gptel-anthropic.el (gptel-curl--parse-stream): When parsing
responses from Anthropic, wait for more input when the
corresponding data chunk for the event hasn't arrived yet. (#261)
* gptel-transient.el (gptel--suffix-send): Don't pre-fill the
minibuffer prompt with the current line when reading the query
from the minibuffer. (If the region is active, it is used as the
initial contents -- this behavior is unchanged.)
* gptel-anthropic.el (gptel-curl--parse-stream): Remove extraneous
statements and simplify the stream parser. Addresses #261, but
the main problem is still elusive.
* gptel.el (gptel-backend, gptel-model, gptel-temperature,
gptel-max-tokens, gptel--num-messages-to-send,
gptel--system-message): Make all model/request paramters global
variables, i.e. not buffer-local by default. This is following
the discussion in #249.
* gptel-transient.el (gptel-menu, gptel-system-prompt--setup,
gptel-system-prompt, gptel--suffix-system-message,
gptel--infix-provider, gptel--infix-temperature, gptel--switches,
gptel--set-buffer-locally, gptel--set-with-scope): and associated
transient methods: add a toggle `gptel--set-buffer-locally` to
allow model parameters to be set buffer-locally. The function
`gptel--set-with-scope` can be used to reset a variable or set it
buffer-locally.
Reorder gptel-transient so all the custom classes, methods and
utility functions are at the top.
* README.org (all backend sections): Replace `setq-default` with
setq in the recommended configuration.
* gptel-transient.el (gptel-menu, gptel--infix-add-directive,
gptel--suffix-system-message): Enable the additional directive
option in `gptel-menu` by default, and change the wording of
documentation strings for transient options.
* gptel-ollama.el (gptel-curl--parse-stream): libjansson and
json.el behave differently w.r.t moving point when there is a
parsing error. Fix by explicitly handling point when there is an
error. (#255)
* gptel-transient.el (gptel--infix-provider, gptel--infix-model):
Simplify model and backend selection into a single step. Remove
unused and obsolete option `gptel--infix-provider`.
* gptel-transient.el (gptel--get-directive,
gptel--infix-add-directive, gptel-menu): Rename the
directive-related functions to be shorter/more consistent with the
rest of the code.
gptel--additional-directive -> gptel--infix-add-directive
gptel--additional-directive-get -> gptel--get-directive
* gptel-transient.el (gptel-menu, gptel-system-prompt--setup,
gptel-system-prompt, gptel--infix-temperature,
transient-format-value, gptel--additional-directive,
gptel--suffix-system-message): Tweak to the "additional directive"
overlay display. `gptel-menu` changes based on feedback
from #249 (thanks to @jwr):
- Keys to set the system message are remapped from "h" to
"s" (mnemonic)
- `gptel--infix-temperature` is now hidden by default and requires
enabling `gptel-expert-commands`
- Keys to prompt from minibuf and respond in echo area are changed
to "m" and "e" respectively.
* gptel.el (gptel-end-of-response, gptel-beginning-of-response,
gptel-expert-commands): Add `gptel-expert-commands` to selectively
enable experimental options in `gptel-menu`. This should keep the
interface from overwhelming new users. Add a command to move to
the beginning of a response.
* gptel-transient.el (gptel-menu, gptel-system-prompt,
gptel--instructions-make-overlay, gptel-option-overlaid,
transient-format-value, gptel--additional-directive,
gptel--additional-directive-get): Add a transient option to
include a (short) additional instruction/directive along with the
system message. This makes it convenient to have an extensive
system message and specify additional, per-response tasks (such as
refactoring) on top. Ensure that the dry run options handle this
correctly. This option is made available when
`gptel-expert-commands` is turned on.
NOTE: WIP design. The nomenclature for `gptel-expert-commands`
and "additional directive" is subject to change.
* gptel-transient.el (gptel-menu, gptel-lisp-variable,
gptel--infix-num-messages-to-send, gptel--infix-max-tokens,
gptel--infix-provider): Improve the wording and the display of the
default settings. Define a new class `gptel-lisp-variable` to
faciliate this.
* gptel.el (gptel--inspect-query): Add a function to inspect the
query that will be sent. This is useful to ensure that (only and
all of) what you expect to be sent is being sent.
* gptel-transient.el (gptel-menu): Allow the query in progress to
be inspected from `gptel-menu` as an elisp or JSON object.
* gptel.el (gptel-request, gptel-send, gptel--url-get-response):
Consolidate the HTTP query construction into `gptel-request`,
and use it as the single point for sending gptel queries. This
simplifies the code, makes it easier to debug and (later) advise
or otherwise modify. To this end, `gptel-send` reuses
`gptel-request` and no longer does its own thing. Adjust other
HTTP request-related functions accordingly.
* gptel-curl.el (gptel-curl--get-args, gptel-curl--get-response):
Receive the full request data instead of constructing it partly in
`gptel-curl--get-args`.
* gptel.el (gptel--url-get-response): Log request headers as JSON objects.
* gptel-curl.el (gptel-curl--get-args, gptel-curl--get-response):
Log request headers as JSON objects, Curl command as a shell
command you can copy and paste into the terminal.
Using the libjansson JSON parser gives us a modest boost in speed.
It's not as significant a speedup as it is for LSP clients since
our jSON payloads are smaller and less frequent -- but we might as
well use it.
* gptel.el (gptel--json-read, gptel--json-encode,
gptel--url-get-response, gptel--parse-response): Define macros to
use the libjansson-supported `json-parse-buffer` and
`json-serialize`. Replace use of `json-encode` and `json-read`
appropriately.
* gptel-openai.el: (gptel-curl--parse-stream) : Use
`gptel--json-read` instead of `json-read`.
