@passioncode-ai/fabric-agent-adapter 0.39.0 → 0.40.0

package/CHANGELOG.md

@@ -1,5 +1,129 @@
 # Changelog
 
+## 0.40.0 - 2026-10-21
+
+The kits as production modules (FAA-65). Every name a kit module made public at 0.39.1 is still there; a service that
+copies the kit now installs it with `fabric_kit.py install` (one file is no longer enough, see below).
+
+### Added
+
+- **A shared core, once per language** (layer L0 and L1): `fabric_jsvalue` / `fabric-jsvalue.mjs` (JavaScript's view
+  of JSON values: `show`, `js_to_number`, `same`, `json_equal`, `jcs` and the rest), `fabric_time` / `fabric-time.mjs`
+  (strict RFC 3339, UTC days, formatting, day windows, an injectable clock: the public dates API, on shared cases) and
+  `fabric_crypto` / `fabric-crypto.mjs` (Ed25519 and P-256 checks, small-order keys, base64url, sha256). They used to
+  live, twice, inside the estate and delegation readers; every reader now imports them.
+- **The kit is a manifest-listed set, installable as one.** `kit.json` lists every module in dependency order, with the
+  kit modules it imports, its sha256 and the sha256 of every release since 0.8.0. `fabric_kit.py install <dir>`
+  copies a module's closure (data files included); `status <dir>` says `current`, `older` (with its release) or
+  `modified`, and names a module a copy imports but lacks. SKILL.md said the kit was "one self-contained file"; it was
+  not, and a one-file copy of `fabric_service.py` failed in `usage_findings`.
+- **Connectors** (layer L4, both languages, shared cases): `fabric_http` (one deadline across attempts, bounded
+  retries with jittered backoff only when repeating is safe, `Retry-After` up to a cap, a response size cap, redirects
+  answered and never followed, plain http refused off loopback, redacted URLs in errors) and `fabric_openrouter` (the
+  agent's own key from a named environment variable, a spend ceiling checked before every attempt at the worst case
+  with calls in flight reserved, one usage receipt per answered call, empty, `length`, `error` and filtered answers
+  never returned as success, a fallback of another vendor required, 401/402/403 stop at once, attribution off by
+  default). References: `kit-modules.md`, `connectors.md`.
+- **A support-agent recipe** (`building-fabric-services/recipes/support-agent/`): answers a question from a knowledge
+  file through `fabric_openrouter`, accepts a reply only when code proves it (citations exist and were given, no em
+  dash or substitute, the question's script, a length limit), otherwise hands it to a person with the failed checks
+  named; idempotent per message id. `test/validate.py` lets a recipe import the kit modules `kit.json` lists.
+- **Layering held by tests**: a module imports only modules listed before it (a planted cycle is caught), none is over
+  1000 lines across every skill's scripts, the core is defined once, every module is in the module map, and the
+  0.39.1 public API of both facades is a snapshot test.
+
+### Changed
+
+- `fabric_service` / `fabric-service.mjs` and `fabric_board` / `fabric-board.mjs` are facades over modules split by
+  responsibility (base, platform, paths, protocols, lock, usage, backups, descriptor, auth, events, logs, supervisors;
+  board shapes, session, fixture). The probe's rules moved to `check_service_rules.py`. In working-with-fabric,
+  `fabric_session.py` is a facade over `fabric_session_{env,mcp,mail,hosts,cli}.py`; the hooks, the worker and
+  `install-host-hooks` still run the facade.
+- No import cycle is left: `fabric_estate` no longer imports `fabric_delegation`, in both languages.
+- A Node service that imported a module-private helper of `fabric-service.mjs` or `fabric-board.mjs` (not exported at
+  0.39.1, so outside the snapshot) imports it from the module that holds it now.
+- The probe runs the board responder's self-check in a clean Python (`-E -s`, its own working directory), so it reads
+  the kit it names and not a copy already imported.
+
+### Fixed
+
+- **Found by the release review (three blind readings) and fixed before release:** the OpenRouter ceiling counted
+  only the messages, so a large `tools` list could pass it (the worst case now bounds the messages and every param;
+  `models`, `route`, `plugins` and `web_search_options` are refused); an attempt that may have been billed without an
+  answer to read (a timeout, a 200 over the size cap or not JSON) left no receipt (it now records one with no tokens
+  and no cost, counted at the worst case); the Python transport could overrun its deadline on a slowly trickled body
+  (it reads in chunks against one deadline); the twins differed on a lone surrogate, NaN in a body, a transport bug and
+  `http://127.1` (both now behave the same, on shared cases); `fabric_service.py` could not be loaded by its path from
+  another folder (every kit module now puts its own folder on `sys.path`, tested from `/`); `fabric_kit.py status`
+  judged an older copy by the current release's imports and named only direct ones (it now reads each copy's own
+  imports and follows the closure); an unknown `--module` is a usage error (exit 2); the facade keeps `_number`,
+  `_DAY_MS` and `_utc_date_ms`; `install-host-hooks` requires the session helper's new modules; the recipe hands off a
+  message holding bytes a terminal could not decode instead of exiting, and its dash check also catches U+2012 and
