Update Rust crate reqwest to v0.13.5

Adds a Docker Compose example alongside the existing `docker run` one, using a tagged release and the same hardening options.

Co-authored-by: daru <darupeter@pm.me>
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Nh4Z2JCU4aVC5STFN7usfW

.github/workflows/ci.yml

@@ -22,7 +22,7 @@ jobs:
 
       # 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@v1
+      - uses: actions-rust-lang/setup-rust-toolchain@v2
         with:
           rustflags: ''
 
@@ -42,3 +42,63 @@ jobs:
 
       - 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

.pre-commit-config.yaml

@@ -5,6 +5,10 @@ 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']

CHANGELOG.md

@@ -1,3 +1,10 @@
+# (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).

Cargo.lock

@@ -95,9 +95,9 @@ dependencies = [
 
 [[package]]
 name = "anyhow"
-version = "1.0.103"
+version = "1.0.104"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2a4385e2e34eb35d6b3efe798b9eb88096925d87726c0798709bf56d9ed84af3"
+checksum = "330a5ed07fa54e4702c9d6c4174f74427fc0ef6e214bbd677ae50a5099946470"
 
 [[package]]
 name = "anymap2"
@@ -184,9 +184,9 @@ checksum = "4288f83726785267c6f2ef073a3d83dc3f9b81464e9f99898240cced85fce35a"
 
 [[package]]
 name = "async-openai"
-version = "0.41.1"
+version = "0.41.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3007014661d5b98168b7b6f1014147bce8b1362a194783543eeb9f6117a20be9"
+checksum = "d72db2750faea2ca5edbf6d0c50277a89dc8f75f5e6ddd695ef30f75e335019b"
 dependencies = [
  "async-openai-macros",
  "base64 0.22.1",
@@ -196,7 +196,7 @@ dependencies = [
  "futures",
  "getrandom 0.3.4",
  "rand 0.9.4",
- "reqwest 0.13.4",
+ "reqwest 0.13.5",
  "secrecy",
  "serde",
  "serde_json",
@@ -315,12 +315,12 @@ dependencies = [
 
 [[package]]
 name = "baibot"
-version = "1.24.0"
+version = "1.25.0"
 dependencies = [
  "anthropic",
  "anyhow",
  "async-openai",
- "base64 0.22.1",
+ "base64 0.23.1",
  "chrono",
  "etke_openai_api_rust",
  "matrix-sdk",
@@ -329,7 +329,7 @@ dependencies = [
  "mxlink",
  "quick_cache 0.7.0",
  "regex",
- "reqwest 0.13.4",
+ "reqwest 0.13.5",
  "serde",
  "serde_json",
  "serde_yaml_ng",
@@ -353,6 +353,12 @@ 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"
@@ -2188,7 +2194,7 @@ dependencies = [
  "oauth2-reqwest",
  "percent-encoding",
  "pin-project-lite",
- "reqwest 0.13.4",
+ "reqwest 0.13.5",
  "ruma",
  "rustls",
  "rustls-native-certs 0.8.3",
@@ -2480,9 +2486,9 @@ dependencies = [
 
 [[package]]
 name = "mxidwc"
-version = "1.0.2"
+version = "1.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5e253f96a03d24d1c0006c5661b1e20a13dc3861f509d76c33b6b44349d4ff3b"
+checksum = "45b5d51fcf414d2aa6bffc6cd9b037e62732734a944c5da4ace6b9895ec37b93"
 dependencies = [
  "regex",
 ]
@@ -2583,7 +2589,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "234fb5c965bbce983ee5de636a7a51d6a3223da8067ea02f9ab2d2d78ac08be2"
 dependencies = [
  "oauth2",
- "reqwest 0.13.4",
+ "reqwest 0.13.5",
 ]
 
