Conversation
Simplified chat rendering
This reverts commit 69bf2ca.
Pydantic AI allows setting multiple static and dynamic system prompts to define conversation context and rules. Previously, these were sent to the model API as separate messages, which caused compatibility issues with some self-hosted models (e.g., Gemma3/vLLM). This commit switches from using `system_prompt` to `instruction` as recommended in the Pydantic AI documentation, thus merging several instructions into a single message. Reference: https://ai.pydantic.dev/agents/#system-prompts Signed-off-by: Laurent Paoletti <lp@providenz.fr>
Signed-off-by: Laurent Paoletti <lp@providenz.fr>
fix link color component for default theme
WalkthroughMakefile updated to introduce three frontend Yarn variables and refactor frontend targets to use them. Direct Changes
Sequence Diagram(s)(omitted — changes are Makefile-driven and do not introduce a multi-component runtime control flow) Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes 🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Do not install node modules from local host.
qbey
force-pushed
the
qbey/-node-run-in-docker
branch
from
fcc05b0 to
8434efd
Compare
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
Makefile (1)
342-365: Update help text: “install the frontend locally” is now inaccurate.The target now runs inside Docker, so the help string should reflect that to avoid confusion.
✏️ Suggested tweak
-frontend-development-install: ## install the frontend locally +frontend-development-install: ## install the frontend in Docker
🤖 Fix all issues with AI agents
In `@Makefile`:
- Around line 56-58: The Makefile target vars FRONTEND_YARN,
FRONTEND_CONVERSATIONS_YARN and FRONTEND_CONVERSATIONS_YARN_3000 run yarn in the
bind-mounted node service so installs write host ./src/frontend/node_modules;
change these variables to add anonymous-volume flags to COMPOSE_RUN so
node_modules is mounted inside the container (not on host). For example, update
FRONTEND_YARN to invoke $(COMPOSE_RUN) with an extra -v
/app/src/frontend/node_modules and update FRONTEND_CONVERSATIONS_YARN and
FRONTEND_CONVERSATIONS_YARN_3000 to add -v
/app/src/frontend/apps/conversations/node_modules (and also
/app/src/frontend/node_modules if needed) so yarn writes to container volumes
rather than the host. Ensure you keep the existing -w paths and port override in
FRONTEND_CONVERSATIONS_YARN_3000.
📜 Review details
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
Makefile
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (4)
- GitHub Check: test-e2e-chromium
- GitHub Check: test-back
- GitHub Check: build-and-push-frontend
- GitHub Check: build-and-push-backend
🔇 Additional comments (1)
Makefile (1)
379-384: LGTM — consistent dockerized version bumping.The switch to
COMPOSE_RUNaligns with the PR objective and keeps all version bumps inside containers.
✏️ Tip: You can disable this entire section by setting review_details to false in your review settings.
| FRONTEND_YARN = $(COMPOSE_RUN) -w /app/src/frontend node yarn | ||
| FRONTEND_CONVERSATIONS_YARN = $(COMPOSE_RUN) -w /app/src/frontend/apps/conversations node yarn | ||
| FRONTEND_CONVERSATIONS_YARN_3000 = $(COMPOSE_RUN) -p 3000:3000 -w /app/src/frontend/apps/conversations node yarn |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
# Find compose files in the repository
find . -name 'docker-compose*.yml' -o -name 'compose*.yml' 2>/dev/null | head -20Repository: suitenumerique/conversations
Length of output: 137
🏁 Script executed:
# Search for node service and frontend service definitions in compose files
rg -l 'services:' --type yaml | head -10Repository: suitenumerique/conversations
Length of output: 131
🏁 Script executed:
cat compose.ymlRepository: suitenumerique/conversations
Length of output: 4793
Confirm: The node service writes node_modules to the host via bind mount.
The node service mounts the entire repository as a bind mount (.:/app), which means yarn installing dependencies at /app/src/frontend/node_modules will write directly to ./src/frontend/node_modules on your host machine. This contrasts with the frontend-development service, which uses anonymous volumes (/home/frontend/node_modules and /home/frontend/apps/conversations/node_modules) to prevent host pollution.
To isolate node_modules from the host when running yarn via the Makefile, either:
- Add anonymous volume overrides to the
nodeservice in compose configuration - Or adjust the Makefile to mount anonymous volumes for node_modules paths when invoking
COMPOSE_RUN
🤖 Prompt for AI Agents
In `@Makefile` around lines 56 - 58, The Makefile target vars FRONTEND_YARN,
FRONTEND_CONVERSATIONS_YARN and FRONTEND_CONVERSATIONS_YARN_3000 run yarn in the
bind-mounted node service so installs write host ./src/frontend/node_modules;
change these variables to add anonymous-volume flags to COMPOSE_RUN so
node_modules is mounted inside the container (not on host). For example, update
FRONTEND_YARN to invoke $(COMPOSE_RUN) with an extra -v
/app/src/frontend/node_modules and update FRONTEND_CONVERSATIONS_YARN and
FRONTEND_CONVERSATIONS_YARN_3000 to add -v
/app/src/frontend/apps/conversations/node_modules (and also
/app/src/frontend/node_modules if needed) so yarn writes to container volumes
rather than the host. Ensure you keep the existing -w paths and port override in
FRONTEND_CONVERSATIONS_YARN_3000.
4 participants
Purpose
Do not install node modules from local host.
Proposal
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.