norn-cli 3.3.0 → 4.0.0

package/dist/knowledgeIndexWorker.js

@@ -7592,11 +7592,14 @@ function readAgentPromptBlock(lines, openingLineNumber, opening, stripTrailingCo
   };
 }
 
+// src/agents/agentTypes.ts
+var AGENT_REASONING_EFFORTS = ["none", "low", "medium", "high", "xhigh", "max"];
+
 // src/agents/nornAgentParser.ts
 var IDENTIFIER = "[a-zA-Z_][a-zA-Z0-9_]*";
-var MODEL_PROVIDERS = ["anthropic", "google", "local", "openai"];
+var MODEL_PROVIDERS = ["anthropic", "google", "local", "openai", "openai_compatible"];
 var MODEL_PROVIDER = new RegExp(`^(${MODEL_PROVIDERS.join("|")})$`, "i");
-var MODEL_DIRECTIVES = ["provider", "name", "apiKey", "baseUrl"];
+var MODEL_DIRECTIVES = ["provider", "name", "reasoning", "apiKey", "baseUrl"];
 var MCP_DIRECTIVES = {
   transport: { transport: "both", repeatable: false },
   command: { transport: "stdio", repeatable: false },
@@ -7635,6 +7638,7 @@ function splitHeaderDirective(value) {
 }
 var LIMIT_DIRECTIVES = {
   max_tokens: "maxTokens",
+  max_input_tokens: "maxInputTokens",
   max_depth: "maxDepth",
   max_invocations: "maxInvocations",
   max_turns: "maxTurns",
@@ -8069,6 +8073,23 @@ end mcp
       ));
       model.invalid = true;
     }
+    const reasoning = model.values.reasoning;
+    if (reasoning && !reasoning.value.includes("{{") && !AGENT_REASONING_EFFORTS.some((effort) => effort === reasoning.value.toLowerCase())) {
+      errors.push(parseError(
+        reasoning.lineNumber,
+        `Unknown reasoning effort '${reasoning.value}' in model '${model.alias}'. Expected one of: ${AGENT_REASONING_EFFORTS.join(", ")}.`,
+        "agent-model-reasoning-invalid"
+      ));
+      model.invalid = true;
+    }
+    if (reasoning && provider && !provider.value.includes("{{") && provider.value.toLowerCase() !== "openai") {
+      errors.push(parseError(
+        reasoning.lineNumber,
+        `Model '${model.alias}' can declare reasoning only with provider openai. Provider '${provider.value}' does not support this directive yet.`,
+        "agent-model-reasoning-provider"
+      ));
+      model.invalid = true;
+    }
     if (model.invalid || !provider || !name) {
       return;
     }
@@ -8077,6 +8098,7 @@ end mcp
       providerTemplate: provider.value,
       nameTemplate: name.value,
       targetTemplate: `${provider.value}/${name.value}`,
+      ...reasoning ? { reasoningTemplate: reasoning.value } : {},
       ...model.values.apiKey ? { apiKeyTemplate: model.values.apiKey.value } : {},
       ...model.values.baseUrl ? { baseUrlTemplate: model.values.baseUrl.value } : {},
       lineNumber: model.lineNumber,
@@ -8116,6 +8138,13 @@ end mcp
             "agent-model-alias-unknown"
           ));
           pending.invalid = true;
+        } else if (model.alias !== pending.modelAlias.value) {
+          errors.push(parseError(
+            pending.modelAlias.lineNumber,
+            `Model alias '${pending.modelAlias.value}' in agent '${pending.name}' does not match the declared alias '${model.alias}'. Model aliases are case-sensitive.`,
+            "agent-model-alias-case-mismatch"
+          ));
+          pending.invalid = true;
         }
       }
     }
@@ -8151,6 +8180,7 @@ end mcp
         accepts: pending.accepts,
         returns: pending.returns,
         maxTokens: pending.maxTokens?.value,
+        maxInputTokens: pending.maxInputTokens?.value,
         maxDepth: pending.maxDepth?.value,
         maxInvocations: pending.maxInvocations?.value,
         maxTurns: pending.maxTurns?.value,
@@ -8555,29 +8585,38 @@ end model`,
