
+自带等级、属性倾向和全队加成。
+高费选手的商店概率随赛事进程推进，不再绑定教练等级。
+
+## 8. 每轮 6 人选秀
+
+这是本模式的核心。
+
+### 8.1 固定规则
+
+- 每轮只展示 `6` 名候选选手。
+- 这 `6` 人对所有玩家公开可见。
+- 每位玩家始终保有 5 名首发；购买的新选手进入备战席或与同名选手合成。
+- 调整阵容时必须用备战席选手替换首发，不能让首发少于 5 人。
+- 第一版采用“公开同池、各自购买”的简化方案：
+  - 所有人看到同一组 6 人；
+  - 某个玩家选择后，不会把该候选从其他玩家界面里抢空；
+  - 但底层共享总卡池仍然会影响后续刷新概率。
+- 每名候选都必须展示完整数据：
+  - 编号 `1~6`
+  - 选手名
+  - 费用
+  - 定位
+  - 国家
+  - 主战队
+  - 历史战队
+  - 主数值
+- 玩家通过编号选择，不输入复杂自然语言。
+
+### 8.2 选秀指令
+
+建议指令面如下：
+
+```text
+/自走棋开始
+/自走棋报名
+/自走棋加AI战队
+/自走棋状态
+/选1
+/选2
+/选3
+/选4
+/选5
+/选6
+/选7
+/选8
+/选9
+/选10
+/刷新
+/锁定
+/战术 火力|稳定|残局
+/上阵 备战编号 [首发位]
+/出售 备战编号
+/阵容
+/赛程
+/结束回合
+```
+
+中文是主命令，英文别名可以后补。
+
+### 8.3 刷新与锁定
+
+- 第一轮教练选秀展示固定 10 名教练；第二、三轮选手选秀展示 6 名选手。
+- 训练赛和正赛运营阶段默认展示一组 6 人商店。
+- 玩家可支付金币执行刷新。
+- 玩家可锁定本轮 6 人，使下一轮仍保留同一组候选。
+
+### 8.4 顺位
+
+- 开赛后三轮公共选秀，第一轮选教练，第二、三轮选选手。
+- 第二轮使用反向顺序，避免种子靠前者连续先手。
+- AI 轮次会自动选择，真人只在轮到自己时使用 `/选N`。
+
+第一期建议先做“公开同池、各自结算”，避免群聊交互过重。
+
+## 9. 回合流程
+
+建议一整回合拆成五段：
+
+1. `回合开始播报`
+2. `6 人选秀 / 刷新 / 升级 / 调阵`
+3. `训练赛 / 赛事挑战 / PvP 结算`
+4. `回合结算与经济发放`
+5. `剧情归档`
+
+## 10. 训练赛与赛事挑战
+
+训练赛不再是阈值型 PvE。它是正式小组赛前的多轮真实对阵，用来给玩家
+检验阵容、获取金币并自然插入 D 牌窗口。媒体日和赞助挑战仍作为赛事内
+插曲出现，但只提供资源变动，不淘汰玩家。
+
+### 10.1 活动类型
+
+- 训练赛
+- 媒体日
+- 赞助挑战
+- 本地陪练队热身
+
+### 10.2 训练赛作用
+
+训练赛按参赛队伍生成 round-robin 轮次。四队测试局会有三轮训练赛，
+每队在训练阶段遇到另外三支队伍；奇数队伍时轮空队会与本地陪练队热身。
+训练赛只发放金币，不记录小组胜负，也不扣生命。
+
+每轮训练赛结束后进入运营窗口：
+
+- `/刷新` 即 D 牌，消耗金币换一组 6 人商店；
+- `/选1～/选6` 买入商店选手，重复卡自动累积星级；
+- `/锁定` 保留当前商店；
+- `/上阵` 调整 5 人首发；
+- `/战术 火力|稳定|残局` 改变下一场的回合倾向。
+
+### 10.3 训练赛结算逻辑
+
+训练赛使用与正式比赛相同的单图 MR15 逐回合模拟，只是赛制为 BO1。
+胜方获得更多金币，负方也有保底金币，保证测试局能继续运营。
+
+媒体日和赞助挑战根据阵容完整度、教练、战术和本地确定性随机因子发放
+金币，但播报不展示“目标/发挥”这类计算日志，只写剧情和奖励。
+
+## 11. PvP 赛制
+
+### 11.1 赛事包装
+
+整局赛事名称固定为：
+
+`第 n 届 IEM 盐田 Major`
+
+### 11.2 按参赛人数生成赛制
+
+- `2 人`：直接进入决赛。
+- `3 支队伍`：进行完整单循环，前 2 名进入决赛。
+- `4 人`：不打小组赛，按报名种子直接进行 `1v4`、`2v3` 半决赛。
+- `5~8 人`：进行完整小组单循环，每两支队伍只交手一次，前 4 名晋级。
+
+奇数队伍的小组比赛日会有一队轮空，但不会获得胜场。
+小组赛每场采用 `BO3`。
+
+### 11.3 小组排名
+
+小组赛首先按胜场排序；同胜场依次比较：
+
+1. 相互交手结果；
+2. 当前完整五人阵容战力；
+3. 剩余生命值；
+4. 固定种子编号。
+
+所有配对在开赛时一次性生成并落档，不允许运行中根据结果重排赛程。
+
+### 11.4 淘汰赛
+
+- 四强固定为 `小组第 1 vs 第 4`、`第 2 vs 第 3`。
+- 3 人赛制由小组第 1、2 名直接进入决赛。
+- 4 人赛制使用报名种子 `1v4`、`2v3`。
+- 2 人赛制直接进入决赛。
+- 半决赛胜者进入总决赛，决出本届冠军。
+- 半决赛和总决赛均采用 `BO5`。
+
+## 12. 战斗结算
+
+### 12.1 目标
+
+战斗要做到：
+
+- 本地确定性；
+- 单轮可解释；
+- 支持战报；
+- 不依赖在线模型。
+
+### 12.2 简化模型
+
+建议第一期采用“阵容总分 + 对位修正”的轻量模型。
+
+#### 步骤 1：计算阵容基础战力
+
+`阵容基础战力 = 5 名首发选手战力总和`
+
+#### 步骤 2：加上团队修正
+
+团队修正来源：
+
+- 战队羁绊
+- 国家羁绊
+- 教练等级提供的全队百分比加成
+- 装备/战术卡
+- 连胜或特殊事件 buff
+
+#### 步骤 3：计算克制修正
+
+依次计算：
+
+1. `稳定 > 火力 > 残局 > 稳定` 的属性对位；
+2. `狙击手 > 步枪手 > 指挥 > 狙击手` 的定位对位；
+3. 双方本回合主动选择的战术对位。
+
+克制结果必须进入结构化战报，明确展示双方修正值。
+
+#### 步骤 4：加入小幅波动
+
+只允许 `-2% ~ +2%` 的确定性哈希波动。单次运气不能覆盖成型阵容的
+属性、定位和战术克制优势。
+
+#### 步骤 5：计算比分
+
+单图采用 `MR15`：
+
+- 常规时间先到 `16` 分获胜；
+- 常规时间 `15-15` 进入加时；
+- 加时可产生 `19-17`，多轮加时可产生 `22-20` 等比分；
+- 每次加时除结构化单图结果外，必须额外生成一段加时剧情并落档。
+
+小组赛按 BO3 先赢 2 图，淘汰赛按 BO5 先赢 3 图。系列赛战报必须展示
+大比分、每张图比分、加时次数和克制修正。
+
+## 13. 剧情系统与落档
+
+这是本模式的强制要求。
+
+### 13.1 归档原则
+
+必须先结算，后写剧情。
+
+即：
+
+1. 固化数值结果；
+2. 存档回合事实；
+3. 基于事实生成文字赛报；
+4. 再把文字赛报作为附加档案保存。
+
+### 13.2 必须落档的节点
+
+- 开局报名完成
+- 每轮 6 人选秀结果
+- 每次刷新和关键升星
+- 每轮训练赛和赛事挑战结果
+- 每场 PvP 结果
+- 小组赛排名、晋级和淘汰节点
+- 淘汰赛对阵与结果
+- 冠军总结
+
+### 13.3 档案结构
+
+建议至少保存两类记录：
+
+1. `结构化事件档`
+2. `文本剧情档`
+
+结构化事件档用于回放和调试；
+文本剧情档用于玩家阅读。
+
+示例：
+
+```json
+{
+  "run_id": "major_0001",
+  "round": 4,
+  "phase": "group_2",
+  "event_type": "pvp_result",
+  "player_a": "Jacky",
+  "player_b": "Alice",
+  "winner": "Jacky",
+  "score_band": "close_win",
+  "roster_a_power": 418,
+  "roster_b_power": 403
+}
+```
+
+## 14. 数据持久化设计
+
+建议新增以下 SQLite 表。
+
+### 14.1 对局主表
+
+`autochess_runs`
+
+- run_id
+- group_fingerprint
+- season_number
+- state
+- created_at
+- updated_at
+
+### 14.2 玩家状态表
+
+`autochess_players`
+
+- run_id
+- person_key
+- display_name
+- hp
+- gold
+- coach_level
+- coach_xp
+- wins
+- losses
+- streak
+- board_json
+- bench_json
+- shop_json
+- locked_shop
+
+### 14.3 选秀记录表
+
+`autochess_shop_events`
+
+- run_id
+- round_number
+- person_key
+- visible_pool_json
+- action_type
+- action_payload_json
+- created_at
+
+### 14.4 战斗结果表
+
+`autochess_battles`
+
+- run_id
+- round_number
+- phase
+- battle_type
+- player_a
+- player_b
+- result_json
+- created_at
+
+### 14.5 剧情归档表
+
+`autochess_story_logs`
+
+- run_id
+- round_number
+- phase
+- story_type
+- story_text
+- facts_json
+- source_event_id
+- created_at
+
+### 14.6 幂等与重放表
+
+`autochess_action_replay`
+
+- run_id
+- person_key
+- round_number
+- event_id
+- action_kind
+- response_text
+- created_at
+
+## 15. 回放与幂等
+
+因为群聊环境会出现重复事件、OCR 重读和命令重放，必须保证：
+
+- 同一事件只执行一次；
+- 同一回合不能重复发奖或重复扣款；
+- 同一段剧情不能重复写多份版本；
+- 回合失败时整段事务回滚。
+
+建议沿用现有本地游戏的幂等思路，为自走棋单独增加 action replay 表。
+
+## 16. 指令交互风格
+
+建议所有回复都遵循现有小游戏风格：
+
+多段回复优先。一次主持动作可以拆成欢迎语、参赛名单、种子顺序、候选池、
+状态面板、操作指引等多条消息，每条保持在发送上限内。
+
+例如：
+
+```text
+欢迎来到第一轮选秀，本轮选教练。
+选择顺序：Jacky、Alice、AI 战队 A、AI 战队 B
+1. zonic｜5级教练｜冠军体系｜火78 稳92 残88｜全队+9%
+...
+现在轮到 @Jacky 做出选择，使用 /选1～/选10。
+```
+
+### 16.1 Taffy 主持状态机
+
+主持人必须承担完整赛事主持，而不是只在结算时出现；输出不需要每句都带
+`Taffy：` 前缀。
+
+开赛时必须包含：
+
+- `欢迎大家来到第 n 届 IEM 盐田 Major`
+- 本届参赛者和种子
+- 当前人数对应的完整赛制
+- 小组赛 BO3、淘汰赛 BO5、单图 MR15 和加时规则
+- 三轮选秀规则和当前选择玩家
+- 训练赛、小组赛和淘汰赛的当前阶段
+
+赛前选秀按顺序逐人选择。进入阵容准备、训练赛运营和小组赛运营后，
+所有相关真人发送 `/结束回合` 即可自动推进，不需要主持人手动结算。
+淘汰赛只等待当前对阵中的真人，已经淘汰的玩家不会再被提示准备。
+
+```text
+Jacky 选择了 zonic！
+现在轮到 @Alice 做出选择，使用 /选1～/选10。
+
+训练赛第 1/3 轮对阵：Team Jacky vs Team Alayak；AI 战队 A vs AI 战队 B
+本轮训练结束。现在是运营窗口：/刷新 是 D 牌，/选1～/选6 是买店内选手；
+所有真人发送 /结束回合 后进入下一轮训练。
+```
+
+以下节点都必须由 Taffy 主持并落档：
+
+- 报名开启和新选手加入
+- AI 测试战队加入
+- 赛制与种子公布
+- 三轮选秀候选池、选择结果和选秀完成
+- 每轮训练赛对阵、比分、金币和运营提示
+- 媒体日或赞助挑战
+- 每场 BO3/BO5 对阵与结果
+- 每张加时地图
+- 小组排名和前四晋级
+- 1v4、2v3 半决赛
+- 总决赛和冠军颁奖
+
+## 17. 实现顺序建议
+
+建议按三个阶段落地。
+
+### 第一阶段：最小可玩版
+
+- 建局 / 报名 / 状态
+- 每轮 6 人选秀
+- 买卡、卖卡、升星
+- 教练等级
+- 简化训练赛
+- 简化 PvP
+- 基础剧情归档
+
+### 第二阶段：赛事化增强
+
+- 小组单循环完整配对
+- 1v4、2v3 淘汰赛树
+- 羁绊与装备系统细化
+- 战报模板优化
+
+### 第三阶段：内容扩展
+
+- 在 100+ 人本地卡池基础上增加新赛季棋子
