Venice: add auto-recover for optional params and surface actual error message on 400s

2026-06-23 20:24:40 +01:00
42 changed files with 223 additions and 1207 deletions
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -14,91 +14,13 @@ concurrency:
  group: ci-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true
 jobs:
-  prek:
-    name: Lint, format & test
+  test-and-clippy:
+    name: Unit testing and linting
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v7
-
-      # Toolchain version + components come from rust-toolchain.toml. rustflags is
-      # cleared so plain builds don't fail on warnings; the clippy hook still does.
-      - uses: actions-rust-lang/setup-rust-toolchain@v2
-        with:
-          rustflags: ''
-
+      - uses: dtolnay/rust-toolchain@1.93.0
      - name: Install SQLite3
        run: sudo apt-get update && sudo apt-get install -y libsqlite3-dev
-
-      # just drives the prek recipes; mise provides the pinned prek (mise.toml).
-      - uses: taiki-e/install-action@v2
-        with:
-          tool: just
-      - uses: jdx/mise-action@v4
-
-      # Run the same prek hooks devs run locally; .pre-commit-config.yaml is the
-      # source of truth. Tests are a separate step for visible timing.
-      - name: Lint & format (prek hooks, excluding tests)
-        run: just prek-run-on-all --skip test-unit
-
-      - name: Unit tests
-        run: just test
-
-  # The prek job never builds a container image, so a bump of the Dockerfile's
-  # base image reaches main unvalidated and fails later, in Publish, after
-  # ghcr.io/etkecc/baibot:latest has already been attempted. These two jobs close
-  # that gap: decide whether a Dockerfile changed, and if so build the image the
-  # way Publish does - but without pushing anything.
-  #
-  # The build is gated rather than unconditional because it is a full Rust
-  # release build; running it on every push would turn a ~1 minute pipeline into
-  # a ~10 minute one for changes that cannot affect the image.
-  docker-gate:
-    name: Decide whether the image needs building
-    runs-on: ubuntu-latest
-    outputs:
-      build: ${{ steps.decide.outputs.build }}
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          fetch-depth: 0
-
-      - name: Look for Dockerfile changes against main
-        id: decide
-        run: |
-          if [ "${{ github.event_name }}" = 'workflow_dispatch' ]; then
-            echo 'Forced via workflow_dispatch.'
-            echo 'build=true' >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-
-          # Publish builds and pushes from main, so a main-side build here would
-          # be redundant. This gate exists for branches, before they merge.
-          if [ "${{ github.ref_name }}" = 'main' ]; then
-            echo 'On main; Publish covers this.'
-            echo 'build=false' >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-
-          git fetch --no-tags origin main
-          if git diff --name-only origin/main HEAD -- Dockerfile | grep -q .; then
-            echo 'A Dockerfile changed; the image will be built.'
-            echo 'build=true' >> "$GITHUB_OUTPUT"
-          else
-            echo 'No Dockerfile changed.'
-            echo 'build=false' >> "$GITHUB_OUTPUT"
-          fi
-
-  docker-build:
-    name: Build the container image (without publishing it)
-    needs: docker-gate
-    if: needs.docker-gate.outputs.build == 'true'
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v7
-
-      # No build cache on purpose: a bump of the base image is exactly the case
-      # where a cold build is the honest test.
-      - name: Build
-        uses: docker/build-push-action@v7
-        with:
-          push: false
+      - run: cargo test --all-features
+      - run: cargo clippy
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -5,10 +5,6 @@ repos:
      - id: trailing-whitespace
      - id: end-of-file-fixer
      - id: check-yaml
-        # This is the stock Synapse sample homeserver.yaml (mostly commented-out
-        # docs). prek's stricter YAML parser (serde-saphyr, since v0.4.6) rejects
-        # its long runs of consecutive comment lines in several places.
-        exclude: '^etc/services/synapse/config/homeserver\.yaml$'
      - id: check-merge-conflict
      - id: check-added-large-files
        args: ['--maxkb=1024']
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,18 +1,4 @@
-# (2026-06-29) Version 1.25.0
-
- (**Feature**) [♻️ Context management](./docs/configuration/text-generation.md#️-context-management) now works with every provider, not only [OpenAI](./docs/providers.md#openai). Token counting previously went through [tiktoken-rs](https://github.com/zurawiki/tiktoken-rs), which is accurate only for OpenAI models and silently mis-counted everything else (worst of all for non-English text). OpenAI agents keep using tiktoken-rs; every other provider, including the recommended [Venice](./docs/providers.md#venice), now uses a provider-neutral approximation that needs no per-model tokenizer (ASCII counted at about four characters per token, other scripts such as Cyrillic and CJK at about two), landing within roughly 10-20% of the real count. See the [context management docs](./docs/configuration/text-generation.md#️-context-management).
-
- (**Improvement**) Context management now trims a conversation on whole-turn boundaries for every provider, so an assistant reply is never kept without the user message it answered. This also adjusts how the OpenAI provider trims: a dangling assistant reply at the oldest edge of the kept history is now dropped along with its missing prompt, rather than left in place.
-
-
-# (2026-06-26) Version 1.24.0
-
- (**Feature**) Add an opt-in 💭 **thinking notice** for text generation. When enabled, a slow response (for example, from a reasoning model that runs for minutes) posts a "thinking…" placeholder after a short delay, refreshes it periodically with varying flavor text, and then edits that same message into the final answer, so a long wait no longer looks like a stuck bot. The notice is **disabled by default** and configurable per-room or globally via `text-generation set-thinking-notice-enabled true`. Fast responses (under the delay threshold) never show a placeholder. See the [text-generation configuration docs](./docs/configuration/text-generation.md#-thinking-notice).
-
- (**Bugfix**) The [Venice](https://venice.ai) unsupported-field auto-recovery (added in 1.23.1) now actually remembers rejections across messages. The cache lived on the provider's controller, which is rebuilt on every message for room-local and global agents, so each turn started with an empty cache, re-sent the unsupported field, and logged the same `400 Bad Request` warning again. The cache is now process-global (keyed per Venice deployment), so a field a model rejects is dropped proactively on every later request instead of being re-discovered each turn.
-
-
-# (2026-06-24) Version 1.23.1
+# (2026-06-23) Version 1.23.1

 - (**Bugfix**) The [Venice](https://venice.ai) provider now auto-recovers when a model rejects an optional knob it does not support. Venice's request body is strict (`additionalProperties: false`), so a model that lacks `prompt_cache_retention`, `reasoning_effort`, or `prompt_cache_key` rejected the whole request with a `400 Bad Request` — breaking agent creation and every reply. baibot now drops the unsupported field and retries, remembering the rejection per model so later requests skip it without a wasted round-trip. Only these meaning-preserving fields are dropped; sampling knobs that change the output (`temperature`, `top_p`, the penalties) are never silently removed and still surface as an error.

--- a/Cargo.lock
+++ b/Cargo.lock
@@ -95,9 +95,9 @@ dependencies = [

 [[package]]
 name = "anyhow"
-version = "1.0.104"
+version = "1.0.102"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "330a5ed07fa54e4702c9d6c4174f74427fc0ef6e214bbd677ae50a5099946470"
+checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c"

 [[package]]
 name = "anymap2"
@@ -184,9 +184,9 @@ checksum = "4288f83726785267c6f2ef073a3d83dc3f9b81464e9f99898240cced85fce35a"

 [[package]]
 name = "async-openai"
-version = "0.41.3"
+version = "0.41.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d72db2750faea2ca5edbf6d0c50277a89dc8f75f5e6ddd695ef30f75e335019b"
+checksum = "3007014661d5b98168b7b6f1014147bce8b1362a194783543eeb9f6117a20be9"
 dependencies = [
 "async-openai-macros",
 "base64 0.22.1",
@@ -196,7 +196,7 @@ dependencies = [
 "futures",
 "getrandom 0.3.4",
 "rand 0.9.4",
- "reqwest 0.13.5",
+ "reqwest 0.13.4",
 "secrecy",
 "serde",
 "serde_json",
@@ -315,21 +315,21 @@ dependencies = [

 [[package]]
 name = "baibot"
-version = "1.25.0"
+version = "1.23.1"
 dependencies = [
 "anthropic",
 "anyhow",
 "async-openai",
- "base64 0.23.1",
+ "base64 0.22.1",
 "chrono",
 "etke_openai_api_rust",
 "matrix-sdk",
 "mime_guess",
 "mxidwc",
 "mxlink",
- "quick_cache 0.7.0",
+ "quick_cache",
 "regex",
- "reqwest 0.13.5",
+ "reqwest 0.13.4",
 "serde",
 "serde_json",
 "serde_yaml_ng",
@@ -353,12 +353,6 @@ version = "0.22.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"

-[[package]]
-name = "base64"
-version = "0.23.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ac07cdecf99051d9a5238b80f35af32cdeba5b336e55d957b318b50137e18da5"
-
 [[package]]
 name = "base64ct"
 version = "1.8.3"
@@ -1239,12 +1233,6 @@ version = "0.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d9c4f5dac5e15c24eb999c26181a6ca40b39fe946cbe4c263c7209467bc83af2"

-[[package]]
-name = "foldhash"
-version = "0.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "77ce24cb58228fbb8aa041425bb1050850ac19177686ea6e0f41a70416f56fdb"
-
 [[package]]
 name = "form_urlencoded"
 version = "1.2.2"
@@ -1469,7 +1457,7 @@ version = "0.15.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9229cfe53dfd69f0609a49f65461bd93001ea1ef889cd5529dd176593f5338a1"
 dependencies = [
- "foldhash 0.1.5",
+ "foldhash",
 ]

 [[package]]
@@ -2194,7 +2182,7 @@ dependencies = [
 "oauth2-reqwest",
 "percent-encoding",
 "pin-project-lite",
- "reqwest 0.13.5",
+ "reqwest 0.13.4",
 "ruma",
 "rustls",
 "rustls-native-certs 0.8.3",
@@ -2486,9 +2474,9 @@ dependencies = [

 [[package]]
 name = "mxidwc"
-version = "1.0.3"
+version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "45b5d51fcf414d2aa6bffc6cd9b037e62732734a944c5da4ace6b9895ec37b93"
+checksum = "5e253f96a03d24d1c0006c5661b1e20a13dc3861f509d76c33b6b44349d4ff3b"
 dependencies = [
 "regex",
 ]
@@ -2504,7 +2492,7 @@ dependencies = [
 "hex",
 "matrix-sdk",
 "mime",
- "quick_cache 0.6.24",
+ "quick_cache",
 "rand 0.10.1",
 "serde",
 "serde_json",
@@ -2589,7 +2577,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "234fb5c965bbce983ee5de636a7a51d6a3223da8067ea02f9ab2d2d78ac08be2"
 dependencies = [
 "oauth2",
- "reqwest 0.13.5",
+ "reqwest 0.13.4",
 ]

 [[package]]
@@ -2860,9 +2848,9 @@ checksum = "007d8adb5ddab6f8e3f491ac63566a7d5002cc7ed73901f72057943fa71ae1ae"

 [[package]]
 name = "quick_cache"
-version = "0.6.24"
+version = "0.6.23"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b9c6658afe513a3b484e3abfdaa0d03ef3c0bbf017542c178dd55f94eb3051f9"
+checksum = "3a3db184a8b66cfe87f0263a1de147a6b554c864d1767c6f7fa4eb0e5497b565"
 dependencies = [
 "ahash",
 "equivalent",
@@ -2870,18 +2858,6 @@ dependencies = [
 "parking_lot",
 ]

-[[package]]
-name = "quick_cache"
-version = "0.7.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "403c1a912fec895cafb223201e368234842acb9220aaf08ab042ae89ba5f135c"
-dependencies = [
- "equivalent",
- "foldhash 0.2.0",
- "hashbrown 0.17.1",
- "parking_lot",
-]
-
 [[package]]
 name = "quinn"
 version = "0.11.9"
@@ -3070,9 +3046,9 @@ dependencies = [