+  U+2015.
+- **Found by the second review round and fixed:** a connection cut after a call may have been billed left no receipt
+  (every connection error now records an unmeasured one); `max_completion_tokens` and `n` could raise the output past
+  the bound (refused); an unmeasured call was counted at the current call's worst case (now at its own, while the
+  client runs); Node read a blank or hex price as a number (both twins now read a plain decimal or a number only);
+  Python's deadline started after the headers (it now covers them); `fabric_kit.py status` raised on a copy it could
+  not parse (it reports it `modified`) and now names a missing module's data files; `fabric_http` writes a JSON body
+  byte for byte as `JSON.stringify` (numbers and key order too, through the core's `json_stringify`); loopback edge
+  forms agree in both twins; the recipe's dash check covers U+2E3A, U+2E3B, U+FE58 and no-break spaces, and no longer
+  flags `1 - 2`.
+- **Found by the third review round and fixed:** an answer with no usage was counted at the next call's worst case
+  (now at its own); image, audio and file parts could be sent past the bound (only text content is sent); Python
+  raised outside `OpenRouterError` and kept no receipt on a 400-digit count or cost or JSON nested too deep (both read
+  as unmeasured now); Python's deadline could be held by trickled headers (a watchdog shuts the socket at the
+  deadline); `Response.json()` reads a byte order mark and refuses `NaN` as `JSON.parse` does; a `Retry-After` year
+  before 1000 is no date in either twin.
+- **A usage receipt's project id is checked the same way in both kits.** `fabric_service.py` defined its URI pattern
+  twice and the second won: Python accepted `project_id="urn:"` where Node refused it. Now one pattern per module, and
+  both kits refuse it (a test in each).
+
+## 0.39.1 - 2026-10-21
+
+Fixes from two rounds of blind review of 0.39.0 (FAA-64).
+
+### Fixed
+
+- **The probe no longer crashes on a usage report it is checking.** `check_service.py` compared `unpricedCalls` and
+  `unmeasuredCalls` raw, so `null` or a string raised `TypeError`, and a 400-digit cost raised `OverflowError`; either
+  stopped the whole probe before its other rules ran. Its FAC-SEM-025 arithmetic is now the kit's `usage_findings`, one
+  implementation held to the contract's vectors.
+- **The Python and Node kits answer FAC-SEM-025 as the contract does, message for message.** Both read each count as
+  the contract's `toNumber(x ?? 0)`, each date and project id with `show`, a cost as JavaScript holds the number (an
+  integer beyond a double is Infinity, which is never close to a sum), and a whole number written `5.0` as a count.
+  Python compared raw values and read `5.0` as 0; Node threw on an object such as `{"toString": 1}` in a count, a date
+  or a project id. The vectors now carry each finding's message and both kits compare it: 183 new report cases (208)
+  set every count and the cost of a day and of its first model to eleven values the schema refuses, plus three days
+  with no model rows and four dates and ids that are objects or numbers; eight new cases are the report's JSON text,
+  which each kit parses itself (a 400-digit integer, `1e400`, `2^53 + 1`, `5.0`). The field list is the contract's at this pin,
+  written in the generator.
+- **Messages a person reads carry no em dash**: the probe, the dashboard-kit notice, the board's retry hint and the
+  package refusal (Python and Node alike), the installer and the `npx` CLI, the sample service's page, the session
+  hooks' unread and status lines (`2 unread on the project board: com.list`) and the dashboard kit's Fabric button
+  (`Fabric is not installed. Get it at passioncode.ai/fabric`; kit **1.1.1**, so a service's kit copy is offered the
+  upgrade). The live documentation, evals and the kit's demo page were rewritten the same way.
+
+### Added
+
+- Tests for the producer side of DEC-0091 in both kits: receipts with `tokens_measured=False` through
+  `usage_report`, the day and model `unmeasuredCalls`, none on `byProject`, the probe clean, and the refusal of a
+  non-boolean flag.
+- Evals: the spend scenario expects unknown tokens in `unmeasuredCalls`; a new scenario covers a partner's package
+  and calls (DEC-0090).
+- `interop.md` and `usage.md` say a job whose usage is sent as `null` or `partial` is recorded with
+  `tokens_measured=False`; `estate-record.md` says a service updates its copied kit before a revision carries
+  `publisherScopes` (an older copy trusts a partner's key in every context); FAC-SEM-122 in its header and DEC-0091 in
+  protocol.md's FAC-SEM-025 row.
+- `test/validate.py` fails on U+2014 in the live documentation, the evals, the installer, the CLI and the kit's demo,
+  and when README states which version a checkout is or which release is the latest (it said 0.21.0 until now); both
+  checks have tests. The compiled-revision tests name the two contract revisions they need when they skip.
+
+### Raised with the contract (not changed here)
+
+- `chainOf` names a `{sub, partner}` node by its `org:` id, and job ownership and idempotency keys do not include the
+  partner. The kits follow `c55f2d5` until the contract decides (board thread `6e66a023`, FAA-64).
+
 ## 0.39.0 - 2026-10-20
 
