mirror of
https://github.com/coder/coder.git
synced 2026-09-22 05:05:20 +08:00
fc24c27dfd660fa05c601b7fb571ac6b480ea0e2
20
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Michael Suchacz
|
fc24c27dfd |
fix: reserve chat hook dispatch capacity for running turns (#27656)
## Context Follow-up fix from live UAT of the merged chat lifecycle hooks stack (#27430). Its companion UAT fix (#27655) has merged, so this targets `main` directly. ## Why? UAT measured a burst of 1,500 concurrent chat creations against a consumer with 1.2s latency. 255 were admitted and 1,245 got `502 hook_dispatch_failed (over_capacity)`, which is correct fail-closed behavior. The collateral wasn't: the same burst failed 24 `stop` dispatches, parking chats that had already been admitted and had already executed tools. One 256-slot semaphore served every event, so new-work admission could take every slot and kill turns in flight. Callers now classify each dispatch as admission or generation, and admission draws from a 192-slot gate held *before* the shared pool. At least 64 shared slots stay reachable only by dispatches for work a chat already admitted. The dispatcher is per `coderd` replica, so these limits are per replica, not deployment-wide, and the docs say so. **The caller classifies, not the event type.** Event type isn't a reliable proxy in either direction: a subagent spawn dispatches `user_prompt_submit` from inside a running turn, and the edit path dispatches `session_start` at admission time. `CapacityClassUnset` is rejected in `Dispatch`, so a new call site fails closed rather than silently inheriting a share. **Acquisition order is load-bearing.** Admission takes its own gate first. Taking a shared slot first would let admissions queued on the gate occupy the very capacity the reserve protects. `acquireCapacity` is the only path that takes either pool, so the order can't be bypassed. ## What this does not guarantee Nothing bounds how many turns generate concurrently, so the 192/64 split is a judgement call, not a derived ceiling. This stops an *admission* burst from consuming every slot; it does not make the remainder sufficient. A large enough generation load can still exhaust the reserve and error a running chat. The docs say so explicitly rather than promising a guarantee the code doesn't deliver. Generation can now take all 256 slots, so generation traffic starves admission harder than before. That's the intended priority: rejecting a new prompt is recoverable, ending a turn that already ran tools is not. ## Testing Red-green proved both new tests. Removing the release-on-failure path fails `RefusedSharedAcquireReleasesAdmission` deterministically; removing the expired-deadline check fails `ExpiredDeadlineRefusesFreeSlot` in 18/30 runs. That deadline check fixes a real race found in review. `acquire` previously shared one `time.Timer` across both acquires. Because `select` picks a ready case at random, an admission dispatch could take a slot after its capacity deadline had passed. Measured over 300 trials: 135 late acquisitions, worst overshoot 2.1ms. `acquire` now takes an absolute deadline and refuses an expired one before selecting, which measures 0/300. Go: `coderd/x/agenthooks/...` and `coderd/x/chatd/...`, plus `-race -count=3` on the dispatcher. > Mux opened this PR on Mike's behalf. |
||
|
Michael Suchacz
|
df1c0f9710 |
feat: show what a chat lifecycle hook changed (#27655)
## Stack Context Follow-up fixes from live UAT of the merged chat lifecycle hooks stack (#27430). Two PRs: 1. **This PR**: make hook effects visible and correctly attributed in the transcript. 2. [`mike/chat-hooks-uat/dispatch-capacity`]: reserve dispatch capacity so an admission burst can't fail running turns. ## Why? UAT found three ways the transcript misrepresented what a lifecycle hook did. All three are user-visible and share the same surface (`chathooks/effects.go`, `codersdk.ChatMessagePart`, the conversation timeline), so they're reviewed together. **A prompt `input_override` silently discarded attachments.** `ComposeUserPromptContent` replaced the entire submitted part list with one text part, dropping `file` and `file-reference` parts along with their `chat_file_links`. The user saw their attachments vanish with no explanation. The override now replaces submitted *text* parts only and preserves non-text parts in order. A consumer that wants to block attachments uses `deny`, which is the documented mechanism for refusing a submission. **Every user-visible `system` row was labelled "Lifecycle hook".** The timeline keyed the notice off `role === "system"`. That was correct only by accident, because the hook `user_message` was the sole client-visible system row. The backend now emits the notice as a typed `hook-notice` part and the timeline renders on that, so a future system row can't be mislabelled as a policy notice. **Nothing marked a tool call the hook had rewritten.