 [[package]]
 name = "regex"
-version = "1.13.1"
+version = "1.12.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f020237b6c8eed93db2e2cb53c00c60a8e1bc73da7d073199a1180401450218d"
+checksum = "f1292b7759ae1cb9ec195452d1390a074f0cd8541ab7a5a8c31cd6db45d4a6ba"
 dependencies = [
 "aho-corasick",
 "memchr",
@@ -3082,9 +3058,9 @@ dependencies = [

 [[package]]
 name = "regex-automata"
-version = "0.4.16"
+version = "0.4.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8fcfdb36bda0c880c5931cdc7a2bcdc8ba4556847b9d912bca70bc94708711ad"
+checksum = "6e1dd4122fc1595e8162618945476892eefca7b88c52820e74af6262213cae8f"
 dependencies = [
 "aho-corasick",
 "memchr",
@@ -3140,11 +3116,11 @@ dependencies = [

 [[package]]
 name = "reqwest"
-version = "0.13.5"
+version = "0.13.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "16a1cfa75cc186dd73d5818e510e042e40927bccc9c236b061cea97e1eb08029"
+checksum = "219c5811de6525e5416c7d5d53bb656d3afdbc6c5af816e0802bcfa42dbdc1c3"
 dependencies = [
- "base64 0.23.1",
+ "base64 0.22.1",
 "bytes",
 "futures-core",
 "futures-util",
@@ -3617,9 +3593,9 @@ checksum = "8a7852d02fc848982e0c167ef163aaff9cd91dc640ba85e263cb1ce46fae51cd"

 [[package]]
 name = "serde"
-version = "1.0.229"
+version = "1.0.228"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4148590afebada386688f18773da617792bf2ef03ffc1e4cbd2b1d45b023e0ba"
+checksum = "9a8e94ea7f378bd32cbbd37198a4a91436180c5bb472411e48b5ec2e2124ae9e"
 dependencies = [
 "serde_core",
 "serde_derive",
@@ -3648,22 +3624,22 @@ dependencies = [

 [[package]]
 name = "serde_core"
-version = "1.0.229"
+version = "1.0.228"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "67dca2c9c51e58a4791a4b1ed58308b39c64224d349a935ab5039aa360942a48"
+checksum = "41d385c7d4ca58e59fc732af25c3983b67ac852c1a25000afe1175de458b67ad"
 dependencies = [
 "serde_derive",
 ]

 [[package]]
 name = "serde_derive"
-version = "1.0.229"
+version = "1.0.228"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e7a5d71263a5a7d47b41f6b3f06ba276f10cc18b0931f1799f710578e2309348"
+checksum = "d540f220d3187173da220f885ab66608367b6574e925011a9353e4badda91d79"
 dependencies = [
 "proc-macro2",
 "quote",
- "syn 3.0.0",
+ "syn 2.0.117",
 ]

 [[package]]
@@ -3681,9 +3657,9 @@ dependencies = [

 [[package]]
 name = "serde_json"
-version = "1.0.151"
+version = "1.0.150"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c841b55ecdae098c80dcae9cf767f6f8a0c2cdb3416bbef72181df4d0fe73f14"
+checksum = "e8014e44b4736ed0538adeecded0fce2a272f22dc9578a7eb6b2d9993c74cfb9"
 dependencies = [
 "itoa",
 "memchr",
@@ -3905,17 +3881,6 @@ dependencies = [
 "unicode-ident",
 ]

-[[package]]
-name = "syn"
-version = "3.0.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f2fac314a64dc9a36e61a9eb4261a5e9bbfbc922b27e518af97bc32b926cf967"
-dependencies = [
- "proc-macro2",
- "quote",
- "unicode-ident",
-]
-
 [[package]]
 name = "sync_wrapper"
 version = "1.0.2"
@@ -4081,9 +4046,9 @@ checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"

 [[package]]
 name = "tokio"
-version = "1.53.1"
+version = "1.52.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "202caea871b69668250d242070849eb495be178ed697a3e98aebce5bc81a0bed"
+checksum = "8fc7f01b389ac15039e4dc9531aa973a135d7a4135281b12d7c1bc79fd57fffe"
 dependencies = [
 "bytes",
 "libc",
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -7,7 +7,7 @@ license = "AGPL-3.0-or-later"
 readme = "README.md"
 keywords = ["matrix", "chat", "bot", "AI", "LLM"]
 include = ["/etc/assets/baibot-torso-768.png", "/src", "/README.md", "/CHANGELOG.md", "/LICENSE"]
-version = "1.25.0"
+version = "1.23.1"
 edition = "2024"

 [lib]
@@ -18,7 +18,7 @@ path = "src/lib.rs"
 anthropic = { git = "https://github.com/etkecc/anthropic-rs.git", branch = "fix-content-block-image" }
 anyhow = "1.0.*"
 async-openai = { version = "0.41.0", features = ["audio", "chat-completion", "image", "responses"] }
-base64 = "0.23.*"
+base64 = "0.22.*"
 chrono = { version = "0.4.*", default-features = false, features = ["std", "now"] }
 # We'd rather not depend on this, but we cannot use the ruma-events EventContent macro without it.
 matrix-sdk = { version = "0.18.0", default-features = false }
@@ -26,8 +26,8 @@ mime_guess = "2.0.*"
 mxidwc = "1.0.*"
 mxlink = ">=1.15.0"
 etke_openai_api_rust = "0.1.*"
-quick_cache = "0.7.*"
-regex = "1.13.*"
+quick_cache = "0.6.*"
+regex = "1.12.*"
 # HTTP client for the native `venice` provider. rustls only (no extra TLS stack), matching the
 # reqwest copy async-openai/matrix-sdk/mxlink already use.
 reqwest = { version = "0.13.*", default-features = false, features = ["json", "multipart", "rustls"] }
@@ -36,7 +36,7 @@ serde_json = "1.0.*"
 serde_yaml_ng = "0.10.*"
 tempfile = "3.27.*"
 tiktoken-rs = { version = "0.12.*", default-features = false }
-tokio = { version = "1.53.*", features = ["rt", "rt-multi-thread", "macros"] }
+tokio = { version = "1.52.*", features = ["rt", "rt-multi-thread", "macros"] }
 tracing = "0.1.*"
 tracing-subscriber = { version = "0.3.*", features = ["env-filter"] }
 url = "2.5.*"
--- a/2
+++ b/2
@@ -4,7 +4,7 @@
 #                                     #
 #######################################

-FROM docker.io/rust:1.98.0-slim-trixie AS build
+FROM docker.io/rust:1.96.0-slim-trixie AS build

 RUN apt-get update && apt-get install -y build-essential pkg-config libssl-dev libsqlite3-dev

--- a/Dockerfile.ci
+++ b/Dockerfile.ci
@@ -0,0 +1,35 @@
+#######################################
+#                                     #
+# Stage 1: building                   #
+#                                     #
+#######################################
+
+FROM docker.io/rust:1.96.0-slim-trixie AS build
+
+RUN apt-get update && apt-get install -y build-essential pkg-config libssl-dev libsqlite3-dev
+
+WORKDIR /app
+
+COPY . /app
+
+RUN cargo build --release
+
+#######################################
+#                                     #
+# Stage 2: packaging                  #
+#                                     #
+#######################################
+
+FROM docker.io/debian:trixie-slim
+
+RUN apt-get update && apt-get install -y ca-certificates sqlite3 && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+COPY --from=build /app/target/release/baibot .
+
+ENTRYPOINT ["/bin/sh", "-c"]
+
+CMD ["/app/baibot"]
--- a/README.md
+++ b/README.md
@@ -30,7 +30,7 @@ It's influenced by [chaz](https://github.com/arcuru/chaz), but does **not** use

 - 🔒 Supports [encryption](./docs/features.md#-encryption) for Matrix communication and Account-Data-stored configuration

- ♻️ Supports [context-management](./docs/configuration/text-generation.md#️-context-management) for every [provider](./docs/providers.md) (automatically trimming older messages on whole-turn boundaries once a conversation outgrows the context window)
+- ♻️ Supports [context-management](./docs/configuration/text-generation.md#️-context-management) handling on some models (automatically adjusting the message history length, etc.)

 - 🛠️ Allows **customizing much of the bot's [configuration](./docs/configuration/README.md)** at runtime (using commands sent via chat)

--- a/docs/configuration/text-generation.md
+++ b/docs/configuration/text-generation.md
@@ -50,22 +50,13 @@ Example: `!bai config room text-generation set-auto-usage only_for_voice` (this

 ### ♻️ Context Management

-The bot also supports ♻️ **context management**, which automatically trims the oldest messages once a conversation grows past the context window. It drops whole turns at a time, so a reply is never separated from the message it answered.
+The bot also supports ♻️ **context management**, which automatically adjusts the message history length, etc.

-Counting tokens precisely needs the model's own tokenizer. For [OpenAI](../providers.md#openai) models, the bot counts them with the [tiktoken-rs](https://github.com/zurawiki/tiktoken-rs) library. For every other provider, including the recommended [Venice](../providers.md#venice), the bot falls back to a provider-neutral **approximation** that needs no per-model tokenizer: it counts ASCII text at about four characters per token and other scripts (Cyrillic, CJK, and so on) at about two. Treat it as rough, within roughly 10-20% of the real count for typical text, which is plenty for keeping a long conversation inside the context window.
+This feature relies on [tokenization](https://en.wikipedia.org/wiki/Large_language_model#Tokenization) performed by the [tiktoken-rs](https://github.com/zurawiki/tiktoken-rs) library which is [poorly well-maintained](https://github.com/zurawiki/tiktoken-rs/issues/50) and only works well for [OpenAI](../providers.md#openai) models.

 This setting is **disabled by default**, but can be enabled via `!bai config room text-generation set-context-management-enabled true` (this can also be set globally, see [🛠️ Room Settings](./README.md#room-settings)).


-### 💭 Thinking Notice
-
-The bot can post a 💭 **"thinking…" notice** while text generation is running, useful for slow models (for example, reasoning models that may run for minutes) where the response would otherwise look stuck.
-
-When enabled, a placeholder message appears only after a short delay (so fast responses get no notice), updates periodically with varying status text, and is then edited in place to become the final answer.
-
-This setting is **disabled by default**, but can be enabled via `!bai config room text-generation set-thinking-notice-enabled true` (this can also be set globally, see [🛠️ Room Settings](./README.md#room-settings)).
-
-
 ### 👤 Sender Context Mode