     }
     const knowledgeGrantMatch = trimmed.match(/^knowledge(?:\s+(.*))?$/i);
     if (knowledgeGrantMatch) {
-      const alias = (knowledgeGrantMatch[1] ?? "").trim();
-      if (!new RegExp(`^${IDENTIFIER}$`).test(alias)) {
+      const rawValue = (knowledgeGrantMatch[1] ?? "").trim();
+      const aliases = rawValue ? rawValue.split(",").map((part) => part.trim()) : [];
+      if (aliases.length === 0 || aliases.some((alias) => !new RegExp(`^${IDENTIFIER}$`).test(alias))) {
         errors.push(parseError(
           index,
-          `Invalid knowledge grant '${trimmed}' in agent '${pending.name}'. Expected: knowledge <Alias>.`,
+          `Invalid knowledge grant '${trimmed}' in agent '${pending.name}'. Expected: knowledge <Alias>[, <Alias>\u2026].`,
           "agent-knowledge-grant-invalid"
         ));
         pending.invalid = true;
-      } else if (pending.knowledge.some((grant) => grant.alias.toLowerCase() === alias.toLowerCase())) {
-        errors.push(parseError(
-          index,
-          `Agent '${pending.name}' grants knowledge '${alias}' more than once.`,
-          "agent-knowledge-grant-duplicate"
-        ));
-        pending.invalid = true;
-      } else if (!knowledgeBases.has(alias.toLowerCase())) {
-        errors.push(parseError(
-          index,
-          `Unknown knowledge alias '${alias}' in agent '${pending.name}'.`,
-          "agent-knowledge-alias-unknown"
-        ));
-        pending.invalid = true;
-      } else {
+        continue;
+      }
+      const granted = new Set(pending.knowledge.map((grant) => grant.alias.toLowerCase()));
+      for (const alias of aliases) {
+        if (granted.has(alias.toLowerCase())) {
+          errors.push(parseError(
+            index,
+            `Agent '${pending.name}' grants knowledge '${alias}' more than once.`,
+            "agent-knowledge-grant-duplicate"
+          ));
+          pending.invalid = true;
+          continue;
+        }
+        if (!knowledgeBases.has(alias.toLowerCase())) {
+          errors.push(parseError(
+            index,
+            `Unknown knowledge alias '${alias}' in agent '${pending.name}'.`,
+            "agent-knowledge-alias-unknown"
+          ));
+          pending.invalid = true;
+          continue;
+        }
+        granted.add(alias.toLowerCase());
         pending.knowledge.push({ alias, lineNumber: index });
       }
       continue;
@@ -9533,6 +9572,7 @@ function isNonNegativeInteger(value) {
 var AGENT_LIMIT_CONFIG_KEYS = /* @__PURE__ */ new Set([
   "_comment",
   "max_tokens",
+  "max_input_tokens",
   "max_depth",
   "max_invocations",
   "max_turns",
@@ -9542,7 +9582,7 @@ function hasOnlyKeys(value, allowedKeys) {
   return Object.keys(value).every((key) => allowedKeys.has(key));
 }
 function hasValidNornAgentLimits(value) {
-  return (value.max_tokens === void 0 || isPositiveInteger(value.max_tokens)) && (value.max_depth === void 0 || isPositiveInteger(value.max_depth)) && (value.max_invocations === void 0 || isPositiveInteger(value.max_invocations)) && (value.max_turns === void 0 || isPositiveInteger(value.max_turns)) && (value.contract_retries === void 0 || isNonNegativeInteger(value.contract_retries));
+  return (value.max_tokens === void 0 || isPositiveInteger(value.max_tokens)) && (value.max_input_tokens === void 0 || isPositiveInteger(value.max_input_tokens)) && (value.max_depth === void 0 || isPositiveInteger(value.max_depth)) && (value.max_invocations === void 0 || isPositiveInteger(value.max_invocations)) && (value.max_turns === void 0 || isPositiveInteger(value.max_turns)) && (value.contract_retries === void 0 || isNonNegativeInteger(value.contract_retries));