+- 更多俱乐部和国家
+- 特殊赛事事件
+- 更细的剧情风格与本届 Major 年鉴
+
+## 18. 第一版明确不做的内容
+
+为保证能上线，第一版先不做：
+
+- 实时地图微操
+- 复杂技能动画
+- 过多职业分类
+- 在线爬取实时战队数据
+- 大量开放文本输入解析
+
+## 19. 最终结论
+
+这套模式最适合按“强运营、轻操作、重赛报”路线实现。
+
+最重要的三个锚点已经确定：
+
+1. `每轮固定 6 人公开选秀`
+2. `训练赛与挑战负责资源，PvP 负责小组单循环与淘汰赛`
+3. `每一段剧情都必须落档`
+
+如果按这个设计推进，实现出来的成品会更像一场可回放、可复盘、
+可连载的本地 Major 模拟器，而不是一个只有数值结算的普通抽卡游戏。
@@ -0,0 +1,68 @@
+# alpha 0.6.3.1015 多人彩票与游戏记录
+
+## 一把彩票怎么玩
+
+1. 任意群友发送 `/彩票 开始`。发起人是本轮主持人。
+2. 每个人发送 `/彩票 报名 3 4 7 100`，表示选择 3、4、7，下注 100
+   金币。也可简写为 `/彩票347100`；省略金额时默认下注 10。
+3. 发送 `/彩票 当前状态` 查看本轮主持人、报名人数、每个人的号码和下注。
+4. 主持人发送 `/彩票 开奖`。机器人从 0～9 中抽取三个互不重复的数字，
+   统一排序后结算。
+5. 主持人也可在开奖前发送 `/彩票 取消`，所有报名者全额退款。
+
+命令关键词和数字之间的空格均可省略。`/买彩票` 和 `/lottery` 保留为
+对应别名。
+
+## 选号与报名
+
+- 每张票必须是三个互不重复的 0～9 数字。
+- 数字顺序不影响结果：`347`、`743` 和 `3 4 7` 都保存为 `3 4 7`。
+- 每人每把只有一张票。再次报名会更新号码和下注，不增加个人局号。
+- 更新到更高下注时只补扣差额；降低下注时退回差额。
+- 下注范围是 1～500，省略时为 10。
+- 没有进行中的彩票时不能报名；没有报名者时不能开奖。
+- 只有创建本轮的主持人可以开奖或取消，状态查询对群内所有人开放。
+
+支持的报名示例：
+
+```text
+/彩票 347
+/彩票 743 100
+/彩票 报名 3 4 7 100
+/彩票报名347金额100
+/彩票347100
+/lottery join 347 100
+```
+
+## 返还规则
+
+报名时先扣除下注。开奖号和玩家号码按集合比较，返还包含本金：
+
+| 命中数 | 返还 |
+|---|---:|
+| 0 个 | 0% |
+| 1 个 | 50% |
+| 2 个 | 120% |
+| 3 个 | 300% |
+
+金币只使用整数；百分比计算的小数部分向下取整。例如下注 100，命中两个
+返还 120，净变化为 `+20`。
+
+## 个人局号与记录
+
+抽奖、彩票和 21 点分别维护本人的游戏局号。第一次参与某种游戏显示
+`Jacky #1：...`，下一把显示 `Jacky #2：...`。配置别名解析到同一人物时，
+共用同一账户、局号和历史。
+
+发送 `/游戏记录 [页码]`、`/个人记录 [页码]` 或
+`/gamehistory [page]` 查看最近记录，每页五条。记录包含游戏、个人局号、
+结果、下注、返还和净变化，最多保留最近 50 条。
+
+21 点下注范围同步调整为 1～500。`/21点 开始 100` 只表示本局下注 100；
+发牌后再单独发送 `/21点 要牌` 或 `/21点 停牌`。
+
+## 持久化与并发
+
+彩票轮次、报名和结算保存在 Edge SQLite。报名/改注、所有玩家的开奖返还、
+取消退款和事件重放响应都在 `BEGIN IMMEDIATE` 事务中提交。重复事件不会
+重复扣款、发奖或增加局号；进程重启后未开奖轮次和个人记录仍然保留。
@@ -0,0 +1,131 @@
+# alpha 0.6.1.1015 本地插件与消息抓取
+
+本版本增加三个插件。全部由本机命令引擎执行，不调用 DeepSeek 或
+OpenClaw；中文、英文命令对应同一实现，英文不区分大小写，OCR 丢失
+命令与参数间的空格时仍可解析。正常使用时仍需 @ 当前配置的机器人。
+
+| 插件 | 中文指令 | 英文指令 |
+|---|---|---|
+| context-summary | `/上下文 [100|200|300]` | `/context [100|200|300]` |
+| single-player-games | `/金币` | `/wallet` |
+| coin-ranking | `/大富翁榜`、`/金币排行` | `/richlist` |
+| coin-transfer | `/转账 对方 金额` | `/transfer name amount` |
+| coin-loan | `/贷款 [金额]`、`/还款 [金额\|全部]` | `/loan amount`、`/repay [amount\|all]` |
+| single-player-games | `/抽奖 [金额]` | `/draw [金额]` |
+| single-player-games | `/彩票 开始/报名/当前状态/开奖/取消` | `/lottery start/join/status/draw/cancel` |
+| single-player-games | `/21点 开始 [金额]`（空格可省略） | `/blackjack start [金额]`（空格可省略） |
+| single-player-games | `/21点 要牌/停牌/状态/结束` | `/blackjack hit/stand/status/end` |
+| single-player-games | `/游戏记录 [页码]` | `/gamehistory [page]` |
+| single-player-games | `/游戏帮助` | `/games` |
+| person-directory | `/人物列表 [页码]`、`/别名列表 [页码]` | `/people [页码]` |
+| person-directory | `/人物 [名称或别名]`、`/个人属性 [名称或别名]` | `/person [名称或别名]` |
+
+命令所有权来自 `descriptors.py`，由同步工具生成三套受审核 SDK adapter。
+每个 adapter 只提交命名 service-profile 请求，由 Kernel 执行数据库操作。
+注册在启动期完成，运行期冻结。`/余额` 保持查询提供商余额；
+游戏虚拟余额使用 `/金币`。
+
+## 上下文总结
+
+默认选择最近 100 条，也可选择 200 或 300。查询限定当前群，排除当前
+请求事件，按观察时间和事件 ID 选出最近记录，再恢复时间顺序。
+不足指定数量时明确报告实际数量；没有记录时返回空历史提示。
+
+总结采用本地抽取式方法：统计参与人数、时间范围、重复话题，选出五条
+具有代表性的内容并按时间排列。它保留原话，不生成未经原文支持的决定
+或待办。覆盖范围是本机已经成功记录的文字消息，不包含图片、语音、
+未加载的微信历史或本机没观察到的消息。所有历史只保存在本机私有状态。
+独立的 `context_history` 保留短消息，避免复读排行的长度过滤影响最近
+100/200/300 条计数；启动时从现有复读历史补入旧记录，查询时从 OCR
+历史导入已识别发送人的文字。
+
+## 人物与账户索引
+
+当前 OCR 输入只有显示名，没有微信原生账号 ID。Kernel 将昵称或别名
+解析到私有配置中的 canonical_name，再以“当前群＋规范人物名”计算
+person_key。相同人物的已配置别名共用金币和牌局，其他群使用独立账户。
+没有配置的显示名使用独立临时身份；未识别到发送人的消息不能操作账户。
+
+`/人物` 默认查看本人；指定参数时只查询已配置人物。输出包括展示名、
+截短的群内索引、别名和经过安全过滤的基本属性，不返回 SteamID 或密钥。
+`/人物列表` 每页五人。真实人物资料仍只存放于 `~/.config/jwebot/`，
+仓库没有生产人物或映射文件。
+
+昵称识别不是账号身份认证。修改 canonical_name 会改变当前人物作用域；
+应优先追加别名而不是重命名。除 `/转账` 外，用户不能通过游戏命令
+指定他人的账户；转账只支持同群虚拟金币账户，收款人需先发送 `/金币`
+初始化。`/贷款` 和 `/还款` 只作用于本人账户。虚拟金币不能充值、
+赠币或兑换真实资产。
+
+## 虚拟金币与游戏管理
+
+每个群内人物首次使用账户时一次性获得 1000 虚拟金币。再次查询、
+重启服务或切换已配置别名都不会重复领取。抽奖下注为 2～100，彩票和
+21 点下注为 1～500；余额不足或参数非法不扣款。
+
+`/转账 对方 金额` 会把本人的虚拟金币转给同群已初始化账户，英文为
+`/transfer name amount`。金额范围 1～100000；不允许给自己转账。
+转账、响应记录和重试去重写在同一个 ledger 事务内，同一 event_id
+不会重复扣款。
+
+`/贷款 [金额]` 会给本人账户借入 1～500 金币；同一账户同一时间最多
+一笔未还贷款。`/还款 [金额|全部]` 从当前金币余额中扣除并减少未还
+贷款，借款、还款、响应记录和重试去重同样写在一个 ledger 事务内。
+
+`/大富翁榜` 或 `/金币排行 [人数]` 只读取当前群已有金币账户，不会创建
+调用者账户。榜单按当前金币余额降序排列，人数范围 1～20；账户存在
+未还贷款时会在名字后标注贷款本金。
+
+抽奖默认下注 10：5% 概率返还五倍下注，20% 返还两倍，其余无返还。
+alpha 0.6.3 将旧的个人即时彩票替换为群内多人轮次。三位数字顺序无关，
+下注范围 1～500，命中 1/2/3 个分别返还 50%/120%/300%。完整流程见
+[多人彩票与游戏记录](group-lottery-0.6.3.md)。
+
+21 点默认下注 50、范围 1～500。`/21点 开始 100` 表示拿 100 金币作为本局下注进场，
+等价的 OCR 紧凑形式是 `/21点开始100`。开局会扣除下注并发两张牌，
+然后根据牌面单独发送 `/21点 要牌` 或 `/21点 停牌`；开局与操作写在
+同一条消息时不会扣款，而会返回分步提示。牌局使用洗牌后的单副 52 张牌，
+牌堆、双方手牌、下注和最后操作时间持久化。A 可作为 1 或 11；
+庄家软 17 停牌。开始后只公开一张庄家牌；要牌、停牌、认输和查询都
+仅针对本人牌局。发牌、状态和结算回复以当前群内人物的配置展示名开头，
+例如 `jacky #1：你的牌 ...`；别名解析到同一人物时沿用相同展示名、
+账户、局号和游戏记录。
+
+多人 21 点使用 `/21点 多人 启动` 创建 Taffy 牌桌，开桌者自动入座。
+其他玩家在下注前用 `/21点 加入` 进入当前牌桌；主持人发送 `/21点 多人 开始`
+后，Taffy 会按座位顺序提示每个人 `/21点 放200` 放筹码，范围 1～10000。
+所有玩家下注后统一发牌，轮到本人时用 `/21点 要牌` 或 `/21点 停牌` 操作；
+结算按座位顺序列出每个人的下注、返还、净变化和当前金币。
+自然 21 点立即结算，返还 2.5 倍下注向下取整；普通胜利返还两倍，
+平局返还下注，失败不返还。每人最多一局；牌局进行中不接受另一笔
+抽奖或 21 点开局，多人彩票报名仍可独立进行。
+
+十分钟无有效游戏操作的牌局在下一次账户操作时按认输结束；查询状态
+不延长有效期。主动结束同样按认输处理，不退下注。其他人可以各自
+独立玩，不能加入或结束你的牌局。旧的群游戏保持独立。
+
+Kernel 用一个 `BEGIN IMMEDIATE` 事务同时保存：
+
+1. `player_accounts` 中的金币、牌局和胜负统计；
+2. `player_actions` 中的事件、命令及响应。
+
+同一群中的同一 event_id 只结算一次，重试返回原响应。相同事件若变更
+人物或命令则拒绝。事务失败全部回滚，避免扣款后丢失结果。新的独立
+指令会创建新的游戏操作，即使文字相同也不会被当成重试。
+数据库迁移仅新增表，旧版本可以忽略它们；运行文件回滚不会主动删除
+游戏数据。使用协调部署器回滚整库时，以部署前已验证备份为恢复基线。
+
+## 单条消息抓取修复
+
+独立观察证据表明，新气泡完成绘制后有时没有对应的有效 XDamage
+事件；先前截图仍是旧布局，后续消息的绘制才唤醒生产抓取。
+
+保留 XDamage 快速路径，同时将无有效变化时的复核等待窗口缩短到两秒。
+空闲超时后走相同截图、跟随最新消息、视觉哈希和缓冲去重流程。
+画面没变化时不进入重复 OCR；最终绘制漏事件时也能补抓。等待 X socket
+前先检查 Xlib 已缓冲事件，避免用户态已有事件却阻塞等待另一次通知。
+
+新增 `source=reconcile` 遥测用于识别补抓路径。两秒是等待窗口，
+不是端到端响应承诺；截图、OCR、生成和 GUI 投递仍有各自耗时。
+短周期复核增加空闲截图开销，上线后需观测实际负载。
+群指纹、窗口就绪、GUI 串行、视觉确认和投递去重规则保持有效。
@@ -1,6 +1,6 @@
 # Plugin Contract