 [[package]]
@@ -3064,9 +3070,9 @@ dependencies = [
 
 [[package]]
 name = "regex"
-version = "1.12.4"
+version = "1.13.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f1292b7759ae1cb9ec195452d1390a074f0cd8541ab7a5a8c31cd6db45d4a6ba"
+checksum = "f020237b6c8eed93db2e2cb53c00c60a8e1bc73da7d073199a1180401450218d"
 dependencies = [
  "aho-corasick",
  "memchr",
@@ -3076,9 +3082,9 @@ dependencies = [
 
 [[package]]
 name = "regex-automata"
-version = "0.4.14"
+version = "0.4.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6e1dd4122fc1595e8162618945476892eefca7b88c52820e74af6262213cae8f"
+checksum = "8fcfdb36bda0c880c5931cdc7a2bcdc8ba4556847b9d912bca70bc94708711ad"
 dependencies = [
  "aho-corasick",
  "memchr",
@@ -3134,11 +3140,11 @@ dependencies = [
 
 [[package]]
 name = "reqwest"
-version = "0.13.4"
+version = "0.13.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "219c5811de6525e5416c7d5d53bb656d3afdbc6c5af816e0802bcfa42dbdc1c3"
+checksum = "16a1cfa75cc186dd73d5818e510e042e40927bccc9c236b061cea97e1eb08029"
 dependencies = [
- "base64 0.22.1",
+ "base64 0.23.1",
  "bytes",
  "futures-core",
  "futures-util",
@@ -3611,9 +3617,9 @@ checksum = "8a7852d02fc848982e0c167ef163aaff9cd91dc640ba85e263cb1ce46fae51cd"
 
 [[package]]
 name = "serde"
-version = "1.0.228"
+version = "1.0.229"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9a8e94ea7f378bd32cbbd37198a4a91436180c5bb472411e48b5ec2e2124ae9e"
+checksum = "4148590afebada386688f18773da617792bf2ef03ffc1e4cbd2b1d45b023e0ba"
 dependencies = [
  "serde_core",
  "serde_derive",
@@ -3642,22 +3648,22 @@ dependencies = [
 
 [[package]]
 name = "serde_core"
-version = "1.0.228"
+version = "1.0.229"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "41d385c7d4ca58e59fc732af25c3983b67ac852c1a25000afe1175de458b67ad"
+checksum = "67dca2c9c51e58a4791a4b1ed58308b39c64224d349a935ab5039aa360942a48"
 dependencies = [
  "serde_derive",
 ]
 
 [[package]]
 name = "serde_derive"
-version = "1.0.228"
+version = "1.0.229"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d540f220d3187173da220f885ab66608367b6574e925011a9353e4badda91d79"
+checksum = "e7a5d71263a5a7d47b41f6b3f06ba276f10cc18b0931f1799f710578e2309348"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 3.0.0",
 ]
 
 [[package]]
@@ -3675,9 +3681,9 @@ dependencies = [
 
 [[package]]
 name = "serde_json"
-version = "1.0.150"
+version = "1.0.151"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e8014e44b4736ed0538adeecded0fce2a272f22dc9578a7eb6b2d9993c74cfb9"
+checksum = "c841b55ecdae098c80dcae9cf767f6f8a0c2cdb3416bbef72181df4d0fe73f14"
 dependencies = [
  "itoa",
  "memchr",
@@ -3899,6 +3905,17 @@ 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"
@@ -4064,9 +4081,9 @@ checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"
 
 [[package]]
 name = "tokio"
-version = "1.52.3"
+version = "1.53.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8fc7f01b389ac15039e4dc9531aa973a135d7a4135281b12d7c1bc79fd57fffe"
+checksum = "202caea871b69668250d242070849eb495be178ed697a3e98aebce5bc81a0bed"
 dependencies = [
  "bytes",
  "libc",