 ### Changed
@@ -12,7 +136,8 @@
 - **Unmeasured tokens are named** (DEC-0091, contract CT-62). `make_usage_receipt(..., tokens_measured=False)` /
   `makeUsageReceipt(..., { tokensMeasured: false })` writes `tokensMeasured: false`; the report counts such calls in
   `unmeasuredCalls` on the day and the model row, and FAC-SEM-025 in both kits and `check_service.py` refuses a row
-  with more unmeasured calls than calls or a day whose count is not its models' sum. Three new usage vectors (25).
+  with more unmeasured calls than calls or a day whose count is not its models' sum. Four new usage vectors (25; this
+  line said three until 0.39.1).
 - **A partner in the delegation chain** (DEC-0090, contract CT-58). Both verifiers take `{partner: "org:<id>"}` as the
   innermost actor under at least one agent: it counts toward the depth limit and ends the chain, and the checked chain
   lists it by its `org:` id. Outermost, with an `act` beneath, `personal` or an `ORG:` prefix is `malformed-chain`.

package/README.md

@@ -8,7 +8,7 @@
 
 **Fabric Agent Adapter** makes any agent Fabric-compatible. Fabric is PassionCode.ai's
 product, the CEO AI agent: you talk to Fabric, and it chooses, binds and runs the agents that
-do the work. This adapter is how an agent becomes one Fabric can bind — four Agent Skills,
+do the work. This adapter is how an agent becomes one Fabric can bind: four Agent Skills,
 Python and Node reference kits and a live conformance probe for the
 [Fabric Agent Contract](https://github.com/passioncode-ai/fabric-agent-contract). It also works
 on its own: the skills, kits and probe need no Fabric install.
@@ -51,12 +51,18 @@ is the board-first workflow.
 