 In multi-user rooms, it may be useful for the model to know which participant sent each message in the conversation context.
--- a/docs/installation.md
+++ b/docs/installation.md
@@ -57,34 +57,6 @@ CONTAINER_IMAGE_NAME=ghcr.io/etkecc/baibot:v1.0.0
  $CONTAINER_IMAGE_NAME
 ```

-Alternatively, you can use [Docker Compose](https://docs.docker.com/compose/) with a `compose.yml` file like this:
-
-```yaml
-services:
-  baibot:
-    container_name: baibot
-    # Adjust the version tag to point to the latest available tagged version.
-    # If building your own container image name, adjust to something like `localhost/baibot:latest`.
-    image: ghcr.io/etkecc/baibot:v1.0.0
-    # Set `UID` and `GID` in a `.env` file next to `compose.yml` (e.g. `UID=1000`, `GID=1000`)
-    # or export them in your shell (`export UID GID="$(id -g)"`).
-    # These should match the user that owns the data directory.
-    user: "${UID:-1000}:${GID:-1000}"
-    environment:
-      # Other settings can also be set via environment variables.
-      # See the 🛠️ Configuration documentation (docs/configuration/README.md) for details.
-      BAIBOT_PERSISTENCE_DATA_DIR_PATH: /data
-    volumes:
-      - /path/to/config.yml:/app/config.yml:ro
-      - /path/to/data:/data
-    cap_drop:
-      - ALL
-    read_only: true
-    tmpfs:
-      - /tmp:rw,noexec,nosuid,size=1024m
-    restart: unless-stopped
-```
-
 💡 If you've defined the `persistence.data_dir_path` setting in the `config.yml` file, you can skip the `BAIBOT_PERSISTENCE_DATA_DIR_PATH` environment variable.


--- a/docs/providers.md
+++ b/docs/providers.md
@@ -24,7 +24,7 @@ The list of supported providers is below.

 ### How to choose a provider

-If you're not sure which provider to start with, **we recommend [Venice](#venice)**: it's the most capable provider baibot supports (covering [💬 text-generation](./features.md#-text-generation) with vision, file inputs, prompt caching, and native web search, plus [🖌️ image-generation](./features.md#️-image-creation) incl. editing, [🦻 speech-to-text](./features.md#-speech-to-text), and [🗣️ text-to-speech](./features.md#️-text-to-speech)) and the only one that runs inference with no logging and no training on your data. If you'd rather start with the most widely-used option, [OpenAI](#openai) is a solid, well-supported choice too.
+If you're not sure which provider to start with, **we recommend [OpenAI](#openai)** as it's the most popular and has the **widest range of capabilities**: [💬 text-generation](./features.md#-text-generation) (incl. vision, incl. [🛠️ tools](./features.md#️-built-in-tools-openai-only)), [🖌️ image-generation](./features.md#️image-generation), [🦻 speech-to-text](./features.md#-speech-to-text), [🗣️ text-to-speech](./features.md#️-text-to-speech).

 You don't need to choose just one though. The bot supports [mixing & matching models](./features.md#-mixing--matching-models), so you can use multiple providers at the same time.

@@ -176,10 +176,10 @@ This provider is just as featureful as the [OpenAI](#openai) provider, but is mo

 ### Venice

-[Venice AI](https://venice.ai/chat?ref=kpXDe6) _(ref link with a $10 bonus for you)_ runs inference on Venice-controlled GPUs or zero-data-retention partner infrastructure and stores no prompts or responses, so your conversations don't linger anywhere. It serves both frontier proprietary models and the latest open-source ones.
+[Venice AI](https://venice.ai) runs inference on Venice-controlled GPUs or zero-data-retention partner infrastructure and stores no prompts or responses, so your conversations don't linger anywhere. It serves both frontier proprietary models and the latest open-source ones.

 - 🆔 Identifier: `venice`
- 🔗 Links: [🏠 Home page](https://venice.ai/chat?ref=kpXDe6), [👤 Sign up](https://venice.ai/chat?ref=kpXDe6), [📋 Models list](https://docs.venice.ai/models/overview)
+- 🔗 Links: [🏠 Home page](https://venice.ai), [👤 Sign up](https://venice.ai), [📋 Models list](https://api.venice.ai/api/v1/models)
 - 🌟 Capabilities: [🖌️ image-generation](./features.md#️-image-creation) (incl. editing, via the native knob-rich `/image/generate` and `/image/edit` endpoints), [💬 text-generation](./features.md#-text-generation) (incl. vision, file inputs like PDF and DOCX, and prompt caching; native web search via the `venice_parameters` config), [🗣️ text-to-speech](./features.md#️-text-to-speech), [🦻 speech-to-text](./features.md#-speech-to-text)
 - 🗲 Quick start:
  - create a room-local agent: `!bai agent create-room-local venice my-venice-agent`
--- a/etc/services/continuwuity/compose.yml
+++ b/etc/services/continuwuity/compose.yml
@@ -1,14 +1,14 @@
 services:
  continuwuity:
-    image: forgejo.ellis.link/continuwuation/continuwuity:v26.8.1
+    image: forgejo.ellis.link/continuwuation/continuwuity:v0.5.10
    user: "${UID}:${GID}"
    restart: unless-stopped
    cap_drop:
      - ALL
    read_only: true
    environment:
-      CONTINUWUITY_CONFIG: /etc/continuwuity/continuwuity.toml
-      CONTINUWUITY_DATABASE_PATH: /var/lib/continuwuity
+      CONDUWUIT_CONFIG: /etc/continuwuity/continuwuity.toml
+      CONDUWUIT_DATABASE_PATH: /var/lib/continuwuity
    ports:
      - "${SERVICE_CONTINUWUITY_BIND_PORT_CLIENT_API}:6167"
    volumes:
--- a/etc/services/element-web/compose.yml
+++ b/etc/services/element-web/compose.yml
@@ -1,6 +1,6 @@
 services:
  element-web:
-    image: ghcr.io/element-hq/element-web:v1.12.27
+    image: ghcr.io/element-hq/element-web:v1.12.21
    user: "${UID}:${GID}"
    restart: unless-stopped
    environment:
--- a/etc/services/ollama/compose.yml
+++ b/etc/services/ollama/compose.yml
@@ -1,6 +1,6 @@
 services:
  ollama:
-    image: docker.io/ollama/ollama:0.33.3
+    image: docker.io/ollama/ollama:0.30.10
    restart: unless-stopped
    ports:
      - "${SERVICE_OLLAMA_BIND_PORT_HTTP}:11434"
--- a/etc/services/synapse/compose.yml
+++ b/etc/services/synapse/compose.yml
@@ -1,6 +1,6 @@
 services:
  postgres:
-    image: docker.io/postgres:18.6-alpine
+    image: docker.io/postgres:18.4-alpine
    user: ${UID}:${GID}
    restart: unless-stopped
    environment:
@@ -14,7 +14,7 @@ services:
    - /etc/passwd:/etc/passwd:ro

  synapse:
-    image: ghcr.io/element-hq/synapse:v1.160.0
+    image: ghcr.io/element-hq/synapse:v1.155.0
    user: "${UID}:${GID}"
    restart: unless-stopped
    entrypoint: python
--- a/24
+++ b/24
@@ -271,29 +271,7 @@ prek-run-on-all *args: _ensure_mise_tools_installed

 # Installs the git pre-commit hook (runs prek automatically before each commit)
 prek-install-git-pre-commit-hook: _ensure_mise_tools_installed
-	#!/usr/bin/env sh
-	set -eu
-	just --justfile {{ justfile() }} mise exec -- prek install
-	# The installed git hooks run later under Git, outside this just/mise environment,
-	# so they need to be told how to find their tooling:
-	#
-	# - MISE_DATA_DIR / MISE_TRUSTED_CONFIG_PATHS make mise resolve against this project's
-	#   own data directory. Without them mise falls back to the global one and silently
-	#   installs a second copy of the tool there.
-	# - prek bakes the full path of the currently installed version into the hook
-	#   (var/mise/installs/prek/<version>/...), which stops working as soon as the pinned
-	#   version changes or old versions are pruned. Pointing at mise's shim instead makes
-	#   the hook resolve whatever mise.toml pins, at the time it runs.
-	#
-	# Which hook files prek installs depends on `default_install_hook_types` in
-	# .pre-commit-config.yaml, so patch every hook file that prek generated.
-	for hook in "{{ justfile_directory() }}"/.git/hooks/*; do
-		[ -f "$hook" ] || continue
-		grep -q 'generated by prek' "$hook" || continue
-		grep -q '^export MISE_DATA_DIR=' "$hook" || sed -i '2iexport MISE_DATA_DIR="{{ mise_data_dir }}"' "$hook"
-		grep -q '^export MISE_TRUSTED_CONFIG_PATHS=' "$hook" || sed -i '3iexport MISE_TRUSTED_CONFIG_PATHS="{{ mise_trusted_config_paths }}"' "$hook"
-		sed -i 's#^PREK=".*"$#PREK="{{ mise_data_dir }}/shims/prek"#' "$hook"
-	done
+	@just --justfile {{ justfile() }} mise exec -- prek install

 # Internal - ensures var/mise directory exists
 _ensure_mise_data_directory:
--- a/mise.toml
+++ b/mise.toml
@@ -1,2 +1,6 @@
 [tools]
-prek = "0.5.2"
+prek = "0.4.5"
+
+[settings]
+# Disable automatic trust prompts - we trust this config
+yes = true
--- a/renovate.json
+++ b/renovate.json
@@ -5,62 +5,5 @@
 	],
 	"labels": [
 		"dependencies"
-	],
-	"packageRules": [
-		{
-			"description": "Cargo dependencies, the Rust toolchain pin, prek (via mise) and the workflows' own actions merge by pushing to main, without a pull request. ci.yml runs on `push: [\"**\"]`, so the Renovate branch itself is compiled, linted with `clippy -D warnings` and unit-tested first; a failure leaves the branch red and Renovate raises a pull request instead of merging.",
-			"matchManagers": [
-				"cargo",
-				"rust-toolchain",
-				"mise",
-				"github-actions"
-			],
-			"matchUpdateTypes": [
-				"minor",
-				"patch",
-				"digest"
-			],
-			"automerge": true,
-			"automergeType": "branch",
-			"platformAutomerge": false
-		},
-		{
-			"description": "The release image's base (Dockerfile). Gated by ci.yml's docker-build job, which builds the image exactly as Publish does but with `push: false`, and which only runs when the Dockerfile actually changed.",
-			"matchManagers": [
-				"dockerfile"
-			],
-			"matchUpdateTypes": [
-				"minor",
-				"patch",
-				"digest"
-			],
-			"automerge": true,
-			"automergeType": "branch",
-			"platformAutomerge": false
-		},
-		{
-			"description": "Local development service images under etc/services/** - the homeservers and LLM backends that `just services-start` brings up. They are never part of a shipped artifact and CI does not run them, so the justification here is blast radius rather than validation: the worst case is a broken local development stack, fixed by pinning back.",
-			"matchManagers": [
-				"docker-compose"
-			],
-			"matchFileNames": [
-				"etc/services/**"
-			],
-			"matchUpdateTypes": [
-				"minor",
-				"patch",
-				"digest"
-			],
-			"automerge": true,
-			"automergeType": "branch",
-			"platformAutomerge": false
-		},
-		{
-			"description": "Major updates always get a pull request and a human. This is deliberately the last rule so that it overrides the automerge rules above for every manager.",
-			"matchUpdateTypes": [
-				"major"
-			],
-			"automerge": false
-		}
 	]
 }
--- a/rust-toolchain.toml
+++ b/rust-toolchain.toml
@@ -1,4 +1,4 @@
 [toolchain]
-channel = "1.98.1"
+channel = "1.96.0"
 components = ["rustfmt", "clippy"]
 profile = "default"
--- a/src/agent/provider/anthropic/controller.rs
+++ b/src/agent/provider/anthropic/controller.rs
@@ -15,7 +15,7 @@ use crate::agent::provider::{
 };
 use crate::conversation::llm::{
    Author as LLMAuthor, Conversation as LLMConversation, Message as LLMMessage,
-    MessageContent as LLMMessageContent, TokenEstimate, shorten_messages_list_to_context_size,
+    MessageContent as LLMMessageContent, shorten_messages_list_to_context_size,
 };
 use crate::strings;

@@ -130,7 +130,7 @@ impl ControllerTrait for Controller {
            tracing::trace!("Shortening messages list to context size");

            conversation_messages = shorten_messages_list_to_context_size(
-                TokenEstimate::Approximate,
+                &text_generation_config.model_id,
                &prompt_message,
                conversation_messages,
                Some(text_generation_config.max_response_tokens),
--- a/src/agent/provider/entity/text_generation/prompt_variables.rs
+++ b/src/agent/provider/entity/text_generation/prompt_variables.rs
@@ -1,7 +1,6 @@
 use chrono::{DateTime, Utc};
 use std::collections::HashMap;

-#[derive(Clone)]
 pub struct TextGenerationPromptVariables {
    map: HashMap<String, String>,
 }
--- a/src/agent/provider/openai/controller.rs
+++ b/src/agent/provider/openai/controller.rs
@@ -24,7 +24,7 @@ use crate::{
    },
    conversation::llm::{
        Author as LLMAuthor, Conversation as LLMConversation, Message as LLMMessage,
-        MessageContent as LLMMessageContent, TokenEstimate, shorten_messages_list_to_context_size,
+        MessageContent as LLMMessageContent, shorten_messages_list_to_context_size,
    },
    utils::base64::base64_decode,
 };
@@ -117,7 +117,7 @@ impl ControllerTrait for Controller {
            tracing::trace!("Shortening messages list to context size");

            conversation_messages = shorten_messages_list_to_context_size(
-                TokenEstimate::Tiktoken(&text_generation_config.model_id),
+                &text_generation_config.model_id,
                &prompt_message,
                conversation_messages,
                text_generation_config.max_response_tokens,
--- a/src/agent/provider/openai_compat/controller.rs
+++ b/src/agent/provider/openai_compat/controller.rs
@@ -15,7 +15,7 @@ use crate::{
