Records a `Captain::Session` row for every Captain V2 assistant response
delivered in a conversation, so we can show how a response was generated
and report on credit, FAQ, and document usage. Stacked on #14970 (the
`captain_sessions` model).
## What changed
- `FaqLookupTool` now records the retrieved FAQ ids (and their backing
document ids) into the shared run state, accumulated across tool calls.
- `AgentRunnerService` exposes the raw ai-agents run result via
`last_run_result`; the `generate_response` return shape is unchanged, so
the playground path is unaffected.
- New `Captain::Assistant::SessionCaptureService` builds the session:
scenario resolved from the answering agent name, model from
`assistant.agent_model`, token usage plus the trimmed current-turn
conversation history stored in `run_context`.
- `ResponseBuilderJob` captures after delivery: `credits_consumed`
mirrors the actual charge (1.0 for a billed response, 0.0 for handoffs,
where the session points at the customer-facing handoff message).
Capture runs outside the delivery transaction and swallows its own
failures, so a logging bug can never block or roll back a customer
reply.
V1 responses and copilot are out of scope; copilot capture comes next.
## How to test
On an account with `captain_integration_v2` enabled and an inbox
connected to an assistant with approved FAQs, send a customer message on
a pending conversation. After the assistant replies, a
`Captain::Session` row should exist with the conversation as subject,
the reply message as result, the FAQs/documents used, and the run
context for that turn. Asking for a human agent should produce a
zero-credit session pointing at the handoff message.
<img width="2428" height="1058" alt="CleanShot 2026-07-15 at 17 25
40@2x"
src="https://github.com/user-attachments/assets/d8e44923-c17b-494f-8c33-c8fa4219438c"
/>
# Pull Request Template
## Description
Fixes: https://github.com/chatwoot/chatwoot/issues/13880
Uses approaches discussed from:
https://github.com/chatwoot/chatwoot/pull/13883
Activity messages pertaining to resolve are included along with an
instruction for the LLM to choose whether to consider them or not along
## Type of change
- [x] Bug fix (non-breaking change which fixes an issue)
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
locally and with specs
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
---------
Co-authored-by: Sony Mathew <sony@chatwoot.com>
Captain custom tools configured with API key authentication now send the
configured key in the requested HTTP header. Existing tools begin
working without needing to be recreated or reconfigured, while
credentials remain protected across redirects.
## How to reproduce
1. Create a Captain custom tool using API Key authentication.
2. Configure `X-API-Key` as the header name and save the tool.
3. Invoke the tool and inspect the incoming request.
4. Before this change, the API key header is absent; after this change,
the configured endpoint receives it.
## What changed
The UI persists API key authentication as `name` and `key`, but the
request builder also required an unused `location: header` property. The
request builder now treats API key authentication as header-based,
matching the only mode exposed by the UI.
Custom authentication headers are also registered as sensitive with
`SafeFetch`. They are retained for the configured endpoint and
same-origin redirects, but stripped when a redirect crosses origins to
prevent credential leakage. Factory, request, and redirect specs cover
the real UI payload and both public and private-network fetch paths.
Improves Captain V1 → V2 migration for complex legacy instructions so
mandatory triggers, workflows, language rules, and escalation behavior
remain active while query-dependent product knowledge is prepared as
pending FAQ candidates.
## What changed
- Added explicit preservation rules for mandatory triggers, verification
steps, escalation conditions, exceptions, and language behavior.
- Added an auditor that checks the draft and fixes any issues before
manual review.
- Kept the existing migration application contract and schema limits
unchanged
- Added focused regression coverage for the complex-prompt classifier
contract.
## How to reproduce
Generate a migration draft for an assistant with dense legacy
instructions containing mandatory handoff triggers, verification rules,
product facts, and multi-step workflows. The resulting draft should keep
actions active, place query-dependent facts in FAQ candidates, and avoid
silently dropping or reversing source requirements.
Focused Captain migration specs and RuboCop checks pass locally.
Ensures Captain follows explicit mandatory-transfer rules from active
Response Guidelines and Guardrails instead of allowing the generic
consent-first fallback to override those rules.
## What changed
- Made explicit transfer requirements take precedence over generic
consent-first handoff defaults only when their condition matches.