** A consumer could replace tool input via `input_override` and the transcript showed the rewritten input as if the model had produced it. `ChatMessagePart` gains `hook_rewritten`, set from `preflight.Overrides` on the same path that already carries `ToolCallCreatedAt`, and the tool row renders a "Modified by policy" badge. `ToolCall.PolicyProvider` renders the badge itself, at four wrap sites: the `Tool` dispatch wrapper, the `ReadFilesTool` aggregate and its per-file rows, and `ReadFileTimelineBlock` (grouped and single `read_file` rows bypass `Tool`). Renderer props do not include the flag; descendants consume it through the provider context. The badge is emitted by the provider rather than by the shared header because several renderer branches return early without one, including the auth-required `execute` card, a completed `ask_user_question`, and an empty question payload. Those branches would drop the attribution with no type or runtime error, and the gap is not greppable: every renderer file contains a header somewhere, only individual branches do not. Emitting at the provider removes the possibility instead of enumerating the cases. A rewritten call is wrapped in a group labelled by its badge, so one rewritten file inside a merged read is attributed on its own rather than inheriting the group's badge. `HeaderButton` still appends the policy wording to an explicit `ariaLabel`, since an explicit `aria-label` replaces the name computed from descendants. Provider-executed calls are excluded from attribution. Hooks never see them, and duplicate tool-call ID rejection deliberately skips them, so a reused ID would otherwise mark a provider-executed call as policy-rewritten. ## Testing Go: `coderd/x/chatd/...`, `coderd/x/agenthooks/...`, `codersdk/...`, and `coderd -run 'Hook|Chat'`. Frontend: `tsc` plus every `AgentsPage` story; the only failures are `MCP Tool Completed` and `Scroll To Bottom Button Works With Inverse Scroll`, both of which fail on trunk. A registry-wide story asserts every registered renderer shows the badge, verified against three inverted toggles: removing the badge, hiding it with `display:none`, and skipping the provider for one renderer (which names that renderer). Storybook also covers the rewritten subagent spawn, a completed empty question payload, a non-hook system message, and a failed `read_file` guarding the accessible name. > Mux opened this PR on Mike's behalf. |
||
|
Michael Suchacz
|
c17bed25e0 |
feat: wire chat lifecycle hooks into chatd (#27429)
Wires chat lifecycle hooks into chatd, gated by the `agent-lifecycle-hooks` experiment. Part of the lifecycle hooks stack (#27401, #27428, #27430). See `docs/admin/setup/chat-lifecycle-hooks.md` for the consumer-facing contract. ## Summary When a hook URL is configured, chatd dispatches `session_start`, `user_prompt_submit`, `pre_tool_use`, `post_tool_use`, `pre_compact`, `post_compact`, and `stop` events to the consumer and applies its responses. ## Design - **Stateless**: Coder stores no hook dispatch or decision state. Delivery is at least once; consumers deduplicate on stable payload identifiers (chat ID, event type, tool-use ID) and answer duplicates with the same decision. - **Admission-time prompt effects**: `user_prompt_submit` dispatches exactly once per submission (create, send, queue, edit, subagent spawn) and folds its effects into the stored prompt as typed message parts: original-or-overridden user parts, then model-only `hook-context`, then a user-visible `hook-notice`. Hook context is stripped from every client-facing conversion; hook notices are excluded from model prompts. The server rejects hook parts in client-submitted content. - **Tool gating**: `pre_tool_use` allow can override tool input; deny becomes a synthetic denied tool result, with any returned model context persisted as a model-only transcript row so it never reaches clients. The denial text identifies an external policy (the deployment's lifecycle hook) as the source and marks the decision as persistent, so the model explains the denial instead of retrying it or misreporting it as an infrastructure failure. - **Fail closed**: a dispatch failure rejects the triggering request or moves the chat to the error state in the same transaction as the affected step, so a runnable state is never published with unapproved content. - **Admission before persistence**: `pre_tool_use` is dispatched for the calls the model produced, before the assistant message is stored. See "Staged tool admission" below. - **Fresh dispatch per tool call**: every non-provider-executed tool call is decided by its own `pre_tool_use` dispatch; Coder never reuses an earlier decision on the consumer's behalf. Retries re-dispatch the same logical event. ## Structure All hook dispatch flows through one seam: entry points build a `chathooks.Chat` (chat identity) and a `chathooks.Message` (event details) and call `Trigger.Trigger`, the only component that talks to the dispatcher. The integration lives in the `coderd/x/chatd/chathooks` subpackage, split by responsibility: - `trigger.go`: the trigger seam; builds the wire envelope per event, normalizes deny into a typed error, and holds the package's single enabled-check. - `effects.go`: pure conversion of hook results into transcript rows and prompt parts. - `errors.go`: failure classification (dispatch error messages, denial