 }
 function isNornAgentProviderConfig(value) {
   if (!isObjectRecord(value)) {
@@ -9562,7 +9602,13 @@ function isNornAgentRecordingConfig(value) {
   }
   return hasOnlyKeys(value, /* @__PURE__ */ new Set(["_comment", "enabled"])) && (value.enabled === void 0 || typeof value.enabled === "boolean");
 }
-var AGENT_PROVIDER_NAMES = /* @__PURE__ */ new Set(["openai", "anthropic", "google", "local"]);
+var AGENT_PROVIDER_NAMES = /* @__PURE__ */ new Set([
+  "openai",
+  "openai_compatible",
+  "anthropic",
+  "google",
+  "local"
+]);
 function isNornAgentsConfig(value) {
   if (value === void 0) {
     return true;

package/package.json

@@ -2,7 +2,7 @@
   "name": "norn-cli",
   "displayName": "Norn",
   "description": "Version-controlled API and database tests. Author in VS Code, then run the same files from the CLI and CI.",
-  "version": "3.3.0",
+  "version": "4.0.0",
   "publisher": "Norn-PeterKrustanov",
   "author": {
     "name": "Peter Krastanov"
@@ -10,7 +10,7 @@
   "license": "SEE LICENSE IN LICENSE",
   "repository": {
     "type": "git",
-    "url": "https://github.com/PeterCrest/Norn"
+    "url": "git+https://github.com/PeterCrest/Norn.git"
   },
   "bugs": {
     "url": "https://github.com/PeterCrest/Norn/issues"
@@ -665,6 +665,6 @@
     "tough-cookie": "^6.0.0"
   },
   "bin": {
-    "norn": "./dist/cli.js"
+    "norn": "dist/cli.js"
   }
 }

package/schemas/norn.config.schema.json

@@ -440,6 +440,11 @@
           "minimum": 1,
           "description": "Provider-specific maximum output-token ceiling for each agent invocation."
         },
+        "max_input_tokens": {
+          "type": "integer",
+          "minimum": 1,
+          "description": "Optional cumulative provider-reported input-token budget for one top-level agent invocation subtree."
+        },
         "max_depth": {
           "type": "integer",
           "minimum": 1,
@@ -492,6 +497,11 @@
           "minimum": 1,
           "description": "Maximum output-token ceiling for each agent invocation. This is a ceiling, not a spend; hosted providers default to 16000 and local defaults to 4096."
         },
+        "max_input_tokens": {
+          "type": "integer",
+          "minimum": 1,
+          "description": "Optional cumulative provider-reported input-token budget for one top-level agent invocation subtree. When omitted, Norn records usage without applying this spend guardrail."
+        },
         "max_depth": {
           "type": "integer",
           "minimum": 1,
@@ -536,6 +546,9 @@
             "openai": {
               "$ref": "#/definitions/agentProviderLimits"
             },
+            "openai_compatible": {
+              "$ref": "#/definitions/agentProviderLimits"
+            },
             "anthropic": {
               "$ref": "#/definitions/agentProviderLimits"
             },

package/CLAUDE.md

@@ -1,69 +0,0 @@
-# Norn Extension — Claude Code instructions
-
-## Read these first
-
-1. **[`NOW.md`](NOW.md)** — the tool-agnostic active-work board shared by every agent and by
-   Peter. Whatever sits under **Active now** is the current priority. This board, not any
-   assistant's memory, is the source of truth for what we are working on.
-2. **[`AGENTS.md`](AGENTS.md)** — the full repo instructions (CLI parity requirement, how to
-   run the local CLI, code style, testing). Everything in that file applies here.