 `building-fabric-services` makes an agent a long-lived local service with a dashboard
 that is always alive, runs as one copy, keeps its state through a reinstall and appears
-in Fabric Dashboards by itself — the `fabric-service/0.1` extension. It also makes an **online** agent
-or dashboard — an `https` origin on a platform — a Fabric service (the remote placement, DEC-0019): the same
+in Fabric Dashboards by itself: the `fabric-service/0.1` extension. It also makes an **online** agent
+or dashboard (an `https` origin on a platform) a Fabric service (the remote placement, DEC-0019): the same
 four routes behind the token, a `__Host-` session cookie, and one descriptor on the operator's computer;
-`scripts/sample-remote-service.mjs` is the complete example. It ships Python and
-Node reference kits (`scripts/fabric_service.py`, `scripts/fabric-service.mjs`), a
-complete `scripts/sample_service.py`, and `scripts/check_service.py`, a live probe. A service that answers
+`scripts/sample-remote-service.mjs` is the complete example. It ships the service kit in Python and
+Node: layered modules listed in `scripts/kit.json` behind the `fabric_service` / `fabric-service.mjs` facades,
+installed into a service with `scripts/fabric_kit.py install` and checked with `fabric_kit.py status`
+([kit modules](plugins/fabric-agent-adapter/skills/building-fabric-services/references/kit-modules.md), including
+the dates API); connectors for outbound HTTP and OpenRouter (`fabric_http`, `fabric_openrouter`: one deadline, safe
+retries, the agent's own key, a spend ceiling before every attempt, usage receipts, a fallback model;
+[connectors](plugins/fabric-agent-adapter/skills/building-fabric-services/references/connectors.md)); a ready
+[support-agent recipe](plugins/fabric-agent-adapter/skills/building-fabric-services/recipes/support-agent/README.md);
+a complete `scripts/sample_service.py`; and `scripts/check_service.py`, a live probe. A service that answers
 requests other Projects post to its Project on Fabric's project board uses the board responder
 (`scripts/fabric_hub.py` and `scripts/fabric_board.py`, Node `fabric-hub.mjs` and `fabric-board.mjs`): the
 `board.respond` grant, enroll, claim, accept the exact digest, complete, a checkpoint before every step, and restarts
@@ -68,8 +74,8 @@ python3 plugins/fabric-agent-adapter/skills/building-fabric-services/scripts/che
 
 The dashboard itself is built from the **dashboard kit** (`assets/dashboard-kit/`, `fabric-dashboard/0.1`,
 contract DEC-0036): one stylesheet and one script that keep the page usable from 360 CSS px inside a host
-pane beside the agent console — navigation that folds into a More menu, wide tables in their own scroll
-box, sticky chrome at most 120 px — with seven WCAG AA themes (light and dark) that follow the host's
+pane beside the agent console (navigation that folds into a More menu, wide tables in their own scroll
+box, sticky chrome at most 120 px) with seven WCAG AA themes (light and dark) that follow the host's
 `fabric_appearance` cookie. `scripts/dashboard_kit.py install|status` copies and checks it,
 `scripts/check_dashboard_layout.mjs` measures a rendered page in WebKit at 360, 480, 768 and 1280 px
 (Playwright; `NOT_RUN` without it), and the probe's `dashboard.declared` checks the declaration. The
@@ -117,7 +123,7 @@ yet ship the host registry/runtime needed to connect and authorize a live provid
 ### Install
 
