Provider-neutral context management

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.github/workflows/ci.yml

@@ -14,13 +14,31 @@ concurrency:
   group: ci-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
 jobs:
-  test-and-clippy:
-    name: Unit testing and linting
+  prek:
+    name: Lint, format & test
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v7
-      - uses: dtolnay/rust-toolchain@1.93.0
+
+      # 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
+        with:
+          rustflags: ''
+
       - name: Install SQLite3
         run: sudo apt-get update && sudo apt-get install -y libsqlite3-dev
-      - run: cargo test --all-features
-      - run: cargo clippy
+
+      # 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

CHANGELOG.md

@@ -1,3 +1,10 @@
+# (2026-06-28) 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 = "1.0.102"
+version = "1.0.103"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c"
+checksum = "2a4385e2e34eb35d6b3efe798b9eb88096925d87726c0798709bf56d9ed84af3"
 
 [[package]]
 name = "anymap2"
@@ -315,7 +315,7 @@ dependencies = [
 
 [[package]]
 name = "baibot"
-version = "1.24.0"
+version = "1.25.0"
 dependencies = [
  "anthropic",
  "anyhow",
@@ -327,7 +327,7 @@ dependencies = [
  "mime_guess",
  "mxidwc",
  "mxlink",
- "quick_cache",
+ "quick_cache 0.7.0",
  "regex",
  "reqwest 0.13.4",
  "serde",
@@ -1233,6 +1233,12 @@ 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"
@@ -1457,7 +1463,7 @@ version = "0.15.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9229cfe53dfd69f0609a49f65461bd93001ea1ef889cd5529dd176593f5338a1"
 dependencies = [
- "foldhash",
+ "foldhash 0.1.5",
 ]
 
 [[package]]
@@ -2492,7 +2498,7 @@ dependencies = [
  "hex",
  "matrix-sdk",
  "mime",
- "quick_cache",
+ "quick_cache 0.6.24",
  "rand 0.10.1",
  "serde",
  "serde_json",
@@ -2848,9 +2854,9 @@ checksum = "007d8adb5ddab6f8e3f491ac63566a7d5002cc7ed73901f72057943fa71ae1ae"
 
 [[package]]
 name = "quick_cache"
-version = "0.6.23"
+version = "0.6.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3a3db184a8b66cfe87f0263a1de147a6b554c864d1767c6f7fa4eb0e5497b565"
+checksum = "b9c6658afe513a3b484e3abfdaa0d03ef3c0bbf017542c178dd55f94eb3051f9"
 dependencies = [
  "ahash",
  "equivalent",
@@ -2858,6 +2864,18 @@ 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"

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]
@@ -26,7 +26,7 @@ mime_guess = "2.0.*"
 mxidwc = "1.0.*"
 mxlink = ">=1.15.0"
 etke_openai_api_rust = "0.1.*"
-quick_cache = "0.6.*"
+quick_cache = "0.7.*"
 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.

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/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.
 
@@ -176,10 +176,10 @@ This provider is just as featureful as the [OpenAI](#openai) provider, but is mo
 
 ### Venice
 
-[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.
+[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), [👤 Sign up](https://venice.ai), [📋 Models list](https://api.venice.ai/api/v1/models)
+- 🔗 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)
 - 🌟 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`

etc/services/ollama/compose.yml

@@ -1,6 +1,6 @@
 services:
   ollama:
-    image: docker.io/ollama/ollama:0.30.10
+    image: docker.io/ollama/ollama:0.30.11
     restart: unless-stopped
     ports:
       - "${SERVICE_OLLAMA_BIND_PORT_HTTP}:11434"

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/bot/messaging.rs

@@ -2,7 +2,8 @@ use mxlink::matrix_sdk::{
     Room,
     room::edit::EditedContent,
     ruma::{
-        EventId, OwnedEventId, api::client::receipt::create_receipt::v3::ReceiptType,
+        EventId, OwnedEventId,
+        api::client::receipt::create_receipt::v3::ReceiptType,
         events::room::message::{
             OriginalSyncRoomMessageEvent, RoomMessageEventContentWithoutRelation,
         },

src/controller/chat_completion/mod.rs

@@ -558,7 +558,9 @@ async fn handle_stage_text_generation(
     // 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);
+        let generation = controller
+            .generate_text(conversation, params)
+            .instrument(span);
         tokio::pin!(generation);
 
         let mut placeholder: Option<OwnedEventId> = None;

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
-    // se construct the BPE instance once and then use it for all messages.
-    let bpe = get_bpe_for_model(model);
+    // 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),
+    };
 
     // 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)
-            + max_response_tokens.unwrap_or(0)
+        count(prompt_message) + 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.
-/// Related to `calculate_token_size_for_model_message`.
-fn calculate_token_size_for_message(bpe: &CoreBPE, model: &str, message: &Message) -> u32 {
+/// 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 {
     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/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.",
     )
 }
 

src/strings/thinking.rs

@@ -84,11 +84,23 @@ mod tests {
         // 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(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);
+        assert_eq!(
+            messages_for_elapsed(Duration::from_secs(600)),
+            MESSAGES_DEEP
+        );
     }
 
     #[test]