mapping, tool-result dispatch-failure scanning). - `tooluse.go`: the tool-call gate (`pre_tool_use` preflight, `post_tool_use` payloads, applying admitted input to the step). Server-bound glue stays in `coderd/x/chatd/hook_server.go`: the chat-parking dispatch error handlers, the step-commit row insertion wrappers, and the dynamic post-tool-use state loader, which depends on chatd validation types. This PR adopts the `codersdk/x/agenthooks` and `coderd/x/agenthooks/dispatch` import paths introduced at the tip of #27401; intermediate commits still reference the pre-move paths and are not individually buildable. ## Staged tool admission `pre_tool_use` originally ran at tool execution time, which is after the assistant message carrying the tool call was already committed. An `input_override` therefore had to rewrite stored message content in place. @hugodutka pointed out that chatd treats message content as immutable, and that the rewrite was a shortcut rather than a requirement. It was also a correctness problem in its own right: the rewrite only updated the database, so the transcript could show one input while a different one had executed. The hook now runs before the step is persisted: ```text provider stream ends (tool calls complete, in memory) -> pre_tool_use dispatch per call -> ONE transaction: assistant row with admitted inputs, synthetic denials, hook rows -> execute ``` The step is inserted once, carrying the input the tool runs with. `UpdateChatMessageContentByID` and `Tx.UpdateMessageContent` are deleted from #27428, so message content stays immutable. Two consequences, both intentional: - **Clients converge rather than wait.** Tool-call parts still stream live, so a rewritten call briefly shows the model's proposed input before the committed message replaces it. The chat store already clears stream state when an assistant message arrives, so the stored input wins with no frontend change and no added latency before tool cards appear. - **A call already in history was already admitted.** Execution consumes the stored input instead of dispatching a second decision, which keeps one dispatch and one set of hook effects per call. A consumer policy change between admission and execution applies to later calls, not to calls already admitted. The per-chat debug endpoint still records the provider's original tool input. Its purpose is to report provider behavior, and it requires an explicit per-chat debug flag; the invariant here covers the transcript. ## Configuration Adds `chat-hook-url`, `chat-hook-secret`, `chat-hook-timeout`, and `chat-hook-enabled` deployment options with startup validation. The flags are hidden from `coder server --help` while the feature is experimental; the setup guide documents them. ## Tool input validation Built-in tool arguments reach a consumer as raw JSON with key spelling preserved, but the tools decode those bytes with Go, which matches struct fields case-insensitively and keeps the last match. A policy reading `path` could therefore authorize one value while the tool executed another, and a lone case variant such as `{"PATH":"/secret"}` was invisible to a policy checking for `path`. Coder now rejects a built-in tool call whose input repeats a key or spells a schema property with different capitalization, before the `pre_tool_use` dispatch, so a consumer is never asked to authorize bytes whose meaning depends on the reader. Rejected calls produce an error result the model can retry; unambiguous calls in the same batch still run. A consumer-authored `input_override` is rechecked after the dispatch and fails the turn closed, because the model cannot correct it. Dynamic and MCP inputs are excluded because the client and the workspace agent execute those calls rather than coderd. Two paths needed more than a schema check. Execution resolves a deprecated tool name to its canonical tool, so validation resolves aliases first. The `edit_files` decoder also reads `search` and `replace`, which its schema does not advertise, so those aliases are now matched exactly and their case variants ignored. A hook denial now returns a structured 403 carrying `kind: "hook_denied"`, mirroring the dispatch-failure response that already carries its own kind. Without it a client cannot tell a policy decision apart from a generic failure, and the chat UI titled a denial "Request failed". Adding a kind needs no migration: `ChatErrorKind` is persisted only inside the JSONB `chats.last_error` column, whose decoder accepts unknown kinds. The hook docs also correct the tool-input convergence window. A batch dispatches sequentially before the assistant row commits, so the original input stays visible for a span that scales with the number of tool calls in the step rather than a single hook timeout. > This PR was written by Mux, an AI coding agent, on Mike's behalf. |
||
|
Michael Suchacz
|
3227cac217 |
feat: add manual chat compaction via /compact (#27081)
Adds a user-triggered `/compact` action for Coder Agents chats: typing
`/compact` in the composer (or picking it from the `/` trigger menu)
summarizes the conversation so far to free up context window space.