-Status: authoritative for the `alpha 0.6.x` extension API.
+Status: authoritative for the `beta 1.0.x` extension API.

 ## Scope

@@ -6,9 +6,11 @@ exception.

 ## Release Discipline

- Version format is `alpha X.Y.Z.MMDD`.
- Patch changes increment `Z`; minor version changes require explicit user
-  approval.
+- Version format is `beta X.Y.Z.MMDD` for current beta releases.
+- Python package versions use the matching PEP 440 beta form, such as
+  `X.Y.Zb1+MMDD`.
+- Patch changes increment `Z`; minor, major, or stable-release changes require
+  explicit user approval.
 - A release change must update:
  - `VERSION`;
  - root `pyproject.toml`;
@@ -1,6 +1,6 @@
 # Runtime Telemetry And ACK Semantics

-Status: local instrumentation contract for `alpha 0.6.x`.
+Status: local instrumentation contract for `beta 1.0.x`.

 ## What ACK Means

@@ -1,20 +1,24 @@
 # Versioning

-JWeBot uses an alpha version string:
+JWeBot uses a human-readable product version string:

 ```text
-alpha X.Y.Z.MMDD
+beta X.Y.Z.MMDD
 ```

 Rules:

- `alpha` means the public API and deployment process may still change.
+- `beta` means the project has passed the local, staging, privacy, and
+  production-safety gates expected for wider testing, while still allowing
+  controlled breaking changes before a stable release.
 - `X.Y.Z` is the project version.
 - `MMDD` is the delivery date.
+- Python package versions use PEP 440 pre-release form. For beta builds,
+  `beta 1.0.1.1016` maps to `1.0.1b1+1016`.
 - Normal small updates increment only the patch version, for example
-  `alpha 0.0.1.1014` to `alpha 0.0.2.1014`.
- Minor versions such as `0.1.x` require explicit user review and milestone
-  approval.
+  `beta 1.0.1.1016` to `beta 1.0.2.1016`.
+- Minor, major, or stable-release changes require explicit user review and
+  milestone approval.
 - Local repository migration does not imply a production deployment.
 - Production services must not be changed unless the operator explicitly asks
  for deployment or runtime verification.
@@ -0,0 +1,22 @@
+# coin-loan
+
+Author: `jwebot`
+
+贷款
+
+Help:
+
+- `/贷款；/还款`
+
+Registered commands:
+
+- `/贷款`
+- `/借款`
+- `/loan`
+- `/borrow`
+- `/还款`
+- `/repay`
+
+The adapter has no direct Ledger, GUI, environment, shell, or network access.
+It delegates to the reviewed `coin-loan` Kernel service profile
+and returns a structured `ReplyPlan`.
@@ -0,0 +1,14 @@
+id = "coin-loan"
+author = "jwebot"
+description = "贷款"
+help = ["/贷款；/还款"]
+version = "1.0.0"
+api_version = "1"
+entrypoint = "coin_loan:plugin"
+type = "command"
+
+[capabilities]
+commands = ["/贷款", "/借款", "/loan", "/borrow", "/还款", "/repay"]
+storage = false
+network_profiles = []
+service_profiles = ["coin-loan"]
@@ -0,0 +1,45 @@
+"""Generated reviewed adapter for coin-loan."""
+
+from jwebot_sdk import Event, ExtensionResult, ReplyPlan, SingleGroupContext
+
+
+PROFILE = 'coin-loan'
+AUTHOR = 'jwebot'
+DESCRIPTION = '贷款'
+HELP_ENTRIES = ('/贷款；/还款',)
+COMMANDS = ('/贷款', '/借款', '/loan', '/borrow', '/还款', '/repay')
+
+
+def _handler(context: SingleGroupContext, command: str):
+    def handle(event: Event, arguments: str) -> ExtensionResult:
+        response = context.services.call(
+            PROFILE,
+            operation="execute",
+            payload={
+                "command": command,
+                "arguments": arguments,
+                "event": event.to_mapping(),
+            },
+        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
+        text = response.get("text")
+        if not isinstance(text, str) or not text.strip():
+            raise ValueError("local service returned invalid text")
+        return ExtensionResult(
+            reply=ReplyPlan.text(text),
+            metadata={"local_extension": PROFILE, "author": AUTHOR},
+        )
+
+    return handle
+
+
+def plugin(context: SingleGroupContext) -> None:
+    for command in COMMANDS:
+        context.commands.register(command, _handler(context, command))
@@ -0,0 +1,29 @@
+import sys
+import unittest
+from pathlib import Path
+from unittest import mock
+
+
+SOURCE = Path(__file__).resolve().parents[1] / "src"
+sys.path.insert(0, str(SOURCE))
+
+from coin_loan import AUTHOR, DESCRIPTION, HELP_ENTRIES, plugin
+
+
+class PluginTests(unittest.TestCase):
+    def test_registers_declared_commands_and_author(self):
+        context = mock.Mock()
+        plugin(context)
+        registered = [
+            call.args[0]
+            for call in context.commands.register.call_args_list
+        ]
+        self.assertEqual(AUTHOR, 'jwebot')
+        self.assertEqual(DESCRIPTION, '贷款')
+        self.assertEqual(HELP_ENTRIES, ('/贷款；/还款',))
+        self.assertIn('/贷款', registered)
+        self.assertEqual(len(registered), 6)
+
+
+if __name__ == "__main__":
+    unittest.main()
@@ -0,0 +1,20 @@
+# coin-ranking
+
+Author: `jwebot`
+
+富榜
+
+Help:
+
+- `/大富翁榜`
+
+Registered commands:
+
+- `/金币排行`
+- `/金币排行榜`
+- `/大富翁榜`
+- `/richlist`
+
+The adapter has no direct Ledger, GUI, environment, shell, or network access.
+It delegates to the reviewed `coin-ranking` Kernel service profile
+and returns a structured `ReplyPlan`.
@@ -0,0 +1,14 @@
+id = "coin-ranking"
+author = "jwebot"
+description = "富榜"
+help = ["/大富翁榜"]
+version = "1.0.0"
+api_version = "1"
+entrypoint = "coin_ranking:plugin"
+type = "command"
+
+[capabilities]
+commands = ["/金币排行", "/金币排行榜", "/大富翁榜", "/richlist"]
+storage = false
+network_profiles = []
+service_profiles = ["coin-ranking"]
@@ -0,0 +1,45 @@
+"""Generated reviewed adapter for coin-ranking."""
+
+from jwebot_sdk import Event, ExtensionResult, ReplyPlan, SingleGroupContext
+
+
+PROFILE = 'coin-ranking'
+AUTHOR = 'jwebot'
+DESCRIPTION = '富榜'
+HELP_ENTRIES = ('/大富翁榜',)
+COMMANDS = ('/金币排行', '/金币排行榜', '/大富翁榜', '/richlist')
+
+
+def _handler(context: SingleGroupContext, command: str):
+    def handle(event: Event, arguments: str) -> ExtensionResult:
+        response = context.services.call(
+            PROFILE,
+            operation="execute",
+            payload={
+                "command": command,
+                "arguments": arguments,
+                "event": event.to_mapping(),
+            },
+        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
+        text = response.get("text")
+        if not isinstance(text, str) or not text.strip():
+            raise ValueError("local service returned invalid text")
+        return ExtensionResult(
+            reply=ReplyPlan.text(text),
+            metadata={"local_extension": PROFILE, "author": AUTHOR},
+        )
+
+    return handle
+
+
+def plugin(context: SingleGroupContext) -> None:
+    for command in COMMANDS:
+        context.commands.register(command, _handler(context, command))
@@ -0,0 +1,29 @@
+import sys
+import unittest
+from pathlib import Path
+from unittest import mock
+
+
+SOURCE = Path(__file__).resolve().parents[1] / "src"
+sys.path.insert(0, str(SOURCE))
+
+from coin_ranking import AUTHOR, DESCRIPTION, HELP_ENTRIES, plugin
+
+
+class PluginTests(unittest.TestCase):
+    def test_registers_declared_commands_and_author(self):
+        context = mock.Mock()
+        plugin(context)
+        registered = [
+            call.args[0]
+            for call in context.commands.register.call_args_list
+        ]
+        self.assertEqual(AUTHOR, 'jwebot')
+        self.assertEqual(DESCRIPTION, '富榜')
+        self.assertEqual(HELP_ENTRIES, ('/大富翁榜',))
+        self.assertIn('/金币排行', registered)
+        self.assertEqual(len(registered), 4)
+
+
+if __name__ == "__main__":
+    unittest.main()
@@ -0,0 +1,18 @@
+# coin-taffy
+
+Author: `jwebot`
+
+Taffy金币
+
+Help:
+
+- `/Taffy金币`
+
+Registered commands:
+
+- `/Taffy金币`
+- `/taffycoins`
+
+The adapter has no direct Ledger, GUI, environment, shell, or network access.
+It delegates to the reviewed `coin-taffy` Kernel service profile
+and returns a structured `ReplyPlan`.
@@ -0,0 +1,14 @@
+id = "coin-taffy"
+author = "jwebot"
+description = "Taffy金币"
+help = ["/Taffy金币"]
+version = "1.0.0"
+api_version = "1"
+entrypoint = "coin_taffy:plugin"
+type = "command"
+
+[capabilities]
+commands = ["/Taffy金币", "/taffycoins"]
+storage = false
+network_profiles = []
+service_profiles = ["coin-taffy"]
@@ -0,0 +1,45 @@
+"""Generated reviewed adapter for coin-taffy."""
+
+from jwebot_sdk import Event, ExtensionResult, ReplyPlan, SingleGroupContext
+
+
+PROFILE = 'coin-taffy'
+AUTHOR = 'jwebot'
+DESCRIPTION = 'Taffy金币'
+HELP_ENTRIES = ('/Taffy金币',)
+COMMANDS = ('/Taffy金币', '/taffycoins')
+
+
+def _handler(context: SingleGroupContext, command: str):
+    def handle(event: Event, arguments: str) -> ExtensionResult:
+        response = context.services.call(
+            PROFILE,
+            operation="execute",
+            payload={
+                "command": command,
+                "arguments": arguments,
+                "event": event.to_mapping(),
+            },
+        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
+        text = response.get("text")
+        if not isinstance(text, str) or not text.strip():
+            raise ValueError("local service returned invalid text")
+        return ExtensionResult(
+            reply=ReplyPlan.text(text),
+            metadata={"local_extension": PROFILE, "author": AUTHOR},
+        )
+
+    return handle
+
+
+def plugin(context: SingleGroupContext) -> None:
+    for command in COMMANDS:
+        context.commands.register(command, _handler(context, command))
@@ -0,0 +1,29 @@
+import sys
+import unittest
+from pathlib import Path
+from unittest import mock
+
+
+SOURCE = Path(__file__).resolve().parents[1] / "src"
+sys.path.insert(0, str(SOURCE))
+
+from coin_taffy import AUTHOR, DESCRIPTION, HELP_ENTRIES, plugin
+
+
+class PluginTests(unittest.TestCase):
+    def test_registers_declared_commands_and_author(self):
+        context = mock.Mock()
+        plugin(context)
+        registered = [
+            call.args[0]
+            for call in context.commands.register.call_args_list
+        ]
+        self.assertEqual(AUTHOR, 'jwebot')
+        self.assertEqual(DESCRIPTION, 'Taffy金币')
+        self.assertEqual(HELP_ENTRIES, ('/Taffy金币',))
+        self.assertIn('/Taffy金币', registered)
+        self.assertEqual(len(registered), 2)
+
+
+if __name__ == "__main__":
+    unittest.main()
@@ -0,0 +1,18 @@
+# coin-transfer
+
+Author: `jwebot`
+
+金币转账
+
+Help:
+
+- `/转账 对方 金额；/transfer`
+
+Registered commands:
+
+- `/转账`
+- `/transfer`
+
+The adapter has no direct Ledger, GUI, environment, shell, or network access.
+It delegates to the reviewed `coin-transfer` Kernel service profile
+and returns a structured `ReplyPlan`.
@@ -0,0 +1,14 @@
+id = "coin-transfer"
+author = "jwebot"
+description = "金币转账"
+help = ["/转账 对方 金额；/transfer"]
+version = "1.0.0"
+api_version = "1"
+entrypoint = "coin_transfer:plugin"
+type = "command"
+
+[capabilities]
+commands = ["/转账", "/transfer"]
+storage = false
+network_profiles = []
+service_profiles = ["coin-transfer"]
@@ -0,0 +1,45 @@
+"""Generated reviewed adapter for coin-transfer."""
+
+from jwebot_sdk import Event, ExtensionResult, ReplyPlan, SingleGroupContext
+
+
+PROFILE = 'coin-transfer'
+AUTHOR = 'jwebot'
+DESCRIPTION = '金币转账'
+HELP_ENTRIES = ('/转账 对方 金额；/transfer',)
+COMMANDS = ('/转账', '/transfer')
+
+
+def _handler(context: SingleGroupContext, command: str):
+    def handle(event: Event, arguments: str) -> ExtensionResult:
+        response = context.services.call(
+            PROFILE,
+            operation="execute",
+            payload={
+                "command": command,
+                "arguments": arguments,
+                "event": event.to_mapping(),
+            },
+        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
+        text = response.get("text")
+        if not isinstance(text, str) or not text.strip():
+            raise ValueError("local service returned invalid text")
+        return ExtensionResult(
+            reply=ReplyPlan.text(text),
+            metadata={"local_extension": PROFILE, "author": AUTHOR},
+        )
+
+    return handle
+
+
+def plugin(context: SingleGroupContext) -> None:
+    for command in COMMANDS:
+        context.commands.register(command, _handler(context, command))
@@ -0,0 +1,29 @@
+import sys
+import unittest
+from pathlib import Path
+from unittest import mock
+
+
+SOURCE = Path(__file__).resolve().parents[1] / "src"
+sys.path.insert(0, str(SOURCE))
+
+from coin_transfer import AUTHOR, DESCRIPTION, HELP_ENTRIES, plugin
+
+
+class PluginTests(unittest.TestCase):
+    def test_registers_declared_commands_and_author(self):
+        context = mock.Mock()
+        plugin(context)
+        registered = [
+            call.args[0]
+            for call in context.commands.register.call_args_list
+        ]
+        self.assertEqual(AUTHOR, 'jwebot')
+        self.assertEqual(DESCRIPTION, '金币转账')
+        self.assertEqual(HELP_ENTRIES, ('/转账 对方 金额；/transfer',))
+        self.assertIn('/转账', registered)
+        self.assertEqual(len(registered), 2)