    },
    conversation::llm::{
        Author as LLMAuthor, Conversation as LLMConversation, Message as LLMMessage,
-        MessageContent as LLMMessageContent, TokenEstimate, shorten_messages_list_to_context_size,
+        MessageContent as LLMMessageContent, shorten_messages_list_to_context_size,
    },
 };
 use crate::{
@@ -114,7 +114,7 @@ impl ControllerTrait for Controller {
            tracing::trace!("Shortening messages list to context size");

            conversation_messages = shorten_messages_list_to_context_size(
-                TokenEstimate::Approximate,
+                &text_generation_config.model_id,
                &prompt_message,
                conversation_messages,
                text_generation_config.max_response_tokens,
--- a/src/agent/provider/venice/chat.rs
+++ b/src/agent/provider/venice/chat.rs
@@ -8,7 +8,7 @@ use crate::agent::AgentPurpose;
 use crate::agent::provider::entity::{TextGenerationParams, TextGenerationResult};
 use crate::conversation::llm::{
    Author as LLMAuthor, Conversation as LLMConversation, Message as LLMMessage,
-    MessageContent as LLMMessageContent, TokenEstimate, shorten_messages_list_to_context_size,
+    MessageContent as LLMMessageContent, shorten_messages_list_to_context_size,
 };
 use crate::strings;

@@ -64,7 +64,7 @@ pub async fn generate_text(

    if params.context_management_enabled {
        conversation_messages = shorten_messages_list_to_context_size(
-            TokenEstimate::Approximate,
+            &text_generation_config.model_id,
            &prompt_message,
            conversation_messages,
            text_generation_config.max_response_tokens,
--- a/src/agent/provider/venice/controller.rs
+++ b/src/agent/provider/venice/controller.rs
@@ -35,15 +35,10 @@ impl Controller {
            .build()
            .unwrap_or_else(|_| reqwest::Client::new());

-        // Process-global per-deployment cache rather than a fresh one: dynamic agents rebuild their
-        // controller on every message, so an instance-owned cache would never retain a learned
-        // rejection and the same unsupported field would 400 (and warn) on every turn.
-        let unsupported_fields = UnsupportedFieldsCache::shared_for(&config.base_url);
-
        Self {
            config,
            http,
-            unsupported_fields,
+            unsupported_fields: UnsupportedFieldsCache::default(),
        }
    }
 }
--- a/src/agent/provider/venice/recovery.rs
+++ b/src/agent/provider/venice/recovery.rs
@@ -45,38 +45,7 @@ pub(super) struct UnsupportedFieldsCache {
    inner: Arc<RwLock<HashMap<String, HashSet<String>>>>,
 }

-/// Process-global registry of per-deployment caches, keyed by Venice base URL. A `Controller` is
-/// rebuilt from its config on every message for dynamic (global/room-local) agents (see
-/// `agent::manager::available_room_agents_by_room_config_context`), so a cache stored on the
-/// controller would be reset each message and the "process-lived" intent above would never hold.
-/// The registry lets a rebuilt controller re-attach to the same cache. Keyed by base URL because
-/// "which fields a model rejects" is a property of the deployment+model, not of the agent instance:
-/// agents on the same Venice deployment share learnings, while a distinct deployment keeps its own,
-/// so a model name that supports a field on one deployment is never proactively stripped against
-/// another.
-fn registry() -> &'static RwLock<HashMap<String, UnsupportedFieldsCache>> {
-    static REGISTRY: OnceLock<RwLock<HashMap<String, UnsupportedFieldsCache>>> = OnceLock::new();
-    REGISTRY.get_or_init(|| RwLock::new(HashMap::new()))
-}
-
 impl UnsupportedFieldsCache {
-    /// The process-global cache for `base_url`, created on first use and shared by every controller
-    /// for that deployment thereafter. This is what makes a learned rejection survive the
-    /// per-message controller rebuild. A poisoned registry lock degrades to an isolated cache:
-    /// correctness holds, only cross-controller sharing is lost for that call.
-    pub(super) fn shared_for(base_url: &str) -> Self {
-        if let Ok(map) = registry().read()
-            && let Some(cache) = map.get(base_url)
-        {
-            return cache.clone();
-        }
-
-        match registry().write() {
-            Ok(mut map) => map.entry(base_url.to_owned()).or_default().clone(),
-            Err(_) => Self::default(),
-        }
-    }
-
    /// Fields already known unsupported for `model_id`. Returns an empty set on an unknown model or
    /// a poisoned lock, so a cache failure degrades to "strip nothing proactively" rather than
    /// breaking the request path.
@@ -262,33 +231,6 @@ mod tests {
        assert!(cache.known_for("kimi-k2-5").is_empty());
    }

-    #[test]
-    fn shared_for_survives_controller_rebuild_and_isolates_deployments() {
-        // Distinct, test-only base URLs so the process-global registry can't collide with another
-        // test running in parallel.
-        let url_a = "https://shared-for-test-a.invalid/api/v1";
-        let url_b = "https://shared-for-test-b.invalid/api/v1";
-
-        // A controller rebuilt for the same deployment (a fresh `shared_for` call, as happens per
-        // message for dynamic agents) re-attaches to the SAME cache, so an earlier learning holds.
-        let first = UnsupportedFieldsCache::shared_for(url_a);
-        first.record("model-x", "reasoning_effort");
-
-        let rebuilt = UnsupportedFieldsCache::shared_for(url_a);
-        assert!(
-            rebuilt.known_for("model-x").contains("reasoning_effort"),
-            "a rebuilt controller for the same deployment must see the earlier rejection"
-        );
-
-        // A different deployment keeps its own learnings: a model name that rejects a field on one
-        // Venice must not silence/strip it on another.
-        let other_deployment = UnsupportedFieldsCache::shared_for(url_b);
-        assert!(
-            other_deployment.known_for("model-x").is_empty(),
-            "rejections must not leak across deployments"
-        );
-    }
-
    #[test]
    fn extracts_a_human_message_from_error_envelopes() {
        assert_eq!(
--- a/src/bot/messaging.rs
+++ b/src/bot/messaging.rs
@@ -1,12 +1,8 @@
 use mxlink::matrix_sdk::{
    Room,
-    room::edit::EditedContent,
    ruma::{
-        EventId, OwnedEventId,
-        api::client::receipt::create_receipt::v3::ReceiptType,
-        events::room::message::{
-            OriginalSyncRoomMessageEvent, RoomMessageEventContentWithoutRelation,
-        },
+        OwnedEventId, api::client::receipt::create_receipt::v3::ReceiptType,
+        events::room::message::OriginalSyncRoomMessageEvent,
    },
 };

@@ -56,83 +52,6 @@ impl Messaging {
        }
    }

-    /// Like `send_text_markdown_no_fail`, but logs send failures at `warn` instead of `error`.
-    /// For cosmetic, best-effort sends (the thinking-notice placeholder) where a failure is
-    /// acceptable-impact: the real response still ships, so this must NOT page the team.
-    pub async fn send_text_markdown_no_fail_quietly(
-        &self,
-        room: &Room,
-        message: String,
-        response_type: MessageResponseType,
-    ) -> Option<mxlink::matrix_sdk::ruma::api::client::message::send_message_event::v3::Response>
-    {
-        let result = self
-            .bot
-            .matrix_link()
-            .messaging()
-            .send_text_markdown(room, message, response_type)
-            .await;
-
-        match result {
-            Ok(result) => Some(result),
-            Err(err) => {
-                tracing::warn!(
-                    room_id = format!("{:?}", room.room_id()),
-                    ?err,
-                    "Failed to send thinking-notice placeholder to room",
-                );
-                None
-            }
-        }
-    }
-
-    /// Edits an existing message's text in place (`m.replace`), best-effort.
-    ///
-    /// Built and sent directly via matrix-sdk's `make_edit_event` + `room.send`,
-    /// deliberately bypassing the mxlink messaging layer: that layer overwrites
-    /// `relates_to` from a `MessageResponseType`, which would clobber the
-    /// `m.replace` relation and turn the edit into a brand-new message. The edit
-    /// stays in the original's thread by inheritance, so no `response_type` is needed.
-    /// Failures are warned and swallowed so a flickered notice never breaks the real response.
-    pub async fn edit_text_markdown_no_fail(
-        &self,
-        room: &Room,
-        event_id: &EventId,
-        markdown: String,
-    ) -> Option<mxlink::matrix_sdk::ruma::api::client::message::send_message_event::v3::Response>
-    {
-        let new_content = RoomMessageEventContentWithoutRelation::text_markdown(markdown);
-
-        let edit_content = match room
-            .make_edit_event(event_id, EditedContent::RoomMessage(new_content))
-            .await
-        {
-            Ok(edit_content) => edit_content,
-            Err(err) => {
-                tracing::warn!(
-                    room_id = format!("{:?}", room.room_id()),
-                    ?event_id,
-                    ?err,
-                    "Failed to build edit event",
-                );
-                return None;
-            }
-        };
-
-        match room.send(edit_content).await {
-            Ok(result) => Some(result.response),
-            Err(err) => {
-                tracing::warn!(
-                    room_id = format!("{:?}", room.room_id()),
-                    ?event_id,
-                    ?err,
-                    "Failed to send edit to room",
-                );
-                None
-            }
-        }
-    }
-
    pub async fn send_notice_markdown_no_fail(
        &self,
        room: &Room,
--- a/src/controller/cfg/controller_type.rs
+++ b/src/controller/cfg/controller_type.rs
@@ -38,9 +38,6 @@ pub enum ConfigTextGenerationSettingRelatedControllerType {
    GetContextManagementEnabled,
    SetContextManagementEnabled(Option<bool>),

-    GetThinkingNoticeEnabled,
-    SetThinkingNoticeEnabled(Option<bool>),
-
    GetPrefixRequirementType,
    SetPrefixRequirementType(Option<TextGenerationPrefixRequirementType>),

--- a/src/controller/cfg/determination/text_generation/mod.rs
+++ b/src/controller/cfg/determination/text_generation/mod.rs
@@ -55,44 +55,6 @@ pub(super) fn determine(
        );
    }

-    if let Some(remaining_text) = text.strip_prefix("thinking-notice-enabled") {
-        let remaining_text = remaining_text.trim();
-
-        if !remaining_text.is_empty() {
-            return Err(ControllerType::Error(
-                strings::cfg::configuration_getter_used_with_extra_text(
-                    "thinking-notice-enabled",
-                    remaining_text,
-                )
-                .to_owned(),
-            ));
-        }
-
-        return Ok(ConfigTextGenerationSettingRelatedControllerType::GetThinkingNoticeEnabled);
-    }
-
-    if let Some(value_string) = text.strip_prefix("set-thinking-notice-enabled") {
-        let value_string = value_string.trim().to_owned();
-        let value_opt = if value_string.is_empty() {
-            None
-        } else {
-            let value_string_lowercase = value_string.to_lowercase();
-            Some(match value_string_lowercase.as_str() {
-                "true" => true,
-                "false" => false,
-                _ => {
-                    return Err(ControllerType::Error(
-                        strings::cfg::configuration_value_unrecognized(&value_string).to_owned(),
-                    ));
-                }
-            })
-        };
-
-        return Ok(
-            ConfigTextGenerationSettingRelatedControllerType::SetThinkingNoticeEnabled(value_opt),
-        );
-    }
-
    if let Some(remaining_text) = text.strip_prefix("prefix-requirement-type") {
        let remaining_text = remaining_text.trim();

--- a/src/controller/cfg/dispatching/text_generation.rs
+++ b/src/controller/cfg/dispatching/text_generation.rs
@@ -43,27 +43,6 @@ pub(super) async fn dispatch(
            }
        }

-        ConfigTextGenerationSettingRelatedControllerType::GetThinkingNoticeEnabled => {
-            let value = &room_settings.text_generation.thinking_notice_enabled;
-            setting_get::<bool>(bot, message_context, value).await
-        }
-        ConfigTextGenerationSettingRelatedControllerType::SetThinkingNoticeEnabled(value) => {
-            let value = value.to_owned();
-
-            let setter_callback = Box::new(move |room_settings: &mut RoomSettings| {
-                room_settings.text_generation.thinking_notice_enabled = value;
-            });
-
-            match config_type {
-                SettingsStorageSource::Room => {
-                    room_setting_set::<bool>(bot, message_context, &value, setter_callback).await