## How it works
- New `POST /api/experimental/chats/{chat}/compact` endpoint
(owner-only, RBAC `ActionUpdate`, excluded from the public API reference
via `x-apidocgen skip`). It marks the chat with a durable one-shot
`chats.compaction_requested_at` signal and moves it `waiting -> running`
via a new `RequestCompaction` state transition; no message row is
inserted. AI Gateway attribution needs no per-request key: generation
preparation resolves the owner's synthetic API key (#27170) like any
other turn.
- `RequestCompaction` hands off chat ownership (clears
`worker_id`/`runner_id`) so a worker acquisition hint is published;
since the transition changes no history, the previous runner could
otherwise miss the request under reordered pubsub delivery.
- The background chat worker picks the chat up like any other turn. A
pending manual request takes precedence over turn completion in the
generation decision, and forces compaction even below the automatic
threshold (and when compaction is disabled via threshold=100). The
commit step consumes the request marker in the same transaction; any
transition that ends the turn clears stale markers.
- The summary triplet reuses the automatic-compaction path, now tagged
with a `source` (`automatic` | `manual`) that is plumbed through
streamed progress parts, persisted tool JSON, and the UI label
("Summarized (manual)").
- Validation order: busy chats reject with 409 (state-machine conflict),
empty/already-compacted chats with 409 "nothing to compact", archived
chats with 400; the owner usage-limit check runs last so no-op requests
surface the specific conflict instead of a limit error.
- Web UI: the `/` trigger menu now has a built-in "Commands" group
listing `/compact`; submit intercepts exactly `/compact` and calls the
endpoint instead of sending a message. A personal or workspace skill
named `compact` takes precedence over the built-in command; while skill
collisions are still resolving, an exact `/compact` submission is
blocked with a retryable hint instead of leaking as message text.
History and queued-message edits are never intercepted. After
compaction, the context usage indicator resets to its unknown state
until the next assistant response reports fresh usage, instead of
showing the stale pre-compaction number.
- codersdk: `ExperimentalClient.CompactChat`.
Worker-path execution (rather than compacting synchronously in the
handler) reuses the existing lock fencing, live "Summarizing..."
streaming, retry accounting, restart resilience, and debug-run
observability. Rationale documented in `coderd/x/chatd/ARCHITECTURE.md`.
## Testing
- State machine: transition-matrix coverage for `RequestCompaction`,
marker lifecycle tests (carried by lease renewals/queue appends, cleared
by terminal transitions, consumed by commit), ownership handoff +
acquisition hint assertions.
- Worker: decision-ordering and forced-compaction unit tests;
active-server end-to-end test (manual compact below threshold produces a
`source=manual` summary, returns to `waiting`, no assistant follow-up;
busy chat rejected).
- API: success, archived, non-owner, RBAC-denied, empty-chat, no-daemon
cases; usage-limit ordering (at-limit owners still get
state/nothing-to-compact conflicts for no-op requests, with marker
rollback).
- Frontend: Storybook play tests for the Commands menu group, submit
intercept, skill-name collision, queued-edit passthrough, and
manual/automatic tool rendering; unit tests for command availability
resolution and the post-compaction context usage reset.
