johns-harness 2026.9.20 → 2026.9.22

package/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## 2026.9.22
+
+- Family 69: enforce the latest DeepSeek Flash/Pro, Muse and Gemini Lite alias targets across all 14 shipped copies; document `/model deepseek` and retain Family 68 on the separate `extended` release line.
+
 ## 2026.9.20
 
 - Family 67: native DeepSeek V4.1 Flash/V4 Pro catalog, environment auth, aliases, model-specific effort mapping and tool/reasoning replay through the supported Chat Completions transport.

package/README.md

@@ -55,9 +55,9 @@ Expired ChatGPT credentials trigger an owner notice with the `/login` recovery c
 
 <!-- JOHNNESS_PATCH_DEFAULTS_61 -->
 ### Batteries included
-The harness ships the current model catalog and the short aliases `opus`, `sonnet`, `fable`, `astra`, `sol`, `luna`, `terra`, `gpt`, `flash`, `banana`, and `image`, so `/model opus` works on a fresh install with no `models.providers` block. Channels you configure load without a `plugins.allow` list; only an explicit `enabled: false` or `plugins.deny` turns one off. Updating the harness updates the catalog and aliases for every agent. Any `openai-codex/<model>` primary that hits its ChatGPT usage limit fails over to `openai/<model>` on the API key first, then to your configured fallbacks, with no config (the sibling is skipped when no OpenAI API key is present). Image generation and editing use GPT Image 2 through the `image_generate` tool: `openai-codex/gpt-image-2` on the ChatGPT subscription first, `openai/gpt-image-2` on the API key second (`agents.defaults.imageGenerationModel`). Nano Banana Pro (`google/gemini-3-pro-image-preview`) ships in the catalog as a selectable image model, reachable with `model: "nano-banana"` and its own `aspectRatio` option; the default stays GPT Image 2 because the subscription path costs nothing.
+The harness ships the current model catalog and the short aliases `opus`, `sonnet`, `fable`, `astra`, `sol`, `luna`, `terra`, `gpt`, `flash`, `banana`, `image`, `deepseek`, `deepseek-pro`, `muse`, and `gemini-lite`, so `/model opus` works on a fresh install with no `models.providers` block. Channels you configure load without a `plugins.allow` list; only an explicit `enabled: false` or `plugins.deny` turns one off. Updating the harness updates the catalog and aliases for every agent. Any `openai-codex/<model>` primary that hits its ChatGPT usage limit fails over to `openai/<model>` on the API key first, then to your configured fallbacks, with no config (the sibling is skipped when no OpenAI API key is present). Image generation and editing use GPT Image 2 through the `image_generate` tool: `openai-codex/gpt-image-2` on the ChatGPT subscription first, `openai/gpt-image-2` on the API key second (`agents.defaults.imageGenerationModel`). Nano Banana Pro (`google/gemini-3-pro-image-preview`) ships in the catalog as a selectable image model, reachable with `model: "nano-banana"` and its own `aspectRatio` option; the default stays GPT Image 2 because the subscription path costs nothing.
 
-**The alias contract.** Every shipped alias points at the newest model in its line, so an install or an `/update` moves every agent forward with zero per-instance config. Your own `agents.defaults.models[*].alias` entries are still consulted first and still win. Every catalog bump must move the matching alias; the verifier fails the release if it does not.
+**The alias contract.** Every shipped alias points at the newest model in its line, so an install or an `/update` moves every agent forward with zero per-instance config. Your own `agents.defaults.models[*].alias` entries are still consulted first and still win. Every catalog bump must move the matching alias; the verifier fails the release if it does not. `/model deepseek` always selects the newest DeepSeek model (currently V4.1 Flash); `deepseek-pro` the newest Pro.
 
 ### Updating from chat
 Send `/update` to install the newest `johns-harness` on the machine the gateway runs on and restart into it; `/update 2026.9.14` pins an exact version. Owner only. The reply names the current and target versions, a second `/update` while one is running is refused, and the first message after the restart confirms the running version. On a writable host the package is reinstalled into the existing global prefix. On an immutable image with a persistent volume (Fly), it is installed into `$JOHNNESS_STATE_DIR/runtime/johnness` and the entrypoint prefers that runtime when it is newer than the image: `exec node "$(node /opt/johnness/lib/node_modules/johns-harness/dist/runtime-path.js)" gateway run`. `JOHNNESS_UPDATE_PREFIX` overrides the target. On failure the reply carries the last lines of npm output and the one command that fixes it.

package/docs/PATCHES.md

@@ -2562,3 +2562,13 @@ The 65.1 updater budgets fresh installs from the old dependency size. A very ful
 ## Family 67: native DeepSeek and current provider catalog
 
 Verified September 13, 2026 against official provider catalogs and harmless live API probes. Adds DeepSeek V4.1 Flash/V4 Pro via the existing supported Chat Completions adapter, Gemini Flash-Lite, current prices and Claude xhigh mappings. Preserves all legacy IDs, configured selection, deliberate context budgets and provider-default omission. [Full source/evidence/limits](PROVIDER-CATALOG.md). Canonical adapters live in the version-checked pi-ai overlay; `patch-provider-catalog.py --check` validates exact registry/auth/alias/adapter snapshots without network or secrets. Historical reconstruction retains exact byte comparisons through the Family 67 helper.
+
+## Family 69: DeepSeek alias contract
+
+Release: `johns-harness@2026.9.22` (`latest`). Extends the release gate, not the runtime aliases already shipped in Family 67.
+`scripts/check-alias-contract.mjs` now pins `deepseek` to `deepseek/deepseek-flash` (V4.1 Flash),
+`deepseek-pro` to `deepseek/deepseek-v4-pro`, `muse` to `meta/muse-spark-1.3`, and `gemini-lite` to `google/gemini-3.5-flash-lite`.
+All 14 alias copies must match these exact targets, agree with each other, and resolve every shipped alias in the catalog.
+Verifier checks 69.1 and 69.2 enforce the contract and exactly one DeepSeek Flash alias per copy.
+Future catalog releases must move the matching contract targets; user-configured aliases still win.
+Family 68 remains on the `extended` release line and is not included in this `latest` artifact.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "johns-harness",
-  "version": "2026.9.20",
+  "version": "2026.9.22",
   "description": "John's Harness: a production agent harness that runs autonomous coding agents as one cooperative swarm.",
   "keywords": [
     "ai-agents",