* gptel-ollama.el (gptel-curl--parse-stream): Use
`gptel--json-read` instead of `json-read`.
* gptel-gemini.el (gptel-curl--parse-stream): Use
`gptel--json-read` instead of `json-read`.
* gptel-curl.el (gptel-curl--get-args, gptel-curl--get-response,
gptel-curl--log-response, gptel-curl--stream-cleanup,
gptel-curl--parse-response): Use `gptel--json-read` and
`gptel--json-encode` in place of the json.el versions.
* gptel-anthropic.el (gptel-curl--parse-stream): Use
`gptel--json-read` instead of `json-read`.
* test/gptel-org-test.el: Use `gptel--json-read`.
* gptel.el (gptel--sanitize-model, gptel): Check for mismatches
between the default values of gptel-backend and gptel-model when
starting a new gptel chat. Previously the default value of
gptel-backend was compared against the buffer-local value of
gptel-model.
* gptel.el (gptel--insert-response, gptel--restore-state): Don't
set the rear-nonsticky property on the gptel response text.
Instead, the gptel text-property is globally declared to be
nonsticky via `text-property-default-nonsticky`.
This change is since markdown-mode makes rear-nonsticky a
font-lock-managed property and we can't set it manually. Setting
this property explicitly also makes all text properties in the
range nonsticky, which can have unintended side effects.
* gptel-curl.el (gptel-curl--stream-insert-response): Ditto.
gptel.el (gptel--convert-markdown->org,
gptel--stream-convert-markdown->org): Handle the case of Markdown
bullet lists that begin with a "*", which the Gemini LLMs produce
often. Address #238.
gptel-anthropic.el (gptel-curl--parse-stream): Reset point
explicitly when parsing streaming responses returned by the
Anthropic API. Try to address #233.
gptel.el (gptel--url-parse-response): Handle HTTP 100 followed by
200. Note: this fix is brittle, it will break if 100 is followed
by an error code.
gptel-curl.el (gptel-curl--stream-filter,
gptel-curl--parse-stream): Ditto. Address #194.
gptel-curl.el (gptel-curl--stream-cleanup): The LLM response can
be empty with HTTP status 200, for example when the API responds
with an error description instead. Handle this case gracefully.
When `gptel-mode` is enabled, also inform the user that the
response was empty. Fix#234.
gptel.el (gptel-post-response-functions): Documentation. Explain
the arguments passed to each hook function in this hook when the
response fails or is empty.
gptel-curl.el (gptel-curl--stream-cleanup,
gptel-curl--stream-insert-response): Don't consider
`gptel-response-prefix-string` part of the response for the
purpose of running `gptel-post-response-functions`.
* gptel.el: Mention Anthropic in the package description.
* gptel-anthropic.el (gptel-anthropic, gptel-make-anthropic,
gptel--parse-response, gptel--request-data, gptel--parse-buffer,
gptel-curl--parse-stream): Add support for Anthropic AI's Claude 3
models.
* README.org: Add instructions for using Anthropic AI's Claude 3
models.
gptel-transient (gptel--system-prompt-setup): When assigning keys
to directives, avoid clashes with the system-message edit key
(`h`), and use an arbitrary unused key if no mnemonic key
assignments are possible.
gptel-openai.el (gptel-backend, gptel-make-openai,
gptel-make-azure): Add a curl-args slot to the backend struct for
additional Curl arguments.
Usage example: This can be used to set the `--cert` and `--key`
options in a custom backend that uses mutal TLS to communicate
with an OpenAI proxy/gateway.
gptel-curl.el (gptel-curl--get-args): Add backend-specific
curl-args when creating HTTP requests.
gptel-gemini.el (gptel-make-gemini): Add a curl-args slot to the
constructor.
gptel-kagi.el (gptel-make-kagi): Ditto.
gptel-ollama.el (gptel-make-ollama): Ditto.
* gptel.el (gptel-display-buffer-action, gptel): Add
`gptel-display-buffer-action` to customize the display of the
gptel buffer.
* README: Mention new option.
* gptel-gemini.el (gptel-make-gemini, gptel--request-data): The
Gemini API misclassifies harmless questions (like "What's 2+2",
see #208) as harmful. Use the most permissive safety settings the
API offers.
Also respect the value of `:stream` used when defining Gemini
backends.
* gptel.el (gptel--attach-response-history, gptel--ediff,
gptel--next-variant, gptel--previous-variant,
gptel--mark-response):
Add `gptel--attach-response-history` -- this can be used to add
text properties to the next gptel response in the buffer. This
is (currently) useful for tracking changes when the response
overwrites existing text.
The next three commands -- `gptel--ediff`,
`gptel--previous-variant`, `gptel--next-variant` -- provide
facilities for manipulating a gptel response at point when there
is history. `gptel--mark-response` marks the response at point.
These are considered internal functions for now and can be
accessed from the transient menu, where they work together with
`gptel--regenerate`.
The input arguments to these commands are expected to change to
support copilot-style functionality in the near future.
* gptel-transient.el (gptel-menu, gptel--suffix-send,
gptel--regenerate):
Change the transient menu layout to be more compact (with a newly
added column.) When overwriting the prompt with a response, save
the prompt to the gptel response's history. Add
`gptel--regenerate` to regenerate a response. This is accessible
from the transient menu when the point is inside response text.
* gptel.el (gptel--debug, gptel-log-level, gptel--log-buffer-name,
gptel--url-get-response, gptel--parse-response): Optionally log
all request and response data to `gptel--log-buffer-name`, with
the log level governed by `gptel-log-level`. Obsolete
`gptel--debug`.
* gptel-curl.el (gptel-curl--log-response, gptel-curl--get-args,
gptel-curl--get-response, gptel-curl--stream-cleanup,
gptel-curl--sentinel): Add support for logging.
