This is an automated email from the ASF dual-hosted git repository.

davsclaus pushed a commit to branch CAMEL-26942-checks-for-agents
in repository https://gitbox.apache.org/repos/asf/camel.git

commit 7eab2e727f0f54b82658cba3aff1331d3fe739cb
Author: Claus Ibsen <[email protected]>
AuthorDate: Sat Nov 14 09:01:50 2026 +0100

    CAMEL-26942: design - CLI short commands: telling an agent to check is not 
enough, the checks run for it
    
    A benchmark with a local model (159 answers per run) told the model at the
    start of each conversation to look options up and to validate every snippet.
    It read more and answered the first question better, but it wrote 2.6 times
    as much code and validated none of it: options that do not exist went from
    6 to 32. The design now says so, and recommends checks that run without the
    agent's choice: marks on the code of an answer (CAMEL-26960) and a hook that
    runs camel validate yaml on each edited file, the call the daemon speeds up
    most. Links CAMEL-26961, the daemon itself.
    
    Co-Authored-By: Claude Opus 5.5 <[email protected]>
    Signed-off-by: Claus Ibsen <[email protected]>
---
 design/cli-short-commands.adoc | 62 ++++++++++++++++++++++++++++++++++--------
 1 file changed, 51 insertions(+), 11 deletions(-)

diff --git a/design/cli-short-commands.adoc b/design/cli-short-commands.adoc
index 4794abd5b3ed..0a0e8fa1aa40 100644
--- a/design/cli-short-commands.adoc
+++ b/design/cli-short-commands.adoc
@@ -5,10 +5,12 @@ authors:
 reviewers: []
 approvers: []
 creation-date: 2026-11-13
-last-updated: 2026-11-13
+last-updated: 2026-11-14
 status: proposed
 see-also:
   - "CAMEL-26942"
+  - "CAMEL-26961"
+  - "CAMEL-26960"
   - "CAMEL-26935"
   - "CAMEL-26937"
   - "CAMEL-26938"
@@ -38,8 +40,11 @@ against 10-40 ms estimated), for a fraction of the build and 
release work.
 The seconds a daemon saves are small next to the turns of the model. The 
reason to build it is that a command that
 answers at once can be called after every step. An agent makes fewer mistakes 
when it validates after every edit, looks
 an option up with `camel doc` instead of guessing it, and checks `camel 
status` after every reload. Speed alone
-does not make an agent do that, it has to be told (see the motivation), but 
speed makes it cheap to do. With the Java
-client the daemon answers in 50-65 ms, under the 0.1 s at which a response 
feels instant, like a native command.
+does not make an agent do that, and telling it to is not enough: in a 
benchmark with a local model, an instruction to
+check made the model read more, but it checked none of the code it wrote (see 
the motivation). The checks have to run
+whether the model asks for them or not, for example in a hook of the agent 
that validates every edited file, and a
+check that runs on every edit is where a fast command pays the most. With the 
Java client the daemon answers in
+50-65 ms, under the 0.1 s at which a response feels instant, like a native 
command.
 
 == Motivation
 
@@ -77,6 +82,31 @@ got it wrong; with a hint in the question it read the doc 
and got it right. It s
 exist, and validated nothing in 9 answers. A lookup also costs context: the 
doc of the file component is 17K
 characters, and three docs in one answer forced a compaction of the history.
 
+Two full runs on the night of 2026-11-13 then asked the same model 53 
questions about 5 example apps, 3 times each,
+the second with an instruction at the start of each conversation: look options 
up with `camel_catalog_doc`, and check
+every snippet with `camel_validate_source` before you answer. Per run of 159 
answers, without and with the
+instruction:
+
+- The first question of each conversation, the one with the instruction, was 
always "what does this app do". The
+  model read more for it (3.9 tool calls per answer instead of 2.1) and passed 
it 12 of 15 times instead of 8. Most
+  of that gain is one app: in the first run, the model answered from the 
AI-written summary that the readme tool
+  returned, and left a step out. Since CAMEL-26946 that tool returns the facts 
of the routes by default.
+- On the questions after it, the instruction faded: 0.10 lookups and no 
validation per answer. Yet the model wrote
+  2.6 times as much code in all (221 code blocks instead of 84) and validated 
none of it: its 3 calls of
+  `camel_validate_source`, all on the first question, checked the route file 
of the app, not a snippet. Options that
+  do not exist went from 6 in 4 answers to 32 in 14, all after the first 
question, and "how can I make it better"
+  passed 5 of 15 times instead of 12.
+- It cost context and time: 13 compactions of the history instead of 6, and 
8.1 s of model time per answer instead
+  of 5.8 s.
+- In all, 128 answers passed instead of 130: 4 more on the first question, 6 
fewer on the others.
+
+This is one model and one run each. The changes in code, invented options, 
compactions and time are well beyond the
+variance between the rounds; most changes in the pass rate of a single 
question are not.
+
+Telling the model to check made it read more and write more, not check what it 
wrote. The check of the code in an
+answer has to run whether the model asks for it or not: CAMEL-26960 proposes 
to mark the mistakes in the code of an
+answer, such as an option that does not exist, in the AI panel and in `camel 
ask`.
+
 == Goals
 
