chore(release): 0.135.4 — accept the agent-interface 0.54 generation and move the sibling floors with it

CHANGELOG.md

@@ -1,5 +1,24 @@
 # Changelog
 
+## 0.135.4
+
+- Widen the `@tangle-network/agent-interface` peer range to `>=0.53.0 <0.56.0`, which holds three generations.
+Interface 0.54.0 took the npm `latest` tag on `2026-08-16T04:30:11Z`, 88 seconds after 0.135.3 merged with a `<0.54.0` cap, and `agent-knowledge` 8.0.2 then moved its own peer to `>=0.54.0 <0.55.0`.
+The two ranges were disjoint, so `npm install @tangle-network/agent-runtime@latest @tangle-network/agent-knowledge@latest` could not resolve at all.
+Interface 0.55.0 published `2026-08-16T06:44:30Z`, 2 hours 14 minutes after 0.54.0 and before this release could land, and took `latest` in turn.
+- Both generations are additive.
+0.54.0 adds `isCredentialBearingProfileConfigName` and `isRuntimeProcessControlEnvironmentName`, and widens `RequestedInteractions` from a three-key strict object to a string-keyed boolean record.
+0.55.0 adds the `environment-interactive` module, the optional `startInteractive` and `interactive` methods on `AgentEnvironment`, and the optional `interactiveAgent` capability block.
+Neither removes a symbol or adds a required field.
+Typecheck and the test suite pass against 0.55.0.
+- The range holds every generation this release verifies against, rather than only the newest.
+A consumer that still carries a package capped below 0.54 resolves against interface 0.53; one that carries `agent-knowledge` 8.0.2 resolves against 0.54; one that carries `agent-core` 0.9.2 resolves against 0.55.
+A single-generation window makes every adoption wave atomic, and interface minors publish faster than a wave can finish, which is the condition that produced this break.
+A consumer needs no change to adopt this release.
+- Move the `@tangle-network/agent-eval` peer floor to 0.145.16, the release `agent-knowledge` 8.0.2 requires (`>=0.145.16`), and the release that depends on interface 0.54.0.
+The development catalog moves `agent-knowledge` to 8.0.2, `agent-core` to 0.9.1, and `agent-profile-materialize` to 0.15.2 for the same reason.
+No runtime behavior changes.
+
 ## 0.135.3
 
 - Move the `@tangle-network/agent-interface` peer range to `>=0.53.0 <0.54.0`.

bench/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tangle-network/agent-bench",
-  "version": "0.8.11",
+  "version": "0.8.12",
   "type": "module",
   "description": "Benchmark adapters and execution for agent-runtime across coding, tool-use, RAG, memory, browser, and terminal tasks.",
   "repository": {

docs/api/primitive-catalog.md

@@ -7,7 +7,7 @@
 
 # Primitive catalog — the never-stale anti-reinvention inventory
 
-> **GENERATED** from `@tangle-network/agent-runtime@0.135.3` and `@tangle-network/agent-eval@0.145.15` by `scripts/gen-primitive-catalog.mjs`. Do NOT hand-edit — run `pnpm run docs:api`. This is the mechanical companion to the JUDGMENT in `canonical-api.md` (§2 decision table + §1.5 AgentProfile law): that doc says WHICH primitive to reach for and what NOT to build; this catalog proves WHAT exists. Per-symbol signatures + `file:line` live in the per-module pages under `docs/api/`.
+> **GENERATED** from `@tangle-network/agent-runtime@0.135.4` and `@tangle-network/agent-eval@0.145.16` by `scripts/gen-primitive-catalog.mjs`. Do NOT hand-edit — run `pnpm run docs:api`. This is the mechanical companion to the JUDGMENT in `canonical-api.md` (§2 decision table + §1.5 AgentProfile law): that doc says WHICH primitive to reach for and what NOT to build; this catalog proves WHAT exists. Per-symbol signatures + `file:line` live in the per-module pages under `docs/api/`.
 
 ## 1. agent-runtime — own public surface
 

docs/canonical-api.md

@@ -4,11 +4,11 @@
 Generated signatures and the complete export list live in docs/api/.
 Run pnpm docs:freshness after editing this file. -->
 
-> **Version 0.135.3.**
+> **Version 0.135.4.**
 > [`docs/api/primitive-catalog.md`](./api/primitive-catalog.md) lists every export and import path.
-> `agent-eval` must satisfy `>=0.145.15 <0.146.0`.
+> `agent-eval` must satisfy `>=0.145.16 <0.146.0`.
 > `sandbox` must satisfy `>=0.27.0 <0.28.0`.
-> Portable profile and tool-part types come from `@tangle-network/agent-interface` `>=0.53.0 <0.54.0`.
+> Portable profile and tool-part types come from `@tangle-network/agent-interface` `>=0.53.0 <0.56.0`.
 >
 > **`./kernel` is the execution kernel**: `package.json` maps it to `src/runtime/index.ts`. Everything below labelled `/kernel` lives there — the recursive atom (`Scope`/`Supervisor`), the executor registry, budget conservation, the finalizer seam, analyst wiring, and the round-synchronous loop.
 >