-                }
-                SettingsStorageSource::Global => {
-                    global_setting_set::<bool>(bot, message_context, &value, setter_callback).await
-                }
-            }
-        }
-
        ConfigTextGenerationSettingRelatedControllerType::GetPrefixRequirementType => {
            let value = &room_settings.text_generation.prefix_requirement_type;
            setting_get::<TextGenerationPrefixRequirementType>(bot, message_context, value).await
--- a/src/controller/cfg/help.rs
+++ b/src/controller/cfg/help.rs
@@ -136,7 +136,7 @@ fn build_section_text_generation(command_prefix: &str, bot_username: &str) -> St
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_show(
+        &strings::help::cfg::current_setting_show(
            command_prefix,
            "text-generation prefix-requirement-type"
        )
@@ -144,7 +144,7 @@ fn build_section_text_generation(command_prefix: &str, bot_username: &str) -> St
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_set(
+        &strings::help::cfg::current_setting_set(
            command_prefix,
            "text-generation set-prefix-requirement-type VALUE"
        )
@@ -152,7 +152,7 @@ fn build_section_text_generation(command_prefix: &str, bot_username: &str) -> St
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_unset(
+        &strings::help::cfg::current_setting_unset(
            command_prefix,
            "text-generation set-prefix-requirement-type"
        )
@@ -176,12 +176,12 @@ fn build_section_text_generation(command_prefix: &str, bot_username: &str) -> St
    message.push_str("\n\n");
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_show(command_prefix, "text-generation auto-usage")
+        &strings::help::cfg::current_setting_show(command_prefix, "text-generation auto-usage")
    ));
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_set(
+        &strings::help::cfg::current_setting_set(
            command_prefix,
            "text-generation set-auto-usage VALUE"
        )
@@ -189,7 +189,10 @@ fn build_section_text_generation(command_prefix: &str, bot_username: &str) -> St
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_unset(command_prefix, "text-generation set-auto-usage")
+        &strings::help::cfg::current_setting_unset(
+            command_prefix,
+            "text-generation set-auto-usage"
+        )
    ));
    message.push_str("\n\n");

@@ -208,7 +211,7 @@ fn build_section_text_generation(command_prefix: &str, bot_username: &str) -> St
    message.push_str("\n\n");
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_show(
+        &strings::help::cfg::current_setting_show(
            command_prefix,
            "text-generation context-management-enabled"
        )
@@ -216,7 +219,7 @@ fn build_section_text_generation(command_prefix: &str, bot_username: &str) -> St
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_set(
+        &strings::help::cfg::current_setting_set(
            command_prefix,
            "text-generation set-context-management-enabled VALUE"
        )
@@ -224,51 +227,13 @@ fn build_section_text_generation(command_prefix: &str, bot_username: &str) -> St
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_unset(
+        &strings::help::cfg::current_setting_unset(
            command_prefix,
            "text-generation set-context-management-enabled"
        )
    ));
    message.push_str("\n\n");

-    // Thinking Notice
-
-    message.push_str(&format!(
-        "#### {}",
-        strings::help::cfg::text_generation_thinking_notice_heading()
-    ));
-    message.push_str("\n\n");
-    message.push_str(&strings::help::cfg::text_generation_thinking_notice_intro());
-    message.push('\n');
-    message.push_str(
-        &strings::help::cfg::the_following_configuration_values_are_recognized(vec![true, false]),
-    );
-    message.push_str("\n\n");
-    message.push_str(&format!(
-        "- {}",
-        strings::help::cfg::current_setting_show(
-            command_prefix,
-            "text-generation thinking-notice-enabled"
-        )
-    ));
-    message.push('\n');
-    message.push_str(&format!(
-        "- {}",
-        strings::help::cfg::current_setting_set(
-            command_prefix,
-            "text-generation set-thinking-notice-enabled VALUE"
-        )
-    ));
-    message.push('\n');
-    message.push_str(&format!(
-        "- {}",
-        strings::help::cfg::current_setting_unset(
-            command_prefix,
-            "text-generation set-thinking-notice-enabled"
-        )
-    ));
-    message.push_str("\n\n");
-
    // Sender Context

    message.push_str(&format!(
@@ -286,7 +251,7 @@ fn build_section_text_generation(command_prefix: &str, bot_username: &str) -> St
    message.push_str("\n\n");
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_show(
+        &strings::help::cfg::current_setting_show(
            command_prefix,
            "text-generation sender-context-mode"
        )
@@ -294,7 +259,7 @@ fn build_section_text_generation(command_prefix: &str, bot_username: &str) -> St
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_set(
+        &strings::help::cfg::current_setting_set(
            command_prefix,
            "text-generation set-sender-context-mode VALUE"
        )
@@ -302,7 +267,7 @@ fn build_section_text_generation(command_prefix: &str, bot_username: &str) -> St
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_unset(
+        &strings::help::cfg::current_setting_unset(
            command_prefix,
            "text-generation set-sender-context-mode"
        )
@@ -320,12 +285,15 @@ fn build_section_text_generation(command_prefix: &str, bot_username: &str) -> St
    message.push_str("\n\n");
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_show(command_prefix, "text-generation prompt-override")
+        &strings::help::cfg::current_setting_show(
+            command_prefix,
+            "text-generation prompt-override"
+        )
    ));
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_set(
+        &strings::help::cfg::current_setting_set(
            command_prefix,
            "text-generation set-prompt-override VALUE"
        )
@@ -333,7 +301,7 @@ fn build_section_text_generation(command_prefix: &str, bot_username: &str) -> St
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_unset(
+        &strings::help::cfg::current_setting_unset(
            command_prefix,
            "text-generation set-prompt-override"
        )
@@ -351,7 +319,7 @@ fn build_section_text_generation(command_prefix: &str, bot_username: &str) -> St
    message.push_str("\n\n");
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_show(
+        &strings::help::cfg::current_setting_show(
            command_prefix,
            "text-generation temperature-override"
        )
@@ -359,7 +327,7 @@ fn build_section_text_generation(command_prefix: &str, bot_username: &str) -> St
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_set(
+        &strings::help::cfg::current_setting_set(
            command_prefix,
            "text-generation set-temperature-override VALUE"
        )
@@ -367,7 +335,7 @@ fn build_section_text_generation(command_prefix: &str, bot_username: &str) -> St
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_unset(
+        &strings::help::cfg::current_setting_unset(
            command_prefix,
            "text-generation set-temperature-override"
        )
@@ -404,12 +372,12 @@ fn build_section_speech_to_text(command_prefix: &str) -> String {
    message.push_str("\n\n");
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_show(command_prefix, "speech-to-text flow-type")
+        &strings::help::cfg::current_setting_show(command_prefix, "speech-to-text flow-type")
    ));
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_set(
+        &strings::help::cfg::current_setting_set(
            command_prefix,
            "speech-to-text set-flow-type VALUE"
        )
@@ -417,7 +385,7 @@ fn build_section_speech_to_text(command_prefix: &str) -> String {
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_unset(command_prefix, "speech-to-text set-flow-type")
+        &strings::help::cfg::current_setting_unset(command_prefix, "speech-to-text set-flow-type")
    ));
    message.push_str("\n\n");

@@ -438,7 +406,7 @@ fn build_section_speech_to_text(command_prefix: &str) -> String {
    message.push_str("\n\n");
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_show(
+        &strings::help::cfg::current_setting_show(
            command_prefix,
            "speech-to-text msg-type-for-non-threaded-only-transcribed-messages"
        )
@@ -446,7 +414,7 @@ fn build_section_speech_to_text(command_prefix: &str) -> String {
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_set(
+        &strings::help::cfg::current_setting_set(
            command_prefix,
            "speech-to-text set-msg-type-for-non-threaded-only-transcribed-messages VALUE"
        )
@@ -454,7 +422,7 @@ fn build_section_speech_to_text(command_prefix: &str) -> String {
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_unset(
+        &strings::help::cfg::current_setting_unset(
            command_prefix,
            "speech-to-text set-msg-type-for-non-threaded-only-transcribed-messages"
        )
@@ -472,12 +440,12 @@ fn build_section_speech_to_text(command_prefix: &str) -> String {
    message.push_str("\n\n");
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_show(command_prefix, "speech-to-text language")
+        &strings::help::cfg::current_setting_show(command_prefix, "speech-to-text language")
    ));
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_set(
+        &strings::help::cfg::current_setting_set(
            command_prefix,
            "speech-to-text set-language VALUE"
        )
@@ -485,7 +453,7 @@ fn build_section_speech_to_text(command_prefix: &str) -> String {
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_unset(command_prefix, "speech-to-text set-language")
+        &strings::help::cfg::current_setting_unset(command_prefix, "speech-to-text set-language")
    ));
    message.push_str("\n\n");

@@ -520,7 +488,7 @@ fn build_section_text_to_speech(command_prefix: &str) -> String {
    message.push_str("\n\n");
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_show(
+        &strings::help::cfg::current_setting_show(
            command_prefix,
            "text-to-speech bot-msgs-flow-type"
        )
@@ -528,7 +496,7 @@ fn build_section_text_to_speech(command_prefix: &str) -> String {
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_set(
+        &strings::help::cfg::current_setting_set(
            command_prefix,
            "text-to-speech set-bot-msgs-flow-type VALUE"
        )
@@ -536,7 +504,7 @@ fn build_section_text_to_speech(command_prefix: &str) -> String {
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_unset(
+        &strings::help::cfg::current_setting_unset(
            command_prefix,
            "text-to-speech set-bot-msgs-flow-type"
        )
@@ -560,7 +528,7 @@ fn build_section_text_to_speech(command_prefix: &str) -> String {
    message.push_str("\n\n");
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_show(
+        &strings::help::cfg::current_setting_show(
            command_prefix,
            "text-to-speech user-msgs-flow-type"
        )
@@ -568,7 +536,7 @@ fn build_section_text_to_speech(command_prefix: &str) -> String {
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_set(
+        &strings::help::cfg::current_setting_set(
            command_prefix,
            "text-to-speech set-user-msgs-flow-type VALUE"
        )
@@ -576,7 +544,7 @@ fn build_section_text_to_speech(command_prefix: &str) -> String {
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_unset(
+        &strings::help::cfg::current_setting_unset(
            command_prefix,
            "text-to-speech set-user-msgs-flow-type"
        )
@@ -594,12 +562,12 @@ fn build_section_text_to_speech(command_prefix: &str) -> String {
    message.push_str("\n\n");
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_show(command_prefix, "text-to-speech speed-override")
+        &strings::help::cfg::current_setting_show(command_prefix, "text-to-speech speed-override")
    ));
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_set(
+        &strings::help::cfg::current_setting_set(
            command_prefix,
            "text-to-speech set-speed-override VALUE"
        )
@@ -607,7 +575,7 @@ fn build_section_text_to_speech(command_prefix: &str) -> String {
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_unset(
+        &strings::help::cfg::current_setting_unset(
            command_prefix,
            "text-to-speech set-speed-override"
        )
@@ -625,12 +593,12 @@ fn build_section_text_to_speech(command_prefix: &str) -> String {
    message.push_str("\n\n");