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 = "1.24.0"
+version = "1.25.0"
 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 = "0.22.*"
+base64 = "0.23.*"
 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 }
@@ -27,7 +27,7 @@ mxidwc = "1.0.*"
 mxlink = ">=1.15.0"
 etke_openai_api_rust = "0.1.*"
 quick_cache = "0.7.*"
-regex = "1.12.*"
+regex = "1.13.*"
 # 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 = "1.52.*", features = ["rt", "rt-multi-thread", "macros"] }
+tokio = { version = "1.53.*", features = ["rt", "rt-multi-thread", "macros"] }
 tracing = "0.1.*"
 tracing-subscriber = { version = "0.3.*", features = ["env-filter"] }
 url = "2.5.*"

Dockerfile

@@ -4,7 +4,7 @@
 #                                     #
 #######################################
 
-FROM docker.io/rust:1.96.0-slim-trixie AS build
+FROM docker.io/rust:1.98.0-slim-trixie AS build
 
 RUN apt-get update && apt-get install -y build-essential pkg-config libssl-dev libsqlite3-dev
 

Dockerfile.ci

@@ -1,35 +0,0 @@
-#######################################
-#                                     #
-# 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"]

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) handling on some models (automatically adjusting the message history length, etc.)
+- ♻️ 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)
 
 - 🛠️ Allows **customizing much of the bot's [configuration](./docs/configuration/README.md)** at runtime (using commands sent via chat)
 

docs/configuration/text-generation.md

@@ -50,9 +50,9 @@ Example: `!bai config room text-generation set-auto-usage only_for_voice` (this
 
 ### ♻️ Context Management
 
-The bot also supports ♻️ **context management**, which automatically adjusts the message history length, etc.
+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.
 
-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.
+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 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)).
 

docs/installation.md

@@ -57,6 +57,34 @@ 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.
 
 

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 [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).
+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.
 
 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.
 
@@ -176,7 +176,7 @@ 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 $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/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.
 
 - 🆔 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)

etc/services/continuwuity/compose.yml

@@ -1,14 +1,14 @@
 services:
   continuwuity:
-    image: forgejo.ellis.link/continuwuation/continuwuity:v0.5.10
+    image: forgejo.ellis.link/continuwuation/continuwuity:v26.8.1
     user: "${UID}:${GID}"
     restart: unless-stopped
     cap_drop:
       - ALL
     read_only: true
     environment:
-      CONDUWUIT_CONFIG: /etc/continuwuity/continuwuity.toml
+      CONTINUWUITY_CONFIG: /etc/continuwuity/continuwuity.toml
-      CONDUWUIT_DATABASE_PATH: /var/lib/continuwuity
+      CONTINUWUITY_DATABASE_PATH: /var/lib/continuwuity
     ports:
       - "${SERVICE_CONTINUWUITY_BIND_PORT_CLIENT_API}:6167"
     volumes:

etc/services/element-web/compose.yml

@@ -1,6 +1,6 @@
 services:
   element-web:
-    image: ghcr.io/element-hq/element-web:v1.12.22
+    image: ghcr.io/element-hq/element-web:v1.12.27
     user: "${UID}:${GID}"
     restart: unless-stopped
     environment:

etc/services/ollama/compose.yml

@@ -1,6 +1,6 @@
 services:
   ollama:
-    image: docker.io/ollama/ollama:0.30.11
+    image: docker.io/ollama/ollama:0.33.3
     restart: unless-stopped
     ports:
       - "${SERVICE_OLLAMA_BIND_PORT_HTTP}:11434"

etc/services/synapse/compose.yml

@@ -1,6 +1,6 @@
 services:
   postgres:
-    image: docker.io/postgres:18.4-alpine
+    image: docker.io/postgres:18.6-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:v1.155.0
+    image: ghcr.io/element-hq/synapse:v1.160.0
     user: "${UID}:${GID}"
     restart: unless-stopped
     entrypoint: python

justfile

@@ -271,7 +271,29 @@ 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
-	@just --justfile {{ justfile() }} mise exec -- prek install
+	#!/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
 