 - The short commands an agent runs most answer in under 0.1 s, the usual limit 
for a response to feel instant, as a
@@ -326,15 +356,23 @@ daemon or a native front does not serve too, and the 
start of the daemon itself.
    readiness pushed over the WebSocket transport.
 . Keep the Java client. At 50-65 ms it answers under the 0.1 s at which a 
response feels instant, so the commands
   already feel native. A native client for the main platforms, with the Java 
client as the fallback, is optional.
-. Tell the agents. Speed alone does not change how an agent uses the CLI, so 
what agents read (the Camel CLI pages,
-  the instructions of the MCP server, the system prompt of the AI panel) says 
that the short commands are cheap to
-  call: look an option up instead of guessing it, asking only for the options 
needed (the `optionsFilter` of
-  `camel_catalog_doc`) as a whole doc page costs context, and validate every 
snippet before answering.
+. Tell the agents, and check for them. Speed alone does not change how an 
agent uses the CLI, so what agents read
+  (the Camel CLI pages, the instructions of the MCP server, the system prompt 
of the AI panel) says that the short
+  commands are cheap to call: look an option up instead of guessing it, asking 
only for the options needed (the
+  `optionsFilter` of `camel_catalog_doc`) as a whole doc page costs context. 
Telling is not enough for the checks:
+  told to validate every snippet, the local model wrote more code and 
validated none of it (see the motivation). So
+  the checks run without the agent's choice. The AI panel and `camel ask` mark 
the mistakes in the code of an answer
+  (CAMEL-26960). The MCP server already validates a file before 
`camel_write_file` writes it. An agent that edits
+  files with its own tools needs a hook that runs `camel validate yaml` on 
each edited route file, and the Camel CLI
+  pages show one. That hook runs on every edit, so it is where the daemon 
saves the most.
 . Measure the agents, not only the commands. The local-model benchmark runs in 
the AI panel of the TUI, whose tools
-  run in the process, so it measures the instruction, not the daemon: run it 
with and without the instruction, and
-  compare the pass rate, the calls and the invented options per answer, the 
compactions and the time of the model.
-  The daemon needs a benchmark that drives `camel` through a shell. Make the 
daemon the default only after a release
-  as opt-in, and when that benchmark shows the gain.
+  run in the process, so it measures the instruction and the checks, not the 
daemon. It compares the pass rate, the
+  calls and the invented options per answer, the compactions and the time of 
the model. After the run with the
+  instruction in the first message (see the motivation), next are a run with 
such a line in the system prompt of
+  the AI panel, which may last past the first question (two jars that differ 
only in that line), and a run with the
+  marks of CAMEL-26960, which counts the invented options shown without a 
mark. The daemon needs a benchmark that
+  drives `camel` through a shell. Make the daemon the default only after a 
release as opt-in, and when that
+  benchmark shows the gain.
 . Do not build the native front. A daemon with a native client is in the same 
range (21-37 ms measured, against
   10-40 ms estimated), and the native front costs the most: the base classes 
of the commands change, GraalVM metadata
   must follow every command and option, aesh needs a change, and each release 
needs a binary per platform, all before
@@ -348,12 +386,14 @@ measure.
 == Related tickets
 
 - CAMEL-26942: this design.
+- CAMEL-26961: the opt-in resident daemon of this design, in its stages.
 - CAMEL-26935: make the Camel CLI faster for AI agents, the parent of the 
sub-tasks below.
 - CAMEL-26936: `camel run --background` learns at once that Camel has started.
 - CAMEL-26937: faster startup of the short commands (no JLine terminal or 
log4j when not needed, C1).
 - CAMEL-26938: shorter action polls.
 - CAMEL-26940: a JDK 25 AOT cache instead of a CDS archive per command.
 - CAMEL-26941: `camel status`, the state of an integration in one call.
+- CAMEL-26960: mark the mistakes in the code of AI answers, such as options 
that do not exist.
 - CAMEL-26913: CLI startup and config (CDS archives shared between installs).
 - CAMEL-25388: the Camel CLI reliable for AI agents and scripts.
 - CAMEL-23810: the port of the CLI to aesh.

Reply via email to