+
+
+if __name__ == "__main__":
+    unittest.main()
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -0,0 +1,30 @@
+# cs-major-autochess
+
+Author: `jwebot`
+
+自走棋
+
+Help:
+
+- `/自走棋 开始|报名|选`
+
+Registered commands:
+
+- `/自走棋`
+- `/cs自走棋`
+- `/autochess`
+- `/选`
+- `/刷新`
+- `/锁定`
+- `/战术`
+- `/升级教练`
+- `/上阵`
+- `/下阵`
+- `/出售`
+- `/阵容`
+- `/赛程`
+- `/结束回合`
+
+The adapter has no direct Ledger, GUI, environment, shell, or network access.
+It delegates to the reviewed `cs-major-autochess` Kernel service profile
+and returns a structured `ReplyPlan`.
@@ -0,0 +1,14 @@
+id = "cs-major-autochess"
+author = "jwebot"
+description = "自走棋"
+help = ["/自走棋 开始|报名|选"]
+version = "1.0.0"
+api_version = "1"
+entrypoint = "cs_major_autochess:plugin"
+type = "command"
+
+[capabilities]
+commands = ["/自走棋", "/cs自走棋", "/autochess", "/选", "/刷新", "/锁定", "/战术", "/升级教练", "/上阵", "/下阵", "/出售", "/阵容", "/赛程", "/结束回合"]
+storage = false
+network_profiles = []
+service_profiles = ["cs-major-autochess"]
@@ -0,0 +1,45 @@
+"""Generated reviewed adapter for cs-major-autochess."""
+
+from jwebot_sdk import Event, ExtensionResult, ReplyPlan, SingleGroupContext
+
+
+PROFILE = 'cs-major-autochess'
+AUTHOR = 'jwebot'
+DESCRIPTION = '自走棋'
+HELP_ENTRIES = ('/自走棋 开始|报名|选',)
+COMMANDS = ('/自走棋', '/cs自走棋', '/autochess', '/选', '/刷新', '/锁定', '/战术', '/升级教练', '/上阵', '/下阵', '/出售', '/阵容', '/赛程', '/结束回合')
+
+
+def _handler(context: SingleGroupContext, command: str):
+    def handle(event: Event, arguments: str) -> ExtensionResult:
+        response = context.services.call(
+            PROFILE,
+            operation="execute",
+            payload={
+                "command": command,
+                "arguments": arguments,
+                "event": event.to_mapping(),
+            },
+        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
+        text = response.get("text")
+        if not isinstance(text, str) or not text.strip():
+            raise ValueError("local service returned invalid text")
+        return ExtensionResult(
+            reply=ReplyPlan.text(text),
+            metadata={"local_extension": PROFILE, "author": AUTHOR},
+        )
+
+    return handle
+
+
+def plugin(context: SingleGroupContext) -> None:
+    for command in COMMANDS:
+        context.commands.register(command, _handler(context, command))
@@ -0,0 +1,29 @@
+import sys
+import unittest
+from pathlib import Path
+from unittest import mock
+
+
+SOURCE = Path(__file__).resolve().parents[1] / "src"
+sys.path.insert(0, str(SOURCE))
+
+from cs_major_autochess import AUTHOR, DESCRIPTION, HELP_ENTRIES, plugin
+
+
+class PluginTests(unittest.TestCase):
+    def test_registers_declared_commands_and_author(self):
+        context = mock.Mock()
+        plugin(context)
+        registered = [
+            call.args[0]
+            for call in context.commands.register.call_args_list
+        ]
+        self.assertEqual(AUTHOR, 'jwebot')
+        self.assertEqual(DESCRIPTION, '自走棋')
+        self.assertEqual(HELP_ENTRIES, ('/自走棋 开始|报名|选',))
+        self.assertIn('/自走棋', registered)
+        self.assertEqual(len(registered), 14)
+
+
+if __name__ == "__main__":
+    unittest.main()
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -0,0 +1,35 @@
+# single-player-games
+
+Author: `jwebot`
+
+金币游戏
+
+Help:
+
+- `/金币 /wallet；/游戏记录 /gamehistory`
+- `/抽奖 [金额]；/draw`
+- `/彩票 开始|报名|状态|开奖|取消；/lottery`
+- `/21点 单人开始|要牌|停牌|状态；多人启动|加入|开始|放200`
+- `/游戏帮助；/games`
+
+Registered commands:
+
+- `/金币`
+- `/wallet`
+- `/抽奖`
+- `/draw`
+- `/彩票`
+- `/买彩票`
+- `/lottery`
+- `/21点`
+- `/二十一点`
+- `/blackjack`
+- `/游戏记录`
+- `/个人记录`
+- `/gamehistory`
+- `/游戏帮助`
+- `/games`
+
+The adapter has no direct Ledger, GUI, environment, shell, or network access.
+It delegates to the reviewed `single-player-games` Kernel service profile
+and returns a structured `ReplyPlan`.
@@ -0,0 +1,14 @@
+id = "single-player-games"
+author = "jwebot"
+description = "金币游戏"
+help = ["/金币 /wallet；/游戏记录 /gamehistory", "/抽奖 [金额]；/draw", "/彩票 开始|报名|状态|开奖|取消；/lottery", "/21点 单人开始|要牌|停牌|状态；多人启动|加入|开始|放200", "/游戏帮助；/games"]
+version = "1.0.0"
+api_version = "1"
+entrypoint = "single_player_games:plugin"
+type = "command"
+
+[capabilities]
+commands = ["/金币", "/wallet", "/抽奖", "/draw", "/彩票", "/买彩票", "/lottery", "/21点", "/二十一点", "/blackjack", "/游戏记录", "/个人记录", "/gamehistory", "/游戏帮助", "/games"]
+storage = false
+network_profiles = []
+service_profiles = ["single-player-games"]
@@ -0,0 +1,45 @@
+"""Generated reviewed adapter for single-player-games."""
+
+from jwebot_sdk import Event, ExtensionResult, ReplyPlan, SingleGroupContext
+
+
+PROFILE = 'single-player-games'
+AUTHOR = 'jwebot'
+DESCRIPTION = '金币游戏'
+HELP_ENTRIES = ('/金币 /wallet；/游戏记录 /gamehistory', '/抽奖 [金额]；/draw', '/彩票 开始|报名|状态|开奖|取消；/lottery', '/21点 单人开始|要牌|停牌|状态；多人启动|加入|开始|放200', '/游戏帮助；/games')
+COMMANDS = ('/金币', '/wallet', '/抽奖', '/draw', '/彩票', '/买彩票', '/lottery', '/21点', '/二十一点', '/blackjack', '/游戏记录', '/个人记录', '/gamehistory', '/游戏帮助', '/games')
+
+
+def _handler(context: SingleGroupContext, command: str):
+    def handle(event: Event, arguments: str) -> ExtensionResult:
+        response = context.services.call(
+            PROFILE,
+            operation="execute",
+            payload={
+                "command": command,
+                "arguments": arguments,
+                "event": event.to_mapping(),
+            },
+        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
+        text = response.get("text")
+        if not isinstance(text, str) or not text.strip():
+            raise ValueError("local service returned invalid text")
+        return ExtensionResult(
+            reply=ReplyPlan.text(text),
+            metadata={"local_extension": PROFILE, "author": AUTHOR},
+        )
+
+    return handle
+
+
+def plugin(context: SingleGroupContext) -> None:
+    for command in COMMANDS:
+        context.commands.register(command, _handler(context, command))
@@ -0,0 +1,29 @@
+import sys
+import unittest
+from pathlib import Path
+from unittest import mock
+
+
+SOURCE = Path(__file__).resolve().parents[1] / "src"
+sys.path.insert(0, str(SOURCE))
+
+from single_player_games import AUTHOR, DESCRIPTION, HELP_ENTRIES, plugin
+
+
+class PluginTests(unittest.TestCase):
+    def test_registers_declared_commands_and_author(self):
+        context = mock.Mock()
+        plugin(context)
+        registered = [
+            call.args[0]
+            for call in context.commands.register.call_args_list
+        ]
+        self.assertEqual(AUTHOR, 'jwebot')
+        self.assertEqual(DESCRIPTION, '金币游戏')
+        self.assertEqual(HELP_ENTRIES, ('/金币 /wallet；/游戏记录 /gamehistory', '/抽奖 [金额]；/draw', '/彩票 开始|报名|状态|开奖|取消；/lottery', '/21点 单人开始|要牌|停牌|状态；多人启动|加入|开始|放200', '/游戏帮助；/games'))
+        self.assertIn('/金币', registered)
+        self.assertEqual(len(registered), 15)
+
+
+if __name__ == "__main__":
+    unittest.main()
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -0,0 +1,18 @@
+# context-summary
+
+Author: `official`
+
+上下文总结
+
+Help:
+
+- `/上下文 [100|200|300]；/context [100|200|300]`
+
+Registered commands:
+
+- `/上下文`
+- `/context`
+
+The adapter has no direct Ledger, GUI, environment, shell, or network access.
+It delegates to the reviewed `context-summary` Kernel service profile
+and returns a structured `ReplyPlan`.
@@ -0,0 +1,14 @@
+id = "context-summary"
+author = "official"
+description = "上下文总结"
+help = ["/上下文 [100|200|300]；/context [100|200|300]"]
+version = "1.0.0"
+api_version = "1"
+entrypoint = "context_summary:plugin"
+type = "command"
+
+[capabilities]
+commands = ["/上下文", "/context"]
+storage = false
+network_profiles = []
+service_profiles = ["context-summary"]
@@ -0,0 +1,45 @@
+"""Generated reviewed adapter for context-summary."""
+
+from jwebot_sdk import Event, ExtensionResult, ReplyPlan, SingleGroupContext
+
+
+PROFILE = 'context-summary'
+AUTHOR = 'official'
+DESCRIPTION = '上下文总结'
+HELP_ENTRIES = ('/上下文 [100|200|300]；/context [100|200|300]',)
+COMMANDS = ('/上下文', '/context')
+
+
+def _handler(context: SingleGroupContext, command: str):
+    def handle(event: Event, arguments: str) -> ExtensionResult:
+        response = context.services.call(
+            PROFILE,
+            operation="execute",
+            payload={
+                "command": command,
+                "arguments": arguments,
+                "event": event.to_mapping(),
+            },
+        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
+        text = response.get("text")
+        if not isinstance(text, str) or not text.strip():
+            raise ValueError("local service returned invalid text")
+        return ExtensionResult(
+            reply=ReplyPlan.text(text),
+            metadata={"local_extension": PROFILE, "author": AUTHOR},
+        )
+
+    return handle
+
+
+def plugin(context: SingleGroupContext) -> None:
+    for command in COMMANDS:
+        context.commands.register(command, _handler(context, command))
@@ -0,0 +1,29 @@
+import sys
+import unittest
+from pathlib import Path
+from unittest import mock
+
+
+SOURCE = Path(__file__).resolve().parents[1] / "src"
+sys.path.insert(0, str(SOURCE))
+
+from context_summary import AUTHOR, DESCRIPTION, HELP_ENTRIES, plugin
+
+
+class PluginTests(unittest.TestCase):
+    def test_registers_declared_commands_and_author(self):
+        context = mock.Mock()
+        plugin(context)
+        registered = [
+            call.args[0]
+            for call in context.commands.register.call_args_list
+        ]
+        self.assertEqual(AUTHOR, 'official')
+        self.assertEqual(DESCRIPTION, '上下文总结')
+        self.assertEqual(HELP_ENTRIES, ('/上下文 [100|200|300]；/context [100|200|300]',))
+        self.assertIn('/上下文', registered)
+        self.assertEqual(len(registered), 2)
+
+
+if __name__ == "__main__":
+    unittest.main()
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -0,0 +1,22 @@
+# person-directory
+
+Author: `official`
+
+查询当前群已配置人物、基本属性和别名
+
+Help:
+
+- `/人物列表 [页码] /people；/人物 [名称或别名] /person`
+
+Registered commands:
+
+- `/人物列表`
+- `/别名列表`
+- `/people`
+- `/人物`
+- `/个人属性`
+- `/person`
+
+The adapter has no direct Ledger, GUI, environment, shell, or network access.
+It delegates to the reviewed `person-directory` Kernel service profile
+and returns a structured `ReplyPlan`.
@@ -0,0 +1,14 @@
+id = "person-directory"
+author = "official"
+description = "查询当前群已配置人物、基本属性和别名"
+help = ["/人物列表 [页码] /people；/人物 [名称或别名] /person"]
+version = "1.0.0"
+api_version = "1"
+entrypoint = "person_directory:plugin"
+type = "command"
+
+[capabilities]
+commands = ["/人物列表", "/别名列表", "/people", "/人物", "/个人属性", "/person"]
+storage = false
+network_profiles = []
+service_profiles = ["person-directory"]
@@ -0,0 +1,45 @@
+"""Generated reviewed adapter for person-directory."""
+
+from jwebot_sdk import Event, ExtensionResult, ReplyPlan, SingleGroupContext
+
+
+PROFILE = 'person-directory'
+AUTHOR = 'official'
+DESCRIPTION = '查询当前群已配置人物、基本属性和别名'
+HELP_ENTRIES = ('/人物列表 [页码] /people；/人物 [名称或别名] /person',)
+COMMANDS = ('/人物列表', '/别名列表', '/people', '/人物', '/个人属性', '/person')
+
+
+def _handler(context: SingleGroupContext, command: str):
+    def handle(event: Event, arguments: str) -> ExtensionResult:
+        response = context.services.call(
+            PROFILE,
+            operation="execute",
+            payload={
+                "command": command,
+                "arguments": arguments,
+                "event": event.to_mapping(),
+            },
+        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
+        text = response.get("text")
+        if not isinstance(text, str) or not text.strip():
+            raise ValueError("local service returned invalid text")
+        return ExtensionResult(
+            reply=ReplyPlan.text(text),
+            metadata={"local_extension": PROFILE, "author": AUTHOR},
+        )
+
+    return handle
+
+
+def plugin(context: SingleGroupContext) -> None:
+    for command in COMMANDS:
+        context.commands.register(command, _handler(context, command))
@@ -0,0 +1,29 @@
+import sys
+import unittest
+from pathlib import Path
+from unittest import mock
+
+
+SOURCE = Path(__file__).resolve().parents[1] / "src"
+sys.path.insert(0, str(SOURCE))
+
+from person_directory import AUTHOR, DESCRIPTION, HELP_ENTRIES, plugin
+
+
+class PluginTests(unittest.TestCase):
+    def test_registers_declared_commands_and_author(self):
+        context = mock.Mock()
+        plugin(context)
+        registered = [
+            call.args[0]
+            for call in context.commands.register.call_args_list
+        ]
+        self.assertEqual(AUTHOR, 'official')
+        self.assertEqual(DESCRIPTION, '查询当前群已配置人物、基本属性和别名')
+        self.assertEqual(HELP_ENTRIES, ('/人物列表 [页码] /people；/人物 [名称或别名] /person',))
+        self.assertIn('/人物列表', registered)
+        self.assertEqual(len(registered), 6)
+
+
+if __name__ == "__main__":
+    unittest.main()
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"