- Added explicit Response Guideline and Guardrail transfer rules to the
human-handoff protocol.
- Added focused prompt regression coverage.
## How to reproduce
Configure a Response Guideline or Guardrail that requires immediate
transfer for a specific condition, then send a request matching that
condition. Captain should invoke the human-handoff path without asking
the user to consent again. Unmatched requests continue to use the
existing consent-first fallback.
The assistant prompt renderer, agent prompt context, and focused
regression specs pass locally.
# Pull Request Template
## Description
Please include a summary of the change and issue(s) fixed. Also, mention
relevant motivation, context, and any dependencies that this change
requires.
Fixes
https://linear.app/chatwoot/issue/AI-136/check-conversation-status-while-auto-resolving
- After 60mins of inactivity, we run a job that decides if pending
conversations are resolvable or need handoff
- the prompt was a bit conservative and didn't have conversation state
context
## Type of change
Please delete options that are not relevant.
- [x] Bug fix (non-breaking change which fixes an issue)
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
locally ran a sample eval
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
---------
Co-authored-by: Sony Mathew <sony@chatwoot.com>
This PR adds internal tooling and planning docs for migrating existing
Captain assistant instructions into the new General Guidelines
structure.
**Summary**
This PR adds a controlled migration path for moving existing Captain V1
assistant instructions into the structured Captain architecture.
It introduces a classifier that reads the current `config.instructions`
and produces reviewed migration drafts with separate sections for:
- assistant description / business context
- response guidelines
- guardrails
- scenario candidates
- conversation messages
- FAQ/document candidates
- needs-review items
The migration is intentionally staged. It only targets V1-style
assistants that still have custom instructions, are connected to
inboxes, and do not already have structured response guidelines,
guardrails, or scenario records.
When applied, the task writes the extracted business context to the
assistant description, response guidelines to `response_guidelines`,
guardrails to `guardrails`, and stores scenario candidates / FAQ
candidates / review notes under `config["assistant_migration"]`.
Scenario candidates are also flattened into response guidelines for now
so customer behavior is preserved before we create real
`Captain::Scenario` records in a later rollout.
The applier stores the original assistant values under migration
metadata so conversation message config can be restored if needed. It
does not create scenario records yet.
**How to generate drafts**
For specific assistant IDs:
```bash
bundle exec rake captain:assistant_migration:generate \
IDS=546,636,819 \
LIMIT=0 \
OUTPUT=tmp/captain_migration_drafts.jsonl
```
For the first 50 eligible assistants:
```bash
bundle exec rake captain:assistant_migration:generate \
OUTPUT=tmp/captain_migration_drafts.jsonl
```
For all eligible assistants:
```bash
bundle exec rake captain:assistant_migration:generate \
LIMIT=0 \
OUTPUT=tmp/captain_migration_drafts.jsonl
```
**How to apply drafts**
Dry run first:
```bash
bundle exec rake captain:assistant_migration:apply \
INPUT=tmp/captain_migration_drafts.jsonl \
DRY_RUN=true
```
Apply changes:
```bash
bundle exec rake captain:assistant_migration:apply \
INPUT=tmp/captain_migration_drafts.jsonl \
DRY_RUN=false
```
**How to restore conversation messages**
If extracted `welcome_message`, `handoff_message`, or
`resolution_message` need to be reverted to their pre-migration values:
```bash
bundle exec rake captain:assistant_migration:restore_messages \
IDS=546,636,819 \
DRY_RUN=true
```
```bash
bundle exec rake captain:assistant_migration:restore_messages \
IDS=546,636,819 \
DRY_RUN=false
```
**Notes**
- `LIMIT=0` means no limit.
- `generate` overwrites the output file.
- The apply task skips assistants that are no longer V1 migration
candidates.
- This PR does not create `Captain::Scenario` records; scenario
candidates are staged in assistant config for a future migration.
---------
Co-authored-by: Muhsin <12408980+muhsin-k@users.noreply.github.com>
Co-authored-by: aakashb95 <aakashbakhle@gmail.com>
Co-authored-by: Aakash Bakhle <48802744+aakashb95@users.noreply.github.com>
# Pull Request Template
## Description
Tightens v2 prompt and config to match v1
## Type of change
Please delete options that are not relevant.