> This PR was created by Mux, an AI coding agent, working on Mike's
behalf.
|
||
|
Michael Suchacz
|
4ed6fcced7 |
refactor(coderd): stop storing chat gateway key IDs and drop the columns (#27171)
> Mux is working on behalf of Mike. ## Summary Stop reading and writing the legacy `api_key_id` columns on chat messages and queued messages, and drop the columns in the same PR. Runtime AI Gateway attribution continues to use the per-user synthetic key introduced by #27170. With the columns gone, `sqlc` generates `database.ChatMessage` and `database.ChatQueuedMessage` without `api_key_id`, so no transitional query scaffolding is needed. Migration `000548` drops the `api_key_id` columns. #27170 already removed their foreign keys, so the down migration re-adds nullable text columns without constraints. Previous column values cannot be restored. Also moves the model config validation in `CreateChat` above the message-building work so a disabled or invalid model fails fast. On main this mattered more: the old ordering minted a synthetic API key before rejecting the request. Deploy note: replicas still running the previous release write `api_key_id` on insert, so chat message inserts on old replicas fail during the rolling window after the column drop. This was previously split across two PRs to avoid that window; per review feedback the split added more churn than it was worth for an experimental surface. Depends on #27170 (merged). |
||
|
Michael Suchacz
|
997b5d0843 |
feat: add synthetic gateway keys (#27170)
> Mux is working on behalf of Mike. ## Summary Add a per-user synthetic API key for chatd AI Gateway attribution. Chatd resolves the key from the chat owner, extends it before expiry, and discards the generated bearer token so the key is never a usable credential. There is no mapping table. The key is resolved from `api_keys` by a deterministic token name (`chatd_<owner_id>_session_token`), mirroring the provisionerd session token model, with three deltas that chatd needs: - **Login type guard**: token names are unvalidated user input, so a user can create a bearer token with the colliding name. The lookup excludes `login_type = 'token'` rows, so chatd never picks up (or extends) a real user token. Synthetic keys are minted with the owner's login type, which is never `token`. - **In-place expiry extension instead of delete-and-reinsert**: chat generations have no stop boundary, and an in-flight generation may have already delegated the current key ID to aibridged. Extending `expires_at` keeps the key ID stable forever. - **Advisory-lock mint**: the unique index on token names is partial (`WHERE login_type = 'token'`), so nothing DB-enforces uniqueness for synthetic keys. A per-user advisory lock serializes concurrent mints. Keys carry a minimal scope (`api_key:read`) as defense in depth; the delegated gateway path never evaluates scopes and the secret is discarded at mint. Migration 000544 removes the foreign keys from the legacy message and queue `api_key_id` columns while chatd continues stamping them for rolling compatibility. Stale IDs are tolerated because routing uses `chats.owner_id`. Individual key deletion, delete-all, and password reset remove the key without changing chat history or queue versions, and the next lookup remints it. Suspension does not delete the key; delegated gateway authorization rejects inactive users at request time. This is the first PR in a three-PR rollout and must be fully deployed before #27171. Refs https://linear.app/codercom/issue/CODAGT-561/maintain-synthetic-api-key-per-user-per-chat |
||
|
Michael Suchacz
|
a567f6a89f | feat: allow admins to override the chat compaction model (#27151) | ||
|
Hugo Dutka
|
96130e2bc5 |
chore(coderd/x/chatd): address generation review items (#26517)
Addresses the deferred `coderd/x/chatd/generation.go` review comments from PR #26109: [required generation dependencies](https://github.com/coder/coder/pull/26109#discussion_r3380311853), [scoped chat variables](https://github.com/coder/coder/pull/26109#discussion_r3387161874), [generation state error handling](https://github.com/coder/coder/pull/26109#discussion_r3387191468), [generation attempt return values](https://github.com/coder/coder/pull/26109#discussion_r3387251382), [generation fence verification](https://github.com/coder/coder/pull/26109#discussion_r3387288234), and [chatdebug outcome recording](https://github.com/coder/coder/pull/26109#discussion_r3387544273). This makes generation task dependencies explicit, packages generation attempt episode state into a struct, and centralizes generation task fence checks for generation transitions. Generated by Coder Agents, closely reviewed by Hugo. |
||
|
Cian Johnston
|
b21e0717d5 |
feat: remove chat chain mode (#26980)
Removes OpenAI Responses "chain mode" from chatd. Closes CODAGT-445.
- Deletes `chatopenai/responses.go` (chain detection, activation, prompt filtering, response ID extraction) and its tests.
- Deletes the `ChainBroken` classification in `chaterror` and the chatloop retry bookkeeping that disabled chain mode mid-generation.
- Drops the `chain_broken` label from the `coderd_chatd_stream_retries_total` metric.
- Stops reading and writing `chat_messages.provider_response_id`
- Deletes the dead `ClearChatMessageProviderResponseIDsByChatID` query. Dropping the column is a follow-up migration.