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tangle-network/agent-runtime",
-  "version": "0.135.3",
+  "version": "0.135.4",
   "description": "Shared task-lifecycle skeleton for agents: a recursive loop kernel for chat turns, one-shot tasks, and multi-attempt loops, with trace capture and eval-gated self-improvement. Domain behavior lives in adapters; scoring and ship-gates in @tangle-network/agent-eval.",
   "homepage": "https://github.com/tangle-network/agent-runtime#readme",
   "repository": {
@@ -170,8 +170,8 @@
   "license": "MIT",
   "packageManager": "pnpm@11.17.0",
   "peerDependencies": {
-    "@tangle-network/agent-eval": ">=0.145.15 <0.146.0",
-    "@tangle-network/agent-interface": ">=0.53.0 <0.54.0",
+    "@tangle-network/agent-eval": ">=0.145.16 <0.146.0",
+    "@tangle-network/agent-interface": ">=0.53.0 <0.56.0",
     "@tangle-network/sandbox": ">=0.27.0 <0.28.0"
   },
   "peerDependenciesMeta": {

pnpm-workspace.yaml

@@ -18,12 +18,12 @@ allowBuilds:
 catalog:
   '@arethetypeswrong/cli': 0.18.5
   '@modelcontextprotocol/sdk': 1.30.0
-  '@tangle-network/agent-core': 0.9.0
+  '@tangle-network/agent-core': 0.9.1
   '@types/node': 26.1.1
-  '@tangle-network/agent-eval': 0.145.15
-  '@tangle-network/agent-interface': 0.53.0
-  '@tangle-network/agent-knowledge': 8.0.1
-  '@tangle-network/agent-profile-materialize': 0.15.1
+  '@tangle-network/agent-eval': 0.145.16
+  '@tangle-network/agent-interface': 0.55.0
+  '@tangle-network/agent-knowledge': 8.0.2
+  '@tangle-network/agent-profile-materialize': 0.15.2
   '@tangle-network/agent-trace-contract': ^1.0.2
   '@tangle-network/sandbox': 0.27.0
   publint: 0.3.22

src/testing/fixtures/agent-improvement-proposal.json

@@ -1,6 +1,6 @@
 {
   "changedSurfaces": ["prompt"],
-  "digest": "sha256:07f5feab1f94522b087d74c57cf28ea58fb23529760340eec07e3b5adc22597e",
+  "digest": "sha256:aa0b9046662d61691324a4afdcb8f244799c04711f350083dc8d4e82e8b9e848",
   "evaluation": {
     "decision": {
       "contributingChecks": [
@@ -4882,7 +4882,7 @@
     ],
     "metadata": {
       "fixture": "agent-improvement-proposal",
-      "runtimeVersion": "0.135.3"
+      "runtimeVersion": "0.135.4"
     },
     "objectives": [
       {
@@ -4993,8 +4993,8 @@
       "baselineContentHash": "sha256:5c21ee53e513fc604cb09754e21c392b24a424da0ef37dbf8f1ee4a8a0b08f09",
       "candidateContentHash": "sha256:60fcbb1c728194bd51d7d19cb732d1c3f1881dce7e0a6266b41c8b98cfd65693",
       "kind": "agent-eval-loop",
-      "recordDigest": "sha256:9822541e4417230ccd66b9472e71b9d8eb9bac4ac1e9d09c4e5e6a3af84e2813",
-      "runId": "agent-runtime-0.135.3-proposal-fixture",
+      "recordDigest": "sha256:14f13bfd5e207fd7755131f2d75d8b1177de2b6cb157adacea3842dcf63ef479",
+      "runId": "agent-runtime-0.135.4-proposal-fixture",
       "schema": "agent-candidate-experiment"
     }
   },
@@ -5021,5 +5021,5 @@
   ],
   "kind": "agent-improvement-proposal",
   "proposedAt": "2026-07-10T01:00:00.000Z",
-  "runId": "agent-runtime-0.135.3-proposal-fixture"
+  "runId": "agent-runtime-0.135.4-proposal-fixture"
 }

src/testing/fixtures/agent-profile-improvement-proposal.json

@@ -1,6 +1,6 @@
 {
   "changedSurfaces": ["prompt", "skills"],
-  "digest": "sha256:f7c90771a7ffdd312ced71fb40c5b5b135e0bfe48958b4ea63293d9c96c43a56",
+  "digest": "sha256:31fe07295513b7533b97ca98754d885d24a5fcd446da6c48efaaad2f460e91e9",
   "evaluation": {
     "decision": {
       "contributingChecks": [
@@ -1715,7 +1715,7 @@
     ],
     "metadata": {
       "fixture": "agent-profile-improvement-proposal",
-      "runtimeVersion": "0.135.3"
+      "runtimeVersion": "0.135.4"
     },
     "objectives": [
       {
@@ -1826,7 +1826,7 @@
       "baselineContentHash": "sha256:21c495a37c418c10bde64fbaa188beddeed31f1f051ea60a6a6582a9ee0db704",
       "candidateContentHash": "sha256:103f77bc8481601eef1ad5fe6ba84a40dffabc3a44f421f8c8559121edab84e9",
       "kind": "agent-eval-loop",
-      "recordDigest": "sha256:a4cdb060f9fd6e889591168ff879341052673456d5ef32c53563236f4c7f889b",
+      "recordDigest": "sha256:0f8bc1f0aad52ccb73ad9c1b148bad56aa33f2e084a95dce8bec3e71b39c6744",
       "runId": "profile-improvement-1",
       "schema": "agent-profile-improvement-experiment"
     }