-
-## Skills: consult `.github/skills/` — always
-
-This repo keeps its accumulated implementation knowledge in **[`.github/skills/`](.github/skills/)**,
-maintained by every agent that works here. Treat it as required reading, not an optional
-reference.
-
-**Before touching any area of the codebase, check `.github/skills/` for a skill covering it
-and read that skill.** Do this even for changes that look small — the skills exist precisely
-because these areas have non-obvious rules that are easy to break.
-
-Current skills and what they cover:
-
-| Skill | Read it when working on |
-|-------|------------------------|
-| `norn-syntax-highlighting` | TextMate grammars in `syntaxes/`, token scopes, highlighting bugs |
-| `norn-agent-workbench` | `.nornagent` sidecars, agent `run` steps, providers, contracts, record/replay, agent graph |
-| `norn-intellisense-preferences` | Completion providers, IntelliSense behaviour |
-| `norn-value-resolution` | Variables, interpolation, `.nornenv`, value precedence |
-| `add-norn-keyword` | Adding a keyword to the `.norn` language |
-| `add-assertion-operator` | Adding an assertion operator |
-| `add-sequence-step-type` | Adding a new sequence step type |
-| `add-imported-sidecar-language` | Adding a new imported sidecar file type |
-| `norn-cli-integration` | `src/cli.ts` and CLI parity |
-| `norn-editor-decorations` | Drawing onto the editor — end-of-line chips, hiding markup, folding, caret traps |
-| `norn-debugger-integration` | DAP / debugger work |
-| `norn-response-panel` | The response webview panel |
-| `norn-test-explorer` | VS Code Test Explorer integration |
-| `norn-sequence-tags` | Sequence tags and filtering |
-| `norn-api-coverage` | `.nornapi` coverage features |
-| `norn-mcp-tools` | MCP client and tool wiring |
-| `norn-k8s` | Kubernetes features |
-| `norn-terminal` | Norn Terminal / PTY work |
-| `norn-env-templates` | `.nornenv` templates |
-| `norn-publishing` | Packaging and publishing the extension |
-| `norn-starter-catalog` | Starter templates catalog |
-| `norn-title-cards` | Title cards |
-| `demo-task-helper` | Building demos |
-| `readme-sync` | Keeping README/docs in sync with features |
-
-The table can go stale — list the directory when the work doesn't obviously map to a row.
-
-### Maintaining skills
-
-Per `AGENTS.md`, skills are living documents:
-
-- If a skill is **wrong or outdated**, fix it as part of the change.
-- If a skill is **missing** for an area you just learned, write one in Agent Skills format.
-- After creating or editing any skill, run `npm run validate:skills`.
-
-Capture the lesson that was hard to learn, not a restatement of the code.
-
-## Verification
-
-Never use `npx norn` — that runs the published package, not local changes:
-
-```bash
-npm run compile
-node ./dist/cli.js tests/file.norn --env prelive
-```

package/NOW.md

@@ -1,223 +0,0 @@
-# NOW — Active Work Board
-
-> **The single source of truth for what we are working on _right now_** — for Peter and
-> for every AI agent (Claude, Codex, Copilot, Cursor, any). Deliberately tool-agnostic:
-> it lives here in the repo, **not** in any one assistant's memory or private notes.
->
-> We have a lot of planning docs; this board exists so nobody (human or AI) has to guess
-> what's current. If it's on this board, it's the work. If it's not, it isn't — yet.
-
-## How this board works
-
-- **Empty by default.** Nothing is "current" unless it has been explicitly **Accepted**
-  onto this board by Peter. An empty "Active now" means: no directed work in flight —
-  don't start big work off a backlog/plan doc without Peter accepting it here first.
-- **Accepting work:** Peter says "Accept X" (or moves it here). That's the signal it
-  becomes current. Until then, ideas live in the plan/backlog docs, not here.
-- **This board is an _index_, not the detail.** Each item is one or two lines + a link to
-  its real plan doc. Keep the detail in the linked doc; keep this page short and scannable.