- Deletes three chatloop hooks no caller sets (`ReloadMessages`, `DisableChainMode`, `PrepareMessages`), the dead `const AgentChatContextSentinelPath`, and stale chain-mode comments.
🤖 Generated by Coder Agents on behalf of @johnstcn.
|
||
|
Cian Johnston
|
4936ff9808 |
refactor: deprecate AIGatewayRoutingEnabled, remove direct chat routing (#26862)
This PR removes the now-dead direct-routing code: - Deletes the direct routing implementation. - Collapses the resolvedModelRoute discriminated union into aiGatewayModelRoute. - Removes the dead providerKeys cascade. - Deletes the preferredShortTextCandidates quickgen function. - Simplifies the advisor override error handling. - Deprecates the AIGatewayRoutingEnabled deployment option. It is now a no-op so as to not break existing deployments on upgrade. Once direct routing was gone, the AI Gateway became mandatory for chat, which surfaced gaps in how the product behaves with the gateway disabled: - Exposes ai-gateway-enabled to the frontend via embedded page metadata. - Disables the chat composer via the existing AgentSetupNotice when the gateway is disabled, for both new and existing chats. - Fixes nil/typed-nil chatDaemon panics on startup and shutdown when gateway is disabled. - Fixes chat WebSocket from retrying the still-gated stream endpoint forever when the gateway is disabled. |
||
|
Mathias Fredriksson
|
59fcc9c0ad |
feat: improve sub-agent orchestration tools (#26673)
Tool errors caused orchestrators to abandon spawned agents. Bare error responses and the close_agent name framed delegation as one-shot: one transient failure or timeout ended the work, and the orchestrator had no way to recover or reuse agents. Renames close_agent to interrupt_agent with a hidden backward-compatible alias. wait_agent and message_agent return structured payloads instead of bare errors, so the orchestrator can retry after a timeout, recover from an error status, or redirect an idle agent. Adds list_agents so orchestrators can rediscover spawned agents. Adds root-only orchestration guidance for error recovery. |
||
|
Kyle Carberry
|
32217259b7 |
feat: cap tool output to fit the model context window (#26637)
## Problem
Local tool results were persisted and replayed to the model verbatim,
with no size cap. A single oversized result, most often a multi-megabyte
response from an MCP tool, overflows the prompt on the next request.
Every retry rebuilds the same history and fails the same way, leaving
the chat wedged in `error`. Auto-compaction is reactive (token usage is
only known after a response), so it can't catch a single result that
blows the very next request.
## Fix
Cap every locally-executed tool result at its single choke point,
`executeSingleTool` in `chatloop`, so the cap covers built-in tools,
**global (deployment-pinned) MCP**, **workspace MCP**, and provider
runners uniformly. Because this runs before the result is published to
the live stream and before it is committed, the SSE preview, the
persisted message, and the model replay all see the same bounded output.
The budget is token-aware: a single tool result may use at most half the
model's context window (`~4 bytes/token`), with a `16KB` floor and a
`64KB` default when the window is unknown. Truncation keeps the head and
tail of the output and replaces the middle with a marker telling the
model how much was removed and to narrow its query; it is UTF-8 safe and
never exceeds the budget. Binary media `Data` is passed through
untouched (only the text payload is bounded).
A `coderd_chatd_tool_result_truncated_total{provider,model,tool_name}`
counter and a warning log record each truncation.
## Out of scope
- Provider-executed results (e.g. web search) arrive via the stream, not
`executeSingleTool`.
- Dynamic/external tool results submitted through the `/tool-results`
API are validated as JSON elsewhere.
- Cumulative growth across many results is still handled by context
compaction; this change only bounds any single result.
<details>
<summary>Implementation notes</summary>
- New `coderd/x/chatd/chatloop/tooltruncate.go`:
`toolResultByteBudget(contextLimitTokens)` and
`truncateToolResultText(text, maxBytes)` (pure, unit-tested).
- `chatloop.go`: added `ContextLimit` to `ExecuteLocalToolsOptions`;
threaded a computed byte budget through `executeTools` into
`executeSingleTool`, where `resp.Content` is capped for the text,
media-text, and error branches.
- `generation.go`: passes `ContextLimit: prepared.ContextLimitFallback`
(the model's configured context limit).