 # Internal - ensures var/mise directory exists
 _ensure_mise_data_directory:

mise.toml

@@ -1,6 +1,2 @@
 [tools]
-prek = "0.4.5"
+prek = "0.5.2"
-
-[settings]
-# Disable automatic trust prompts - we trust this config
-yes = true

renovate.json

@@ -5,5 +5,62 @@
 	],
 	"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
+		}
 	]
 }

rust-toolchain.toml

@@ -1,4 +1,4 @@
 [toolchain]
-channel = "1.96.0"
+channel = "1.98.1"
 components = ["rustfmt", "clippy"]
 profile = "default"

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, shorten_messages_list_to_context_size,
+    MessageContent as LLMMessageContent, TokenEstimate, 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(
-                &text_generation_config.model_id,
+                TokenEstimate::Approximate,
                 &prompt_message,
                 conversation_messages,
                 Some(text_generation_config.max_response_tokens),

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, shorten_messages_list_to_context_size,
+        MessageContent as LLMMessageContent, TokenEstimate, 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(
-                &text_generation_config.model_id,
+                TokenEstimate::Tiktoken(&text_generation_config.model_id),
                 &prompt_message,
                 conversation_messages,
                 text_generation_config.max_response_tokens,

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, shorten_messages_list_to_context_size,
+        MessageContent as LLMMessageContent, TokenEstimate, 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(
-                &text_generation_config.model_id,
+                TokenEstimate::Approximate,
                 &prompt_message,
                 conversation_messages,
                 text_generation_config.max_response_tokens,

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, shorten_messages_list_to_context_size,
+    MessageContent as LLMMessageContent, TokenEstimate, 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(
-            &text_generation_config.model_id,
+            TokenEstimate::Approximate,
             &prompt_message,
             conversation_messages,
             text_generation_config.max_response_tokens,

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"
         )
@@ -189,10 +189,7 @@ 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-auto-usage")
-            command_prefix,
-            "text-generation set-auto-usage"
-        )
     ));
     message.push_str("\n\n");
 
@@ -211,7 +208,7 @@ 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"
         )
@@ -219,7 +216,7 @@ 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"
         )
@@ -227,7 +224,7 @@ 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-context-management-enabled"
         )
@@ -249,7 +246,7 @@ 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 thinking-notice-enabled"
         )
@@ -257,7 +254,7 @@ 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-thinking-notice-enabled VALUE"
         )
@@ -265,7 +262,7 @@ 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-thinking-notice-enabled"
         )
@@ -289,7 +286,7 @@ 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"
         )
@@ -297,7 +294,7 @@ 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"
         )
@@ -305,7 +302,7 @@ 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"
         )
@@ -323,15 +320,12 @@ 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(
+        strings::help::cfg::current_setting_show(command_prefix, "text-generation prompt-override")
-            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"
         )
@@ -339,7 +333,7 @@ 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"
         )
@@ -357,7 +351,7 @@ 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"
         )
@@ -365,7 +359,7 @@ 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"
         )
@@ -373,7 +367,7 @@ 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"
         )
@@ -410,12 +404,12 @@ 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"
         )
@@ -423,7 +417,7 @@ 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");
 
@@ -444,7 +438,7 @@ 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"
         )
@@ -452,7 +446,7 @@ 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"
         )
@@ -460,7 +454,7 @@ 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"
         )
@@ -478,12 +472,12 @@ 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"
         )
@@ -491,7 +485,7 @@ 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");
 
@@ -526,7 +520,7 @@ 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"
         )
@@ -534,7 +528,7 @@ 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"
         )
@@ -542,7 +536,7 @@ fn build_section_text_to_speech(command_prefix: &str) -> String {
     message.push('\n');
     message.push_str(&format!(
         "- {}",
-        &strings::help::cfg::current_setting_unset(
+        strings::help::cfg::current_setting_unset(
             command_prefix,
             "text-to-speech set-bot-msgs-flow-type"
         )
@@ -566,7 +560,7 @@ 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"
         )
@@ -574,7 +568,7 @@ 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"
         )
@@ -582,7 +576,7 @@ 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"
         )
@@ -600,12 +594,12 @@ 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"
         )
@@ -613,7 +607,7 @@ 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"
         )
@@ -631,12 +625,12 @@ 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"
         )
@@ -644,7 +638,7 @@ 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"
         )

src/controller/chat_completion/mod.rs

@@ -147,9 +147,7 @@ pub async fn handle(
         // Let's proceed below where we potentially handle text-generation.
     }
 