- [x] Bug fix (non-breaking change which fixes an issue)
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
locally
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
# Pull Request Template
## Description
https://linear.app/chatwoot/issue/AI-179/false-promise-soft-handoff-guard
## Type of change
- [x] Bug fix (non-breaking change which fixes an issue)
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
Against negative cases identified by evals
## Checklist:
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [ ] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged and published in downstream
modules
Captain custom tools previously used their own hand-rolled `Net::HTTP`
request code. This moves them onto `SafeFetch`, the same shared
HTTP-fetching helper already used by webhooks, uploads, avatar imports,
and the Captain page crawler. Behavior for normal tools is unchanged —
they just now share one consistent path for host resolution, timeouts,
response size limits, and redirect handling.
**What changed**
- `HttpTool#execute_http_request` now delegates to `SafeFetch.fetch`
instead of building `Net::HTTP` requests by hand. Auth headers, basic
auth, metadata headers, JSON content-type, and the 1 MB response cap all
map onto `SafeFetch` options.
- Removed ~80 lines of bespoke request/validation plumbing from
`HttpTool`.
- The custom tools `test` endpoint now reads the response body string
directly (the executor returns the body rather than a response object).
**How to test**
1. Enable `custom_tools` (or `captain_integration_v2`) for an account.
2. Create a Captain custom tool pointing at a public HTTPS endpoint
(e.g. a test API).
3. Use the **Test** button in the tool form — you should get a success
result.
4. Run the tool from a Captain conversation and confirm the response is
returned/templated as before.
**Gotchas**
- **Local dev:** `SafeFetch` blocks requests to private/loopback
addresses by default. If you're testing a custom tool against a service
on `localhost` or a private IP during development, set
`SAFE_FETCH_ALLOW_PRIVATE_NETWORK=true` or the request will be rejected.
(This matches how the rest of `SafeFetch` already behaves locally.)
- **Test endpoint status field:** on success the `test` response now
reports `status: 200` rather than the exact 2xx code (201/204/etc.),
because `SafeFetch` signals success-vs-failure rather than exposing the
raw response. The UI only checks the 2xx range, so this is invisible
there — but worth knowing if anything consumes the API directly.
- **Non-2xx responses** still surface as an error (same as before), now
via `SafeFetch::HttpError`.
# Pull Request Template
## Description
Fixes:
https://linear.app/chatwoot/issue/CW-7167/label-suggestions-bad-ux
## Type of change
Please delete options that are not relevant.
- [x] Bug fix (non-breaking change which fixes an issue)
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
## Checklist:
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [ ] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged and published in downstream
modules
# Pull Request Template
## Description
Captain (v1) makes false promises by saying it will handoff but doesn't.
This happens due to an exact string match comparison and the prompt
gives the model a lot of responsibilities:
- identity
- what to respond
- obey custom instructions
- decide on tool calls
This PR decouples responsibility, the core prompt responds, and an
additional llm call evaluates if handoff was needed or not after that
message.
## Type of change
- [x] Bug fix (non-breaking change which fixes an issue)
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
Locally
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
Removes sentry flooding of unnecessary rubyllm logs of wrong API key.
Logs only system api key error since it would be P0.
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
# Pull Request Template
## Description
The initial version of prompt deciding to resolve or hand-off to human
agents was too conservative especially in cases where a link or an
action was told to customer. If the customer didn't respond, Captain was
told to hand it off to the agent, but customer may actually have solved
the issue. If not, they can come back and continue the conversation.
Removed two lines about the same and now we should not see needless
handoffs.
## Type of change
- [x] Bug fix (non-breaking change which fixes an issue)
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
locally
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
# Pull Request Template
## Description
For our account, the conversation completion evaluator was proving to be
too conservative. This resulted in queue noise.
This PR adds a line to handle gibberish/single worded messages with no
further context.
## Type of change
- [x] Bug fix (non-breaking change which fixes an issue)
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
<img width="3012" height="978" alt="CleanShot 2026-03-23 at 11 44 55@2x"
src="https://github.com/user-attachments/assets/328195e8-6ea0-4c3a-9049-ee80196eecad"
/>
<img width="2202" height="866" alt="CleanShot 2026-03-23 at 11 47 15@2x"
src="https://github.com/user-attachments/assets/8d51cff4-b18f-4582-9455-8119ec7eff3a"
/>
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
# Pull Request Template
## Description
Add account setting and store_accessor for
`captain_force_legacy_auto_resolve`.