 With the [PassionCode.ai launcher](https://github.com/passioncode-ai/passioncode) the adapter
-comes with every other PassionCode.ai skill — `npx @passioncode-ai/passioncode@latest update`,
+comes with every other PassionCode.ai skill: `npx @passioncode-ai/passioncode@latest update`,
 then restart your agents. Alone, without any account:
 
 ```bash
@@ -175,8 +181,8 @@ kill %1
 
 Verified 2026-10-01 from the published npm package 0.5.4 (`npx` into a throwaway hub, `KIT`
 pointing at the installed skill) with Claude Code 2.1.286: the probe reported 27 rules, 0 FAIL;
-the CLI connected to the sample over streamable HTTP, called `sample.echo` and printed `ping`. The probe prints one line per rule —
-`PASS`, `FAIL` or `NOT_RUN` with its evidence — and exits 1 on any `FAIL`; run it against your
+the CLI connected to the sample over streamable HTTP, called `sample.echo` and printed `ping`. The probe prints one line per rule
+(`PASS`, `FAIL` or `NOT_RUN` with its evidence) and exits 1 on any `FAIL`; run it against your
 own service by its id once its installer has written the descriptor.
 `FABRIC_REAL_CLIENT=1 python3 -m unittest discover -s test -p test_real_client.py` repeats the connection check
 (every sample tool listed, no model call) in the test suite.
@@ -264,8 +270,8 @@ The default pin for new bundles is [`fabric-contract.lock.json`](fabric-contract
 - version: `0.1.0`
 - commit: `c55f2d5a11c9a0197e958e87212fca7ae1154769`
 
-Every other mention of the default contract revision — this section, the skills' metadata, the
-skill card, `adapt_project.py` — must equal it; `python3 test/validate.py` fails a tree
+Every other mention of the default contract revision (this section, the skills' metadata, the
+skill card, `adapt_project.py`) must equal it; `python3 test/validate.py` fails a tree
 where one does not. The sole live legacy exception is the immutable
 `SUPPORTED_CONTRACT_COMMITS` declaration in the scaffolder: previously issued bundles
 keep their selected legacy lock and require that exact clean contract checkout. The
@@ -288,14 +294,16 @@ FABRIC_CONTRACT_OLD=/path/to/legacy-contract FABRIC_CONTRACT_NEW=/path/to/curren
   python3 -m unittest discover -s test -p test_contract_revisions.py -v
 ```
 
-Without both environment variables, those tests explicitly skip as `NOT_RUN`.
-This source checkout is 0.21.0. 0.20.0 is the latest published GitHub/npm release (2026-10-12; 0.7.0 and 0.11.0
-were never released); 0.21.0 is published by its `v0.21.0` tag. Source delivery does not update installed skills or live sessions.
+`FABRIC_CONTRACT_OLD` is a checkout of the legacy fixtures' revision (`OLD` in `test/test_contract_revisions.py`) and
+`FABRIC_CONTRACT_NEW` one of the pin; each needs `pnpm install --frozen-lockfile` in its own folder (pnpm refuses a
+symlinked `node_modules`). Without both environment variables, those tests explicitly skip as `NOT_RUN`, naming the
+two revisions. What each version changed and when it was released is in [CHANGELOG.md](CHANGELOG.md). Source delivery
+does not update installed skills or live sessions.
 
 ## License
 
 Open source under the [GNU AGPL-3.0](LICENSE). A [commercial license](COMMERCIAL-LICENSE.md) is
-available for use that does not meet the AGPL's terms — [passioncode.ai/business](https://passioncode.ai/business/).
+available for use that does not meet the AGPL's terms: [passioncode.ai/business](https://passioncode.ai/business/).
 Versions before 0.5.3 were released under PolyForm Noncommercial or Internal Use (v0.4.3 to
 v0.5.2) and MIT (v0.4.2 and earlier); each keeps the licence it was released under.
 Contributions are accepted under [CLA.md](CLA.md) ([CONTRIBUTING.md](CONTRIBUTING.md)).