-    let text_to_speech_stage_params: Option<TextToSpeechParams>;
+    let text_to_speech_stage_params: Option<TextToSpeechParams> = if message_context
-
-    if message_context
         .room_config_context()
         .should_auto_text_generate(original_message_is_audio)
     {
@@ -210,7 +208,7 @@ pub async fn handle(
             return Ok(());
         };
 
-        text_to_speech_stage_params = match message_context
+        match message_context
             .room_config_context()
             .text_to_speech_bot_messages_flow_type()
         {
@@ -243,7 +241,7 @@ pub async fn handle(
                 text_to_speech_eligible_payload,
                 response_type,
             )),
-        };
+        }
     } else {
         tracing::debug!("Not generating text due to auto-usage configuration");
 
@@ -262,7 +260,7 @@ pub async fn handle(
             event_id: message_context.event_id().clone(),
         };
 
-        text_to_speech_stage_params = match message_context
+        match message_context
             .room_config_context()
             .text_to_speech_user_messages_flow_type()
         {
@@ -275,8 +273,8 @@ 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.
 

src/conversation/llm/mod.rs

@@ -6,5 +6,5 @@ mod utils;
 mod tests;
 
 pub use entity::*;
-pub use tokenization::shorten_messages_list_to_context_size;
+pub use tokenization::{TokenEstimate, shorten_messages_list_to_context_size};
 pub use utils::*;

src/conversation/llm/tokenization.rs

@@ -4,6 +4,22 @@ 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"))
@@ -13,21 +29,27 @@ fn get_bpe_for_model(model: &str) -> &'static CoreBPE {
 }
 
 pub fn shorten_messages_list_to_context_size(
-    model: &str,
+    estimate: TokenEstimate<'_>,
     prompt_message: &Option<Message>,
     mut messages: Vec<Message>,
     max_response_tokens: Option<u32>,
     max_context_tokens: u32,
 ) -> Vec<Message> {
-    // Loading the tokenization data is an expensive process, so
+    // Loading the tiktoken data is expensive, so we resolve the counter once up
-    // se construct the BPE instance once and then use it for all messages.
+    // front and reuse it for every message.
-    let bpe = get_bpe_for_model(model);
+    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),
+    };
 
     // 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 {
-        calculate_token_size_for_message(bpe, model, prompt_message)
+        count(prompt_message) + max_response_tokens.unwrap_or(0)
-            + max_response_tokens.unwrap_or(0)
     } else {
         0
     };
@@ -37,7 +59,7 @@ 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 = calculate_token_size_for_message(bpe, model, &message);
+        let tokens_for_message = count(&message);
 
         if current_context_length + tokens_for_message > max_context_tokens {
             break;
@@ -48,14 +70,26 @@ 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
 }
 
-/// Calculate the token size of a message for a given model, with a preloaded CoreBPE object.
+/// Token size of a message via tiktoken, for a preloaded CoreBPE object.
-/// Related to `calculate_token_size_for_model_message`.
+/// Accurate only for OpenAI models (see [`TokenEstimate::Tiktoken`]).
-fn calculate_token_size_for_message(bpe: &CoreBPE, model: &str, message: &Message) -> u32 {
+fn tiktoken_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
@@ -80,6 +114,52 @@ fn calculate_token_size_for_message(bpe: &CoreBPE, model: &str, message: &Messag
     (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() {
@@ -94,7 +174,7 @@ pub mod test {
             timestamp: chrono::Utc::now(),
         };
 