-- **Finishing work:** when an item is done, move it to "Recently done" (keep the last
-  handful), then prune. Don't let this page grow.
-- **Agents:** treat items under "Active now" as the current priority order. Do these
-  before picking up anything from the wider `Docs/` set.
-
----
-
-## Active now
-
-### 📚 Knowledge Base — the third pillar
-**Accepted 2026-08-15.** Norn covers **models** (providers, contracts, evals, record/replay) and
-**capabilities** (MCP servers and tools). What an agent still cannot get is **context**. The user
-writes prose in a declared folder and Norn derives the structure; because our runs have ground
-truth, *"did editing this document make agent runs better?"* is answerable here and nowhere else.
-Eight stages, ordered by dependency — **1 → 2 → 3** is the spine and where a wrong call is most
-expensive. **Stages 1, 2, 3 and 4 are built as of 2026-08-15.** Stage 1 established declared membership,
-topic identity, source-bounded domains, tombstones and deterministic DAG lineage. Stage 2 replaced
-its temporary JSON cache with one project-global built-in SQLite authority: atomic content-addressed
-snapshots, occurrence-scoped authored metadata, versioned action caches, conservative typed entity
-crossing, FTS5 diagnostics, retention/pins, and a queued extension worker. The calibrated fixture
-kept all nine entity kinds; exact values cross automatically while service spelling aliases remain
-proposals only. The database/WAL byte test proves `.nornenv` values and ciphertext do not persist.
-The CLI remains deliberately narrow and generic at index-backed `knowledge ls --explain`. Stage 3
-now applies sidecar-local grants to one lazily pinned snapshot per top-level run, routes exact typed
-entities with one conservative lexical fallback, assembles literal cache-stable prompt blocks under
-four explicit budgets, offers the bounded `load_knowledge` tool, and writes durable masked SQLite
-run/invocation/domain/topic/load telemetry independently of rolling replay files. Pure replay stays
-offline; a live tail fails closed without its recorded snapshot. The extension awaits its worker
-queue and the compiled local CLI shares identical runner semantics without new subcommands.
-**Stage 4 turned the ordinary Markdown editor into the authoring surface** — extension-only, no CLI
-command. A declared document now shows its own interpretation (topics, effective type and its
-origin, `use_when`, token estimates, exact entities that cross into the project), honest recorded
-use from Stage 3 telemetry, folded metadata, dimmed exclusions, and actions that write
-`type`/`use_when` and exclusions without moving a topic hash. The cost boundary is the design: a
-keystroke parses the open buffer once per version and reads cached memory, while every SQLite read
-runs on the index worker. Counts are raw co-occurrence — distinct completed runs for the headline,
-invocations and earlier lineage versions in their own rows, no causal language anywhere. Nine
-Stage 1, eleven Stage 2, eleven Stage 3 and eighteen Stage 4 focused tests pass under Node 24; 345
-pass across every vscode-free suite. **One gate stays open: the visual smoke test
-(light/dark/high-contrast) needs Peter's eyes — fixture at
-[`demos/knowledge-editor`](demos/knowledge-editor).**
-**Stage 5, the coverage panel, is the next dependency boundary and its cold-session handoff is
-ready.** Reviewing it against the built code moved three things: the mock's `402 runs 94%` is two
-different measurements plus one that does not exist anywhere (`K-20`), a panel row must be an
-endpoint rather than an entity or it contradicts itself on the first screen (`K-48`), and the
-"stale ref" list is where extractor false positives accumulate (`K-46`). Three gates need Peter
-before code: those, plus CLI scope and `K-47`.
-→ **Stage 5 implementation handoff (start here next session):
-[`Docs/to-be-built/knowledge-base-stage-5.md`](Docs/to-be-built/knowledge-base-stage-5.md).**
-→ **Stage 4 build record:
-[`Docs/to-be-built/knowledge-base-stage-4.md`](Docs/to-be-built/knowledge-base-stage-4.md).**
-→ **Stage 3 build record:
-[`Docs/to-be-built/knowledge-base-stage-3.md`](Docs/to-be-built/knowledge-base-stage-3.md).**
-→ Stage 2 build record: [`Docs/to-be-built/knowledge-base-stage-2.md`](Docs/to-be-built/knowledge-base-stage-2.md).