Enterprise job now skips LLM evaluation when this flag is true and falls
back to legacy time-based resolution. Add spec to cover the fallback.
## Type of change
We recently rolled out Captain deciding if a conversation is resolved or
not. While it is an improvement for majority of customers, some still
prefer the old way of auto-resolving based on inactivity. This PR adds a
check.
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
legacy_auto_resolve = true
<img width="1282" height="848" alt="CleanShot 2026-03-13 at 19 55 55@2x"
src="https://github.com/user-attachments/assets/dfdcc5d5-6d21-462b-87a6-a5e1b1290a8b"
/>
legacy_auto_resolve = false
<img width="1268" height="864" alt="CleanShot 2026-03-13 at 20 00 50@2x"
src="https://github.com/user-attachments/assets/f4719ec6-922a-4c3b-bc45-7b29eaced565"
/>
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
# Pull Request Template
## Description
Add an api_key override so internal conversation completions prefers
using the system API key and do not consume customer OpenAI credits.
## Type of change
Please delete options that are not relevant.
- [x] Bug fix (non-breaking change which fixes an issue)
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
specs and locally
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
# Pull Request Template
## Description
captain decides if conversation should be resolved or open
Fixes
https://linear.app/chatwoot/issue/AI-91/make-captain-resolution-time-configurable
Update: Added 2 entries in reporting events:
`conversation_captain_handoff` and `conversation_captain_resolved`
## Type of change
Please delete options that are not relevant.
- [x] New feature (non-breaking change which adds functionality)
- [x] This change requires a documentation update
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
LLM call decides that conversation is resolved, drops a private note
<img width="1228" height="438" alt="image"
src="https://github.com/user-attachments/assets/fb2cf1e9-4b2b-458b-a1e2-45c53d6a0158"
/>
LLM call decides conversation is still open as query was not resolved
<img width="1215" height="573" alt="image"
src="https://github.com/user-attachments/assets/2d1d5322-f567-487e-954e-11ab0798d11c"
/>
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
---------
Co-authored-by: Sojan Jose <sojan@pepalo.com>
Add a temporary `captain_disable_auto_resolve` boolean setting on
accounts to prevent Captain from resolving conversations. Guards both
the scheduled resolution job and the assistant's resolve tool.
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
# Pull Request Template
## Description
Adds a new built-in tool that allows Captain scenarios to resolve
conversations programmatically. This enables automated workflows like
the misdirected contact deflector to close conversations after handling
them, while still allowing human review via label filtering.
## Type of change
Please delete options that are not relevant.
- [x] New feature (non-breaking change which adds functionality)
## How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration.
tested by mentioning it to be used in captain v2 scenario
<img width="1180" height="828" alt="image"
src="https://github.com/user-attachments/assets/e70baf96-0c70-407e-af2c-328500ac5434"
/>
## Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented on my code, particularly in hard-to-understand
areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream
modules
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Tanmay Deep Sharma <32020192+tds-1@users.noreply.github.com>
Migration Guide: https://chwt.app/v4/migration
This PR imports all the work related to Captain into the EE codebase. Captain represents the AI-based features in Chatwoot and includes the following key components:
- Assistant: An assistant has a persona, the product it would be trained on. At the moment, the data at which it is trained is from websites. Future integrations on Notion documents, PDF etc. This PR enables connecting an assistant to an inbox. The assistant would run the conversation every time before transferring it to an agent.
- Copilot for Agents: When an agent is supporting a customer, we will be able to offer additional help to lookup some data or fetch information from integrations etc via copilot.
- Conversation FAQ generator: When a conversation is resolved, the Captain integration would identify questions which were not in the knowledge base.
- CRM memory: Learns from the conversations and identifies important information about the contact.
---------
Co-authored-by: Vishnu Narayanan <vishnu@chatwoot.com>
Co-authored-by: Sojan <sojan@pepalo.com>
Co-authored-by: iamsivin <iamsivin@gmail.com>
Co-authored-by: Sivin Varghese <64252451+iamsivin@users.noreply.github.com>