package/bin/fabric-agent-adapter.js

@@ -26,7 +26,7 @@ Usage:
   npx @passioncode-ai/fabric-agent-adapter [--force]
       install every skill into the agents hub ~/.agents/skills
   npx @passioncode-ai/fabric-agent-adapter --target claude [--force]
-      plain copy into ~/.claude/skills — refused while the plugin is installed
+      plain copy into ~/.claude/skills (refused while the plugin is installed)
   npx @passioncode-ai/fabric-agent-adapter --prune-shadow
       remove plain ~/.claude/skills copies that shadow the installed plugin
   npx @passioncode-ai/fabric-agent-adapter --help
@@ -124,7 +124,7 @@ function main(argv) {
 
   const { skillRoot, names } = skillNames();
   if (!names.length) {
-    console.error(`error: no skills found under ${skillRoot} — corrupted package?`);
+    console.error(`error: no skills found under ${skillRoot}; corrupted package?`);
     return 1;
   }
   const home = os.homedir();
@@ -132,7 +132,7 @@ function main(argv) {
 
   if (prune) {
     if (!hasPlugin) {
-      console.error(`error: the ${PLUGIN_ID} plugin is not installed, so a copy in ~/.claude/skills is not a shadow — nothing removed.`);
+      console.error(`error: the ${PLUGIN_ID} plugin is not installed, so a copy in ~/.claude/skills is not a shadow; nothing removed.`);
       return 1;
     }
     pruneShadows(home, names);
@@ -151,8 +151,8 @@ function main(argv) {
       // One owner per artefact on disk: a plain copy over someone else's link freezes the skill
       // at this version, and its owner stops updating it. --force does not override this.
       console.log(owner === 'launcher'
-        ? `skip: ${name} at ${dest} is managed by the PassionCode launcher — update it with: npx @passioncode-ai/passioncode@latest update`
-        : `skip: ${name} at ${dest} is a link managed elsewhere — remove the link first to install a copy here`);
+        ? `skip: ${name} at ${dest} is managed by the PassionCode launcher; update it with: npx @passioncode-ai/passioncode@latest update`
+        : `skip: ${name} at ${dest} is a link managed elsewhere; remove the link first to install a copy here`);
       continue;
     }
     if (fs.existsSync(dest) && !force) {
@@ -166,7 +166,7 @@ function main(argv) {
   if (target === 'agents' && !hasPlugin) {
     console.log(`Claude Code reads plugins, not the hub:\n  claude plugin marketplace add ${REPO} && claude plugin install ${PLUGIN_ID}`);
   }
-  console.log('Restart your agent — skills load at session start.');
+  console.log('Restart your agent: skills load at session start.');
   return 0;
 }
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@passioncode-ai/fabric-agent-adapter",
-  "version": "0.39.0",
+  "version": "0.40.0",
   "description": "Create Fabric-compatible agents, run them as always-alive local services with dashboards (fabric-service/0.1), and adapt existing projects to the Fabric Agent Contract. This package is the installer CLI.",
   "scripts": {
     "test": "python3 test/validate.py && python3 -m unittest discover -s test -q && node --test 'test/*.test.mjs'"

package/plugins/fabric-agent-adapter/.claude-plugin/plugin.json

@@ -3,7 +3,7 @@
   "name": "fabric-agent-adapter",
   "displayName": "Fabric Agent Adapter",
   "description": "Create new Fabric-compatible agents, build them as always-alive local services with dashboards (fabric-service/0.1), and adapt existing projects to the Fabric Agent Contract through evidence-backed MCP, A2A, or local-runner provider bundles; and teach a coding agent to work in a project through Fabric (fabric-mcp, fabric_whoami, claim and release), with Claude Code session hooks.",
-  "version": "0.39.0",
+  "version": "0.40.0",
   "author": {
     "name": "PassionCode.ai",
     "url": "https://passioncode.ai/"