-→ Stage 1 build record: [`Docs/to-be-built/knowledge-base-stage-1.md`](Docs/to-be-built/knowledge-base-stage-1.md).
-→ Decision record: [`knowledge-base-refinement.md`](Docs/to-be-built/knowledge-base-refinement.md)
-(`K-01`…`K-45`, every Stage 1/2 gate shut and the Stage 3 review carried forward). Reasoning lives
-here; **do not re-litigate** — if a decision looks wrong, say so and stop.
-→ Design and the *why*: [`knowledge-base.md`](Docs/to-be-built/knowledge-base.md).
-
-**The `K-28` spike answered its question — markdown cuts it, no custom renderer.** It and the
-`playground/knowledgeBase/` development corpus were deleted at the Stage 1 gate. Its durable
-findings remain in skill `norn-editor-decorations`; production knowledge code shares no spike
-foundation.
-
-Two decisions the spike overturned, both worth knowing before reading anything else: per-topic
-metadata sits **inline under each heading** (`K-13`), which removed the binding-key problem rather
-than solving it; and **depth counts** for domains (`K-30`), so a folder inside a domain is a
-sub-domain and splitting an oversized domain actually works.
-→ **Refinement worksheet (start here): [`Docs/to-be-built/knowledge-base-refinement.md`](Docs/to-be-built/knowledge-base-refinement.md)**
-→ Parent spec: [`Docs/to-be-built/knowledge-base.md`](Docs/to-be-built/knowledge-base.md)
-→ Runtime floor and SQLite authority are recorded in `K-11` / `K-12` / `K-31`; Stage 2 applied
-them and removed the temporary Stage 1 JSON store.
-
----
-
-## Backlog / awaiting acceptance
-
-_Nothing awaiting acceptance._ (Slice 5f was scrapped 2026-08-15 — it had decayed into a reminder
-to update docs. Docs get reviewed as one pass when the website is updated for the knowledge base.
-Its spec remains at [`agent-workbench-slice-5f.md`](Docs/to-be-built/agent-workbench-slice-5f.md)
-if it is ever wanted.)
-
-## Parked
-
-### Contract & Drift + Voiden-playbook marketing
-The previous direction, parked 2026-08-07 — untested, not failed. Stages 1+2 are built and
-shipped in 2.9.8; the QA dogfood and the "why Norn, now" hook never happened. Full
-narrative and how to resume:
-[`Docs/random/parked_contract_drift_and_marketing.md`](Docs/random/parked_contract_drift_and_marketing.md)
-
-## Recently done
-
-- **3.2.0 — the knowledge base ships, quietly** (2026-08-19) — **done.** Stages 1–4 of the
-  Knowledge Base are in the published build: declared `knowledge` blocks in `.nornagent`,
-  the project-global SQLite authority, grant-scoped routing with the bounded `load_knowledge`
-  tool, and the Markdown authoring surface. **Deliberately undocumented in public** — Peter's
-  call at release time. Stages 5–8 are unbuilt and the coverage panel is still the next
-  dependency boundary, so the website says nothing about it and neither does the README. The
-  feature is reachable by anyone who writes the block; that is accepted, not overlooked.
-  **Agent graph details now open on click, not hover.** The 650ms open delay and 120ms hide
-  delay are gone: the reader either waited on a canvas that looked inert or was chased across
-  it by a popover they never asked for. A second click closes, Escape dismisses, and the
-  navigation that used to live on the tile — reveal source, step replay, reveal declaration —
-  is now one labelled button in the detail footer, so a tile has exactly one gesture. The
-  website's two "hover an agent or a boundary" sentences were updated to match, and the
-  response panel's agent invocation tree got the docs line it never had.