-        let tokens = super::calculate_token_size_for_message(bpe, model, &message);
+        let tokens = super::tiktoken_token_size_for_message(bpe, model, &message);
 
         assert_eq!(8, tokens);
     }
@@ -118,7 +198,7 @@ pub mod test {
 
         assert_eq!(
             prompt_length,
-            super::calculate_token_size_for_message(bpe, model, &prompt)
+            super::tiktoken_token_size_for_message(bpe, model, &prompt)
         );
 
         let mut conversation_messages = Vec::new();
@@ -133,7 +213,7 @@ pub mod test {
 
         assert_eq!(
             first_length,
-            super::calculate_token_size_for_message(bpe, model, &first)
+            super::tiktoken_token_size_for_message(bpe, model, &first)
         );
 
         conversation_messages.push(first);
@@ -148,7 +228,7 @@ pub mod test {
 
         assert_eq!(
             second_length,
-            super::calculate_token_size_for_message(bpe, model, &second)
+            super::tiktoken_token_size_for_message(bpe, model, &second)
         );
 
         conversation_messages.push(second);
@@ -165,7 +245,7 @@ pub mod test {
 
         assert_eq!(
             third_length,
-            super::calculate_token_size_for_message(bpe, model, &third)
+            super::tiktoken_token_size_for_message(bpe, model, &third)
         );
 
         conversation_messages.push(third.clone());
@@ -182,7 +262,7 @@ pub mod test {
 
         assert_eq!(
             forth_length,
-            super::calculate_token_size_for_message(bpe, model, &forth)
+            super::tiktoken_token_size_for_message(bpe, model, &forth)
         );
 
         conversation_messages.push(forth.clone());
@@ -190,7 +270,7 @@ pub mod test {
         assert_eq!(4, conversation_messages.len());
 
         let new_conversation_messages = super::shorten_messages_list_to_context_size(
-            model,
+            super::TokenEstimate::Tiktoken(model),
             &Some(prompt),
             conversation_messages,
             max_response_tokens,
@@ -229,7 +309,7 @@ pub mod test {
 
         assert_eq!(
             prompt_length,
-            super::calculate_token_size_for_message(bpe, model, &prompt)
+            super::tiktoken_token_size_for_message(bpe, model, &prompt)
         );
 
         let mut conversation_messages = Vec::new();
@@ -244,7 +324,7 @@ pub mod test {
 
         assert_eq!(
             first_length,
-            super::calculate_token_size_for_message(bpe, model, &first)
+            super::tiktoken_token_size_for_message(bpe, model, &first)
         );
 
         conversation_messages.push(first);
@@ -259,7 +339,7 @@ pub mod test {
 
         assert_eq!(
             second_length,
-            super::calculate_token_size_for_message(bpe, model, &second)
+            super::tiktoken_token_size_for_message(bpe, model, &second)
         );
 
         conversation_messages.push(second);
@@ -276,7 +356,7 @@ pub mod test {
 
         assert_eq!(
             third_length,
-            super::calculate_token_size_for_message(bpe, model, &third)
+            super::tiktoken_token_size_for_message(bpe, model, &third)
         );
 
         conversation_messages.push(third.clone());
@@ -293,7 +373,7 @@ pub mod test {
 
         assert_eq!(
             forth_length,
-            super::calculate_token_size_for_message(bpe, model, &forth)
+            super::tiktoken_token_size_for_message(bpe, model, &forth)
         );
 
         conversation_messages.push(forth.clone());
@@ -301,7 +381,7 @@ pub mod test {
         assert_eq!(4, conversation_messages.len());
 
         let new_conversation_messages = super::shorten_messages_list_to_context_size(
-            model,
+            super::TokenEstimate::Tiktoken(model),
             &Some(prompt),
             conversation_messages,
             max_response_tokens,
@@ -320,4 +400,126 @@ 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);
+    }
 }

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,)
                 ));
             }
         }

src/strings/help/cfg.rs

@@ -128,7 +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.",
-        "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.",
+        "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.",
     )
 }