 [project]
 name = "jwebot-config"
-version = "0.6.0a0+1015"
+version = "1.0.2b1+1016"
 description = "Profile-based configuration compiler for JWeBot"
 requires-python = ">=3.9"
 dependencies = [
@@ -36,4 +36,4 @@ __all__ = [
    "write_default_profile",
 ]

-__version__ = "0.6.0a0+1015"
+__version__ = "1.0.2b1+1016"
@@ -4,12 +4,12 @@ build-backend = "setuptools.build_meta"

 [project]
 name = "jwebot-extension-host"
-version = "0.6.0a0+1015"
+version = "1.0.2b1+1016"
 description = "Single-release, single-invocation process host for JWeBot extensions"
 requires-python = ">=3.9"
 dependencies = [
-  "jwebot-sdk==0.6.0a0+1015",
-  "jwebot-kernel==0.6.0a0+1015",
+  "jwebot-sdk==1.0.2b1+1016",
+  "jwebot-kernel==1.0.2b1+1016",
 ]

 [project.scripts]
@@ -16,4 +16,4 @@ __all__ = [
    "process_request",
 ]

-__version__ = "0.6.0a0+1015"
+__version__ = "1.0.2b1+1016"
@@ -4,13 +4,13 @@ build-backend = "setuptools.build_meta"

 [project]
 name = "jwebot-kernel"
-version = "0.6.0a0+1015"
+version = "1.0.2b1+1016"
 description = "Stable routing and extension authority for JWeBot"
 requires-python = ">=3.9"
 dependencies = [
-  "jwebot-config==0.6.0a0+1015",
-  "jwebot-sdk==0.6.0a0+1015",
-  "jwebot-official-extensions==0.6.0a0+1015",
+  "jwebot-config==1.0.2b1+1016",
+  "jwebot-sdk==1.0.2b1+1016",
+  "jwebot-official-extensions==1.0.2b1+1016",
  "tomli>=2; python_version < '3.11'",
 ]

@@ -107,4 +107,4 @@ __all__ = [
    "verify_installed_release_signature",
 ]

-__version__ = "0.6.0a0+1015"
+__version__ = "1.0.2b1+1016"
@@ -4,12 +4,15 @@ build-backend = "setuptools.build_meta"

 [project]
 name = "jwebot-official-extensions"
-version = "0.6.0a0+1015"
+version = "1.0.2b1+1016"
 description = "Reviewed local command adapters and broker implementation for JWeBot"
 requires-python = ">=3.9"
 dependencies = [
-  "jwebot-sdk==0.6.0a0+1015",
+  "jwebot-sdk==1.0.2b1+1016",
 ]

 [tool.setuptools.packages.find]
 where = ["src"]
+
+[tool.setuptools.package-data]
+jwebot_official_extensions = ["data/cs_autochess/*.json"]
@@ -1,5 +1,18 @@
 """Reviewed JWeBot local command adapters and broker implementation."""

+from .cs_autochess import (
+    CARD_BY_ID,
+    COACH_BONUSES,
+    COACH_POOL,
+    MAX_PLAYERS,
+    MIN_PLAYERS,
+    PLAYER_POOL,
+    CsMajorAutochess,
+    build_round_plan,
+    lineup_power,
+    matchup_modifier,
+    parse_autochess_action,
+)
 from .descriptors import (
    DIRECT_KERNEL_COMMANDS,
    DIRECT_KERNEL_COMMAND_KINDS,
@@ -20,6 +33,8 @@ from .local_commands import (
    LocalCommandError,
    deterministic_int,
    local_command_parts,
+    pack_reply_parts,
+    unpack_reply_parts,
 )
 from .runtime import (
    LocalExtensionError,
@@ -35,6 +50,10 @@ from .steam import (
 )

 __all__ = [
+    "CARD_BY_ID",
+    "COACH_BONUSES",
+    "COACH_POOL",
+    "CsMajorAutochess",
    "DICE_CHALLENGE_TIMEOUT_SECONDS",
    "DEFAULT_STEAM_MIHOMO_PROXY_URL",
    "DIRECT_KERNEL_COMMANDS",
@@ -43,8 +62,12 @@ __all__ = [
    "LOCAL_COMMAND_ALIASES",
    "LOCAL_EXTENSIONS",
    "LOCAL_GAME_TIMEOUT_SECONDS",
+    "MAX_PLAYERS",
    "MAX_RPS_PLAYERS",
+    "MIN_PLAYERS",
    "OFFICIAL_AUTHOR",
+    "PLAYER_POOL",
+    "build_round_plan",
    "KernelCommandDescriptor",
    "LocalExtensionDescriptor",
    "LocalExtensionError",
@@ -58,8 +81,13 @@ __all__ = [
    "deterministic_int",
    "local_command_parts",
    "local_extension_command_token",
+    "lineup_power",
+    "matchup_modifier",
+    "pack_reply_parts",
+    "parse_autochess_action",
+    "unpack_reply_parts",
    "extension_for_kind",
    "render_feature_list",
 ]

