catalog: add dia + csm service entries (status: down) + repro audits

dia (:8200) — OpenAI-compat /v1/audio/speech, seedable (not byte-exact),
Apache-2.0 weights. Clean catalog fit; flip to ready after first exercise.

csm (:8201) — OpenAI-compat, but NO seed + temperature-sampled =
non-reproducible (contract's fix-before-adding case), catalogued by
operator direction with a reproducibility caveat + gated-license warning;
belongs at experimental once running.

Fields read from each wrapper's API docs (2026-05-31), to confirm against
live OpenAPI/Pydantic at deploy. No catalog_version bump (add-service =
no bump). NOTE: services.schema.json is stale (pre-existing — 13 errors;
live catalog uses lifecycle, schema predates it); regen via dump_schema.py.

docs/asset-engine/services.yaml

@@ -1234,6 +1234,180 @@ services:
       /history. Until then, expose ComfyUI as an external link in the UI.
       User state at /worktank/comfyui/basedir/.
 
+  - id: dia
+    name: Dia / Dia2 TTS
+    description: >
+      Nari Labs' dialogue TTS — multi-speaker turn-taking in one pass with
+      [S1]/[S2] speaker tags and nonverbals (laughs)/(coughs)/(sighs).
+      Dia2 family (1B streaming, 2B high-quality) selectable on the host.
+    category: tts
+    version: 1
+    status: down
+    host: irv-ml1
+    lifecycle:
+      stack: dia
+      vram_gb: 7
+      gpu_device_id: 0
+    endpoint: http://10.100.79.3:8200/v1/audio/speech
+    method: POST
+    content_type: application/json
+    model:
+      id: nari-labs/Dia-1.6B
+      revision: null
+      image: local/dia:v1
+    fields:
+      - name: input
+        type: textarea
+        label: Text ([S1]/[S2] dialogue + nonverbals)
+        required: true
+        max_length: 5000
+        description: >
+          [S1]/[S2] tags mark speaker turns; nonverbals like (laughs),
+          (coughs), (sighs), (clears throat) go inline. For a clone voice,
+          prepend the reference transcript manually.
+      - name: model
+        type: select
+        options: [dia-1.6b]
+        default: dia-1.6b
+        description: >
+          Ignored by /v1/audio/speech (serves whatever checkpoint is loaded).
+          Switch Dia 1.6B / Dia2-1B / Dia2-2B via the wrapper config or Web UI.
+      - name: voice
+        type: select
+        label: Voice / mode
+        default: S1
+        description: >
+          S1 | S2 | dialogue, or a predefined/clone reference filename under
+          /worktank/dia/reference_audio (e.g. "my_ref.wav").
+      - name: response_format
+        type: select
+        options: [opus, wav]
+        default: opus
+      - name: speed
+        type: slider
+        min: 0.5
+        max: 2.0
+        step: 0.05
+        default: 1.0
+        description: Post-generation playback speed multiplier.
+      - name: seed
+        type: number
+        required: false
+        default: -1
+        description: -1 = random; any integer for repeatable (not byte-exact) output.
+    response:
+      type: audio
+      mime_from_field: response_format
+    reproducibility:
+      seedable: true
+      deterministic: false
+      notes: >
+        Seed gives consistent voice/prosody but NOT byte-exact output —
+        upstream notes float-arithmetic variance across hardware/versions.
+        A richer custom /tts endpoint exposes cfg_scale/temperature/top_p/
+        cfg_filter_top_k for finer control.
+    estimated_latency:
+      cold_start_s: 10
+      warm_per_unit: "dialogue one-pass; ~realtime on the 3090"
+    license: "Apache-2.0 (Dia weights); MIT (devnen wrapper)"
+    notes: |
+      OpenAI-compat /v1/audio/speech plus a richer custom /tts (cfg_scale 3.0,
+      temperature 1.3, top_p 0.95, cfg_filter_top_k 35, max_tokens,
+      split_text/chunk_size). Fields read from devnen documentation.md
+      (2026-05-31); confirm against live OpenAPI/Pydantic at deploy. Deployed
+      to irv-ml1 but PARKED (asset-engine orchestrates start) — flip to ready