- `metrics.go`: new `ToolResultTruncatedTotal` counter +
`RecordToolResultTruncated`.
- Tunable knobs live as constants in `tooltruncate.go`
(`toolResultContextDivisor = 2`, `bytesPerTokenEstimate`,
`minToolResultBytes`, `defaultToolResultBytes`).
Verified: `go build ./coderd/x/chatd/...`, `go test
./coderd/x/chatd/chatloop/...`, and the `chatd` test binary compiles.
</details>
---
Resolves CODAGT-678
Generated by Coder Agents on behalf of @kylecarbs.
|
||
|
Kyle Carberry
|
cd56ab9e33 |
refactor: remove legacy live-read and injected-history chat context paths (#26585)
This PR makes the agent-pushed pinned snapshot (`chat_context_resources`) the sole source of workspace context for chats, completing the "Release 5" cleanup. It removes legacy mechanisms now superseded by the snapshot that agents push over dRPC (`PushContextState`) and refresh via `chat-context/refresh`. Removed: - **Live-read at turn time.** MCP tool discovery, skill live-body reads, and the instruction/skill history fallback that dialed the workspace on every turn. - **Context injected as message history.** The `persist_workspace_context` generation action and its decision-loop guard. - **The legacy write path.** `POST`/`DELETE /api/v2/workspaceagents/me/experimental/chat-context`, the agentsdk `AddChatContext`/`ClearChatContext` methods, and the CLI one-shot writer. - **The `chats.last_injected_context` column** and all of its plumbing (migration `000529`, queries, `db2sdk`, `dbauthz`, audit table, and the frontend `ContextUsageIndicator` fallback). Subagent context inheritance no longer copies parent context messages; children now hydrate the parent's pinned `chat_context_resources` on create, which yields an identical pin for the same workspace and agent. What stays (still served by the live agent connection, not the snapshot): `read_skill_file` supporting-file reads, `read_skill` supporting-file listing, and MCP tool execution. > [!NOTE] > Migration `000529` drops `chats.last_injected_context` and recreates the `chats_expanded` view without it. The down migration restores both. <details> <summary>Decision log (D1-D5)</summary> - **D1 (subagent inheritance):** Re-point inheritance from the legacy message copy to a pinned hydrate. Children call `hydrateChatContextOnCreate` instead of copying parent context messages. - **D2 (`persist_workspace_context`):** Remove the generation action entirely along with the decision-loop guard it existed to satisfy, since context is never injected into history anymore. - **D3 (legacy HTTP + CLI):** Remove the experimental `chat-context` POST/DELETE endpoints, the agentsdk methods, and the CLI one-shot. The dRPC push + `chat-context/refresh` replace them. - **D4 (frontend fallback):** Remove the `last_injected_context` fallback in `ContextUsageIndicator`; pinned `resources` are the sole source. - **D5 (sequencing):** Ship as a single PR rather than a stacked pair. </details> --- Coder Agents generated on behalf of @kylecarbs. |
||
|
Hugo Dutka
|
c0c0d1e353 |
chore(coderd/x/chatd): improve runner logging (#26522)
Follow up to https://github.com/coder/coder/pull/26412. - Ensure that each `errTaskExpectedExit` and any other error is joined with a descriptive reason. This will enable [`runChatWithRetry`](https://github.com/coder/coder/blob/5601ea18ed650deafa4a2da7286a144f9f382330/coderd/x/chatd/tasks.go#L113) to log a descriptive message when a task exits. - Pass additional task information like chat id into `runTaskWithRetry` so logs can be more descriptive. |
||
|
Hugo Dutka
|
61a7b800e2 |
fix(coderd/x/chatd): always commit a workspace context marker (#26520)