package/plugins/fabric-agent-adapter/skills/adapting-projects-to-fabric/SKILL.md

@@ -1,11 +1,11 @@
 ---
 name: adapting-projects-to-fabric
-description: Use when adapting an existing agent, MCP server, A2A peer, HTTP service, or terminal CLI to the Fabric Agent Contract—choosing MCP/A2A/local-runner, scaffolding a provider bundle, or checking Fabric compatibility; also for «подключить проект к Fabric» or «сделать агента совместимым с Fabric». NOT for building the Fabric host/orchestrator, configuring an MCP client, or a brand-new agent — that is creating-fabric-agents.
+description: Use when adapting an existing agent, MCP server, A2A peer, HTTP service, or terminal CLI to the Fabric Agent Contract (choosing MCP/A2A/local-runner, scaffolding a provider bundle, or checking Fabric compatibility); also for «подключить проект к Fabric» or «сделать агента совместимым с Fabric». NOT for building the Fabric host/orchestrator, configuring an MCP client, or a brand-new agent (that is creating-fabric-agents).
 license: AGPL-3.0-only OR LicenseRef-PassionCode-Commercial
 compatibility: Requires filesystem access and Python 3.9+. Exact schema checks additionally need git, Node.js, pnpm, and the pinned fabric-agent-contract checkout (a public repository). Works without those tools in an explicitly degraded structural-check mode.
 metadata:
   author: PassionCode.ai
-  version: "0.39.0"
+  version: "0.40.0"
   contract-version: "0.1.0"
   contract-commit: "c55f2d5a11c9a0197e958e87212fca7ae1154769"
 ---
@@ -23,9 +23,9 @@ Use this skill to adapt or assess a provider project. Do not use it to:
 - design the Fabric host, registry, scheduler, admission service, or project binding runtime;
 - add an MCP server to Claude Code, Codex, or an agent gateway;
 - answer wire-level MCP or A2A questions (transports, sessions, auth handshakes, task
-  states on the wire) — that is `agent-interop` (agent-stack); the pinned contract stays
+  states on the wire): that is `agent-interop` (agent-stack); the pinned contract stays
   normative for what Fabric requires;
-- design a new agent from scratch — that is the sibling skill creating-fabric-agents;
+- design a new agent from scratch: that is the sibling skill creating-fabric-agents;
 - claim admission merely because generated files or a valid manifest exist.
 
 If the project has only a browser interface and no stable API, MCP/A2A surface, or CLI,
@@ -133,14 +133,14 @@ Preserve the chosen ownership boundary:
   heartbeat, and partial results without relying on ambient accounts.
 
 Keep model selection and provider-internal reasoning outside the Fabric contract. Expose
-typed outcomes, evidence, artifacts, and protocol-visible state—not chain-of-thought.
+typed outcomes, evidence, artifacts, and protocol-visible state, not chain-of-thought.
 Treat all provider output as untrusted until schemas and semantic assertions pass.
 
 ### 4b. Announce an agent that is not a service
 
 An agent Fabric reaches as a CLI or a stdio MCP server gets a provider entry, written by
 its installer with [`scripts/fabric_provider.py`](scripts/fabric_provider.py) and removed
-by its uninstaller — argv arrays only, env values as `secret-ref:` references, never the
+by its uninstaller: argv arrays only, env values as `secret-ref:` references, never the
 id of an existing service, and a `providerId` equal to the manifest's `provider.id`. Load [provider entries](references/provider-entry.md). An
 agent that runs as a service uses a descriptor instead (`building-fabric-services`).
 