-  Verified at 426 Extension Host tests and 198/200 regression; the two failures are the live
-  SQL Server Docker fixture, which was not running and was accepted as a known failure.
-
-- **Agent results view** (2026-08-14; performance follow-up 2026-08-15) — **done.** The normal
-  response panel has a safe themed invocation tree; rows/details now start collapsed and large
-  MCP values remain host-side until reveal/copy. Streamed contract/agent rows also have distinct
-  toggle identities. → [Spec](Docs/to-be-built/agent-results-view.md)
-- **3.1.0 — MCP authoring parity, and the changelog is gone** (2026-08-13) — **done.**
-  Three fixes that all came out of one painful hour authoring a real server by hand. **`header`
-  now reads like HTTP**: `header Name: value` is accepted alongside the original no-colon form,
-  because the colon form is what a `.norn` request writes and what everyone arrives with —
-  rejecting it silently produced a header *named* `Authorization:` and the only complaint came
-  from `Headers.append` at dial time, three layers from the line at fault. The name is now
-  validated against the RFC 9110 token set at parse time, so an unsendable one is red in the
-  editor. The header name and value carry `.norn`'s own `entity.name.tag.http` /
-  `string.unquoted.http` scopes, so the identical header is the identical colour in both files,
-  and the quoted-string pattern is gone from that rule — it advertised an escape that does not
-  exist, and quotes really do end up inside the token. IntelliSense offers the shared
-  `commonHeaders` list after `header `, inserting the colon form and chaining into the
-  `Bearer {{$env.…}}` value completion.
-  **`run mcp` completions now see sidecar-declared servers.** The precedence rule lived in three
-  copies and the completion copy was left on config-only, so a project that declared every server
-  in its sidecar offered no aliases at all while running perfectly. It is now one shared module,
-  `src/mcpAliasScope.ts`, and the alias carries its origin — which matters because the tools cache
-  is written beside whatever *declared* the server, so tool-name completions and signature help
-  were reading the wrong `.norn-cache` even once an alias resolved. **Config `mcp.servers` stays**:
-  supporting both is one function and one line per caller, so retiring it would have been strictly
-  more work than keeping it.
-  **`CHANGELOG.md` deleted** at Peter's call — the release record is git history plus this board,
-  and a changelog was a third place saying the same thing and the likeliest to drift.
-  Also fixed: `@vscode/test-electron` 2.5.2 could not launch VS Code 1.133 (the binary was renamed
-  from `Electron` to `Code`), which had left the Extension Host suite dark.
-- **Agent Workbench — declared MCP servers** (2026-08-12) — **done, all five items.**
-  Agents can now *do* things. A `.nornagent` sidecar declares the servers it uses beside the
-  models it uses — `mcp <Alias> … end mcp`, stdio and http, credentials as `.nornenv`
-  references — and each agent is granted a whole server with `mcp <Alias>` or named tools with
-  `tools <Alias>.<tool>`. The two stay visibly different statements on purpose: a granted tool
-  executes when the model asks, so the authored grant *is* the permission boundary and dropping
-  four characters must not widen it from one tool to twenty. `session run | agent | call` makes
-  shared server state a decision rather than a surprise; `run` stays the default because five
-  agents testing one website are one testing session, and `session agent` is how an agent asks
-  not to inherit a login it never earned. Config `mcp.servers` keeps working with the sidecar
-  winning, `run mcp` steps reach declared servers so a server is provable with no model and no
-  cost, and a granted server is a real node on the canvas — **declared servers only**, per
-  Peter: the graph draws the program the file describes.