Closes [CODAGT-629](https://linear.app/codercom/issue/CODAGT-629/agents-can-get-stuck-and-ignore-stop-or-nudge). A stuck chat had these logs associated with it: ``` 1781735334322 2026-06-17T22:28:54.322Z 2026-06-17 22:28:54.322 [debu] coderd.chatd.processor: workspace context build: workspace agent not resolvable chat_id=d4524ebb-4494-47df-b258-d933c0248942 owner_id=d96bf761-3f94-46b3-a1da-6316e2e4735d 1781735334298 2026-06-17T22:28:54.298Z 2026-06-17 22:28:54.298 [debu] coderd.chatd.processor: plan path instruction: agent not reachable chat_id=d4524ebb-4494-47df-b258-d933c0248942 owner_id=d96bf761-3f94-46b3-a1da-6316e2e4735d chat_id=d4524ebb-4494-47df-b258-d933c0248942 ... error= workspace has no running agent: the workspace is likely stopped. Use the start_workspace tool to start it: github.com/coder/coder/v2/coderd/x/chatd.init <autogenerated>:1 ``` "workspace agent not resolvable" is printed by [`fetchContextForBuild`](<https://github.com/coder/coder/blob/fecc991ac9f9d673d7a772b0042ca821d19b6296/coderd/x/chatd/workspace_context_builder.go#L145>). this causes [`buildWorkspaceContext`](<https://github.com/coder/coder/blob/fecc991ac9f9d673d7a772b0042ca821d19b6296/coderd/x/chatd/workspace_context_builder.go#L60>) to exit with a `errWorkspaceContextUnavailable` error. That in turn is interpreted by [`persistWorkspaceContext`](<https://github.com/coder/coder/blob/fecc991ac9f9d673d7a772b0042ca821d19b6296/coderd/x/chatd/generation.go#L838>) as an "expected exit" scenario. That's a bug: because the task exits without changing the chat state, the runner never issues another task to process the chat any further. But even if it did, it'd go through the same code path and exit again. We need to ensure that `persistWorkspaceContext` commits a marker file even if it cannot reach the agent. |
||
|
Hugo Dutka
|
054d0c45de |
fix(coderd/x/chatd): log retry errors and add a task timeout (#26412)
This PR adds logging when the chat runner retries and exits because of an error. It also adds a 15-minute task timeout to ensure that stuck tasks do not hang forever. |
||
|
Cian Johnston
|
21a2652343 |
fix(coderd/x/chatd): show correct provider and clean detail for Bedrock errors (#26338)
## Problem
Bedrock errors (routed through aibridge) showed the wrong provider
("Anthropic ...")
and a doubly-wrapped detail string instead of the clean message.
## Fix (chatd only)
- **Provider label:** thread the configured provider to error
classification via
`GenerateAssistantOptions.ErrorProvider`. Transport provider still
drives prompt
prep, sanitization, and metric labels (unchanged).
- **Detail:** unwrap the SDK transport wrapper (`METHOD "URL": NNN
{body}`) to surface
the inner message; handles top-level `{"message":...}` and nested
`{"error":{"message":...}}`.
## Notes
- Surfacing a top-level `message` now applies to all providers
(intentional; nested wins when both present).
- The advisor path keeps the transport label; accepted as-is (it returns
`err.Error()`, not the classification).
- Fixes display in chatd only; the wrapper originates in aibridge (out
of scope here).
🤖 Generated by Coder Agents.
|
||
|
Hugo Dutka
|
3cde346cbb |
fix(coderd/x/chatd): fix compaction still over limit check (#26377)
Addresses [CODAGT-620](https://linear.app/codercom/issue/CODAGT-620/session-can-get-stuck-at-compaction-with-request-failed). We have logic that checks whether message compaction still leaves the chat over the context limit. We want to abort if it does - if we didn't, we'd get into an endless compaction loop. The check's logic was faulty. This PR changes fixes it. The new flow is: 1. In iteration 1, a chat runner commits a message compaction summary. 2. In iteration 2, the runner submits the newly compacted conversation to the LLM provider in order to generate the next message. 3. In iteration 3, 4, 5, etc., if the conversation needs compaction, the runner looks up the configured context limit and the first assistant message after the last compaction summary. It compares the context usage on that message with the context limit. If the usage is over the limit, it returns an error. |
||
|
Hugo Dutka
|
4cf4ee0121 |
chore(coderd/x/chatd): log all chat errors (#26371)
When a chat hits a terminal error, for example "Request failed unexpectedly", we don't log the full underlying error anywhere. This fixes that. |
||
|
Hugo Dutka
|
4debd23cbb |
fix: chatd refactor (#26270)
Implements the chatd stabilization RFC. Combines: - https://github.com/coder/coder/pull/25908 - https://github.com/coder/coder/pull/25923 - https://github.com/coder/coder/pull/26109 - https://github.com/coder/coder/pull/26110 - https://github.com/coder/coder/pull/26111 - https://github.com/coder/coder/pull/26112 |