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_show(command_prefix, "text-to-speech voice-override")
+        &strings::help::cfg::current_setting_show(command_prefix, "text-to-speech voice-override")
    ));
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_set(
+        &strings::help::cfg::current_setting_set(
            command_prefix,
            "text-to-speech set-voice-override VALUE"
        )
@@ -638,7 +606,7 @@ fn build_section_text_to_speech(command_prefix: &str) -> String {
    message.push('\n');
    message.push_str(&format!(
        "- {}",
-        strings::help::cfg::current_setting_unset(
+        &strings::help::cfg::current_setting_unset(
            command_prefix,
            "text-to-speech set-voice-override"
        )
--- a/src/controller/cfg/status.rs
+++ b/src/controller/cfg/status.rs
@@ -359,33 +359,6 @@ async fn generate_text_generation_section(
        ),
    );

-    // Thinking Notice
-
-    let effective_thinking_notice = room_config_context.text_generation_thinking_notice_enabled();
-    let room_config_thinking_notice = room_config_context
-        .room_config
-        .settings
-        .text_generation
-        .thinking_notice_enabled;
-    let global_config_thinking_notice = room_config_context
-        .global_config
-        .fallback_room_settings
-        .text_generation
-        .thinking_notice_enabled;
-
-    let thinking_notice_set_where = if room_config_thinking_notice.is_some() {
-        strings::cfg::status_badge_set_in_room_config()
-    } else if global_config_thinking_notice.is_some() {
-        strings::cfg::status_badge_set_in_global_config()
-    } else {
-        strings::cfg::status_badge_using_hardcoded_default()
-    };
-
-    message.push_str(&strings::cfg::status_text_generation_entry_thinking_notice(
-        effective_thinking_notice,
-        thinking_notice_set_where,
-    ));
-
    // Sender Context

    let effective_sender_context = room_config_context.text_generation_sender_context_mode();
--- a/src/controller/chat_completion/mod.rs
+++ b/src/controller/chat_completion/mod.rs
@@ -30,13 +30,6 @@ use crate::{
    entity::MessageContext,
 };

-/// How long text generation must run before the first "thinking…" placeholder appears.
-/// Fast responses (under this threshold) never get a placeholder.
-const THINKING_NOTICE_FIRST_DELAY: std::time::Duration = std::time::Duration::from_secs(3);
-
-/// How often the "thinking…" placeholder is refreshed once it has appeared.
-const THINKING_NOTICE_INTERVAL: std::time::Duration = std::time::Duration::from_secs(10);
-
 #[derive(Debug, PartialEq)]
 pub enum ChatCompletionControllerType {
    // Invoked via a command prefix (e.g. `!bai Hello!`)
@@ -147,7 +140,9 @@ pub async fn handle(
        // Let's proceed below where we potentially handle text-generation.
    }

-    let text_to_speech_stage_params: Option<TextToSpeechParams> = if message_context
+    let text_to_speech_stage_params: Option<TextToSpeechParams>;
+
+    if message_context
        .room_config_context()
        .should_auto_text_generate(original_message_is_audio)
    {
@@ -208,7 +203,7 @@ pub async fn handle(
            return Ok(());
        };

-        match message_context
+        text_to_speech_stage_params = match message_context
            .room_config_context()
            .text_to_speech_bot_messages_flow_type()
        {
@@ -241,7 +236,7 @@ pub async fn handle(
                text_to_speech_eligible_payload,
                response_type,
            )),
-        }
+        };
    } else {
        tracing::debug!("Not generating text due to auto-usage configuration");

@@ -260,7 +255,7 @@ pub async fn handle(
            event_id: message_context.event_id().clone(),
        };

-        match message_context
+        text_to_speech_stage_params = match message_context
            .room_config_context()
            .text_to_speech_user_messages_flow_type()
        {
@@ -273,8 +268,8 @@ pub async fn handle(
                text_to_speech_eligible_payload,
                response_type,
            )),
-        }
        };
+    }

    // We're potentially dealing with some text in text_to_speech_eligible_payload - either coming directly from the user or generated by an agent.

@@ -525,16 +520,6 @@ async fn handle_stage_text_generation(
        conversation.start_time(),
    );

-    // Cloned only when the thinking-notice is enabled; the original is moved into `params` below.
-    let notice_prompt_variables = if message_context
-        .room_config_context()
-        .text_generation_thinking_notice_enabled()
-    {
-        Some(prompt_variables.clone())
-    } else {
-        None
-    };
-
    let params = TextGenerationParams {
        context_management_enabled: message_context
            .room_config_context()
@@ -551,76 +536,11 @@ async fn handle_stage_text_generation(
        prompt_variables,
    };

-    // When the thinking-notice is enabled, race generation against a timer that posts and then
-    // periodically edits a "thinking…" placeholder. `biased;` makes generation win a tie, and the
-    // loop exits the instant generation resolves, so there is no detached task and no late edit can
-    // ever clobber the real answer. `placeholder` is the event we must finalize in every exit path.
-    let (result, placeholder) = if let Some(notice_prompt_variables) = notice_prompt_variables {
-        let generation = controller
-            .generate_text(conversation, params)
-            .instrument(span);
-        tokio::pin!(generation);
-
-        let mut placeholder: Option<OwnedEventId> = None;
-        // Seed the flavor sequence per-generation so different turns don't all open on the same
-        // line; the monotonic increment then guarantees consecutive notices differ.
-        let mut notice_sequence: usize = std::time::SystemTime::now()
-            .duration_since(std::time::UNIX_EPOCH)
-            .map(|since| since.subsec_nanos() as usize)
-            .unwrap_or(0);
-        let mut tick = tokio::time::interval_at(
-            tokio::time::Instant::now() + THINKING_NOTICE_FIRST_DELAY,
-            THINKING_NOTICE_INTERVAL,
-        );
-        // If an edit runs long, hold ~INTERVAL spacing rather than bursting the missed ticks.
-        tick.set_missed_tick_behavior(tokio::time::MissedTickBehavior::Delay);
-
-        let result = loop {
-            tokio::select! {
-                biased;
-                generation_result = &mut generation => break generation_result,
-                _ = tick.tick() => {
-                    let message = notice_prompt_variables.format(
-                        strings::thinking::pick_message(start_time.elapsed(), notice_sequence),
-                    );
-                    notice_sequence = notice_sequence.wrapping_add(1);
-
-                    match &placeholder {
-                        None => {
-                            placeholder = bot
-                                .messaging()
-                                .send_text_markdown_no_fail_quietly(
-                                    message_context.room(),
-                                    message,
-                                    response_type.clone(),
-                                )
-                                .await
-                                .map(|response| response.event_id);
-                        }
-                        Some(event_id) => {
-                            bot.messaging()
-                                .edit_text_markdown_no_fail(
-                                    message_context.room(),
-                                    event_id,
-                                    message,
-                                )
-                                .await;
-                        }
-                    }
-                }
-            }
-        };
-
-        (result, placeholder)
-    } else {
    let result = controller
        .generate_text(conversation, params)
        .instrument(span)
        .await;

-        (result, None)
-    };
-
    let duration = std::time::Instant::now().duration_since(start_time);

    tracing::debug!(
@@ -640,17 +560,14 @@ async fn handle_stage_text_generation(
                err,
            );

-            let error_text = strings::agent::error_while_serving_purpose(
+            bot.messaging()
+                .send_error_markdown_no_fail(
+                    message_context.room(),
+                    &strings::agent::error_while_serving_purpose(
                        agent.identifier(),
                        &AgentPurpose::TextGeneration,
                        &err,
-            );
-
-            finalize_thinking_notice_with_error(
-                bot,
-                message_context,
-                placeholder.as_ref(),
-                &error_text,
+                    ),
                    response_type,
                )
                .await;
@@ -666,13 +583,10 @@ async fn handle_stage_text_generation(
            "Agent returned empty text",
        );

-        let empty_text = strings::agent::empty_response_returned(agent.identifier());
-
-        finalize_thinking_notice_with_error(
-            bot,
-            message_context,
-            placeholder.as_ref(),
-            &empty_text,
+        bot.messaging()
+            .send_error_markdown_no_fail(
+                message_context.room(),
+                &strings::agent::empty_response_returned(agent.identifier()),
                response_type,
            )
            .await;
@@ -680,56 +594,15 @@ async fn handle_stage_text_generation(
        return None;
    }

-    // Finalize the answer into a single message. With a placeholder, edit it in place (so the
-    // "thinking…" message becomes the answer); the TTS payload then points at that same event.
-    // If the edit fails, fall back to a fresh send so the real answer is never lost.
-    let event_id = match &placeholder {
-        Some(event_id)
-            if bot
+    let send_message_response = bot
        .messaging()
-                .edit_text_markdown_no_fail(message_context.room(), event_id, text.clone())
-                .await
-                .is_some() =>
-        {
-            event_id.clone()
-        }
-        _ => {
-            bot.messaging()
        .send_text_markdown_no_fail(message_context.room(), text.clone(), response_type)
-                .await?
-                .event_id
-        }
-    };
+        .await?;

-    Some(TextToSpeechEligiblePayload { text, event_id })
-}
-
-/// Finalizes a thinking-notice placeholder (if one was posted) with error/notice text, so a
-/// failed or empty generation never leaves an orphaned "thinking…" message behind. With no
-/// placeholder, this is the original behavior: a fresh error notice.
-async fn finalize_thinking_notice_with_error(
-    bot: &Bot,
-    message_context: &MessageContext,
-    placeholder: Option<&OwnedEventId>,
-    text: &str,
-    response_type: MessageResponseType,
-) {
-    match placeholder {
-        Some(event_id) => {
-            bot.messaging()
-                .edit_text_markdown_no_fail(
-                    message_context.room(),
-                    event_id,
-                    crate::utils::status::create_error_message_text(text),
-                )
-                .await;
-        }
-        None => {
-            bot.messaging()
-                .send_error_markdown_no_fail(message_context.room(), text, response_type)
-                .await;
-        }
-    }
+    Some(TextToSpeechEligiblePayload {
+        text,
+        event_id: send_message_response.event_id,
+    })
 }

 async fn handle_stage_speech_to_text_actual_transcribing(
--- a/src/conversation/llm/mod.rs
+++ b/src/conversation/llm/mod.rs
@@ -6,5 +6,5 @@ mod utils;
 mod tests;

 pub use entity::*;
-pub use tokenization::{TokenEstimate, shorten_messages_list_to_context_size};
+pub use tokenization::shorten_messages_list_to_context_size;
 pub use utils::*;
--- a/src/conversation/llm/tokenization.rs
+++ b/src/conversation/llm/tokenization.rs
@@ -4,22 +4,6 @@ use tiktoken_rs::tokenizer;

 use super::{Author, Message, MessageContent};

-/// How to count the tokens in a conversation when trimming it to fit the context window.
-pub enum TokenEstimate<'a> {
-    /// Count via the [tiktoken-rs](https://github.com/zurawiki/tiktoken-rs) library.
-    /// Accurate for OpenAI models; every other model falls back to the gpt-4
-    /// tokenizer, which misreads it (badly so for non-English text). Use this only
-    /// for the OpenAI provider.
-    Tiktoken(&'a str),
-
-    /// Provider-neutral approximation that needs no per-model tokenizer. Expect it
-    /// to land within roughly 10-20% of the real count for typical text, leaning
-    /// slightly high: over-counting trims a little extra history, while
-    /// under-counting would overflow the model's real context window. Use this for