-  Four corrections the build forced on the spec, all recorded in it: grant expansion **cannot**
-  live above the runner (pure replay never runs that preflight, and a derived root definition
-  never reaches sub-agents), so it is an injected hook with a live and a replay implementation;
-  drift between record and replay is only knowable where a live listing happens, so the
-  acceptance criterion demanding both was impossible as written; preflight needed a session
-  boundary of its own, or `session agent` was already broken by the check that proves an agent's
-  tools exist; and the spec's own demo sketch used an input expression the language does not
-  have. Fixed along the way: a templated URL resolving differently mid-run silently reused the
-  old session, and a refused connection reported the SDK's "fetch failed" instead of naming what
-  it dialled. 60 focused tests across five items; 256 pass across every runnable suite, plus
-  type-check, lint, bundles, skill validation, and regression at 198/200 (two live-SQL-Server
-  sequences needing a database).
-  → Spec: [`Docs/to-be-built/agent-workbench-mcp-servers.md`](Docs/to-be-built/agent-workbench-mcp-servers.md)
-  · Demo: [`demos/mcp-ticket-testing`](demos/mcp-ticket-testing)
-- **Agent Workbench Slice 5e — reporting** (2026-08-10) — **done.**
-  A verdict is now visible in the response panel, the canvas, the debugger, and JUnit, derived
-  once through `agentHopPresentation` so the surfaces cannot disagree. The load-bearing move was
-  putting the verdict on `AgentHopResult` rather than the step: a recording persists the trace
-  and never step results, so a step-only verdict vanished the moment a past run was reopened —
-  the round-trip is now a test. Two bugs the build surfaced: a judged hop has `success === true`
-  even when the verdict failed, so the canvas drew a **green node for a failed run** until the
-  verdict was counted explicitly; and the runner emits its `completed` event before the verdict
-  exists, so the deep-cloned event log needed patching or replay playback showed no verdict.
-  Also: judge statements now draw a sequence handoff edge from whatever produced the value they
-  judge, live progress is emitted as `stepType: 'judge'`, and JUnit gets one testcase per
-  statement with `ExpectationsUnmet` and `JudgeError` kept distinct. 13 new focused tests; 159
-  pass across every runnable suite, plus type-check, lint, bundles, regression, skill validation,
-  and a real CLI run producing JUnit.
-  → [`Docs/to-be-built/agent-workbench-slice-5e.md`](Docs/to-be-built/agent-workbench-slice-5e.md)
-- **Agent Workbench Slice 5c — judge execution and the result contract** (2026-08-10) — **done,
-  one deliverable deferred.** A `judge` statement now runs its judge and produces a verdict.
-  The design that carries it: **the model is never asked for an overall result** — it rules on
-  each expectation and quotes evidence, and Norn computes `passed`, checks one ruling per
-  expectation with indexes in range, and verifies each quote occurs in the judged text. A judge
-  is an ordinary agent invocation; everything judge-specific lives in a derived definition, so
-  there is no judge runtime and no `if (isJudge)` in the runner. `builtInContracts` generalises
-  "a contract that lives in code" and rides the existing generation/validation path.
-  A provider or contract failure sets an error and no verdict, so "the judge said no" never
-  reads like "the judge never answered". **A failed judge stops the sequence**, the same as a
-  failed `assert` — it is the concluding check on an orchestration, so later steps must not run
-  on a disproved premise; the run is still recorded and replayable. A malformed reply *shape* is
-  corrected up to `contract_retries` via the opt-in `retryReturnsContract` (off for `run
-  <Agent>`); the verdict itself is never re-rolled. Evidence that cannot be found in the judged
-  text is flagged and still passes — strictness is intended to become per-expectation, not
-  global. **Deferred:** the automatic replay drift check —
-  `expectationsHash` is recorded and diffable, but pure replay never re-reads the `.norn`, so
-  the comparison needs `runLineNumber` plumbing and lands with 5d, which owns the policy.
-  Fixed along the way: judge hops reported false prompt drift on every replay. 18 new focused
-  tests; 141 pass across every runnable suite, plus type-check, lint, bundles, regression, skill
-  validation, and a real CLI run against a deterministic judge server.
-  → [`Docs/to-be-built/agent-workbench-slice-5c.md`](Docs/to-be-built/agent-workbench-slice-5c.md)
----
-_Last updated: 2026-08-15_