@@ -174,8 +174,8 @@ python3 <skill-dir>/scripts/adapt_project.py check <project-root> \
 ```
 
 The local check also refuses two lifecycle faults (LC-19, LC-21): a Claude Code plugin in
-the project that declares a stdio MCP server — it starts in every session that enables the
-plugin; serve it over HTTP from one resident process or register it at project scope — and a
+the project that declares a stdio MCP server (it starts in every session that enables the
+plugin; serve it over HTTP from one resident process or register it at project scope), and a
 credential in a launch argument or a URL query, where every process and every log can read it.
 Fix both at their cause; never weaken the check.
 
@@ -214,11 +214,11 @@ operator's four steps:
 4. type the code it shows in the chat with the bot.
 
 In a group shared with other bots the channel follows OC-14…OC-17 (DEC-0035): it stays silent
-unless addressed — `/command@ThisBot`, a reply to its own message or a press of its own button; a
-bare `/command` in a group is not addressed — and a channel nobody receives on is `degraded`
+unless addressed (`/command@ThisBot`, a reply to its own message or a press of its own button; a
+bare `/command` in a group is not addressed), and a channel nobody receives on is `degraded`
 (`receiver-missing`). Say so in the proposal when the operator means to bind a shared group.
 
-Record the answer — `accepted`, `declined` or `later` — in the agent's state and the
+Record the answer (`accepted`, `declined` or `later`) in the agent's state and the
 conformance report, and do not ask again; an agent that serves `surfaces.operatorChannel` also
 shows it as `proposal` in its status document. Creating the bot, storing the token and enabling the
 channel are the operator's action: never create the bot, ask for or store the token's value, or
@@ -246,7 +246,7 @@ first commit:
 org-index `scripts/check_format.py` reports 0 findings for it before it is called done. **An agent
 someone builds for themselves is not a PassionCode.ai repository:** its licence is its owner's
 choice, nothing about it is published or listed by the organization, and none of these files is
-required of it — though the verified MCP quick start is still how anyone learns to drive it.
+required of it, though the verified MCP quick start is still how anyone learns to drive it.
 
 ## Completion format
 
@@ -263,7 +263,7 @@ Report:
 Never summarize the outcome as “Fabric-compatible” unless all required admission gates
 passed against a real provider and the project binding is valid.
 
-## Dashboard handoff — also for consumers
+## Dashboard handoff: also for consumers
 
 When handing a registered service dashboard to a person, or writing the generated
 agent's completion/notification instructions, read and apply

package/plugins/fabric-agent-adapter/skills/adapting-projects-to-fabric/references/dashboard-links.md

@@ -1,4 +1,4 @@
-# Dashboard links — producer and consumer rule
+# Dashboard links: producer and consumer rule
 
 Read when an agent creates a dashboard, implements `<tool> dashboard`, or hands
 an existing Fabric service dashboard to a person. This also applies to generated

package/plugins/fabric-agent-adapter/skills/adapting-projects-to-fabric/references/provider-entry.md

@@ -3,7 +3,7 @@
 Normative source: the Fabric Agent Contract's `docs/specification/provider.md`
 (`fabric-provider/0.1`, DEC-0016, rulings DEC-0017) at the commit this plugin pins.
 
-An agent Fabric reaches as a CLI or a stdio MCP server — not a long-running service —
+An agent Fabric reaches as a CLI or a stdio MCP server (not a long-running service)
 is announced by one entry, `providers/<id>.json`, in the same root as the services
 directory:
 
@@ -34,17 +34,17 @@ python3 scripts/fabric_provider.py remove example-agent      # the uninstaller
 
 `--stdio` takes the rest of the line as the argument array; there is no shell string. An entry may carry
 `run.mcp.stdio.scope` (DEC-0044): `project` (started for the sessions of a project that binds it) or `on-demand`;
-`session` — a server in every coding session — is refused (FAC-SEM-056, LC-19). The validator accepts the field; the
+`session` (a server in every coding session) is refused (FAC-SEM-056, LC-19). The validator accepts the field; the
 writer does not set it until Fabric reads it. An argument that carries a credential is refused
 (LC-21, FAC-SEM-057): a key goes in `env` as a `secret-ref:<name>`, never in argv.
 
 It refuses, with one sentence that never quotes a value:
 
 - a manifest that does not resolve, or whose `provider.id` is not the entry's
-  `providerId` — the two URIs are compared as URIs (FAC-SEM-014);
+  `providerId`: the two URIs are compared as URIs (FAC-SEM-014);
 - an id that is already a service in `services/` (FAC-SEM-013);
 - an env value that is not `secret-ref:<name>`, or a reference that has the shape of a
-  credential itself — a token prefix, a private key, a JWT (FAC-SEM-015: a value is
+  credential itself: a token prefix, a private key, a JWT (FAC-SEM-015: a value is
   checked by its form; name patterns apply to names);
 - a URL other than `http://127.0.0.1:<port>/mcp`, a manifest path that is not an
   absolute or `~/` path to `fabric-agent.json`, a shell-string command, unknown fields.