-    /// every non-OpenAI provider.
-    Approximate,
-}
-
 fn get_bpe_for_model(model: &str) -> &'static CoreBPE {
    let tokenizer = tokenizer::get_tokenizer(model)
        .or_else(|| tokenizer::get_tokenizer("gpt-4"))
@@ -29,27 +13,21 @@ fn get_bpe_for_model(model: &str) -> &'static CoreBPE {
 }

 pub fn shorten_messages_list_to_context_size(
-    estimate: TokenEstimate<'_>,
+    model: &str,
    prompt_message: &Option<Message>,
    mut messages: Vec<Message>,
    max_response_tokens: Option<u32>,
    max_context_tokens: u32,
 ) -> Vec<Message> {
-    // Loading the tiktoken data is expensive, so we resolve the counter once up
-    // front and reuse it for every message.
-    let tiktoken = match estimate {
-        TokenEstimate::Tiktoken(model) => Some((get_bpe_for_model(model), model)),
-        TokenEstimate::Approximate => None,
-    };
-    let count = |message: &Message| match tiktoken {
-        Some((bpe, model)) => tiktoken_token_size_for_message(bpe, model, message),
-        None => approximate_token_size_for_message(message),
-    };
+    // Loading the tokenization data is an expensive process, so
+    // se construct the BPE instance once and then use it for all messages.
+    let bpe = get_bpe_for_model(model);

    // We want to retain the prompt in all cases, so we always count it first.
    // We also always reserve enough tokens for the maximum response we expect.
    let mut current_context_length: u32 = if let Some(prompt_message) = prompt_message {
-        count(prompt_message) + max_response_tokens.unwrap_or(0)
+        calculate_token_size_for_message(bpe, model, prompt_message)
+            + max_response_tokens.unwrap_or(0)
    } else {
        0
    };
@@ -59,7 +37,7 @@ pub fn shorten_messages_list_to_context_size(
    let mut messages_to_keep: Vec<Message> = Vec::new();

    for message in messages {
-        let tokens_for_message = count(&message);
+        let tokens_for_message = calculate_token_size_for_message(bpe, model, &message);

        if current_context_length + tokens_for_message > max_context_tokens {
            break;
@@ -70,26 +48,14 @@ pub fn shorten_messages_list_to_context_size(
        messages_to_keep.push(message);
    }

-    // Cut on a turn boundary: the loop may stop right after an assistant reply
-    // whose triggering user message did not fit, which would leave the kept window
-    // starting on an orphaned reply. `messages_to_keep` is newest-first here, so
-    // the oldest kept messages are at the end; drop any trailing assistant messages
-    // until the window begins at the start of a turn (a user message).
-    while matches!(
-        messages_to_keep.last().map(|message| &message.author),
-        Some(Author::Assistant)
-    ) {
-        messages_to_keep.pop();
-    }
-
    messages_to_keep.reverse();

    messages_to_keep
 }

-/// Token size of a message via tiktoken, for a preloaded CoreBPE object.
-/// Accurate only for OpenAI models (see [`TokenEstimate::Tiktoken`]).
-fn tiktoken_token_size_for_message(bpe: &CoreBPE, model: &str, message: &Message) -> u32 {
+/// Calculate the token size of a message for a given model, with a preloaded CoreBPE object.
+/// Related to `calculate_token_size_for_model_message`.
+fn calculate_token_size_for_message(bpe: &CoreBPE, model: &str, message: &Message) -> u32 {
    let (tokens_per_message, tokens_per_name) = if model.starts_with("gpt-3.5") {
        (
            4,  // every message follows <im_start>{role/name}\n{content}<im_end>\n
@@ -114,52 +80,6 @@ fn tiktoken_token_size_for_message(bpe: &CoreBPE, model: &str, message: &Message
    (text_length + role_length + tokens_per_message + tokens_per_name) as u32
 }

-/// ASCII text averages about four characters per token.
-const ASCII_TOKENS_PER_CHAR: f32 = 0.25;
-
-/// Non-ASCII scripts (Cyrillic, CJK, and others) pack more information per
-/// character: real tokenizers land around two characters per token for them, so
-/// each counts as half a token. CJK runs a touch denser than that, so its estimate
-/// can read slightly low, still within the tolerance this approximation targets.
-const WIDE_TOKENS_PER_CHAR: f32 = 0.5;
-
-/// Structural per-message overhead (role marker plus message framing), mirroring
-/// the small constant the tiktoken path adds.
-const APPROX_TOKENS_PER_MESSAGE: u32 = 4;
-
-/// Provider-neutral, tokenizer-free token size of a message
-/// (see [`TokenEstimate::Approximate`]).
-fn approximate_token_size_for_message(message: &Message) -> u32 {
-    let text_tokens = match &message.content {
-        MessageContent::Text(text) => approximate_token_size_for_text(text),
-        // Images and files are not counted as text, matching the tiktoken path.
-        MessageContent::Image(..) | MessageContent::File(..) => 0,
-    };
-
-    text_tokens + APPROX_TOKENS_PER_MESSAGE
-}
-
-/// Rough token estimate for a piece of text, with no tokenizer.
-///
-/// ASCII characters count as a quarter-token each (~4 chars/token); characters
-/// outside ASCII count as half a token each (~2 chars/token), matching how real
-/// tokenizers treat Cyrillic and CJK. Weighting non-ASCII up keeps the estimate
-/// from badly under-counting non-English text, the case the tiktoken fallback gets
-/// most wrong.
-fn approximate_token_size_for_text(text: &str) -> u32 {
-    let mut estimate = 0.0_f32;
-
-    for character in text.chars() {
-        estimate += if character.is_ascii() {
-            ASCII_TOKENS_PER_CHAR
-        } else {
-            WIDE_TOKENS_PER_CHAR
-        };
-    }
-
-    estimate.ceil() as u32
-}
-
 pub mod test {
    #[test]
    fn message_size_counting_works() {
@@ -174,7 +94,7 @@ pub mod test {
            timestamp: chrono::Utc::now(),
        };

-        let tokens = super::tiktoken_token_size_for_message(bpe, model, &message);
+        let tokens = super::calculate_token_size_for_message(bpe, model, &message);

        assert_eq!(8, tokens);
    }
@@ -198,7 +118,7 @@ pub mod test {

        assert_eq!(
            prompt_length,
-            super::tiktoken_token_size_for_message(bpe, model, &prompt)
+            super::calculate_token_size_for_message(bpe, model, &prompt)
        );

        let mut conversation_messages = Vec::new();
@@ -213,7 +133,7 @@ pub mod test {

        assert_eq!(
            first_length,
-            super::tiktoken_token_size_for_message(bpe, model, &first)
+            super::calculate_token_size_for_message(bpe, model, &first)
        );

        conversation_messages.push(first);
@@ -228,7 +148,7 @@ pub mod test {

        assert_eq!(
            second_length,
-            super::tiktoken_token_size_for_message(bpe, model, &second)
+            super::calculate_token_size_for_message(bpe, model, &second)
        );

        conversation_messages.push(second);
@@ -245,7 +165,7 @@ pub mod test {

        assert_eq!(
            third_length,
-            super::tiktoken_token_size_for_message(bpe, model, &third)
+            super::calculate_token_size_for_message(bpe, model, &third)
        );

        conversation_messages.push(third.clone());
@@ -262,7 +182,7 @@ pub mod test {

        assert_eq!(
            forth_length,
-            super::tiktoken_token_size_for_message(bpe, model, &forth)
+            super::calculate_token_size_for_message(bpe, model, &forth)
        );

        conversation_messages.push(forth.clone());
@@ -270,7 +190,7 @@ pub mod test {
        assert_eq!(4, conversation_messages.len());

        let new_conversation_messages = super::shorten_messages_list_to_context_size(
-            super::TokenEstimate::Tiktoken(model),
+            model,
            &Some(prompt),
            conversation_messages,
            max_response_tokens,
@@ -309,7 +229,7 @@ pub mod test {

        assert_eq!(
            prompt_length,
-            super::tiktoken_token_size_for_message(bpe, model, &prompt)
+            super::calculate_token_size_for_message(bpe, model, &prompt)
        );

        let mut conversation_messages = Vec::new();
@@ -324,7 +244,7 @@ pub mod test {

        assert_eq!(
            first_length,
-            super::tiktoken_token_size_for_message(bpe, model, &first)
+            super::calculate_token_size_for_message(bpe, model, &first)
        );

        conversation_messages.push(first);
@@ -339,7 +259,7 @@ pub mod test {

        assert_eq!(
            second_length,
-            super::tiktoken_token_size_for_message(bpe, model, &second)
+            super::calculate_token_size_for_message(bpe, model, &second)
        );

        conversation_messages.push(second);
@@ -356,7 +276,7 @@ pub mod test {

        assert_eq!(
            third_length,
-            super::tiktoken_token_size_for_message(bpe, model, &third)
+            super::calculate_token_size_for_message(bpe, model, &third)
        );

        conversation_messages.push(third.clone());
@@ -373,7 +293,7 @@ pub mod test {

        assert_eq!(
            forth_length,
-            super::tiktoken_token_size_for_message(bpe, model, &forth)
+            super::calculate_token_size_for_message(bpe, model, &forth)
        );

        conversation_messages.push(forth.clone());
@@ -381,7 +301,7 @@ pub mod test {
        assert_eq!(4, conversation_messages.len());

        let new_conversation_messages = super::shorten_messages_list_to_context_size(
-            super::TokenEstimate::Tiktoken(model),
+            model,
            &Some(prompt),
            conversation_messages,
            max_response_tokens,
@@ -400,126 +320,4 @@ pub mod test {
            forth.content
        );
    }
-
-    #[test]
-    fn approximate_counting_weights_ascii_and_wide_scripts() {
-        // 12 ASCII characters at ~4 chars/token = 3 text tokens.
-        assert_eq!(3, super::approximate_token_size_for_text("Hello there!"));
-
-        // 5 CJK characters at ~0.5 token/char = 3 text tokens. The ASCII rate would
-        // have under-counted these to 2, the failure mode this path avoids.
-        assert_eq!(3, super::approximate_token_size_for_text("こんにちは"));
-
-        let message = super::Message {
-            author: super::Author::User,
-            sender_id: None,
-            content: super::MessageContent::Text("Hello there!".to_string()),
-            timestamp: chrono::Utc::now(),
-        };
-
-        // 3 text tokens plus the per-message overhead (4).
-        assert_eq!(7, super::approximate_token_size_for_message(&message));
-    }
-
-    #[test]
-    fn approximate_shortening_trims_to_budget() {
-        let prompt = super::Message {
-            author: super::Author::Prompt,
-            sender_id: None,
-            content: super::MessageContent::Text("You are a bot!".to_string()),
-            timestamp: chrono::Utc::now(),
-        };
-
-        let older = super::Message {
-            author: super::Author::User,
-            sender_id: None,
-            content: super::MessageContent::Text("This is the older message.".to_string()),
-            timestamp: chrono::Utc::now(),
-        };
-        let newer = super::Message {
-            // A user message, so it is a valid window start: keeping a lone
-            // assistant reply would be an orphan and get trimmed (see
-            // `shortening_cuts_on_a_turn_boundary`).
-            author: super::Author::User,
-            sender_id: None,
-            content: super::MessageContent::Text("This is the newer message.".to_string()),
-            timestamp: chrono::Utc::now(),
-        };
-
-        // Budget room for the prompt and only the newest message.
-        let max_context_tokens = super::approximate_token_size_for_message(&prompt)
-            + super::approximate_token_size_for_message(&newer);
-
-        let new_conversation_messages = super::shorten_messages_list_to_context_size(
-            super::TokenEstimate::Approximate,
-            &Some(prompt),
-            vec![older, newer.clone()],
-            None,
-            max_context_tokens,
-        );
-
-        assert_eq!(1, new_conversation_messages.len());
-        assert_eq!(
-            new_conversation_messages.first().unwrap().content,
-            newer.content
-        );
-    }
-
-    #[test]
-    fn shortening_cuts_on_a_turn_boundary() {
-        // A four-message conversation of two full turns. All four messages are the
-        // same length, so they cost the same number of tokens.
-        let prompt = super::Message {
-            author: super::Author::Prompt,
-            sender_id: None,
-            content: super::MessageContent::Text("system".to_string()),
-            timestamp: chrono::Utc::now(),
-        };
-
-        let user_one = super::Message {
-            author: super::Author::User,
-            sender_id: None,
-            content: super::MessageContent::Text("user msg 1".to_string()),
-            timestamp: chrono::Utc::now(),
-        };
-        let asst_one = super::Message {