-__version__ = "0.6.0a0+1015"
+__version__ = "1.0.2b1+1016"
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -0,0 +1,45 @@
+"""Generated reviewed adapter for coin-loan."""
+
+from jwebot_sdk import Event, ExtensionResult, ReplyPlan, SingleGroupContext
+
+
+PROFILE = 'coin-loan'
+AUTHOR = 'jwebot'
+DESCRIPTION = '贷款'
+HELP_ENTRIES = ('/贷款；/还款',)
+COMMANDS = ('/贷款', '/借款', '/loan', '/borrow', '/还款', '/repay')
+
+
+def _handler(context: SingleGroupContext, command: str):
+    def handle(event: Event, arguments: str) -> ExtensionResult:
+        response = context.services.call(
+            PROFILE,
+            operation="execute",
+            payload={
+                "command": command,
+                "arguments": arguments,
+                "event": event.to_mapping(),
+            },
+        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
+        text = response.get("text")
+        if not isinstance(text, str) or not text.strip():
+            raise ValueError("local service returned invalid text")
+        return ExtensionResult(
+            reply=ReplyPlan.text(text),
+            metadata={"local_extension": PROFILE, "author": AUTHOR},
+        )
+
+    return handle
+
+
+def plugin(context: SingleGroupContext) -> None:
+    for command in COMMANDS:
+        context.commands.register(command, _handler(context, command))
@@ -0,0 +1,45 @@
+"""Generated reviewed adapter for coin-ranking."""
+
+from jwebot_sdk import Event, ExtensionResult, ReplyPlan, SingleGroupContext
+
+
+PROFILE = 'coin-ranking'
+AUTHOR = 'jwebot'
+DESCRIPTION = '富榜'
+HELP_ENTRIES = ('/大富翁榜',)
+COMMANDS = ('/金币排行', '/金币排行榜', '/大富翁榜', '/richlist')
+
+
+def _handler(context: SingleGroupContext, command: str):
+    def handle(event: Event, arguments: str) -> ExtensionResult:
+        response = context.services.call(
+            PROFILE,
+            operation="execute",
+            payload={
+                "command": command,
+                "arguments": arguments,
+                "event": event.to_mapping(),
+            },
+        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
+        text = response.get("text")
+        if not isinstance(text, str) or not text.strip():
+            raise ValueError("local service returned invalid text")
+        return ExtensionResult(
+            reply=ReplyPlan.text(text),
+            metadata={"local_extension": PROFILE, "author": AUTHOR},
+        )
+
+    return handle
+
+
+def plugin(context: SingleGroupContext) -> None:
+    for command in COMMANDS:
+        context.commands.register(command, _handler(context, command))
@@ -0,0 +1,45 @@
+"""Generated reviewed adapter for coin-taffy."""
+
+from jwebot_sdk import Event, ExtensionResult, ReplyPlan, SingleGroupContext
+
+
+PROFILE = 'coin-taffy'
+AUTHOR = 'jwebot'
+DESCRIPTION = 'Taffy金币'
+HELP_ENTRIES = ('/Taffy金币',)
+COMMANDS = ('/Taffy金币', '/taffycoins')
+
+
+def _handler(context: SingleGroupContext, command: str):
+    def handle(event: Event, arguments: str) -> ExtensionResult:
+        response = context.services.call(
+            PROFILE,
+            operation="execute",
+            payload={
+                "command": command,
+                "arguments": arguments,
+                "event": event.to_mapping(),
+            },
+        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
+        text = response.get("text")
+        if not isinstance(text, str) or not text.strip():
+            raise ValueError("local service returned invalid text")
+        return ExtensionResult(
+            reply=ReplyPlan.text(text),
+            metadata={"local_extension": PROFILE, "author": AUTHOR},
+        )
+
+    return handle
+
+
+def plugin(context: SingleGroupContext) -> None:
+    for command in COMMANDS:
+        context.commands.register(command, _handler(context, command))
@@ -0,0 +1,45 @@
+"""Generated reviewed adapter for coin-transfer."""
+
+from jwebot_sdk import Event, ExtensionResult, ReplyPlan, SingleGroupContext
+
+
+PROFILE = 'coin-transfer'
+AUTHOR = 'jwebot'
+DESCRIPTION = '金币转账'
+HELP_ENTRIES = ('/转账 对方 金额；/transfer',)
+COMMANDS = ('/转账', '/transfer')
+
+
+def _handler(context: SingleGroupContext, command: str):
+    def handle(event: Event, arguments: str) -> ExtensionResult:
+        response = context.services.call(
+            PROFILE,
+            operation="execute",
+            payload={
+                "command": command,
+                "arguments": arguments,
+                "event": event.to_mapping(),
+            },
+        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
+        text = response.get("text")
+        if not isinstance(text, str) or not text.strip():
+            raise ValueError("local service returned invalid text")
+        return ExtensionResult(
+            reply=ReplyPlan.text(text),
+            metadata={"local_extension": PROFILE, "author": AUTHOR},
+        )
+
+    return handle
+
+
+def plugin(context: SingleGroupContext) -> None:
+    for command in COMMANDS:
+        context.commands.register(command, _handler(context, command))
@@ -0,0 +1,45 @@
+"""Generated reviewed adapter for context-summary."""
+
+from jwebot_sdk import Event, ExtensionResult, ReplyPlan, SingleGroupContext
+
+
+PROFILE = 'context-summary'
+AUTHOR = 'official'
+DESCRIPTION = '上下文总结'
+HELP_ENTRIES = ('/上下文 [100|200|300]；/context [100|200|300]',)
+COMMANDS = ('/上下文', '/context')
+
+
+def _handler(context: SingleGroupContext, command: str):
+    def handle(event: Event, arguments: str) -> ExtensionResult:
+        response = context.services.call(
+            PROFILE,
+            operation="execute",
+            payload={
+                "command": command,
+                "arguments": arguments,
+                "event": event.to_mapping(),
+            },
+        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
+        text = response.get("text")
+        if not isinstance(text, str) or not text.strip():
+            raise ValueError("local service returned invalid text")
+        return ExtensionResult(
+            reply=ReplyPlan.text(text),
+            metadata={"local_extension": PROFILE, "author": AUTHOR},
+        )
+
+    return handle
+
+
+def plugin(context: SingleGroupContext) -> None:
+    for command in COMMANDS:
+        context.commands.register(command, _handler(context, command))
@@ -0,0 +1,45 @@
+"""Generated reviewed adapter for cs-major-autochess."""
+
+from jwebot_sdk import Event, ExtensionResult, ReplyPlan, SingleGroupContext
+
+
+PROFILE = 'cs-major-autochess'
+AUTHOR = 'jwebot'
+DESCRIPTION = '自走棋'
+HELP_ENTRIES = ('/自走棋 开始|报名|选',)
+COMMANDS = ('/自走棋', '/cs自走棋', '/autochess', '/选', '/刷新', '/锁定', '/战术', '/升级教练', '/上阵', '/下阵', '/出售', '/阵容', '/赛程', '/结束回合')
+
+
+def _handler(context: SingleGroupContext, command: str):
+    def handle(event: Event, arguments: str) -> ExtensionResult:
+        response = context.services.call(
+            PROFILE,
+            operation="execute",
+            payload={
+                "command": command,
+                "arguments": arguments,
+                "event": event.to_mapping(),
+            },
+        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
+        text = response.get("text")
+        if not isinstance(text, str) or not text.strip():
+            raise ValueError("local service returned invalid text")
+        return ExtensionResult(
+            reply=ReplyPlan.text(text),
+            metadata={"local_extension": PROFILE, "author": AUTHOR},
+        )
+
+    return handle
+
+
+def plugin(context: SingleGroupContext) -> None:
+    for command in COMMANDS:
+        context.commands.register(command, _handler(context, command))
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -0,0 +1,45 @@
+"""Generated reviewed adapter for person-directory."""
+
+from jwebot_sdk import Event, ExtensionResult, ReplyPlan, SingleGroupContext
+
+
+PROFILE = 'person-directory'
+AUTHOR = 'official'
+DESCRIPTION = '查询当前群已配置人物、基本属性和别名'
+HELP_ENTRIES = ('/人物列表 [页码] /people；/人物 [名称或别名] /person',)
+COMMANDS = ('/人物列表', '/别名列表', '/people', '/人物', '/个人属性', '/person')
+
+
+def _handler(context: SingleGroupContext, command: str):
+    def handle(event: Event, arguments: str) -> ExtensionResult:
+        response = context.services.call(
+            PROFILE,
+            operation="execute",
+            payload={
+                "command": command,
+                "arguments": arguments,
+                "event": event.to_mapping(),
+            },
+        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
+        text = response.get("text")
+        if not isinstance(text, str) or not text.strip():
+            raise ValueError("local service returned invalid text")
+        return ExtensionResult(
+            reply=ReplyPlan.text(text),
+            metadata={"local_extension": PROFILE, "author": AUTHOR},
+        )
+
+    return handle
+
+
+def plugin(context: SingleGroupContext) -> None:
+    for command in COMMANDS:
+        context.commands.register(command, _handler(context, command))
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -0,0 +1,45 @@
+"""Generated reviewed adapter for single-player-games."""
+
+from jwebot_sdk import Event, ExtensionResult, ReplyPlan, SingleGroupContext
+
+
+PROFILE = 'single-player-games'
+AUTHOR = 'jwebot'
+DESCRIPTION = '金币游戏'
+HELP_ENTRIES = ('/金币 /wallet；/游戏记录 /gamehistory', '/抽奖 [金额]；/draw', '/彩票 开始|报名|状态|开奖|取消；/lottery', '/21点 单人开始|要牌|停牌|状态；多人启动|加入|开始|放200', '/游戏帮助；/games')
+COMMANDS = ('/金币', '/wallet', '/抽奖', '/draw', '/彩票', '/买彩票', '/lottery', '/21点', '/二十一点', '/blackjack', '/游戏记录', '/个人记录', '/gamehistory', '/游戏帮助', '/games')