+      after the first successful generation. Pin DIA_SHA before build.
+
+  - id: csm
+    name: Sesame CSM (conversational)
+    description: >
+      Sesame's Conversational Speech Model (CSM-1B) — context-aware speech
+      (Llama backbone + Mimi codec). Usable as plain TTS, but its edge is
+      cross-turn prosody for voice agents, not narration.
+    category: tts
+    version: 1
+    status: down
+    host: irv-ml1
+    lifecycle:
+      stack: csm
+      vram_gb: 8
+      gpu_device_id: 0
+    endpoint: http://10.100.79.3:8201/v1/audio/speech
+    method: POST
+    content_type: application/json
+    model:
+      id: sesame/csm-1b
+      revision: null
+      image: local/csm:v1
+    fields:
+      - name: model
+        type: select
+        options: [csm-1b]
+        default: csm-1b
+      - name: input
+        type: textarea
+        label: Text
+        required: true
+        max_length: 5000
+      - name: voice
+        type: select
+        label: Voice
+        default: alloy
+        description: >
+          alloy | echo | fable | onyx | nova | shimmer, or a cloned voice ID.
+      - name: response_format
+        type: select
+        options: [mp3, opus, aac, flac, wav]
+        default: mp3
+      - name: speed
+        type: slider
+        min: 0.5
+        max: 2.0
+        step: 0.05
+        default: 1.0
+      - name: temperature
+        type: slider
+        min: 0.0
+        max: 1.0
+        step: 0.05
+        default: 0.8
+        description: Sampling temperature — higher = more variation.
+      - name: topk
+        type: number
+        required: false
+        description: Top-k sampling cutoff (1–100).
+      - name: max_audio_length_ms
+        type: number
+        required: false
+        default: 90000
+        description: Max generated audio length in milliseconds.
+    response:
+      type: audio
+      mime_from_field: response_format
+    reproducibility:
+      seedable: false
+      deterministic: false
+      notes: >
+        ⚠️ No seed param and temperature-sampled → output varies run-to-run.
+        Per this contract that is normally a fix-before-adding bug; catalogued
+        by operator direction. asset-engine "regenerate/fork" will NOT
+        reproduce a prior CSM take. Clean fix = upstream seed support.
+    estimated_latency:
+      cold_start_s: 12
+      warm_per_unit: "~realtime on the 3090"
+    license: "Sesame CSM license (gated, non-OSI); MIT (wrapper)"
+    license_warning: |
+      sesame/csm-1b is GATED under Sesame's own (non-OSI) license — accept
+      terms on HF and review before any commercial/redistribution use. Host
+      needs CSM_HF_TOKEN set before first start.
+    notes: |
+      Conversational speech model — context-aware prosody for voice agents,
+      not a narration reader. Fields read from the phildougherty wrapper
+      README/API (2026-05-31); confirm against live OpenAPI at deploy.
+      Deployed to irv-ml1 but PARKED; gated-model token required before
+      first start. Because it is non-deterministic, when started it belongs
+      at status: experimental (not ready). Pin CSM_SHA before build.
+
 # Reproducibility audit — answers per service: (a) seedable, (b) model
 # deterministic without seed, (c) image tag mutable (security/reproducibility risk).
 reproducibility_audit:
@@ -1304,3 +1478,13 @@ reproducibility_audit:
     model_deterministic: true
     image_tag_mutable: false
     notes: "Reproducibility requires persisting full workflow JSON + seed."
+  - service: dia
+    seedable: true
+    model_deterministic: false
+    image_tag_mutable: false
+    notes: "Seed gives consistent voice, not byte-exact (float variance). Build pin via DIA_SHA."
+  - service: csm
+    seedable: false
+    model_deterministic: false
+    image_tag_mutable: false
+    notes: "⚠️ No seed + temperature-sampled → non-reproducible. Catalogued experimental by operator direction; upstream seed support is the fix. Gated Sesame license."