-            author: super::Author::Assistant,
-            sender_id: None,
-            content: super::MessageContent::Text("asst msg 1".to_string()),
-            timestamp: chrono::Utc::now(),
-        };
-        let user_two = super::Message {
-            author: super::Author::User,
-            sender_id: None,
-            content: super::MessageContent::Text("user msg 2".to_string()),
-            timestamp: chrono::Utc::now(),
-        };
-        let asst_two = super::Message {
-            author: super::Author::Assistant,
-            sender_id: None,
-            content: super::MessageContent::Text("asst msg 2".to_string()),
-            timestamp: chrono::Utc::now(),
-        };
-
-        let per_message = super::approximate_token_size_for_message(&user_one);
-        // Budget fits the prompt plus three messages. By raw token budget the loop
-        // would keep asst_two, user_two, and asst_one, but asst_one's own user
-        // message (user_one) does not fit, so it must be dropped too rather than
-        // left as an orphaned reply.
-        let max_context_tokens =
-            super::approximate_token_size_for_message(&prompt) + (per_message * 3);
-
-        let kept = super::shorten_messages_list_to_context_size(
-            super::TokenEstimate::Approximate,
-            &Some(prompt),
-            vec![user_one, asst_one, user_two.clone(), asst_two.clone()],
-            None,
-            max_context_tokens,
-        );
-
-        // Only the last whole turn survives; the orphaned asst_one is dropped.
-        assert_eq!(2, kept.len());
-        assert_eq!(kept.first().unwrap().content, user_two.content);
-        assert_eq!(kept.last().unwrap().content, asst_two.content);
-    }
 }
--- a/src/entity/room_config_context.rs
+++ b/src/entity/room_config_context.rs
@@ -136,20 +136,6 @@ impl RoomConfigContext {
            .unwrap_or(false)
    }

-    pub fn text_generation_thinking_notice_enabled(&self) -> bool {
-        self.room_config
-            .settings
-            .text_generation
-            .thinking_notice_enabled
-            .or({
-                self.global_config
-                    .fallback_room_settings
-                    .text_generation
-                    .thinking_notice_enabled
-            })
-            .unwrap_or(false)
-    }
-
    pub fn text_generation_sender_context_mode(&self) -> TextGenerationSenderContextMode {
        self.room_config
            .settings
--- a/src/entity/roomconfig/entity/text_generation.rs
+++ b/src/entity/roomconfig/entity/text_generation.rs
@@ -14,10 +14,6 @@ pub struct RoomSettingsTextGeneration {
    /// When enabled, the bot will automatically tokenize messages and try to shorten the message context intelligently.
    pub context_management_enabled: Option<bool>,

-    /// Controls whether a "thinking…" notice is posted while text generation runs longer than a threshold.
-    /// When enabled, a placeholder message appears for slow responses and is edited in place (with elapsed-tiered flavor text) until it becomes the final answer.
-    pub thinking_notice_enabled: Option<bool>,
-
    /// Controls how each message in the conversation context is annotated with sender metadata.
    pub sender_context_mode: Option<TextGenerationSenderContextMode>,

--- a/src/strings/agent.rs
+++ b/src/strings/agent.rs
@@ -101,13 +101,13 @@ pub fn post_creation_helpful_commands(
        for purpose in supported_purposes {
            message.push_str(&format!(
                "\n- {}",
-                set_as_purpose_handler_in_room(agent_identifier, purpose, command_prefix,)
+                &set_as_purpose_handler_in_room(agent_identifier, purpose, command_prefix,)
            ));

            if !is_room_local {
                message.push_str(&format!(
                    "\n- {}",
-                    set_as_purpose_handler_globally(agent_identifier, purpose, command_prefix,)
+                    &set_as_purpose_handler_globally(agent_identifier, purpose, command_prefix,)
                ));
            }
        }
--- a/src/strings/cfg.rs
+++ b/src/strings/cfg.rs
@@ -249,10 +249,6 @@ pub fn status_text_generation_entry_context_management(value: bool, set_where: &
    format!("- ♻️ Context management: `{}` ({})\n", value, set_where)
 }

-pub fn status_text_generation_entry_thinking_notice(value: bool, set_where: &str) -> String {
-    format!("- 💭 Thinking notice: `{}` ({})\n", value, set_where)
-}
-
 pub fn status_text_generation_entry_sender_context(
    value: impl std::fmt::Display,
    set_where: &str,
--- a/src/strings/help/cfg.rs
+++ b/src/strings/help/cfg.rs
@@ -128,19 +128,7 @@ pub fn text_generation_context_management_intro() -> String {
    format!(
        "{}\n{}",
        "Controls the bot's ability to **intelligently drop old messages from the conversation context** when it gets too large.",
-        "Counting tokens precisely needs the model's own tokenizer. For [OpenAI](./providers.md#openai) models the bot uses the [tiktoken-rs](https://github.com/zurawiki/tiktoken-rs) library; for every other provider (including the recommended [Venice](./providers.md#venice)) it falls back to a provider-neutral **approximation** (ASCII counted at ~4 characters per token, other scripts at ~2), within roughly 10-20% of the real count for typical text.",
-    )
-}
-
-pub fn text_generation_thinking_notice_heading() -> &'static str {
-    "💭 Thinking Notice"
-}
-
-pub fn text_generation_thinking_notice_intro() -> String {
-    format!(
-        "{}\n{}",
-        "Controls whether the bot posts a **\"thinking…\" notice** while text generation takes a while, so slow responses (for example, from reasoning models that run for minutes) don't look stuck.",
-        "When enabled, a placeholder message appears only after a short delay, updates periodically with varying status text, and is then edited in place to become the final answer. Disabled by default.",
+        "This feature relies on [tokenization](https://en.wikipedia.org/wiki/Large_language_model#Tokenization) performed by the [tiktoken-rs](https://github.com/zurawiki/tiktoken-rs) library which is [poorly well-maintained](https://github.com/zurawiki/tiktoken-rs/issues/50) and only works well for [OpenAI](./providers.md#openai) models.",
    )
 }

--- a/src/strings/mod.rs
+++ b/src/strings/mod.rs
@@ -11,7 +11,6 @@ pub mod provider;
 pub mod room_config;
 pub mod speech_to_text;
 pub mod text_to_speech;
-pub mod thinking;
 pub mod usage;

 pub const PROGRESS_INDICATOR_EMOJI: &str = "⏳";
--- a/src/strings/thinking.rs
+++ b/src/strings/thinking.rs
@@ -1,146 +0,0 @@
-use std::time::Duration;
-
-/// After this much elapsed generation time, the notice escalates to the "medium" pool.
-const TIER_MEDIUM_AFTER: Duration = Duration::from_secs(30);
-
-/// After this much elapsed generation time, the notice escalates to the "deep" pool.
-const TIER_DEEP_AFTER: Duration = Duration::from_secs(90);
-
-/// Early flavor: the response is just taking a moment longer than instant.
-const MESSAGES_LIGHT: &[&str] = &[
-    "*{{ baibot_name }} is thinking…*",
-    "*{{ baibot_name }} is mulling that over…*",
-    "*Hmm, let me think about that…*",
-    "*{{ baibot_name }} is gathering some thoughts…*",
-    "*One moment, {{ baibot_name }} is working on it…*",
-    "*{{ baibot_name }} is putting the pieces together…*",
-    "*Give {{ baibot_name }} a second here…*",
-    "*Let me think this one through…*",
-    "*{{ baibot_name }} is warming up the gears…*",
-    "*{{ baibot_name }} is on it…*",
-];
-
-/// Mid flavor: this is a real question and the model is genuinely working.
-const MESSAGES_MEDIUM: &[&str] = &[
-    "*Huh, good one. {{ baibot_name }} is really thinking now…*",
-    "*Still working on it, {{ baibot_name }} wants to get this right…*",
-    "*This one needs a bit more thought…*",
-    "*{{ baibot_name }} is digging into this…*",
-    "*Hang tight, {{ baibot_name }} is turning it over…*",
-    "*Not a quick one, this. {{ baibot_name }} is still at it…*",
-    "*{{ baibot_name }} is chewing on this properly now…*",
-    "*This deserves some real thought, bear with {{ baibot_name }}…*",
-    "*{{ baibot_name }} is working through the details…*",
-    "*Won't be long, {{ baibot_name }} is closing in on it…*",
-];
-
-/// Deep flavor: a long-running generation (e.g. a reasoning model going for minutes).
-const MESSAGES_DEEP: &[&str] = &[
-    "*Okay, this is a hard one. {{ baibot_name }} is really deep in thought…*",
-    "*{{ baibot_name }} is in the weeds on this one, thanks for your patience…*",
-    "*Still here, still thinking. {{ baibot_name }} doesn't want to rush it…*",
-    "*A proper puzzle, this. {{ baibot_name }} is taking the time to do it justice…*",
-    "*{{ baibot_name }} is really wrestling with this one…*",
-    "*A meaty question. {{ baibot_name }} is still turning it over…*",
-    "*{{ baibot_name }} hasn't forgotten you, just thinking hard…*",
-    "*Almost there, {{ baibot_name }} is pulling it all together…*",
-    "*{{ baibot_name }} is going the extra mile on this one…*",
-    "*Deep thoughts in progress. {{ baibot_name }} appreciates your patience…*",
-];
-
-/// Returns the flavor pool matching how long generation has been running.
-pub fn messages_for_elapsed(elapsed: Duration) -> &'static [&'static str] {
-    if elapsed >= TIER_DEEP_AFTER {
-        MESSAGES_DEEP
-    } else if elapsed >= TIER_MEDIUM_AFTER {
-        MESSAGES_MEDIUM
-    } else {
-        MESSAGES_LIGHT
-    }
-}
-
-/// Picks one (still-untemplated) flavor message from the tier active at `elapsed`,
-/// indexed by a monotonic `sequence` the caller increments once per notice.
-///
-/// Using a monotonic counter (rather than a clock-derived value) guarantees two
-/// things the gesture-novelty goal needs: consecutive notices never repeat a line
-/// (the index advances by one each tick, so it differs whenever the tier has more
-/// than one message), and the pool is fully walked before any line recurs. The
-/// caller seeds `sequence` with a per-generation value so different turns don't all
-/// open on the same line. A clock-derived index can't promise this: `interval_at`
-/// ticks on a near-fixed schedule, so its sub-second component clusters and would
-/// re-pick the same line.
-pub fn pick_message(elapsed: Duration, sequence: usize) -> &'static str {
-    let pool = messages_for_elapsed(elapsed);
-    pool[sequence % pool.len()]
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn messages_for_elapsed_returns_the_right_tier() {
-        // Boundaries: light below 30s, medium [30s, 90s), deep at/after 90s.
-        // The pools have distinct content, so value comparison identifies the tier.
-        assert_eq!(messages_for_elapsed(Duration::from_secs(0)), MESSAGES_LIGHT);
-        assert_eq!(
-            messages_for_elapsed(Duration::from_secs(29)),
-            MESSAGES_LIGHT
-        );
-        assert_eq!(
-            messages_for_elapsed(Duration::from_secs(30)),
-            MESSAGES_MEDIUM
-        );
-        assert_eq!(
-            messages_for_elapsed(Duration::from_secs(89)),
-            MESSAGES_MEDIUM
-        );
-        assert_eq!(messages_for_elapsed(Duration::from_secs(90)), MESSAGES_DEEP);
-        assert_eq!(
-            messages_for_elapsed(Duration::from_secs(600)),
-            MESSAGES_DEEP
-        );
-    }
-
-    #[test]
-    fn every_tier_is_non_empty() {
-        for pool in [MESSAGES_LIGHT, MESSAGES_MEDIUM, MESSAGES_DEEP] {
-            assert!(!pool.is_empty());
-            for message in pool {
-                assert!(!message.trim().is_empty());
-            }
-        }
-    }
-
-    #[test]
-    fn every_tier_uses_the_bot_name_template() {
-        // Not every line names the bot (some are first-person flavor), but each
-        // tier exercises the template var so substitution is wired through.
-        for pool in [MESSAGES_LIGHT, MESSAGES_MEDIUM, MESSAGES_DEEP] {
-            assert!(pool.iter().any(|m| m.contains("{{ baibot_name }}")));
-        }
-    }
-
-    #[test]
-    fn pick_message_stays_within_the_active_tier() {
-        let deep = messages_for_elapsed(Duration::from_secs(120));
-        for sequence in 0..50 {
-            assert!(deep.contains(&pick_message(Duration::from_secs(120), sequence)));
-        }
-    }
-
-    #[test]
-    fn pick_message_never_repeats_on_consecutive_sequences() {
-        // The gesture-novelty guarantee: a monotonic sequence must not pick the same line twice
-        // in a row (and walks the whole tier before any line recurs).
-        let elapsed = Duration::from_secs(0);
-        let pool_len = messages_for_elapsed(elapsed).len();
-        for sequence in 0..(pool_len * 3) {
-            assert_ne!(
-                pick_message(elapsed, sequence),
-                pick_message(elapsed, sequence + 1),
-            );
-        }
-    }
-}