+
+
+def _handler(context: SingleGroupContext, command: str):
+    def handle(event: Event, arguments: str) -> ExtensionResult:
+        response = context.services.call(
+            PROFILE,
+            operation="execute",
+            payload={
+                "command": command,
+                "arguments": arguments,
+                "event": event.to_mapping(),
+            },
+        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
+        text = response.get("text")
+        if not isinstance(text, str) or not text.strip():
+            raise ValueError("local service returned invalid text")
+        return ExtensionResult(
+            reply=ReplyPlan.text(text),
+            metadata={"local_extension": PROFILE, "author": AUTHOR},
+        )
+
+    return handle
+
+
+def plugin(context: SingleGroupContext) -> None:
+    for command in COMMANDS:
+        context.commands.register(command, _handler(context, command))
@@ -21,6 +21,14 @@ def _handler(context: SingleGroupContext, command: str):
                "event": event.to_mapping(),
            },
        )
+        texts = response.get("texts")
+        if isinstance(texts, list) and texts and all(
+            isinstance(item, str) and item.strip() for item in texts
+        ):
+            return ExtensionResult(
+                reply=ReplyPlan.multi_text(texts),
+                metadata={"local_extension": PROFILE, "author": AUTHOR},
+            )
        text = response.get("text")
        if not isinstance(text, str) or not text.strip():
            raise ValueError("local service returned invalid text")
@@ -0,0 +1,185 @@
+{
+  "coaches": [
+    {
+      "bonus": 9,
+      "clutch": 88,
+      "firepower": 78,
+      "id": "zonic",
+      "level": 5,
+      "name": "zonic",
+      "stability": 92,
+      "style": "冠军体系"
+    },
+    {
+      "bonus": 9,
+      "clutch": 84,
+      "firepower": 72,
+      "id": "blade",
+      "level": 5,
+      "name": "B1ad3",
+      "stability": 96,
+      "style": "结构控图"
+    },
+    {
+      "bonus": 8,
+      "clutch": 80,
+      "firepower": 86,
+      "id": "xtqzzz",
+      "level": 4,
+      "name": "XTQZZZ",
+      "stability": 78,
+      "style": "进攻提速"
+    },
+    {
+      "bonus": 8,
+      "clutch": 90,
+      "firepower": 76,
+      "id": "neo",
+      "level": 4,
+      "name": "NEO",
+      "stability": 82,
+      "style": "残局纪律"
+    },
+    {
+      "bonus": 7,
+      "clutch": 82,
+      "firepower": 80,
+      "id": "saw",
+      "level": 3,
+      "name": "sAw",
+      "stability": 80,
+      "style": "临场调整"
+    },
+    {
+      "bonus": 7,
+      "clutch": 78,
+      "firepower": 74,
+      "id": "robban",
+      "level": 3,
+      "name": "RobbaN",
+      "stability": 86,
+      "style": "更衣室管理"
+    },
+    {
+      "bonus": 6,
+      "clutch": 76,
+      "firepower": 84,
+      "id": "kane",
+      "level": 2,
+      "name": "kane",
+      "stability": 72,
+      "style": "明星激活"
+    },
+    {
+      "bonus": 6,
+      "clutch": 74,
+      "firepower": 70,
+      "id": "trace",
+      "level": 2,
+      "name": "trace",
+      "stability": 86,
+      "style": "防守复盘"
+    },
+    {
+      "bonus": 5,
+      "clutch": 72,
+      "firepower": 76,
+      "id": "ash",
+      "level": 1,
+      "name": "ash",
+      "stability": 74,
+      "style": "新人培养"
+    },
+    {
+      "bonus": 5,
+      "clutch": 70,
+      "firepower": 70,
+      "id": "mithr",
+      "level": 1,
+      "name": "mithR",
+      "stability": 78,
+      "style": "基础纪律"
+    },
+    {
+      "bonus": 8,
+      "clutch": 82,
+      "firepower": 74,
+      "id": "kuben",
+      "level": 4,
+      "name": "kuben",
+      "stability": 88,
+      "style": "慢控默认"
+    },
+    {
+      "bonus": 7,
+      "clutch": 78,
+      "firepower": 72,
+      "id": "groove",
+      "level": 3,
+      "name": "groove",
+      "stability": 84,
+      "style": "学院体系"
+    },
+    {
+      "bonus": 8,
+      "clutch": 80,
+      "firepower": 86,
+      "id": "guerri",
+      "level": 4,
+      "name": "guerri",
+      "stability": 76,
+      "style": "巴西爆弹"
+    },
+    {
+      "bonus": 8,
+      "clutch": 82,
+      "firepower": 76,
+      "id": "xizt",
+      "level": 4,
+      "name": "Xizt",
+      "stability": 86,
+      "style": "默认纪律"
+    },
+    {
+      "bonus": 7,
+      "clutch": 78,
+      "firepower": 80,
+      "id": "sycrone",
+      "level": 3,
+      "name": "sycrone",
+      "stability": 80,
+      "style": "青年提拔"
+    },
+    {
+      "bonus": 7,
+      "clutch": 80,
+      "firepower": 82,
+      "id": "malek",
+      "level": 3,
+      "name": "maLeK",
+      "stability": 78,
+      "style": "明星平衡"
+    },
+    {
+      "bonus": 6,
+      "clutch": 76,
+      "firepower": 78,
+      "id": "peacemaker",
+      "level": 2,
+      "name": "peacemaker",
+      "stability": 74,
+      "style": "临时救火"
+    },
+    {
+      "bonus": 6,
+      "clutch": 74,
+      "firepower": 72,
+      "id": "kassad",
+      "level": 2,
+      "name": "kassad",
+      "stability": 82,
+      "style": "纪律重建"
+    }
+  ],
+  "schema_version": 1
+}
@@ -0,0 +1,163 @@
+{
+  "fragments": {
+    "challenges": [
+      "媒体日问题很尖锐，队伍需要在镜头前保持状态。",
+      "赞助商临时加码，要求队伍用指定战术打出观赏性。",
+      "主办方安排了签名会，状态管理成了额外考验。",
+      "训练馆网络短暂波动，队伍必须快速适应备用机器。",
+      "赛前采访拖长，指挥需要把注意力重新拉回比赛。",
+      "赞助商想看激进打法，但稳住节奏的人会拿到更高回报。",
+      "媒体日不是战斗回合，却会影响队伍的运营资源。",
+      "队伍如果阵容完整，就更容易把这次插曲处理成奖金。",
+      "这次挑战只出现一次，处理完就回到小组赛主线。",
+      "主舞台彩排占用了热身时间，教练的管理能力开始生效。",
+      "赞助商要求展示新战术，选错方向也不会淘汰，只会少拿金币。",
+      "现场采访提到了前一场失利，队员心态需要稳住。",
+      "这类挑战不扣生命，目的只是给运营阶段增加变数。",
+      "处理好这次插曲的队伍，会在下一场前多一点经济余地。"
+    ],
+    "closers": [
+      "{team} 没有给翻盘窗口，最后一波回防处理得很完整。",
+      "{team} 在赛点局选择最熟悉的默认，用纪律结束地图。",
+      "{team} 最后一回合没有贪枪，稳稳把人数优势转成胜势。",
+      "{team} 的收官很干净，地图尾声没有出现多余失误。",
+      "{team} 用一波双拉打开包点，最后比分定格。",
+      "{team} 把比赛拖进自己舒服的节奏，收尾阶段非常稳。",
+      "{team} 赛点局的道具层次很清楚，对手没有舒服的回防路线。",
+      "{team} 终于等到对手前压，抓住这个窗口终结地图。",
+      "{team} 收下最后一分时没有冒进，这就是强队式结尾。",
+      "{team} 最后一枪来得很快，但前面的信息铺垫已经足够。",
+      "{team} 在关键经济局之后顺势收掉地图。",
+      "{team} 先控退路再进包点，结尾没有留下残局悬念。",
+      "{team} 把上半场积累的优势守到最后。",
+      "{team} 用一波慢夹收官，比分看起来合理，过程更像真实比赛。",
+      "{team} 没让对手连追，赛点局直接把节奏抢回来。",
+      "{team} 的最后一分赢在补枪，枪线没有断。",
+      "{team} 收官回合把每个角落都清干净，耐心给了回报。",
+      "{team} 把悬念留到最后一刻，但关键枪没有手软。"
+    ],
+    "clutches": [
+      "{player} 留到最后一个残局，靠一颗烟把拆包时间偷了出来。",
+      "{player} 没有急着补枪，等脚步声靠近后才横拉收掉残局。",
+      "{player} 在 1v2 里先断退路，再回头处理包点。",
+      "{player} 的残局处理很冷，假拆骗出第一枪后直接反清。",
+      "{player} 被逼到死角，但一颗反弹闪把局面重新打开。",
+      "{player} 没有追击残血，而是先保住雷包，判断非常老练。",
+      "{player} 关键回合双杀，把本来要崩的经济线救回来。",
+      "{player} 在读秒阶段完成补枪，队友的拉扯给得刚刚好。",
+      "{player} 先拿信息再开枪，这个残局赢在耐心。",
+      "{player} 硬吃白光完成换人，比分没有被对手咬住。",
+      "{player} 从连接位摸出，正好打掉回防节奏。",
+      "{player} 这次不追求集锦，只把枪线封死等队友到位。",
+      "{player} 的狙击枪没有空枪，关键首杀让整回合变得简单。",
+      "{player} 残血仍然敢看第一枪位，队伍因此拿到赛点。",
+      "{player} 拿下残局后没有庆祝，马上提醒队友保枪经济。",
+      "{player} 靠脚步假信息骗出转点，最后一枪很稳。",
+      "{player} 在包点里连续换位，对手始终没能定位。",
+      "{player} 把闪光背身吃完后仍然补到第二枪，这是关键转折。",
+      "{player} 一个人拖住整条回防路线，为队伍争到拆包窗口。",
+      "{player} 最后选择不 peek，让时间替自己赢下这一分。"
+    ],
+    "economy": [
+      "{team} 赢下这一分后可以完整起枪，下一回合选择会更多。",
+      "{team} 输掉长枪局后经济见底，可能要交出一回合调整空间。",
+      "{team} 没有强行追梦，选择保枪把下一回合留住。",
+      "{team} 的连败补偿到位，下一回合有机会靠道具质量反打。",
+      "{team} 这回合缴下两把枪，经济收益比比分更重要。",
+      "{team} 虽然丢分，但保下主狙，下一回合还有破局点。",
+      "{team} 的半甲手枪没有打成，但至少逼出了对手不少道具。",
+      "{team} 经济优势开始显现，可以更大胆地争夺第一枪位。",
+      "{team} 如果下一分再丢，就必须进入半起调整。",
+      "{team} 这一波选择全甲全弹，明显是要在中期一次打穿。",
+      "{team} 保下来的两把枪让下回合不至于完全被动。",
+      "{team} 连续换枪成功，把对手的存款一点点磨掉。",
+      "{team} 用低成本回合换到下包，经济线还没有断。",
+      "{team} 这波赢的不只是分数，还有下一回合的主动权。",
+      "{team} 被重置经济后节奏放慢，先求稳住半场尾声。",
+      "{team} 靠残局胜利拿到额外空间，可以考虑继续 D 牌补强。"
+    ],
+    "openings": [
+      "{team} 开局没有急着提速，先把默认控图铺开。",
+      "{team} 第一波提速很坚决，外场道具落点干净。",
+      "{team} 在手枪局后选择慢摸，试图逼出对手的前压信息。",
+      "{team} 的狙击手早早架住第一交火点，节奏被压得很低。",
+      "{team} 连续用两颗闪光清掉近点，进攻面一下打开。",
+      "{team} 防守开局站位很深，把回防路线留得很完整。",
+      "{team} 先拿地图控制权，再把包点压力一点点推上去。",
+      "{team} 开局没有赌点，靠信息互换慢慢读阵型。",
+      "{team} 在第一枪位赢下后没有贪，马上回收人数优势。",
+      "{team} 用一波假打骗出轮转，第二时间才开始真正爆弹。",
+      "{team} 选择保守开局，宁愿少拿信息也不送首杀。",
+      "{team} 的指挥把默认拉得很散，让对手很难判断重心。",
+      "{team} 手枪局道具很少，但站位互补做得很扎实。",
+      "{team} 没有被前几回合影响，依旧按自己的节奏展开。",
+      "{team} 的第一套进攻明显针对了对手弱侧。",
+      "{team} 在经济局也保留了两颗关键闪，准备打后点反清。",
+      "{team} 上来就抢中路，想用主动权换后续转点空间。",
+      "{team} 先把狙击枪放在安全位，围绕它慢慢组织推进。"
+    ],
+    "pauses": [
+      "比分被拉开后，双方都慢了半拍，像是在重新读这张图。",
+      "这里适合停一下，刚才几回合的经济差已经开始影响下一枪。",
+      "暂停回来之后，防守方明显把第一接触点后撤了半格。",
+      "连续交火后节奏突然变慢，双方都在等对方先犯错。",
+      "这一段没有夸张集锦，但每一颗道具都在改变下一回合。",
+      "场面安静了几秒，真正决定胜负的是下一次首杀。",
+      "队伍语音应该都在压节奏，没人愿意在这里送掉经济。",
+      "这不是简单的比分变化，战术重心已经从爆弹转到控图。",
+      "现场进入短暂拉扯，地图控制权一点点被重新分配。",
+      "两边都知道下一分很贵，所以这回合开局格外谨慎。",
+      "这一小段空白很重要，强队往往就是在这里调整默认。",
+      "比赛没有马上进入下一波交火，指挥正在重新排优先级。",
+      "刚才的连分让对手不得不换站位，防线开始出现试探。",
+      "经济压力让双方都少了一点容错，下一波道具会很关键。",
+      "这里没有急躁的前压，只有一点点互相试探。",
+      "暂停不是为了拖时间，而是在给下一套进攻换答案。",
+      "双方都把节奏压住，地图像被重新归零。",
+      "这一分之前的几秒钟很长，所有人都在等第一个脚步声。",
+      "场上没有无意义的 peek，每个人都在守自己的触发条件。",
+      "这段过渡让比赛更像真正的 BO 系列赛，而不是单纯掷骰子。"
+    ],
+    "runs": [
+      "{team} 连拿 {count} 分之后，现场短暂安静下来。",
+      "{team} 把经济滚起来后，连续 {count} 个回合没有给对手完整开枪空间。",
+      "{team} 这一波 {count} 连分不是纯枪法碾压，而是每回合都换到正确信息。",
+      "{team} 的节奏忽快忽慢，{count} 个回合里每次进点方式都不一样。",
+      "{team} 靠补枪链吃下 {count} 分，队伍语音应该已经很热。",
+      "{team} 的中期处理开始成型，连续 {count} 分把对手钱打空。",
+      "{team} 没有急着结束比赛，而是用 {count} 连分把地图控制牢牢握住。",
+      "{team} 这段 {count} 连分很关键，尤其是第二个残局稳定了军心。",
+      "{team} 在暂停之后突然提速，直接打出 {count} 连分。",
+      "{team} 先抓前压，再抓回防，{count} 个回合把读秒处理做满。",
+      "{team} 的防守交叉火力越站越舒服，{count} 连分让比分拉开。",
+      "{team} 把对手的道具节奏读透，连续 {count} 分都避开了主防区。",
+      "{team} 经济起飞后没有乱买，{count} 连分中枪线一直保持完整。",
+      "{team} 在被首杀的回合仍然能翻，{count} 连分含金量很高。",
+      "{team} 的默认推进开始收利息，{count} 个回合每次都能换到便宜。",
+      "{team} 靠一波小连胜把压力交回去，{count} 分之后对手必须叫停。",
+      "{team} 的二楼夹击反复奏效，{count} 连分让对手开始犹豫。",
+      "{team} 连续 {count} 回合把残局拖到优势人数，后点纪律很稳。",
+      "{team} 打出 {count} 连分后节奏放慢，像是在等对手自己露破绽。",
+      "{team} 这波 {count} 连分让地图气质变了，所有枪位都开始往前压。"
+    ],
+    "training_hooks": [
+      "训练赛不计入小组胜负，但会发金币，方便后续刷新商店。",
+      "这轮训练更像实战热身，每队都会遇到同场参赛对手。",
+      "训练赛重点不是淘汰谁，而是检验当前阵容能不能打完整张图。",
+      "这轮结束后可以 D 牌、锁店或调首发，下一轮再检验成果。",
+      "AI 战队也会参与训练，对局结果会写入档案。",
+      "如果阵容缺少指挥，训练赛的中期回合会更容易失控。",
+      "如果你想追羁绊，现在是最适合刷新商店的窗口。",
+      "训练赛的金币很重要，别把每次刷新都当成免费试错。",
+      "这一阶段没有生命扣除，重点是运营和阵容成型。",
+      "训练赛的地图会轮换，不会一直用同一个固定比分模板。",
+      "每轮训练结束后，真人都需要发送 /结束回合 才会进入下一轮。",
+      "训练赛会按轮次播报，避免一次性刷出一大串结果。",
+      "如果出现轮空，会安排本地陪练队补一张 BO1。",
+      "训练阶段适合观察战术克制，火力、稳定、残局都会影响回合走向。",
+      "连胜会带来金币，但失败也有保底，保证测试局能继续运营。",
+      "这部分是纯文字自走棋的节奏层，不再是单条目标数值判定。"
+    ]
+  },
+  "schema_version": 1
+}
@@ -0,0 +1,309 @@
+{
+  "ai": {
+    "power_multiplier": 0.82,
+    "primary_display_name": "AI 战队",
+    "primary_person_key": "__local_ai_team__",
+    "secondary_display_name": "AI 战队 B",
+    "secondary_person_key": "__local_ai_team_2__"
+  },
+  "battle": {
+    "damage": {
+      "bo5_sweep": 18,
+      "non_sweep": 10,
+      "sweep": 15
+    },
+    "maps": [
+      "Mirage",
+      "Inferno",
+      "Nuke",
+      "Ancient",
+      "Dust2",
+      "Anubis",
+      "Overpass"
+    ],
+    "match_best_of": {
+      "final": 5,
+      "group": 3,
+      "semifinal": 5,
+      "training": 1
+    },
+    "mr_rounds": 30,
+    "overtime_safety_cap": 72,
+    "overtime_segment_rounds": 6,
+    "overtime_start_score": 15,
+    "overtime_target_score": 19,
+    "overtime_win_by": 2,
+    "round_probability": {
+      "base": 0.5,
+      "first_half_side_swing": 0.018,
+      "jitter_center": 350,
+      "jitter_divisor": 10000,
+      "jitter_mod": 701,
+      "max": 0.68,
+      "min": 0.32,
+      "power_edge_cap": 0.16,
+      "power_edge_scale": 0.3,
+      "pressure_cap": 0.04,
+      "pressure_scale": 0.004,
+      "second_half_side_swing": -0.012
+    },
+    "score_bands": [
+      {
+        "label": "压制",
+        "max_loser_score": 6
+      },
+      {
+        "label": "优势",
+        "max_loser_score": 10
+      },
+      {
+        "label": "小胜",
+        "max_loser_score": 13
+      },
+      {
+        "label": "险胜",
+        "max_loser_score": 999
+      }
+    ],
+    "target_score": 16
+  },
+  "coach": {
+    "fallback_bonuses": {
+      "1": 2,
+      "2": 4,
+      "3": 6,
+      "4": 8,
+      "5": 10
+    },
+    "upgrade_costs": {
+      "1": 6,
+      "2": 10,
+      "3": 16,
+      "4": 24
+    }
+  },
+  "draft": {
+    "coach_choice_count": 10,
+    "coach_round": 1,
+    "later_round_preferred_costs": [
+      3,
+      2,
+      4,
+      1,
+      5
+    ],
+    "player_choice_count": 6,
+    "player_copy_count": 3,
+    "round_two_preferred_costs": [
+      2,
+      3,
+      1,
+      4,
+      5
+    ],
+    "rounds": 3
+  },
+  "economy": {
+    "round_income": {
+      "base": 5,
+      "interest_cap": 5,
+      "interest_divisor": 10
+    },
+    "series_rewards": {
+      "group_win_gold": 5,
+      "playoff_win_gold": 6
+    },
+    "starting_gold": 10,
+    "starting_hp": 100,
+    "training_rewards": {
+      "bye_gold": 2,
+      "loss_gold": 1,
+      "win_gold": 3
+    }
+  },
+  "pve_events": {
+    "pve_media": {
+      "loss_gold": 3,
+      "name": "媒体日挑战",
+      "target": 335,
+      "win_gold": 6
+    },
+    "pve_sponsor": {
+      "loss_gold": 4,
+      "name": "赞助挑战",
+      "target": 395,
+      "win_gold": 8
+    },
+    "pve_training": {
+      "loss_gold": 2,
+      "name": "训练赛",
+      "target": 275,
+      "win_gold": 4
+    }
+  },
+  "roster": {
+    "bench_limit": 3,
+    "nation_synergy": {
+      "max_sources": 1,
+      "thresholds": [
+        {
+          "bonus": 18,
+          "min_count": 5
+        },
+        {
+          "bonus": 12,
+          "min_count": 4
+        },
+        {
+          "bonus": 7,
+          "min_count": 3
+        },
+        {
+          "bonus": 3,
+          "min_count": 2
+        }
+      ]
+    },
+    "star_multipliers": {
+      "1": 1.0,
+      "2": 1.35,
+      "3": 1.8
+    },
+    "starter_count": 5,
+    "team_synergy": {
+      "max_sources": 2,
+      "thresholds": [
+        {
+          "bonus": 22,
+          "min_count": 5
+        },
+        {
+          "bonus": 15,
+          "min_count": 4
+        },
+        {
+          "bonus": 9,
+          "min_count": 3
+        },
+        {
+          "bonus": 4,
+          "min_count": 2
+        }
+      ]
+    },
+    "unit_power_weights": {
+      "clutch": 0.25,
+      "firepower": 0.45,
+      "leadership_scale": 0.12,
+      "leadership_threshold": 70,
+      "stability": 0.3
+    }
+  },
+  "schema_version": 1,
+  "shop": {
+    "cost_pool_copies": {
+      "1": 18,
+      "2": 15,
+      "3": 12,
+      "4": 9,
+      "5": 7
+    },
+    "odds": {
+      "1": {
+        "1": 70,
+        "2": 25,
+        "3": 5,
+        "4": 0,
+        "5": 0
+      },
+      "2": {
+        "1": 50,
+        "2": 30,
+        "3": 18,
+        "4": 2,
+        "5": 0
+      },
+      "3": {
+        "1": 30,
+        "2": 35,
+        "3": 25,
+        "4": 9,
+        "5": 1
+      },
+      "4": {
+        "1": 15,
+        "2": 30,
+        "3": 30,
+        "4": 20,
+        "5": 5
+      },
+      "5": {
+        "1": 5,
+        "2": 20,
+        "3": 30,
+        "4": 30,
+        "5": 15
+      }
+    },
+    "refresh_cost": 2,
+    "size": 6
+  },
+  "special_events": {
+    "media": {
+      "loss_gold": 1,
+      "name": "媒体日挑战",
+      "target": 320,
+      "win_gold": 4
+    },
+    "sponsor": {
+      "loss_gold": 1,
+      "name": "赞助挑战",
+      "target": 340,
+      "win_gold": 4
+    }
+  },
+  "tactics": {
+    "attribute_counters": [
+      [
+        "稳定",
+        "火力"
+      ],
+      [
+        "火力",
+        "残局"
+      ],
+      [
+        "残局",
+        "稳定"
+      ]
+    ],
+    "axis_percent_cap": 8.0,
+    "axis_percent_divisor": 12.5,
+    "counters": {
+      "残局": "稳定",
+      "火力": "残局",
+      "稳定": "火力"
+    },
+    "names": [
+      "火力",
+      "稳定",
+      "残局"
+    ],
+    "role_counters": {
+      "指挥": "狙击手",
+      "步枪手": "指挥",
+      "狙击手": "步枪手"
+    },
+    "role_percent_cap": 5.0,
+    "role_percent_scale": 0.8,
+    "selected_axis_multiplier": 1.08,
+    "tactic_counter_percent": 6.0,
+    "total_percent_cap": 15.0
+  },
+  "tournament": {
+    "event_title_template": "第 {season} 届 IEM 盐田 Major",
+    "host_name": "Taffy",
+    "max_players": 8,
+    "min_players": 2
+  }
+}
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
JWeBot Contributors	22edf6ff15	Cache OCR-negative bubbles check / local-gate (push) Failing after 42s Details	2026-10-16 11:38:03 +08:00
JWeBot Contributors	572159f571	Fix OCR thread test isolation check / local-gate (push) Failing after 17m10s Details	2026-10-16 11:19:55 +08:00
JWeBot Contributors	99a251c19a	Limit OCR runtime threads check / local-gate (push) Failing after 44s Details	2026-10-16 11:16:23 +08:00
JWeBot Contributors	3fa04755d0	Add multiplayer blackjack table flow check / local-gate (push) Failing after 51s Details	2026-10-16 11:03:32 +08:00
JWeBot Contributors	afc71e63a7	Release beta 1.0.0 baseline check / local-gate (push) Failing after 1m35s Details	2026-10-16 01:07:07 +08:00
JWeBot Contributors	bf4f28f48e	Add coin leaderboard command check / local-gate (push) Failing after 1m34s Details	2026-10-15 19:00:29 +08:00
JWeBot Contributors	148ae672f4	Install autochess data in runtime check / local-gate (push) Failing after 1m39s Details	2026-10-15 18:48:48 +08:00
JWeBot Contributors	bbddb5be6f	Add virtual coin loans check / local-gate (push) Failing after 42s Details	2026-10-15 18:43:49 +08:00
JWeBot Contributors	2bb2effc04	Externalize autochess game data check / local-gate (push) Failing after 58s Details	2026-10-15 18:37:41 +08:00
JWeBot Contributors	5125b827c0	Release alpha 0.6.8 autochess legacy state fix check / local-gate (push) Failing after 1m33s Details	2026-10-15 18:18:00 +08:00
JWeBot Contributors	3dea42b268	Release alpha 0.6.7 autochess pacing check / local-gate (push) Failing after 32s Details	2026-10-15 18:08:55 +08:00
JWeBot Contributors	a74147e7f1	Release alpha 0.6.6 autochess flow check / local-gate (push) Failing after 40s Details	2026-10-15 17:10:28 +08:00
JWeBot Contributors	9fff57134f	feat: add two-human AI autochess mode check / local-gate (push) Failing after 50s Details	2026-10-15 16:08:59 +08:00
JWeBot Contributors	e713ff369a	feat: add CS Major autochess tournament check / local-gate (push) Failing after 2m1s Details	2026-10-15 15:17:32 +08:00
JWeBot Contributors	f07ae653c7	feat: add multiplayer lottery and game records check / local-gate (push) Failing after 1m35s Details	2026-10-15 13:57:32 +08:00
JWeBot Contributors	0731e5cebb	fix: bound chat latency and clarify blackjack flow	2026-10-15 13:37:57 +08:00
JWeBot Contributors	f7fedc54e4	release: alpha 0.6.1 local player plugins and capture reconciliation check / local-gate (push) Failing after 3m24s Details	2026-10-15 05:01:40 +08:00